Decision curve analysis to evaluate the clinical benefit of prediction models

Machine learning model to preoperatively predict T2/T3 staging of laryngeal and hypopharyngeal cancer based on the CT radiomic signature

OBJECTIVES

To develop and assess a radiomics-based prediction model for distinguishing T2/T3 staging of laryngeal and hypopharyngeal squamous cell carcinoma (LHSCC) METHODS: A total of 118 patients with pathologically proven LHSCC were enrolled in this retrospective study. We performed feature processing based on 851 radiomic features derived from contrast-enhanced CT images and established multiple radiomic models by combining three feature selection methods and seven machine learning classifiers. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were used to assess the performance of the models. The radiomic signature obtained from the optimal model and statistically significant morphological image characteristics were incorporated into the predictive nomogram. The performance of the nomogram was assessed by calibration curve and decision curve analysis.

RESULTS

Using analysis of variance (ANOVA) feature selection and logistic regression (LR) classifier produced the best model. The AUCs of the training, validation, and test sets were 0.919, 0.857, and 0.817, respectively. A nomogram based on the model integrating the radiomic signature and a morphological imaging characteristic (suspicious thyroid cartilage invasion) exhibited C-indexes of 0.899 (95% confidence interval (CI) 0.843-0.955), fitting well in calibration curves (p > 0.05). Decision curve analysis further confirmed the clinical usefulness of the nomogram.

CONCLUSIONS

The nomogram based on the radiomics model derived from contrast-enhanced CT images had good diagnostic performance for distinguishing T2/T3 staging of LHSCC.

CLINICAL RELEVANCE STATEMENT

Accurate T2/T3 staging assessment of LHSCC aids in determining whether laryngectomy or laryngeal preservation therapy should be performed. The nomogram based on the radiomics model derived from contrast-enhanced CT images has the potential to predict the T2/T3 staging of LHSCC, which can provide a non-invasive and robust approach for guiding the optimization of clinical decision-making.

KEY POINTS

• Combining analysis of variance with logistic regression yielded the optimal radiomic model. • A nomogram based on the CT-radiomic signature has good performance for differentiating T2 from T3 staging of laryngeal and hypopharyngeal squamous cell carcinoma. • It provides a non-invasive and robust approach for guiding the optimization of clinical decision-making.

Nomogram for predicting invasive lung adenocarcinoma in small solitary pulmonary nodules

Background

This study aimed to construct a clinical prediction model and nomogram to differentiate invasive from non-invasive pulmonary adenocarcinoma in solitary pulmonary nodules (SPNs).

Method

We analyzed computed tomography and clinical features as well as preoperative biomarkers in 1,106 patients with SPN who underwent pulmonary resection with definite pathology at Qilu Hospital of Shandong University between January 2020 and December 2021. Clinical parameters and imaging characteristics were analyzed using univariate and multivariate logistic regression analyses. Predictive models and nomograms were developed and their recognition abilities were evaluated using receiver operating characteristic (ROC) curves. The clinical utility of the nomogram was evaluated using decision curve analysis (DCA).

Result

The final regression analysis selected age, carcinoembryonic antigen, bronchus sign, lobulation, pleural adhesion, maximum diameter, and the consolidation-to-tumor ratio as associated factors. The areas under the ROC curves were 0.844 (95% confidence interval [CI], 0.817-0.871) and 0.812 (95% CI, 0.766-0.857) for patients in the training and validation cohorts, respectively. The predictive model calibration curve revealed good calibration for both cohorts. The DCA results confirmed that the clinical prediction model was useful in clinical practice. Bias-corrected C-indices for the training and validation cohorts were 0.844 and 0.814, respectively.

Conclusion

Our predictive model and nomogram might be useful for guiding clinical decisions regarding personalized surgical intervention and treatment options.

Simple prediction tools for disease progression in unvaccinated patients with mild/moderate COVID-19 aged under 65 years: Simplified DOATS and DOAT scores

DOATS score and DOAT score, COVID-19 progression prediction tools we have developed, utilize clinical information such as presence of diabetes/obesity (DO), age (A), body temperature (T), and oxygen saturation (S). They showed good predictive power, but their scoring calculation was slightly complex, leading us to develop simplified versions. This report discusses the ability of the simplified versions to assess deterioration risk in unvaccinated, mild/moderate COVID-19 patients aged <65 years. Logistic regression analysis identified independent risk factors for deterioration, to which points were assigned in order to derive overall prediction scores. The simplified versions showed high discriminating power, with the areas under the receiver operating characteristic curve for DOATS and DOAT being 0.79 and 0.77, respectively, indicating their clinical utility. Although the original versions have a slightly higher predictive power, the new versions are easier to use in emergency situations; thus, importantly, selecting the appropriate version depends on the situation.

Understanding decision curve analysis in clinical prediction model research

BACKGROUND

Many medical graduate students lack a thorough understanding of decision curve analysis (DCA), a valuable tool in clinical research for evaluating diagnostic models.

METHODS

This article elucidates the concept and process of DCA through the lens of clinical research practices, exemplified by its application in diagnosing liver cancer using serum alpha-fetoprotein levels and radiomics indices. It covers the calculation of probability thresholds, computation of net benefits for each threshold, construction of decision curves, and comparison of decision curves from different models to identify the one offering the highest net benefit.

RESULTS

The paper provides a detailed explanation of DCA, including the creation and comparison of decision curves, and discusses the relationship and differences between decision curves and receiver operating characteristic curves. It highlights the superiority of decision curves in supporting clinical decision-making processes.

CONCLUSION

By clarifying the concept of DCA and highlighting its benefits in clinical decisionmaking, this article has improved researchers' comprehension of how DCA is applied and interpreted, thereby enhancing the quality of research in the medical field.

A nomogram combining CT-based radiomic features with clinical features for the differentiation of benign and malignant cystic pulmonary nodules

BACKGROUND

Currently, the differentiation between benign and malignant cystic pulmonary nodules poses a significant challenge for clinicians. The objective of this retrospective study was to construct a predictive model for determining the likelihood of malignancy in patients with cystic pulmonary nodules.

METHODS

The current study involved 129 patients diagnosed with cystic pulmonary nodules between January 2017 and June 2023 at the Neijiang First People's Hospital. The study gathered the clinical data, preoperative imaging features of chest CT, and postoperative histopathological results for both cohorts. Univariate and multivariate logistic regression analyses were employed to identify independent risk factors, from which a prediction model and nomogram were developed. In addition, The model's performance was assessed through receiver operating characteristic (ROC) curve analysis, calibration curve analysis, and decision curve analysis (DCA).

RESULTS

A cohort of 129 patients presenting with cystic pulmonary nodules, consisting of 92 malignant and 37 benign lesions, was examined. Logistic data analysis identified a cystic airspace with a mural nodule, spiculation, mural morphology, and the number of cystic cavities as significant independent predictors for discriminating between benign and malignant cystic lung nodules. The nomogram prediction model demonstrated a high level of predictive accuracy, as evidenced by an area under the ROC curve (AUC) of 0.874 (95% CI: 0.804-0.944). Furthermore, the calibration curve of the model displayed satisfactory calibration. DCA proved that the prediction model was useful for clinical application.

CONCLUSION

In summary, the risk prediction model for benign and malignant cystic pulmonary nodules has the potential to assist clinicians in the diagnosis of such nodules and enhance clinical decision-making processes.

CDKL3 is a promising biomarker for diagnosis and prognosis prediction in patients with hepatocellular carcinoma

Cyclin-dependent kinase-like 3 (CDKL3) has been identified as an oncogene in certain types of tumors. Nonetheless, its function in hepatocellular carcinoma (HCC) is poorly understood. In this study, we conducted a comprehensive analysis of CDKL3 based on data from the HCC cohort of The Cancer Genome Atlas (TCGA). Our analysis included gene expression, diagnosis, prognosis, functional enrichment, tumor microenvironment and metabolic characteristics, tumor burden, mRNA expression-based stemness, alternative splicing, and prediction of therapy response. Additionally, we performed a cell counting kit-8 assay, TdT-mediated dUTP nick-end Labeling staining, migration assay, wound healing assay, colony formation assay, and nude mouse experiments to confirm the functional relevance of CDKL3 in HCC. Our findings showed that CDKL3 was significantly upregulated in HCC patients compared to controls. Various bioinformatic analyses suggested that CDKL3 could serve as a potential marker for HCC diagnosis and prognosis. Furthermore, CDKL3 was found to be involved in various mechanisms linked to the development of HCC, including copy number variation, tumor burden, genomic heterogeneity, cancer stemness, and alternative splicing of CDKL3. Notably, CDKL3 was also closely correlated with tumor immune cell infiltration and the expression of immune checkpoint markers. Additionally, CDKL3 was shown to independently function as a risk predictor for overall survival in HCC patients by multivariate Cox regression analysis. Furthermore, the knockdown of CDKL3 significantly inhibited cell proliferation in vitro and in vivo, indicating its role as an oncogene in HCC. Taken together, our findings suggest that CDKL3 shows promise as a biomarker for the detection and treatment outcome prediction of HCC patients.

Automated machine learning for predicting liver metastasis in patients with gastrointestinal stromal tumor: a SEER-based analysis

Gastrointestinal stromal tumors (GISTs) are a rare type of tumor that can develop liver metastasis (LIM), significantly impacting the patient's prognosis. This study aimed to predict LIM in GIST patients by constructing machine learning (ML) algorithms to assist clinicians in the decision-making process for treatment. Retrospective analysis was performed using the Surveillance, Epidemiology, and End Results (SEER) database, and cases from 2010 to 2015 were assigned to the developing sets, while cases from 2016 to 2017 were assigned to the testing set. Missing values were addressed using the multiple imputation technique. Four algorithms were utilized to construct the models, comprising traditional logistic regression (LR) and automated machine learning (AutoML) analysis such as gradient boost machine (GBM), deep neural net (DL), and generalized linear model (GLM). We evaluated the models' performance using LR-based metrics, including the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA), as well as AutoML-based metrics, such as feature importance, SHapley Additive exPlanation (SHAP) Plots, and Local Interpretable Model Agnostic Explanation (LIME). A total of 6207 patients were included in this study, with 2683, 1780, and 1744 patients allocated to the training, validation, and test sets, respectively. Among the different models evaluated, the GBM model demonstrated the highest performance in the training, validation, and test cohorts, with respective AUC values of 0.805, 0.780, and 0.795. Furthermore, the GBM model outperformed other AutoML models in terms of accuracy, achieving 0.747, 0.700, and 0.706 in the training, validation, and test cohorts, respectively. Additionally, the study revealed that tumor size and tumor location were the most significant predictors influencing the AutoML model's ability to accurately predict LIM. The AutoML model utilizing the GBM algorithm for GIST patients can effectively predict the risk of LIM and provide clinicians with a reference for developing individualized treatment plans.

Development and external validation of a perioperative clinical model for predicting myocardial injury after major abdominal surgery: A retrospective cohort study

Purpose

We aimed to develop and validate a predictive model for myocardial injury in individuals undergoing major abdominal surgery.

Methods

This multicenter retrospective cohort analysis included 3546 patients aged ≥45 years who underwent major abdominal surgeries at two Chinese tertiary hospitals. The primary outcome was myocardial injury after noncardiac surgery (MINS), defined as prognostically relevant myocardial injury due to ischemia that occurs during or within 30 days after noncardiac surgery. The LASSO algorithm and logistic regression were used to construct a predictive model for postoperative MINS in the development cohort, and the performance of this prediction model was validated in an external independent cohort.

Results

A total of 3546 patients were included in our study. MINS manifested in 338 (9.53 %) patients after surgery. The definitive predictive model for MINS was developed by incorporating age, American Society of Anesthesiologists (ASA) classification, preoperative hemoglobin concentration, preoperative serum ALB concentration, blood loss, total infusion volume, and operation time. The area under the curve (AUC) of our model was 0.838 and 0.821 in the derivation and validation cohorts, respectively.

Conclusions

Preoperative hemoglobin levels, preoperative serum ALB concentrations, infusion volume, and blood loss are independent predictors of MINS. Our predictive model can prove valuable in identifying patients at moderate-to-high risk prior to non-cardiac surgery.

Mortality prediction and influencing factors for intensive care unit patients with acute tubular necrosis: random survival forest and cox regression analysis

Background: Patients with acute tubular necrosis (ATN) not only have severe renal failure, but also have many comorbidities, which can be life-threatening and require timely treatment. Identifying the influencing factors of ATN and taking appropriate interventions can effectively shorten the duration of the disease to reduce mortality and improve patient prognosis. Methods: Mortality prediction models were constructed by using the random survival forest (RSF) algorithm and the Cox regression. Next, the performance of both models was assessed by the out-of-bag (OOB) error rate, the integrated brier score, the prediction error curve, and area under the curve (AUC) at 30, 60 and 90 days. Finally, the optimal prediction model was selected and the decision curve analysis and nomogram were established. Results: RSF model was constructed under the optimal combination of parameters (mtry = 10, nodesize = 88). Vasopressors, international normalized ratio (INR)_min, chloride_max, base excess_min, bicarbonate_max, anion gap_min, and metastatic solid tumor were identified as risk factors that had strong influence on mortality in ATN patients. Uni-variate and multivariate regression analyses were used to establish the Cox regression model. Nor-epinephrine, vasopressors, INR_min, severe liver disease, and metastatic solid tumor were identified as important risk factors. The discrimination and calibration ability of both predictive models were demonstrated by the OOB error rate and the integrated brier score. However, the prediction error curve of Cox regression model was consistently lower than that of RSF model, indicating that Cox regression model was more stable and reliable. Then, Cox regression model was also more accurate in predicting mortality of ATN patients based on the AUC at different time points (30, 60 and 90 days). The analysis of decision curve analysis shows that the net benefit range of Cox regression model at different time points is large, indicating that the model has good clinical effectiveness. Finally, a nomogram predicting the risk of death was created based on Cox model. Conclusion: The Cox regression model is superior to the RSF algorithm model in predicting mortality of patients with ATN. Moreover, the model has certain clinical utility, which can provide clinicians with some reference basis in the treatment of ATN and contribute to improve patient prognosis.

Integrating IASLC grading and radiomics for predicting postoperative outcomes in stage IA invasive lung adenocarcinoma

BACKGROUND

The International Association for the Study of Lung Cancer (IASLC) Pathology Committee introduced a histologic grading system for invasive lung adenocarcinoma (LUAD) in 2020. The IASLC grading system, hinging on the evaluation of predominant and high-grade histologic patterns, has proven to be practical and prognostic for invasive LUAD. However, there are still limitations in evaluating the prognosis of stage IA LUAD. Radiomics may serve as a valuable complement.

PURPOSE

To establish a model that integrates IASLC grading and radiomics, aimed at predicting the prognosis of stage IA LUAD.

METHODS

We conducted a retrospective analysis of 628 patients diagnosed with stage IA LUAD who underwent surgical resection between January 2015 and December 2018 at our institution. The patients were randomly divided into the training set (n = 439) and testing set (n = 189) at a ratio of 7:3. Overall survival (OS) and disease-free survival (DFS) were taken as the end points. Radiomics features were obtained by PyRadiomics. Feature selection was performed using the least absolute shrinkage and selection operator (LASSO). The prediction models for OS and DFS were developed using multivariate Cox regression analysis, and the models were visualized through nomogram plots. The model's performance was evaluated using area under the curves (AUC), concordance index (C-index), calibration curves, and survival decision curve analysis (DCA).

RESULTS

In total, nine radiomics features were selected for the OS prediction model, and 15 radiomics features were selected for the DFS prediction model. Patients with high radiomics scores were associated with a worse prognosis (p < 0.001). We built separate prediction models using radiomics or IASLC alone, as well as a combined prediction model. In the prediction of OS, we observed that the combined model (C-index: 0.812 ± 0.024, 3 years AUC: 0.692, 5 years AUC: 0.792) achieved superior predictive performance than the radiomics (C-index: 0.743 ± 0.038, 3 years AUC: 0.633, 5 years AUC: 0.768) and IASLC grading (C-index: 0.765 ± 0.042, 3 years AUC: 0.658, 5 years AUC: 0.743) models alone. Similar results were obtained in the models for DFS.

CONCLUSION

The combination of radiomics and IASLC pathological grading proves to be an effective approach for predicting the prognosis of stage IA LUAD. This has substantial clinical relevance in guiding treatment decisions for early-stage LUAD.

A novel nomogram for the prediction of perforation during endoscopic submucosal dissection for colorectal neoplasms

BACKGROUND

High perforation risk hinders the widespread adoption of ESD for colorectal neoplasms. This study was performed to determine the risk factors of colorectal endoscopic submucosal dissection (ESD)-induced perforation and develop a predictive model.

METHODS

A total of 1046 colorectal neoplasms in 1011 patients were retrospectively enrolled from January 2011 to December 2021, in a single tertiary center as the derivation cohort. We identified independent risk factors for perforation using univariate analysis and multi-variate logistic regression. A nomogram was developed based on the logistic regression model and prospectively applied to 266 colorectal neoplasms as the validation cohort. The performance of the predictive model was evaluated with the receiver operating characteristic curve, calibration plot, and decision curve analysis.

RESULTS

Independent pre-operative factors for colorectal ESD-induced perforation were tumor located in the left colon [odds ratio (OR) 2.39, P = 0.040], size ≥ 40 mm (OR 3.36, P < 0.001), ≥2/3 circumference (OR 7.55, P = 0.004), located across folds (OR 6.26, P < 0.001), and laterally spreading tumor (non-granular type, OR 2.34, P = 0.029; granular type, OR 2.46, P = 0.021). The nomogram model incorporating the pre-operative factors performed well in both the derivation and validation cohorts (areas under the curve of 0.750 and 0.806, respectively). Decision curve analysis demonstrated that the clinical benefit of the nomogram was favorable.

CONCLUSIONS

The novel nomogram, developed and prospectively validated, incorporating tumor size, location, and morphology can successfully predict perforation during ESD for colorectal neoplasms.

Nomogram predictive model for in-hospital mortality risk in elderly ICU patients with urosepsis

BACKGROUND

Urinary tract infection (UTI) is a common cause of sepsis. Elderly patients with urosepsis in intensive care unit (ICU) have more severe conditions and higher mortality rates owing to factors such as advanced age, immunosenescence, and persistent host inflammatory responses. However, comprehensive studies on nomograms to predict the in-hospital mortality risk in elderly patients with urosepsis are lacking. This study aimed to construct a nomogram predictive model to accurately assess the prognosis of elderly patients with urosepsis and provide therapeutic recommendations.

METHODS

Data of elderly patients with urosepsis were extracted from the Medical Information Mart for Intensive Care (MIMIC) IV 2.2 database. Patients were randomly divided into training and validation cohorts. A predictive nomogram model was constructed from the training set using logistic regression analysis, followed by internal validation and sensitivity analysis.

RESULTS

This study included 1,251 patients. LASSO regression analysis revealed that the Glasgow Coma Scale (GCS) score, red cell distribution width (RDW), white blood count (WBC), and invasive ventilation were independent risk factors identified from a total of 43 variables studied. We then created and verified a nomogram. The area under the receiver operating characteristic curve (AUC), net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA) of the nomogram were superior to those of the traditional SAPS-II, APACHE-II, and SOFA scoring systems. The Hosmer-Lemeshow test results and calibration curves suggested good nomogram calibration. The IDI and NRI values showed that our nomogram scoring tool performed better than the other scoring systems. The DCA curves showed good clinical applicability of the nomogram.

CONCLUSIONS

The nomogram constructed in this study is a convenient tool for accurately predicting in-hospital mortality in elderly patients with urosepsis in ICU. Improving the treatment strategies for factors related to the model could improve the in-hospital survival rates of these patients.

Systemic Inflammatory Response Index, a Potential Inflammatory Biomarker in Disease Severity of Myasthenia Gravis: A Pilot Retrospective Study

Purpose

Myasthenia gravis (MG) is a chronic autoimmune disease caused by neuromuscular junction (NMJ) dysfunction. Our current understanding of MG's inflammatory component remains poor. The systemic inflammatory response index (SIRI) presents a promising yet unexplored biomarker for assessing MG severity. This study aimed to investigate the potential relationship between SIRI and MG disease severity.

Patients and Methods

We conducted a retrospective analysis of clinical data from 171 MG patients admitted between January 2016 and June 2021. Patients with incomplete data, other autoimmune diseases, or comorbidities were excluded. Disease severity was evaluated using the Myasthenia Gravis Foundation of America (MGFA) classification and Myasthenia Gravis Activities of Daily Living (MG-ADL) on admission. The association between SIRI and disease severity was assessed through logistic regression analysis, along with receiver operating characteristic (ROC) curve and decision curve analysis (DCA) comparisons with established inflammation indicators.

Results

After exclusion, 143 patients were analyzed in our study. SIRI levels significantly differed between patients with higher and lower disease severity (p < 0.001). Univariate logistic regression showed that SIRI had a significant effect on high disease severity (OR = 1.376, 95% CI 1.138-1.664, p = 0.001). This association remained significant even after adjusting for age, sex, disease duration, history of MG medication and thymoma (OR = 1.308, 95% CI 1.072-1.597, p = 0.008). Additionally, a positive correlation between SIRI and MG-ADL was observed (r = 0.232, p = 0.008). Significant interactions were observed between SIRI and immunosuppressor (p interaction = 0.001) and intravenous immunoglobulin (p interaction = 0.005). DCA demonstrated the superior net clinical benefit of SIRI compared to other markers when the threshold probability was around 0.2.

Conclusion

Our findings indicate a strong independent association between SIRI and disease severity in MG, suggesting SIRI's potential as a valuable biomarker for MG with superior clinical benefit to currently utilized markers.

The enhanced connectivity between the frontoparietal, somatomotor network and thalamus as the most significant network changes of chronic low back pain

The prolonged duration of chronic low back pain (cLBP) inevitably leads to changes in the cognitive, attentional, sensory and emotional processing brain regions. Currently, it remains unclear how these alterations are manifested in the interplay between brain functional and structural networks. This study aimed to predict the Oswestry Disability Index (ODI) in cLBP patients using multimodal brain magnetic resonance imaging (MRI) data and identified the most significant features within the multimodal networks to aid in distinguishing patients from healthy controls (HCs). We constructed dynamic functional connectivity (dFC) and structural connectivity (SC) networks for all participants (n = 112) and employed the Connectome-based Predictive Modeling (CPM) approach to predict ODI scores, utilizing various feature selection thresholds to identify the most significant network change features in dFC and SC outcomes. Subsequently, we utilized these significant features for optimal classifier selection and the integration of multimodal features. The results revealed enhanced connectivity among the frontoparietal network (FPN), somatomotor network (SMN) and thalamus in cLBP patients compared to HCs. The thalamus transmits pain-related sensations and emotions to the cortical areas through the dorsolateral prefrontal cortex (dlPFC) and primary somatosensory cortex (SI), leading to alterations in whole-brain network functionality and structure. Regarding the model selection for the classifier, we found that Support Vector Machine (SVM) best fit these significant network features. The combined model based on dFC and SC features significantly improved classification performance between cLBP patients and HCs (AUC=0.9772). Finally, the results from an external validation set support our hypotheses and provide insights into the potential applicability of the model in real-world scenarios. Our discovery of enhanced connectivity between the thalamus and both the dlPFC (FPN) and SI (SMN) provides a valuable supplement to prior research on cLBP.

Development and validation of a nomogram for assessing comorbidity and frailty in triage: a multicentre observational study

Assessing patient frailty in the Emergency Department (ED) is crucial; however, triage frailty and comorbidity assessment scores developed in recent years are unsatisfactory. The underlying causes of this phenomenon could reside in the nature of the tools used, which were not designed specifically for the emergency context and, thus, are difficult to adapt to the emergency environment. The objective of this study was to create and internally validate a nomogram for identifying different levels of patient frailty during triage. Multicenter, prospective, observational exploratory study conducted in two ED. The study was conducted from April 1 to October 31, 2022. Following the triage assessment, the nurse collected variables related to the patient's comorbidities and chronic conditions using a predefined form. The primary outcome was the 90-day mortality rate. A total of 1345 patients were enrolled in this study; 6% died within 90 days. In the multivariate analysis, the Charlson Comorbidity Index, an altered motor condition, an altered cognitive condition, an autonomous chronic condition, arrival in an ambulance, and a previous hospitalization within 90 days were independently associated with death. The internal validation of the nomogram reported an area under the receiver operating characteristic of 0.91 (95% CI 0.884-0.937). A nomogram was created for assessing comorbidity and frailty during triage and was demonstrated to be capable of determining comorbidity and frailty in the ED setting. Integrating a tool capable of identifying frail patients at the first triage assessment could improve patient stratification.

Experimental validation and comprehensive analysis of m6A methylation regulators in intervertebral disc degeneration subpopulation classification

Intervertebral disc degeneration (IVDD) is one of the most prevalent causes of chronic low back pain. The role of m6A methylation modification in disc degeneration (IVDD) remains unclear. We investigated immune-related m6A methylation regulators as IVDD biomarkers through comprehensive analysis and experimental validation of m6A methylation regulators in disc degeneration. The training dataset was downloaded from the GEO database and analysed for differentially expressed m6A methylation regulators and immunological features, the differentially regulators were subsequently validated by a rat IVDD model and RT-qPCR. Further screening of key m6A methylation regulators based on machine learning and LASSO regression analysis. Thereafter, a predictive model based on key m6A methylation regulators was constructed for training sets, which was validated by validation set. IVDD patients were then clustered based on the expression of key m6A regulators, and the expression of key m6A regulators and immune infiltrates between clusters was investigated to determine immune markers in IVDD. Finally, we investigated the potential role of the immune marker in IVDD through enrichment analysis, protein-to-protein network analysis, and molecular prediction. By analysising of the training set, we revealed significant differences in gene expression of five methylation regulators including RBM15, YTHDC1, YTHDF3, HNRNPA2B1 and ALKBH5, while finding characteristic immune infiltration of differentially expressed genes, the result was validated by PCR. We then screen the differential m6A regulators in the training set and identified RBM15 and YTHDC1 as key m6A regulators. We then used RBM15 and YTHDC1 to construct a predictive model for IVDD and successfully validated it in the training set. Next, we clustered IVDD patients based on the expression of RBM15 and YTHDC1 and explored the immune infiltration characteristics between clusters as well as the expression of RBM15 and YTHDC1 in the clusters. YTHDC1 was finally identified as an immune biomarker for IVDD. We finally found that YTHDC1 may influence the immune microenvironment of IVDD through ABL1 and TXK. In summary, our results suggest that YTHDC1 is a potential biomarker for the development of IVDD and may provide new insights for the precise prevention and treatment of IVDD.

Exploring surgical infection prediction: A comparative study of established risk indexes and a novel model

BACKGROUND

Surgical site infections are a major health problem that deteriorates the patients' health and increases health care costs. A reliable method to identify patients with modifiable risk of surgical site infection is necessary to reduce the incidence of them but data are limited. Hence the objective is to assess the predictive validity of a logistic regression model compared to risk indexes to identify patients at risk of surgical site infections.

METHODS

In this study, we evaluated the predictive validity of a new model which incorporates important predictors based on logistic regression model compared to three state-of-the-art risk indexes to identify high risk patients, recruited from 2016 to 2020 from a medium size hospital in North Norway, prone to surgical site infection.

RESULTS

The logistic regression model demonstrated significantly higher scores, defined as high-risk, in 110 patients with surgical site infections than in 110 patients without surgical site infections (p < 0.001, CI 19-44) compared to risk indexes. The logistic regression model achieved an area under the curve of 80 %, which was better than the risk indexes SSIRS (77 %), NNIS (59 %), and JSS-SSI (52 %) for predicting surgical site infections. The logistic regression model identified operating time and length of stay as the major predictors of surgical site infections.

CONCLUSIONS

The logistic regression model demonstrated better performance in predicting surgical site infections compared to three state-of-the-art risk indexes. The model could be further developed into a decision support tool, by incorporating predictors available prior to surgery, to identify patients with modifiable risk prone to surgical site infection.

Evaluating the clinical utility of an easily applicable prediction model of suicide attempts, newly developed and validated with a general community sample of adults

BACKGROUND

A suicide attempt (SA) is a clinically serious action. Researchers have argued that reducing long-term SA risk may be possible, provided that at-risk individuals are identified and receive adequate treatment. Algorithms may accurately identify at-risk individuals. However, the clinical utility of algorithmically estimated long-term SA risk has never been the predominant focus of any study.

METHODS

The data of this report stem from CoLaus|PsyCoLaus, a prospective longitudinal study of general community adults from Lausanne, Switzerland. Participants (N = 4,097; Mage = 54 years, range: 36-86; 54% female) were assessed up to four times, starting in 2003, approximately every 4-5 years. Long-term individual SA risk was prospectively predicted, using logistic regression. This algorithm's clinical utility was assessed by net benefit (NB). Clinical utility expresses a tool's benefit after having taken this tool's potential harm into account. Net benefit is obtained, first, by weighing the false positives, e.g., 400 individuals, at the risk threshold, e.g., 1%, using its odds (odds of 1% yields 1/(100-1) = 1/99), then by subtracting the result (400*1/99 = 4.04) from the true positives, e.g., 5 individuals (5-4.04), and by dividing the result (0.96) by the sample size, e.g., 800 (0.96/800). All results are based on 100 internal cross-validations. The predictors used in this study were: lifetime SA, any lifetime mental disorder, sex, and age.

RESULTS

SA at any of the three follow-up study assessments was reported by 1.2%. For a range of seven a priori selected threshold probabilities, ranging between 0.5% and 2%, logistic regression showed highest overall NB in 97.4% of all 700 internal cross-validations (100 for each selected threshold probability).

CONCLUSION

Despite the strong class imbalance of the outcome (98.8% no, 1.2% yes) and only four predictors, clinical utility was observed. That is, using the logistic regression model for clinical decision making provided the most true positives, without an increase of false positives, compared to all competing decision strategies. Clinical utility is one among several important prerequisites of implementing an algorithm in routine practice, and may possibly guide a clinicians' treatment decision making to reduce long-term individual SA risk. The novel metric NB may become a standard performance measure, because the a priori invested clinical considerations enable clinicians to interpret the results directly.

A pyrimidine metabolism-related signature for prognostic and immunotherapeutic response prediction in hepatocellular carcinoma by integrating analyses

BACKGROUND

Hepatocellular carcinoma (HCC), with discouraging morbidity and mortality, ranks as one of the most prevalent tumors worldwide. Pyrimidine metabolism is a critical process that regulates DNA and RNA synthesis in cells. It is imperative to investigate the significance of pyrimidine metabolism in liver cancer.

METHODS

Transcriptome and clinical data were downloaded from the TCGA database and the GEO database. The genes related to pyrimidine metabolism were sourced from the MSigDB. The pyrimidine metabolism-related signature (PMRS) was constructed through Cox regression and Lasso regression and then verified in the external validation set from the ICGC database. Functional enrichment, immune infiltration analysis, drug sensitivity, and Immunophenoscore (IPS) were further implemented to predict the response to immunotherapy. The role of PMRS in the malignant phenotype of hepatocellular carcinoma was explored by conducting a series of in vitro experiments.

RESULTS

Our study developed a four-genes PMRS which demonstrates a substantial correlation with the prognosis of HCC patients, serving as an independent predictor in clinical practice. The result of risk-stratified analysis yielded evidence that low-risk patients experienced more favorable clinical outcomes. The nomogram exhibited remarkable prognostic predictive value. The subsequent results revealed that low-risk patients manifested a more promising response to immunotherapy. Moreover, the results of cell experiments demonstrated that the downregulation of DCK markedly inhibited the malignant phenotype of hepatocellular carcinoma.

CONCLUSIONS

Our pyrimidine metabolism-centered prognostic signature accurately predicts overall survival, immune status, and treatment response in hepatocellular carcinoma (HCC) patients, offering innovative insights for precise diagnosis, personalized treatment, and improved prognosis.

Development of a Risk Prediction Model for Infection After Kidney Transplantation Transmitted from Bacterial Contaminated Preservation Solution

Background

The risk of transplant recipient infection is unknown when the preservation solution culture is positive.

Methods

We developed a prediction model to evaluate the infection in kidney transplant recipients within microbial contaminated preservation solution. Univariate logistic regression was utilized to identify risk factors for infection. Both stepwise selection with Akaike information criterion (AIC) was used to identify variables for multivariate logistic regression. Selected variables were incorporated in the nomograms to predict the probability of infection for kidney transplant recipients with microbial contaminated preservation solution.

Results

Age, preoperative creatinine, ESKAPE, PCT, hemofiltration, and sirolimus had a strongest association with infection risk, and a nomogram was established with an AUC value of 0.72 (95% confidence interval, 0.64-0.80) and Brier index 0.20 (95% confidence interval, 0.18-0.23). Finally, we found that when the infection probability was between 20% and 80%, the model oriented antibiotic strategy should have higher net benefits than the default strategy using decision curve analysis.

Conclusion

Our study developed and validated a risk prediction model for evaluating the infection of microbial contaminated preservation solutions in kidney transplant recipients and demonstrated good net benefits when the total infection probability was between 20% and 80%.

BNIP3 and DAPK1 methylation in peripheral blood leucocytes are noninvasive biomarkers for gastric cancer

OBJECTIVE

The objective of this study is to comprehensively investigate the potential value of BNIP3 and DAPK1 methylation in peripheral blood leukocytes as a non-invasive biomarker for the detection of gastric cancer (GC), prediction of chemotherapy efficacy, and prognosis assessment.

PATIENTS AND METHODS

Initially, multiple bioinformatic analyses were employed to explore the genetic landscape and biological effects of BNIP3 and DAPK1 in GC tissues. Subsequently, case-control and prospective follow-up studies were conducted to compare the differences in BNIP3 and DAPK1 methylation levels in peripheral blood leukocytes among GC patients and healthy controls, as well as between patients exhibiting sensitivity and resistance to platinum plus fluorouracil treatment, and between patients with varying survival outcomes of GC. Additionally, several predictive nomograms were constructed based on the identified CpG sites and relevant clinical parameters to forecast the occurrence of GC, chemotherapy efficacy, and prognosis.

RESULTS

The upregulation of BNIP3 and DAPK1 was found to be associated with the development and poorer survival outcomes of GC. Furthermore, the expression of BNIP3/DAPK1 exhibited an inverse relationship with their DNA methylation levels and demonstrated a positive correlation with immune cell infiltration, as well as the IC50 values of 5-Fluorouracil and Cisplatin in GC tissues. Increased infiltration of macrophages in the high-expression groups was observed to be linked to unfavorable GC survival. In the case-control and follow-up studies, lower methylation levels of BNIP3 and DAPK1 were identified in the peripheral leukocytes of GC patients compared to healthy controls. Hypomethylation was also associated with more aggressive subtypes, diminished chemotherapy efficacy, and poorer survival outcomes in GC.

CONCLUSION

The DNA methylation of BNIP3 and DAPK1 in peripheral blood leukocytes holds promise as a novel non-invasive biomarker for predicting the occurrence of GC, chemotherapy efficacy, and prognosis assessment.

Bioinformatics analysis of differentially expressed genes related to ischemia and hypoxia in spinal cord injury and construction of miRNA-mRNA or mRNA-transcription factor interaction network

BACKGROUND

Previous studies show that spinal cord ischemia and hypoxia is an important cause of spinal cord necrosis and neurological loss. Therefore, the study aimed to identify genes related to ischemia and hypoxia after spinal cord injury (SCI) and analyze their functions, regulatory mechanism, and potential in regulating immune infiltration.

METHODS

The expression profiles of GSE5296, GSE47681, and GSE217797 were downloaded from the Gene Expression Omnibus database. Gene ontology and Kyoto Encyclopedia of Genes and Genomes analyses were performed to determine the function and pathway enrichment of ischemia- and hypoxia-related differentially expressed genes (IAHRDEGs) in SCI. LASSO model was constructed, and support vector machine analysis was used to identify key genes. The diagnostic values of key genes were evaluated using decision curve analysis and receiver operating characteristic curve analysis. The interaction networks of miRNAs-IAHRDEGs and IAHRDEGs-transcription factors were predicted and constructed with the ENCORI database and Cytoscape software. CIBERSORT algorithm was utilized to analyze the correlation between key gene expression and immune cell infiltration.

RESULTS

There were 27 IAHRDEGs identified to be significantly expressed in SCI at first. These genes were mostly significantly enriched in wound healing function and the pathway associated with lipid and atherosclerosis. Next, five key IAHRDEGs (Abca1, Casp1, Lpl, Procr, Tnfrsf1a) were identified and predicted to have diagnostic value. Moreover, the five key genes are closely related to immune cell infiltration.

CONCLUSION

Abca1, Casp1, Lpl, Procr, and Tnfrsf1a may promote the pathogenesis of ischemic or hypoxic SCI by regulating vascular damage, inflammation, and immune infiltration.

Development of a Prediction Model for Significant Adverse Outcome After Spine Surgery

STUDY DESIGN

Retrospective cohort study.

OBJECTIVES

Development, validation, and decision curve analysis of a novel tool (NZSpine) for modelling risk of complications within 30 days of spine surgery.

METHODS

Data was gathered retrospectively from medical records of patients who underwent spine surgery at a single tertiary centre between January 2019 and December 2020 (n = 488). Postoperative adverse events were classified objectively using the Comprehensive Complication Index (CCI). The model was derived using backward stepwise logistic regression. Validation was undertaken using bootstrap resampling. Discrimination was determined by calculating the area under the receiver operating characteristic (AUC). Calibration was assessed graphically. Clinical utility of the model was assessed using decision curve analysis (DCA). Performance measures were compared to an existing tool, SpineSage.

RESULTS

Overall complication rate was 34%. Modelling showed higher age, surgical invasiveness and preoperative anemia were most strongly predictive of any complication (OR = 1.03, 1.09, 2.1 respectively, P < .001), whereas the occurrence of a major complication (CCI >26) was most strongly associated with the presence of respiratory disease (OR = 2.82, P < .001). At validation, the model showed good discrimination with an AUC of .73 (.71 - .75) and excellent calibration. SpineSage had an AUC of .71, while DCA showed the novel model had greater expected benefit at all risk thresholds.

CONCLUSION

NZSpine is a novel risk assessment tool for patients undergoing acute and elective spine surgery and may help inform clinicians and patients of their perioperative risk.

Identification of influence factors in overweight population through an interpretable risk model based on machine learning: a large retrospective cohort

BACKGROUND

The identification of associated overweight risk factors is crucial to future health risk predictions and behavioral interventions. Several consensus problems remain in machine learning, such as cross-validation, and the resulting model may suffer from overfitting or poor interpretability.

METHODS

This study employed nine commonly used machine learning methods to construct overweight risk models. The general community are the target of this study, and a total of 10,905 Chinese subjects from Ningde City in Fujian province, southeast China, participated. The best model was selected through appropriate verification and validation and was suitably explained.

RESULTS

The overweight risk models employing machine learning exhibited good performance. It was concluded that CatBoost, which is used in the construction of clinical risk models, may surpass previous machine learning methods. The visual display of the Shapley additive explanation value for the machine model variables accurately represented the influence of each variable in the model.

CONCLUSIONS

The construction of an overweight risk model using machine learning may currently be the best approach. Moreover, CatBoost may be the best machine learning method. Furthermore, combining Shapley's additive explanation and machine learning methods can be effective in identifying disease risk factors for prevention and control.

Development and validation of survival nomograms in elder triple-negative invasive ductal breast carcinoma patients

BACKGROUND

We aimed to develop a nomogram to predict the overall survival of elderly patients with Triple-negative invasive ductal breast carcinoma (TNIDC).

RESEARCH DESIGN AND METHODS

12165 elderly patients with nonmetastatic TNIDC were retrieved from the SEER database from 2010 to 2019 and were randomly assigned to training and validation cohorts. Stepwise Cox regression analysis was used to select variables for the nomogram based on the training cohort. Univariate and multivariate Cox analyses were used to calculate the correlation between variables and prognosis of the patients. Survival analysis was performed for high- and low-risk subgroups based on risk score.

RESULTS

Eleven predictive factors were identified to construct our nomograms. Compared with the TNM stage, the discrimination of the nomogram revealed good prognostic accuracy and clinical applicability as indicated by C-index values of 0.741 (95% CI 0.728-0.754) against 0.708 (95% CI 0.694-0.721) and 0.765 (95% CI 0.747-0.783) against 0.725 (95% CI 0.705-0.744) for the training and validation cohorts, respectively. Differences in OS were also observed between the high- and low-risk groups (p < 0.001).

CONCLUSION

The proposed nomogram provides a convenient and reliable tool for individual evaluations for elderly patients with M0_stage TNIDC. However, the model may only for Americans.

Association between traditional Chinese Medicine and osteoarthritis outcome: A 5-year matched cohort study

Objective

The aim of this study was to investigate the relationship between Traditional Chinese medicine (TCM) and pain reduction, hospital readmission, and joint replacement in patients with osteoarthritis (OA). Chinese herbal medicine (CHM) prescription patterns were further analyzed to confirm the association with prognosis and quality of life in OA patients.

Methods

We retrospectively followed 3,850 hospitalized patients with osteoarthritis between January 2018 and December 2022 using the hospital's HIS system. Propensity score matching (PSM) was used for data matching. Cox's proportional risk model was used to assess the impact of various factors on the outcomes of patients with OA, including pain worsening, readmission, and joint replacement. The Kaplan-Meier survival curve was applied to determine the impact of TCM intervention time on patient outcomes. Data mining methods including association rules, cluster analysis, and random walks have been used to assess the efficacy of TCM.

Results

The utilization rate of TCM in OA patients was 67.01% (2,511/3,747). After PSM matching, 1,228 TCM non-user patients and 1,228 TCM user patients were eventually included. The outcomes of pain worsening, re-admission rate, and joint replacement rate of the TCM non-user group were observably higher than those of the TCM user group with OA (p < 0.05). Based on the Cox proportional risk model, TCM is an independent protective factor. Compared with non-TCM users, TCM users had 58.4% lower rates of pain, 51.1% lower rates of re-admission, and 42% lower rates of joint replacement. In addition, patients in the high-exposure subgroup (TCM＞24 months) had a markedly lower risk of outcome events than those in the low-exposure subgroup (TCM ≤24 months). Data mining methods have shown that TCM therapy can significantly improve immune-inflammatory indices, VAS scores, and SF-36 scale scores in OA patients.

Conclusion

s TCM acts as a protective factor to improve the prognosis of patients with OA, and the benefits of long-term use of herbal medicines are even greater.

Development and Validation of a Nomogram for Predicting Obstructive Sleep Apnea Severity in Children

Purpose

The clinical presentation of Obstructive Sleep Apnea (OSA) in children is insidious and harmful. Early identification of children with OSA, particularly those at a higher risk for severe symptoms, is essential for making informed clinical decisions and improving long-term outcomes. Therefore, we developed and validated a risk prediction model for severity in Chinese children with OSA to effectively identify children with moderate-to-severe OSA in a clinical setting.

Patients and Methods

From June 2023 to September 2023, we retrospectively analyzed the medical records of 367 Children diagnosed with OSA through portable bedside polysomnography (PSG). Predictor variables were screened using the least absolute shrinkage and selection operator (LASSO) and logistic regression techniques to construct nomogram to predict the severity of OSA. Receiver operating characteristic curve (ROC), calibration curve, decision curve analysis (DCA), and clinical impact curve (CIC) were used to determine the discrimination, calibration, and clinical usefulness of the nomogram.

Results

A total of 367 children with a median age of 84 months were included in this study. Neck circumference, ANB, gender, learning problem, and level of obstruction were identified as independent risk factors for moderate-severe OSA. The consistency indices of the nomogram in the training and validation cohorts were 0.841 and 0.75, respectively. The nomogram demonstrated a strong concordance between the predicted probabilities and the observed probabilities for children diagnosed with moderate-severe OSA. With threshold probabilities ranging from 0.1 to 1.0, the predictive model demonstrated strong predictive efficacy and yielded improved net benefit for clinical decision-making. ROC analysis was employed to classify the children into high and low-risk groups, utilizing the Optimal Cutoff value of 0.39.

Conclusion

A predictive model using LASSO regression was developed and validated for children with varying levels of OSA. This model identifies children at risk of developing OSA at an early stage.

Construction and validation of a predictive model of invasive adenocarcinoma in pure ground-glass nodules less than 2 cm in diameter

OBJECTIVES

In this study, we aimed to develop a multiparameter prediction model to improve the diagnostic accuracy of invasive adenocarcinoma in pulmonary pure glass nodules.

METHOD

We included patients with pulmonary pure glass nodules who underwent lung resection and had a clear pathology between January 2020 and January 2022 at the Qilu Hospital of Shandong University. We collected data on the clinical characteristics of the patients as well as their preoperative biomarker results and computed tomography features. Thereafter, we performed univariate and multivariate logistic regression analyses to identify independent risk factors, which were then used to develop a prediction model and nomogram. We then evaluated the recognition ability of the model via receiver operating characteristic (ROC) curve analysis and assessed its calibration ability using the Hosmer-Lemeshow test and calibration curves. Further, to assess the clinical utility of the nomogram, we performed decision curve analysis.

RESULT

We included 563 patients, comprising 174 and 389 cases of invasive and non-invasive adenocarcinoma, respectively, and identified seven independent risk factors, namely, maximum tumor diameter, age, serum amyloid level, pleural effusion sign, bronchial sign, tumor location, and lobulation. The area under the ROC curve was 0.839 (95% CI: 0.798-0.879) for the training cohort and 0.782 (95% CI: 0.706-0.858) for the validation cohort, indicating a relatively high predictive accuracy for the nomogram. Calibration curves for the prediction model also showed good calibration for both cohorts, and decision curve analysis showed that the clinical prediction model has clinical utility.

CONCLUSION

The novel nomogram thus constructed for identifying invasive adenocarcinoma in patients with isolated pulmonary pure glass nodules exhibited excellent discriminatory power, calibration capacity, and clinical utility.

A dynamic visualization clinical tool constructed and validated based on the SEER database for screening the optimal surgical candidates for bone metastasis in primary kidney cancer

The implementation of primary tumor resection (PTR) in the treatment of kidney cancer patients (KC) with bone metastases (BM) has been controversial. This study aims to construct the first tool that can accurately predict the likelihood of PTR benefit in KC patients with BM (KCBM) and select the optimal surgical candidates. This study acquired data on all patients diagnosed with KCBM during 2010-2015 from the Surveillance, Epidemiology, and End Results (SEER) database. Propensity score matching (PSM) was utilized to achieve balanced matching of PTR and non-PTR groups to eliminate selection bias and confounding factors. The median overall survival (OS) of the non-PTR group was used as the threshold to categorize the PTR group into PTR-beneficial and PTR-Nonbeneficial subgroups. Kaplan-Meier (K-M) survival analysis was used for comparison of survival differences and median OS between groups. Risk factors associated with PTR-beneficial were identified using univariate and multivariate logistic regression analyses. Receiver operating characteristic (ROC), area under the curve (AUC), calibration curves, and decision curve analysis (DCA) were used to validate the predictive performance and clinical utility of the nomogram. Ultimately, 1963 KCBM patients meeting screening criteria were recruited. Of these, 962 patients received PTR and the remaining 1061 patients did not receive PTR. After 1:1 PSM, there were 308 patients in both PTR and non-PTR groups. The K-M survival analysis results showed noteworthy survival disparities between PTR and non-PTR groups, both before and after PSM (p < 0.001). In the logistic regression results of the PTR group, histological type, T/N stage and lung metastasis were shown to be independent risk factors associated with PTR-beneficial. The web-based nomogram allows clinicians to enter risk variables directly and quickly obtain PTR beneficial probabilities. The validation results showed the excellent predictive performance and clinical utility of the nomograms for accurate screening of optimal surgical candidates for KCBM. This study constructed an easy-to-use nomogram based on conventional clinicopathologic variables to accurately select the optimal surgical candidates for KCBM patients.

Decision Curve Analysis of In-Hospital Mortality Prediction Models: The Relative Value of Pre- and Intraoperative Data For Decision-Making

BACKGROUND

Clinical prediction modeling plays a pivotal part in modern clinical care, particularly in predicting the risk of in-hospital mortality. Recent modeling efforts have focused on leveraging intraoperative data sources to improve model performance. However, the individual and collective benefit of pre- and intraoperative data for clinical decision-making remains unknown. We hypothesized that pre- and intraoperative predictors contribute equally to the net benefit in a decision curve analysis (DCA) of in-hospital mortality prediction models that include pre- and intraoperative predictors.

METHODS

Data from the VitalDB database featuring a subcohort of 6043 patients were used. A total of 141 predictors for in-hospital mortality were grouped into preoperative (demographics, intervention characteristics, and laboratory measurements) and intraoperative (laboratory and monitor data, drugs, and fluids) data. Prediction models using either preoperative, intraoperative, or all data were developed with multiple methods (logistic regression, neural network, random forest, gradient boosting machine, and a stacked learner). Predictive performance was evaluated by the area under the receiver-operating characteristic curve (AUROC) and under the precision-recall curve (AUPRC). Clinical utility was examined with a DCA in the predefined risk preference range (denoted by so-called treatment threshold probabilities) between 0% and 20%.

RESULTS

AUROC performance of the prediction models ranged from 0.53 to 0.78. AUPRC values ranged from 0.02 to 0.25 (compared to the incidence of 0.09 in our dataset) and high AUPRC values resulted from prediction models based on preoperative laboratory values. A DCA of pre- and intraoperative prediction models highlighted that preoperative data provide the largest overall benefit for decision-making, whereas intraoperative values provide only limited benefit for decision-making compared to preoperative data. While preoperative demographics, comorbidities, and surgery-related data provide the largest benefit for low treatment thresholds up to 5% to 10%, preoperative laboratory measurements become the dominant source for decision support for higher thresholds.

CONCLUSIONS

When it comes to predicting in-hospital mortality and subsequent decision-making, preoperative demographics, comorbidities, and surgery-related data provide the largest benefit for clinicians with risk-averse preferences, whereas preoperative laboratory values provide the largest benefit for decision-makers with more moderate risk preferences. Our decision-analytic investigation of different predictor categories moves beyond the question of whether certain predictors provide a benefit in traditional performance metrics (eg, AUROC). It offers a nuanced perspective on for whom these predictors might be beneficial in clinical decision-making. Follow-up studies requiring larger datasets and dedicated deep-learning models to handle continuous intraoperative data are essential to examine the robustness of our results.

The role of adenocarcinoma subtypes and immunohistochemistry in predicting lymph node metastasis in early invasive lung adenocarcinoma

BACKGROUND

Identifying lymph node metastasis areas during surgery for early invasive lung adenocarcinoma remains challenging. The aim of this study was to develop a nomogram mathematical model before the end of surgery for predicting lymph node metastasis in patients with early invasive lung adenocarcinoma.

METHODS

In this study, we included patients with invasive lung adenocarcinoma measuring ≤ 2 cm who underwent pulmonary resection with definite pathology at Qilu Hospital of Shandong University from January 2020 to January 2022. Preoperative biomarker results, clinical features, and computed tomography characteristics were collected. The enrolled patients were randomized into a training cohort and a validation cohort in a 7:3 ratio. The training cohort was used to construct the predictive model, while the validation cohort was used to test the model independently. Univariate and multivariate logistic regression analyses were performed to identify independent risk factors. The prediction model and nomogram were established based on the independent risk factors. Recipient operating characteristic (ROC) curves were used to assess the discrimination ability of the model. Calibration capability was assessed using the Hosmer-Lemeshow test and calibration curves. The clinical utility of the nomogram was assessed using decision curve analysis (DCA).

RESULTS

The overall incidence of lymph node metastasis was 13.23% (61/461). Six indicators were finally determined to be independently associated with lymph node metastasis. These six indicators were: age (P < 0.001), serum amyloid (SA) (P = 0.008); carcinoma antigen 125 (CA125) (P = 0. 042); mucus composition (P = 0.003); novel aspartic proteinase of the pepsin family A (Napsin A) (P = 0.007); and cytokeratin 5/6 (CK5/6) (P = 0.042). The area under the ROC curve (AUC) was 0.843 (95% CI: 0.779-0.908) in the training cohort and 0.838 (95% CI: 0.748-0.927) in the validation cohort. the P-value of the Hosmer-Lemeshow test was 0.0613 in the training cohort and 0.8628 in the validation cohort. the bias of the training cohort corrected C-index was 0.8444 and the bias-corrected C-index for the validation cohort was 0.8375. demonstrating that the prediction model has good discriminative power and good calibration.

CONCLUSIONS

The column line graphs created showed excellent discrimination and calibration to predict lymph node status in patients with ≤ 2 cm invasive lung adenocarcinoma. In addition, the predictive model has predictive potential before the end of surgery and can inform clinical decision making.

Predictive value of HTS grade in patients with intrahepatic cholangiocarcinoma undergoing radical resection: a multicenter study from China

BACKGROUND

Intrahepatic cholangiocarcinoma (ICC) is a highly malignant tumor with a poor prognosis. This study aimed to investigate whether Hemoglobin, Albumin, Lymphocytes, and Platelets (HALP) score and Tumor Burden Score (TBS) serves as independent influencing factors following radical resection in patients with ICC. Furthermore, we sought to evaluate the predictive capacity of the combined HALP and TBS grade, referred to as HTS grade, and to develop a prognostic prediction model.

METHODS

Clinical data for ICC patients who underwent radical resection were retrospectively analyzed. Univariate and multivariate Cox regression analyses were first used to find influencing factors of prognosis for ICC. Receiver operating characteristic (ROC) curves were then used to find the optimal cut-off values for HALP score and TBS and to compare the predictive ability of HALP, TBS, and HTS grade using the area under these curves (AUC). Nomogram prediction models were constructed and validated based on the results of the multivariate analysis.

RESULTS

Among 423 patients, 234 (55.3%) were male and 202 (47.8) were aged ≥ 60 years. The cut-off value of HALP was found to be 37.1 and for TBS to be 6.3. Our univariate results showed that HALP, TBS, and HTS grade were prognostic factors of ICC patients (all P < 0.05), and ROC results showed that HTS had the best predictive value. The Kaplan-Meier curve showed that the prognosis of ICC patients was worse with increasing HTS grade. Additionally, multivariate regression analysis showed that HTS grade, carbohydrate antigen 19-9 (CA19-9), tumor differentiation, and vascular invasion were independent influencing factors for Overall survival (OS) and that HTS grade, CA19-9, CEA, vascular invasion and lymph node invasion were independent influencing factors for recurrence-free survival (RFS) (all P < 0.05). In the first, second, and third years of the training group, the AUCs for OS were 0.867, 0.902, and 0.881, and the AUCs for RFS were 0.849, 0.841, and 0.899, respectively. In the first, second, and third years of the validation group, the AUCs for OS were 0.727, 0.771, and 0.763, and the AUCs for RFS were 0.733, 0.746, and 0.801, respectively. Through the examination of calibration curves and using decision curve analysis (DCA), nomograms based on HTS grade showed excellent predictive performance.

CONCLUSIONS

Our nomograms based on HTS grade had excellent predictive effects and may thus be able to help clinicians provide individualized clinical decision for ICC patients.

Machine learning-based model for prediction of deep vein thrombosis after gynecological laparoscopy: A retrospective cohort study

Successful monitoring of deep vein thrombosis (DVT) remains a challenging problem after gynecological laparoscopy. Thus, this study aimed to create and validate predictive models for DVT with the help of machine learning (ML) algorithms. A total of 489 patients from the Cancer Biology Research Center, Tongji Hospital were included in the study between January 2017 and February 2023, and 35 clinical indicators from electronic health records (EHRs) were collected within 24h of patient admission. Risk factors were identified using the least absolute shrinkage and selection operator (LASSO) regression. Then, the three commonly used DVT prediction models are random forest model (RFM), generalized linear regression model (GLRM), and artificial neural network model (ANNM). In addition, the predictive performance of various prediction models (i.e. the robustness and accuracy of predictions) is evaluated through the receiver operating characteristic curve (ROC) and decision curve analysis (DCA), respectively. We found postoperative DVT in 41 (8.38%) patients. Based on the ML algorithm, a total of 13 types of clinical data were preliminarily screened as candidate variables for DVT prediction models. Among these, age, body mass index (BMI), operation time, intraoperative pneumoperitoneum pressure (IPP), diabetes, complication and D-Dimer independent risk factors for postoperative DVT and can be used as variables in ML prediction models. The RFM algorithm can achieve the optimal DVT prediction performance, with AUC values of 0.851 (95% CI: 0.793-0.909) and 0.862 (95% CI: 0.804-0.920) in the training and validation sets, respectively. The AUC values of the other two prediction models (ANNM and GLRM) range from 0.697 (95% CI: 0.639-0.755) and 0.813 (95% CI: 0.651-0.767). In summary, we explored the potential risk of DVT after gynecological laparoscopy, which helps clinicians identify high-risk patients before gynecological laparoscopy and make nursing interventions. However, external validation will be needed in the future.

Prediction of injury localization in preoperative patients with gastrointestinal perforation: a multiomics model analysis

BACKGROUND

The location of gastrointestinal perforation is essential for severity evaluation and optimizing the treatment approach. We aimed to retrospectively analyze the clinical characteristics, laboratory parameters, and imaging features of patients with gastrointestinal perforation and construct a predictive model to distinguish the location of upper and lower gastrointestinal perforation.

METHODS

A total of 367 patients with gastrointestinal perforation admitted to the department of emergency surgery in Fujian Medical University Union Hospital between March 2014 and December 2020 were collected. Patients were randomly divided into training set and test set in a ratio of 7:3 to establish and verify the prediction model by logistic regression. The receiver operating characteristic curve, calibration map, and clinical decision curve were used to evaluate the discrimination, calibration, and clinical applicability of the prediction model, respectively. The multiomics model was validated by stratification analysis in the prediction of severity and prognosis of patients with gastrointestinal perforation.

RESULTS

The following variables were identified as independent predictors in lower gastrointestinal perforation: monocyte absolute value, mean platelet volume, albumin, fibrinogen, pain duration, rebound tenderness, free air in peritoneal cavity by univariate logistic regression analysis and stepwise regression analysis. The area under the receiver operating characteristic curve of the prediction model was 0.886 (95% confidence interval, 0.840-0.933). The calibration curve shows that the prediction accuracy and the calibration ability of the prediction model are effective. Meanwhile, the decision curve results show that the net benefits of the training and test sets are greater than those of the two extreme models as the threshold probability is 20-100%. The multiomics model score can be calculated via nomogram. The higher the stratification of risk score array, the higher the number of transferred patients who were admitted to the intensive care unit (P < 0.001).

CONCLUSION

The developed multiomics model including monocyte absolute value, mean platelet volume, albumin, fibrinogen, pain duration, rebound tenderness, and free air in the peritoneal cavity has good discrimination and calibration. This model can assist surgeons in distinguishing between upper and lower gastrointestinal perforation and to assess the severity of the condition.

A nomogram for analyzing risk factors of poor treatment response in patients with autoimmune hepatitis

OBJECTIVE

The objective of this study was to identify biochemical and clinical predictors of poor response (including incomplete response and non-response) to standard treatment in autoimmune hepatitis (AIH) patients.

METHODS

This study retrospectively collected clinical data from 297 patients who were first diagnosed with AIH in Beijing Ditan Hospital from 2010 to 2019. Finally, 149 patients were screened out. Risk factors were screened by univariate and multifactorial logistic regression. Then they were used to establish the nomogram. The ROC curve, calibration curve, decision curves analysis (DCA) and clinical impact curves (CIC) were used to evaluate the nomogram.

RESULTS

149 patients were divided into two groups: the response group (n = 120, 80%) and the poor response group (n = 29, 20%). Multivariate logistic regression analysis found that IgG > 26.5 g/L (OR: 22.016; 95% CI: 4.677-103.640) in AIH patients increased the risk. In contrast, treatment response status was better in women (OR: 0.085; 95% CI: 0.015-0.497) aged >60 years (OR: 0.159; 95% CI: 0.045-0.564) with AST > 4.49 × ULN (OR: 0.066; 95% CI: 0.009-0.494). The C index (0.853) and the calibration curve show that the nomogram is well differentiated and calibrated; the DCA and CIC indicate that the model has good clinical benefits and implications.

CONCLUSION

The study found that male patients aged ≤ 60 years with IgG > 26.5 g/L and elevated AST ≤ 4.49 × ULN were more likely to have a non-response/incomplete response to standard treatment.

Construction and validation of a nomogram for predicting fear of falling related activity restrictions in community-dwelling older adults

Fear of falling related activity restrictions are widespread among older adults, leading to several adverse effects. Given these consequences, there is an urgent need for a comprehensive assessment tool that integrates various risk factors to predict the likelihood of older adults experiencing such activity restrictions. This cross-sectional study investigated fear of falling related activity restrictions and its influencing factors, simultaneously constructed and validated a nomogram among older adults residing in the communities in China. The model includes variables like age, gender, self-rated health, past year injurious falls, gait stability, anxiety, and cognitive impairment. It showed an AUC of 0.892. Internal validation had an AUC of 0.893, and external validation had an AUC of 0.939. Calibration curve showed good fit, and decision curve showed high clinical benefits. It's an intuitive tool for medical professionals to identify older adults at high risk of activity restrictions due to fear of falling.

Clinical Utility of Melanoma Sentinel Lymph Node Biopsy Nomograms

BACKGROUND

For patients with melanoma, the decision to perform sentinel lymph node biopsy (SLNB) is based on the estimated risk of lymph node metastasis. We assessed 3 melanoma SLNB risk-prediction models' statistical performance and their ability to improve clinical decision making (clinical utility) on a cohort of melanoma SLNB cases.

STUDY DESIGN

Melanoma patients undergoing SLNB at a single center from 2003 to 2021 were identified. The predicted probabilities of sentinel lymph node positivity using the Melanoma Institute of Australia, Memorial Sloan Kettering Cancer Center (MSK), and Friedman nomograms were calculated. Receiver operating characteristic and calibration curves were generated. Clinical utility was assessed via decision curve analysis, calculating the net SLNBs that could have been avoided had a given model guided selection at different risk thresholds.

RESULTS

Of 2,464 melanoma cases that underwent SLNB, 567 (23.0%) had a positive sentinel lymph node. The areas under the receiver operating characteristic curves for the Melanoma Institute of Australia, MSK, and Friedman models were 0.726 (95% CI, 0.702 to 0.750), 0.720 (95% CI, 0.697 to 0.744), and 0.721 (95% CI, 0.699 to 0.744), respectively. For all models, calibration was best at predicted positivity rates below 30%. The MSK model underpredicted risk. At a 10% risk threshold, only the Friedman model would correctly avoid a net of 6.2 SLNBs per 100 patients. The other models did not reduce net avoidable SLNBs at risk thresholds of ≤10%.

CONCLUSIONS

The tested nomograms had comparable performance in our cohort. The only model that achieved clinical utility at risk thresholds of ≤10% was the Friedman model.

Predictive nomograms for risk and prognostic factors in metastatic bladder cancer: a population-based study

Background

Given the poor prognosis of patients with metastatic bladder cancer (MBC), the development of an effective diagnostic and prognostic model is significant in cancer management and for guidance in clinical practice.

Methods

We acquired data of 23,180 bladder cancer patients from Surveillance Epidemiology and End Results (SEER) database registered from 2010 to 2019. The optimal cut-off value for patient age and tumor size was determined by x-tile software. Independent risk factors for MBC were identified by univariate and multivariate logistic regression analyses and prognosis factors were identified by univariate and multivariate cox regression analyses, and risk and prognostic nomograms were constructed. The accuracy of the nomograms was verified by receiver operating characteristic (ROC) curves, calibration curves, and its clinical utility was determined by decision curve analysis (DCA) curves and clinical impact curves (CIC). Kaplan-Meier (K-M) survival curves further confirmed the clinical validity of the prognostic model.

Results

Through logistic regression analyses, we derived that age, histological type, tumor size, T stage, and N stage were independent risk factors for metastasis in bladder cancer patients. By cox regression analyses, age, chemotherapy, histological type, bone, lung and liver metastases were identified as risk factors influencing prognosis of MBC patients. Area under the curve (AUC) of the risk nomogram was 0.80, the AUC values of 1/2/3 years were 0.74/0.71/0.71 in the training group and 0.81/0.77/0.77 in the validation group. Based on calibration curves, DCA curves, CIC and K-M curves, the nomograms were validated with excellent predictive performance and clinical utility for MBC.

Conclusions

The nomograms we constructed have perfect predictive accuracy and clinical practicality for MBC patients, enabling clinicians to provide treatment advice and clinical guidance to patients.

Development and Validation of Nomograms to Predict Risk and Prognosis in Salivary Gland Carcinoma Patient with Distant Metastases

Background: Salivary gland carcinoma (SGC) patients with distant metastasis (DM) are rare, and understanding this disease is insufficient. Nomograms can predict the prognostic probability of patients, while few studies have examined diagnostic and prognostic factors in SGC patients with DM. The purpose of this study was to establish and validate the risk and prognostic nomograms of SGC patients with DM. Methods: Based on the SEER database, we analyzed the data of SGC patients between 2004 and 2015. Logistic regression analyses and Cox proportional hazards regression analyses were used to identify risk and prognostic factors for DM in SGC patients. Based on the Akaike information criterion (AIC) value and likelihood ratio test, the best-fitting model was selected to build risk and prognostic nomograms, and the results were evaluated by receiver operating characteristic (ROC) curves, calibration curves, decision curve analysis (DCA), and Kaplan-Meier (K-M) survival curves. ROC curves were also used to compare the nomograms with the American Joint Committee on Cancer (AJCC) staging system. Results: 7418 SGC patients were included in the study, and 307 (4.14%) of them were diagnosed with DM. This study identified that there are variables (age ≥ 80, no-parotid gland primary site, histologic type of mucoepidermoid carcinoma and squamous cell carcinoma, T stage ≥ T2, N staged ≥ N1, histologic grade ≥ III, and tumor size ≥ 41 mm) associated with the occurrence of DM in SGC patients. Therefore, we constructed diagnostic and prognostic nomograms after incorporating these variables. ROC curves illustrated the better predictive efficacy of 2 nomograms over the AJCC staging system. DCA curves, calibration curves, and K-M survival curves showed that 2 nomograms can accurately predict the occurrence and prognosis of DM among SGC patients in training and validation sets. Conclusion: It was shown that the nomograms were highly discriminative in predicting the diagnosis and prognosis of SGC patients with DM, and could identify high-risk patients, thereby providing SGC patients with individualized treatment plans.

Development of a novel score (RENSAFE) to determine probability of acute kidney injury and renal functional decline post surgery: A multicenter analysis

OBJECTIVE

To create and validate 2 models called RENSAFE (RENalSAFEty) to predict postoperative acute kidney injury (AKI) and development of chronic kidney disease (CKD) stage 3b in patients undergoing partial (PN) or radical nephrectomy (RN) for kidney cancer.

METHODS

Primary objective was to develop a predictive model for AKI (reduction >25% of preoperative eGFR) and de novo CKD≥3b (<45 ml/min/1.73m2), through stepwise logistic regression. Secondary outcomes include elucidation of the relationship between AKI and de novo CKD≥3a (<60 ml/min/1.73m2). Accuracy was tested with receiver operator characteristic area under the curve (AUC).

RESULTS

AKI occurred in 452/1,517 patients (29.8%) and CKD≥3b in 116/903 patients (12.8%). Logistic regression demonstrated male sex (OR = 1.3, P = 0.02), ASA score (OR = 1.3, P < 0.01), hypertension (OR = 1.6, P < 0.001), R.E.N.A.L. score (OR = 1.2, P < 0.001), preoperative eGFR<60 (OR = 1.8, P = 0.009), and RN (OR = 10.4, P < 0.0001) as predictors for AKI. Age (OR 1.0, P < 0.001), diabetes mellitus (OR 2.5, P < 0.001), preoperative eGFR <60 (OR 3.6, P < 0.001) and RN (OR 2.2, P < 0.01) were predictors for CKD≥3b. AUC for RENSAFE AKI was 0.80 and 0.76 for CKD≥3b. AKI was predictive for CKD≥3a (OR = 2.2, P < 0.001), but not CKD≥3b (P = 0.1). Using 21% threshold probability for AKI achieved sensitivity: 80.3%, specificity: 61.7% and negative predictive value (NPV): 88.1%. Using 8% cutoff for CKD≥3b achieved sensitivity: 75%, specificity: 65.7%, and NPV: 96%.

CONCLUSION

RENSAFE models utilizing perioperative variables that can predict AKI and CKD may help guide shared decision making. Impact of postsurgical AKI was limited to less severe CKD (eGFR<60 ml/min 71.73m2). Confirmatory studies are requisite.

Development and validation of a nomogram for predicting pulmonary infections after Intracerebral hemorrhage in elderly people

OBJECTIVES

The purpose of this study was to develop and validate a nomogram for the prediction of pulmonary infections in elderly patients with intracerebral hemorrhage (ICH) during hospitalization in the intensive care unit (ICU).

METHODS

A total of 1183 elderly patients diagnosed with ICH were included from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and randomly grouped into training (n=831) and validation (n=352) cohorts. Candidate predictors were identified using the least absolute shrinkage and selection operator (LASSO) regression. Meanwhile, the variables derived from the LASSO regression were included in the multivariate logistic regression analysis, the variables with P < 0.05 were included in the final model and the nomogram was constructed. The discriminatory ability was assessed by plotting the receiver operating curve (ROC) and calculating the area under the curve (AUC). The Performance of the model was assessed by calibration plots and the Hosmer-Lemeshow goodness-of-fit test (HL test). In addition, clinical decision curves assess the net clinical benefit.

RESULTS

The nomogram included chronic lung disease, dysphagia, mechanical ventilation, use of antibiotics, Glasgow Coma Scale (GCS), Logical Organ Dysfunction System (LODS), blood oxygen saturation (SpO2), white blood cell count (WBC) and prothrombin time (PT). The AUC of the predictive model was 0.905 (95 % CI: 0.877, 0.764) in the training cohort and 0.888 (95 % CI: 0.754, 0.838) in the validation cohort, which showed satisfactory discriminative ability. Second, the nomogram showed good calibration. Decision curve analysis showed that the predictive nomogram was clinically useful.

CONCLUSION

A prediction model for predicting pulmonary infections in elderly ICH patients was constructed. The model can help clinicians to identify high-risk patients as soon as possible and prevent the occurrence of pulmonary infections.

Development and validation of web calculators to predict early recurrence and long-term survival in patients with duodenal papilla carcinoma after pancreaticoduodenectomy

BACKGROUND

Duodenal papilla carcinoma (DPC) is prone to relapse even after radical pancreaticoduodenectomy (PD) (including robotic, laparoscopic and open approach). This study aimed to develop web calculators to predict early recurrence (ER) (within two years after surgery) and long-term survival in patients with DPC after PD.

METHODS

Patients with DPC after radical PD were included. Univariate and multivariate logistic regression analyses were used to identify independent risk factors. Two web calculators were developed based on independent risk factors in the training cohort and then tested in the validation cohort.

RESULTS

Of the 251 patients who met the inclusion criteria, 180 and 71 patients were enrolled in the training and validation cohorts, respectively. Multivariate logistic regression analysis revealed that tumor size [Odds Ratio (OR) 1.386; 95% confidence interval (CI) 1070-1.797; P = 0.014]; number of lymph node metastasis (OR 2.535; 95% CI 1.114-5.769; P = 0.027), perineural invasion (OR 3.078; 95% CI 1.147-8.257; P = 0.026), and tumor differentiation (OR 3.552; 95% CI 1.132-11.152; P = 0.030) were independent risk factors for ER. Nomogram based on the above four factors achieved good C-statistics of 0.759 and 0.729 in predicting ER in the training and the validation cohorts, respectively. Time-dependent ROC analysis (timeROC) and decision curve analysis (DCA) revealed that the nomogram provided superior diagnostic capacity and net benefit compared with single variable.

CONCLUSIONS

This study developed and validated two web calculators that can predict ER and long-term survival in patients with DPC with high degree of stability and accuracy.

Predicting risk of obesity in overweight adults using interpretable machine learning algorithms

Objective

To screen for predictive obesity factors in overweight populations using an optimal and interpretable machine learning algorithm.

Methods

This cross-sectional study was conducted between June 2011 and January 2012. The participants were randomly selected using a simple random sampling technique. Seven commonly used machine learning methods were employed to construct obesity risk prediction models. A total of 5,236 Chinese participants from Ningde City, Fujian Province, Southeast China, participated in this study. The best model was selected through appropriate verification and validation and suitably explained. Subsequently, a minimal set of significant predictors was identified. The Shapley additive explanation force plot was used to illustrate the model at the individual level.

Results

Machine learning models for predicting obesity have demonstrated strong performance, with CatBoost emerging as the most effective in both model validity and net clinical benefit. Specifically, the CatBoost algorithm yielded the highest scores, registering 0.91 in the training set and an impressive 0.83 in the test set. This was further corroborated by the area under the curve (AUC) metrics, where CatBoost achieved 0.95 for the training set and 0.87 for the test set. In a rigorous five-fold cross-validation, the AUC for the CatBoost model ranged between 0.84 and 0.91, with an average AUC of ROC at 0.87 ± 0.022. Key predictors identified within these models included waist circumference, hip circumference, female gender, and systolic blood pressure.

Conclusion

CatBoost may be the best machine learning method for prediction. Combining Shapley's additive explanation and machine learning methods can be effective in identifying disease risk factors for prevention and control.

Construction and validation of infection risk model for patients with external ventricular drainage: a multicenter retrospective study

PURPOSE

External ventricular drainage (EVD) is a life-saving neurosurgical procedure, of which the most concerning complication is EVD-related infection (ERI). We aimed to construct and validate an ERI risk model and establish a monographic chart.

METHODS

We retrospectively analyzed the adult EVD patients in four medical centers and split the data into a training and a validation set. We selected features via single-factor logistic regression and trained the ERI risk model using multi-factor logistic regression. We further evaluated the model discrimination, calibration, and clinical usefulness, with internal and external validation to assess the reproducibility and generalizability. We finally visualized the model as a nomogram and created an online calculator (dynamic nomogram).

RESULTS

Our research enrolled 439 EVD patients and found 75 cases (17.1%) had ERI. Diabetes, drainage duration, site leakage, and other infections were independent risk factors that we used to fit the ERI risk model. The area under the receiver operating characteristic curve (AUC) and the Brier score of the model were 0.758 and 0.118, and these indicators' values were similar when internally validated. In external validation, the model discrimination had a moderate decline, of which the AUC was 0.720. However, the Brier score was 0.114, suggesting no degradation in overall performance. Spiegelhalter's Z-test indicated that the model had adequate calibration when validated internally or externally (P = 0.464 vs. P = 0.612). The model was transformed into a nomogram with an online calculator built, which is available through the website: https://wang-cdutcm.shinyapps.io/DynNomapp/ .

CONCLUSIONS

The present study developed an infection risk model for EVD patients, which is freely accessible and may serve as a simple decision tool in the clinic.

Development and validation of a nomogram for predicting the early death of anaplastic thyroid cancer: a SEER population-based study

BACKGROUND

Anaplastic thyroid cancer (ATC) is a highly aggressive malignancy with dismal prognosis. This study aimed to identify the independent risk factors and construct a readily-to-use nomogram to predict the probability of early death in ATC patients.

METHOD

Patients diagnosed with ATC between 2004 and 2015 from the Surveillance, Epidemiology, and End Results (SEER) database were enrolled in this study for model development and internal validation. Univariate and multivariate logistic regression analyses were conducted to identify independent risk factors for early death of ATC. Nomograms for predicting the probability of all-cause early death (ACED) and cancer-specific early death (CSED) of ATC were subsequently developed. The performance of the nomograms was comprehensively evaluated and validated in an internal cohort.

RESULT

A total of 696 ATC patients were included in this study, of which 488 patients in the training cohort and 208 patients in the validation cohort. The univariate and multivariate logistic regression analyses identified five independent factors (tumor size, M stage, surgery, radiotherapy and chemotherapy) in the ACED model and six variables in the CSED (gender, tumor size, M stage, surgery, radiotherapy and chemotherapy) model for the establishment of the nomograms. Calibration curves and receiver operating characteristic (ROC) curves showed satisfactory efficacy and consistency both in the training (ACED: AUC values: 0.814 (0.776-0.852); CSED: 0.778 (0.736-0.820)) and validation sets (ACED: 0.762 (0.696-0.827); CSED: 0.745 (0.678-0.812)). In addition, the decision curve analysis (DCA) demonstrated the favorable potential of the two nomograms in clinical application.

CONCLUSION

The two nomograms assist clinicians to identify risk factors and predict the early death probability among ATC patients, thus guide individualized treatment to improve the prognosis.

Inclusion of frailty improved performance of delirium prediction for elderly patients in the cardiac intensive care unit (D-FRAIL): A prospective derivation and external validation study

BACKGROUND

The elderly patients admitted to cardiac intensive care unit (CICU) are at relatively high risk for developing delirium. A simple and reliable predictive model can benefit them from early recognition of delirium followed by timely and appropriate preventive strategies.

OBJECTIVE

To explore the role of frailty in delirium prediction and develop and validate a delirium predictive model including frailty for elderly patients in CICU.

DESIGN

A prospective, observational cohort study.

SETTINGS

CICU at China-Japan Friendship Hospital from March 1, 2022 to August 25, 2022 (derivation cohort); CICU at Beijing Anzhen Hospital affiliated to Capital Medical University from March 14, 2023 to May 8, 2023 (external validation cohort).

PARTICIPANTS

A total of 236 and 90 participants were enrolled in the derivation and external validation cohorts, respectively. Participants in the derivation cohort were assigned into either the delirium (n = 70) or non-delirium group (n = 166) based on the occurrence of delirium.

METHODS

The simplified Chinese version of the Confusion Assessment Method for the Diagnosis of Delirium in the Intensive Care Unit was used to assess delirium twice a day at 8:00-10:00 and 18:00-20:00 until the onset of delirium or discharge from the CICU. Frailty was assessed using the FRAIL scale during the first 24 h in the CICU. Other possible risk factors were collected prospectively through patient interviews and medical records review. After processing missing data via multiple imputations, univariate analysis and bootstrapped forward stepwise logistic regression were performed to select optimal predictors and develop the models. The models were internally validated using bootstrapping and evaluated comprehensively via discrimination, calibration, and clinical utility in both the derivation and external validation cohorts.

RESULTS

The study developed D-FRAIL predictive model using FRAIL score, hearing impairment, Acute Physiology and Chronic Health Evaluation-II score, and fibrinogen. The area under the receiver operating characteristic curve (AUC) was 0.937 (95% confidence interval [CI]: 0.907-0.967) and 0.889 (95%CI: 0.840-0.938) even after bootstrapping in the derivation cohort. Inclusion of frailty was demonstrated to improve the model performance greatly with the AUC increased from 0.851 to 0.937 (p < 0.001). In the external validation cohort, the AUC of D-FRAIL model was 0.866 (95%CI: 0.782-0.907). Calibration plots and decision curve analysis suggested good calibration and clinical utility of the D-FRAIL model in both the derivation and external validation cohorts.

CONCLUSIONS

For elderly patients in the CICU, FRAIL score is an independent delirium predictor and the D-FRAIL model demonstrates superior performance in predicting delirium.

The Nomogram predicting the overall survival of patients with pancreatic cancer treated with radiotherapy: a study based on the SEER database and a Chinese cohort

Objective

Patients with pancreatic cancer (PC) have a poor prognosis. Radiotherapy (RT) is a standard palliative treatment in clinical practice, and there is no effective clinical prediction model to predict the prognosis of PC patients receiving radiotherapy. This study aimed to analyze PC's clinical characteristics, find the factors affecting PC patients' prognosis, and construct a visual Nomogram to predict overall survival (OS).

Methods

SEER*Stat software was used to collect clinical data from the Surveillance, Epidemiology, and End Results (SEER) database of 3570 patients treated with RT. At the same time, the relevant clinical data of 115 patients were collected from the Affiliated Cancer Hospital of Zhengzhou University. The SEER database data were randomly divided into the training and internal validation cohorts in a 7:3 ratio, with all patients at The Affiliated Cancer Hospital of Zhengzhou University as the external validation cohort. The lasso regression was used to screen the relevant variables. All non-zero variables were included in the multivariate analysis. Multivariate Cox proportional risk regression analysis was used to determine the independent prognostic factors. The Kaplan-Meier(K-M) method was used to plot the survival curves for different treatments (surgery, RT, chemotherapy, and combination therapy) and calculate the median OS. The Nomogram was constructed to predict the survival rates at 1, 3, and 5 years, and the time-dependent receiver operating characteristic curves (ROC) were plotted with the calculated curves. Calculate the area under the curve (AUC), the Bootstrap method was used to plot the calibration curve, and the clinical efficacy of the prediction model was evaluated using decision curve analysis (DCA).

Results

The median OS was 25.0, 18.0, 11.0, and 4.0 months in the surgery combined with chemoradiotherapy (SCRT), surgery combined with radiotherapy, chemoradiotherapy (CRT), and RT alone cohorts, respectively. Multivariate Cox regression analysis showed that age, N stage, M stage, chemotherapy, surgery, lymph node surgery, and Grade were independent prognostic factors for patients. Nomogram models were constructed to predict patients' OS. 1-, 3-, and 5-year Time-dependent ROC curves were plotted, and AUC values were calculated. The results suggested that the AUCs were 0.77, 0.79, and 0.79 for the training cohort, 0.79, 0.82, and 0.81 for the internal validation cohort, and 0.73, 0.93, and 0.88 for the external validation cohort. The calibration curves Show that the model prediction probability is in high agreement with the actual observation probability, and the DCA curve shows a high net return.

Conclusion

SCRT significantly improves the OS of PC patients. We developed and validated a Nomogram to predict the OS of PC patients receiving RT.

A novel dual-function SERS-based identification strategy for preliminary screening and accurate diagnosis of circulating tumor cells

Non-specific adsorption of bioprobes based on surface-enhanced Raman spectroscopy (SERS) technology inevitably endows white blood cells (WBC) in the peripheral blood with Raman signals, which greatly interfere the identification accuracy of circulating tumor cells (CTCs). In this study, an innovative strategy was proposed to effectively identify CTCs by using SERS technology assisted by a receiver operating characteristic (ROC) curve. Firstly, a magnetic Fe3O4-Au complex SERS bioprobe was developed, which could effectively capture the triple negative breast cancer (TNBC) cells and endow the tumor cells with distinct SERS signals. Then, the ROC curve obtained based on the comparison of SERS intensity of TNBC cells and WBC was used to construct a tumor cell identification model. The merit of the model was that the detection sensitivity and specificity could be intelligently switched according to different identification purposes such as accurate diagnosis or preliminary screening of tumor cells. Finally, the difunctional recognition ability of the model for accurate diagnosis and preliminary screening of tumor cells was further validated by using the healthy human blood added with TNBC cells and blood samples of real tumor patients. This novel difunctional identification strategy provides a new perspective for identification of CTCs based on the SERS technology.

Development and validation of prediction model for early warning of ovarian metastasis risk of endometrial carcinoma

Ovarian metastasis of endometrial carcinoma (EC) patients not only affects the decision of the surgeon, but also has a fatal impact on the fertility and prognosis of patients. This study aimed build a prediction model of ovarian metastasis of EC based on machine learning algorithm for clinical diagnosis and treatment management guidance. We retrospectively collected 536 EC patients treated in Hubei Cancer Hospital from January 2017 to October 2022 and 487 EC patients from Tongji Hospital (January 2017 to December 2020) as an external validation queue. The random forest model, gradient elevator model, support vector machine model, artificial neural network model (ANNM), and decision tree model were used to build ovarian metastasis prediction model for EC patients. The predictive efficacy of 5 machine learning models was evaluated by receiver operating characteristic curve and decision curve analysis. For screening of candidate predictors of ovarian metastasis of EC, the degree of tumor differentiation, lymph node metastasis, CA125, HE4, Alb, LH can be used as a potential predictor of ovarian metastasis prediction model in EC patients. The effectiveness of the prediction model constructed by the 5 machine learning algorithms was between (area under curve [AUC]: 0.729, 95% confidence interval [CI]: 0.674-0.784) and (AUC: 0.899, 95% CI: 0.844-0.954) in the training set and internal verification set, respectively. Among them, the ANNM was equipped with the best prediction effectiveness (training set: AUC: 0.899, 95% CI: 0.844-0.954) and (internal verification set: AUC: 0.892, 95% CI: 0.837-0.947). The prediction model of ovarian metastasis of EC patients based on machine learning algorithm can achieve satisfactory prediction efficiency, among which ANNM is the best, which can be used to guide clinicians in diagnosis and treatment and improve the prognosis of EC patients.

Predicting survival and prognosis in early-onset locally advanced colon cancer: a retrospective observational study

OBJECTIVE

To predict cancer-specific survival, a refined nomogram model and brand-new risk-stratifying system were established to classify the risk levels of patients with early-onset locally advanced colon cancer (LACC).

METHODS

The clinical factors and survival outcomes of LACC cases from the SEER database from 2010 to 2019 were retrieved retrospectively. Early-onset and late-onset colon cancer were grouped according to the age (50 years old) at diagnosis. Differences between groups were compared to identify mutual significant variables. A multivariate Cox regression analysis was further performed and then constructed a nomogram. We compared it with the AJCC-TNM system. The external validation was performed for evaluation. Finally, a risk-stratifying system of patients with early-onset LACC was established.

RESULTS

A total of 32,855 LACC patients were enrolled in, 4548 (13.84%) patients were included in the early-onset LACC group, and 28,307 (86.16%) patients were included in the late-onset LACC group. The external validation set included 228 early-onset LACC patients. Early-onset colon cancers had poorer prognosis (T4, N2, TNM stage III, CEA, tumor deposit, and nerve invasion), and a higher proportion received radiotherapy and systemic therapy (P<0.001). In the survival analysis, cancer-specific survival (CSS) was better in patients with early-onset LACC than in those with late-onset LACC (P <0.001). This nomogram constructed based on the results of COX analysis showed better accuracy in CSS prediction of early-onset LACC patients than AJCC-TNM system in the training set and external validation set (0.783 vs 0.728; 0.852 vs 0.773).

CONCLUSION

We developed a novel nomogram model to predict CSS in patients with early-onset LACC it provided a reference in prognosis prediction and selection of individualized treatment, helping clinicians in decision-making.