Prediction of the risk of 3-year chronic kidney disease among elderly people: a community-based cohort study

OBJECTIVE

We conducted a community-based cohort study to predict the 3-year occurrence of chronic kidney disease (CKD) among population aged ≥60 years.

METHOD

Participants were selected from two communities through randomized cluster sampling in Jiading District of Shanghai, China. The two communities were randomly divided into a development cohort (n = 12012) and a validation cohort (n = 6248) with a 3-year follow-up. Logistic regression analysis was used to determine the independent predictors. A nomogram was established to predict the occurrence of CKD within 3 years. The area under the curve (AUC), the calibration curve and decision curve analysis (DCA) curve were used to evaluate the model.

RESULT

At baseline, participants in development cohort and validation cohort were with the mean age of 68.24 ± 5.87 and 67.68 ± 5.26 years old, respectively. During 3 years, 1516 (12.6%) and 544 (8.9%) new cases developed CKD in the development and validation cohorts, respectively. Nine variables (age, systolic blood pressure, body mass index, exercise, previous hypertension, triglycerides, fasting plasma glucose, glycated hemoglobin and serum creatinine) were included in the prediction model. The AUC value was 0.742 [95% confidence interval (CI), 0.728-0.756] in the development cohort and 0.881(95%CI, 0.867-0.895) in the validation cohort, respectively. The calibration curves and DCA curves demonstrate an effective predictive model.

CONCLUSION

Our nomogram model is a simple, reasonable and reliable tool for predicting the risk of 3-year CKD in community-dwelling elderly people, which is helpful for timely intervention and reducing the incidence of CKD.

Incorporating low haemoglobin into a risk prediction model for conversion in minimally invasive gynaecologic oncology surgeries

BACKGROUND

A well-known complication of laparoscopic management of gynaecologic masses and cancers is the need to perform an intraoperative conversion to laparotomy. The purpose of this study was to identify novel patient risk factors for conversion from minimally invasive to open surgeries for gynaecologic oncology operations.

METHODS

This was a retrospective cohort study of 1356 patients ≥18 years of age who underwent surgeries for gynaecologic masses or malignancies between February 2015 and May 2020 at a single academic medical centre. Multivariable logistic regression was used to study the effects of older age, higher body mass index (BMI), higher American Society of Anaesthesiologist (ASA) physical status, and lower preoperative haemoglobin (Hb) on odds of converting from minimally invasive to open surgery. Receiver operating characteristic (ROC) curve analysis assessed the discriminatory ability of a risk prediction model for conversion.

RESULTS

A total of 704 planned minimally invasive surgeries were included with an overall conversion rate of 6.1% (43/704). Preoperative Hb was lowest for conversion cases, compared to minimally invasive and open cases (11.6 ± 1.9 vs 12.8 ± 1.5 vs 11.8 ± 1.9 g/dL, p<.001). Patients with preoperative Hb <10 g/dL had an adjusted odds ratio (OR) of 3.94 (CI: 1.65-9.41, p=.002) for conversion while patients with BMI ≥30 kg/m2 had an adjusted OR of 2.86 (CI: 1.50-5.46, p=.001) for conversion. ROC curve analysis using predictive variables of age >50 years, BMI ≥30 kg/m2, ASA physical status >2, and preoperative haemoglobin <10 g/dL resulted in an area under the ROC curve of 0.71. Patients with 2 or more risk factors were at highest risk of requiring an intraoperative conversion (12.0%).

CONCLUSIONS

Lower preoperative haemoglobin is a novel risk factor for conversion from minimally invasive to open gynaecologic oncology surgeries and stratifying patients based on conversion risk may be helpful for preoperative planning.

A nomogram prediction model for mild cognitive impairment in non-dialysis outpatient patients with chronic kidney disease

BACKGROUND

The high prevalence of mild cognitive impairment (MCI) in non-dialysis individuals with chronic kidney disease (CKD) impacts their prognosis and quality of life.

OBJECTIVE

This study aims to investigate the variables associated with MCI in non-dialysis outpatient patients with CKD and to construct and verify a nomogram prediction model.

METHODS

416 participants selected from two hospitals in Chengdu, between January 2023 and June 2023. They were categorized into two groups: the MCI group (n = 210) and the non-MCI (n = 206). Univariate and multivariate binary logistic regression analyses were employed to identify independent influences (candidate predictor variables). Subsequently, regression models was constructed, and a nomogram was drawn. The restricted cubic spline diagram was drawn to further analyze the relationship between the continuous numerical variables and MCI. Internally validated using a bootstrap resampling procedure.

RESULTS

Among 416 patients, 210 (50.9%) had MCI. Logistic regression analysis revealed that age, educational level, occupational status, use of smartphones, sleep disorder, and hemoglobin were independent influencing factors of MCI (all p<.05). The model's area under the curve was 0.926,95% CI (0.902, 0.951), which was a good discriminatory measure; the Calibration curve, the Hosmer-Lemeshow test, and the Clinical Decision Curve suggested that the model had good calibration and clinical benefit. Internal validation results showed the consistency index was 0.926, 95%CI (0.925, 0.927).

CONCLUSION

The nomogram prediction model demonstrates good performance and can be used for early screening and prediction of MCI in non-dialysis patients with CKD. It provides valuable reference for medical staff to formulate corresponding intervention strategies.

Development and Validation of a Predictive Model for Early Identification of Cognitive Impairment Risk in Community-Based Hypertensive Patients

Objective: To investigate the risk factors for the development of mild cognitive dysfunction in hypertensive patients in the community and to develop a risk prediction model. Method: The data used in this study were obtained from two sources: the China Health and Retirement Longitudinal Study (CHARLS) and the Chinese Longitudinal Healthy Longevity Survey (CLHLS). A total of 1121 participants from CHARLS were randomly allocated into a training set and a validation set, following a 70:30 ratio. Meanwhile, an additional 4016 participants from CLHLS were employed for external validation of the model. The patients in this study were divided into two groups: those with mild cognitive impairment and those without. General information, employment status, pension, health insurance, and presence of depressive symptoms were compared between the two groups. LASSO regression analysis was employed to identify the most predictive variables for the model, utilizing 14-fold cross-validation. The risk prediction model for cognitive impairment in hypertensive populations was developed using generalized linear models. The model's discriminatory power was evaluated through the area under the receiver operating characteristic (ROC) curve and calibration curves. Results: In the modeling group, eight variables such as gender, age, residence, education, alcohol use, depression, employment status, and health insurance were ultimately selected from an initial pool of 21 potential predictors to construct the risk prediction model. The area under the curve (AUC) values for the training, internal, and external validation sets were 0.777, 0.785, and 0.782, respectively. All exceeded the threshold of 0.7, suggesting that the model effectively predicts the incidence of mild cognitive dysfunction in community-based hypertensive patients. A risk prediction model was developed using a generalized linear model in conjunction with Lasso regression. The model's performance was evaluated using the area under the receiver operating characteristic (ROC) curve. Hosmer-Lemeshow test values yielded p = .346 and p = .626, both of which exceeded the 0.05 threshold. Calibration curves demonstrated a significant agreement between the nomogram model and observed outcomes, serving as an effective tool for evaluating the model's predictive performance. Discussion: The predictive model developed in this study serves as a promising and efficient tool for evaluating cognitive impairment in hypertensive patients, aiding community healthcare workers in identifying at-risk populations.

Performance of GAP and ILD-GAP models in predicting lung transplant or death in interstitial pneumonia with autoimmune features

OBJECTIVES

To assess the ability of two risk prediction models in interstitial lung disease (ILD) to predict death or lung transplantation in a cohort of patients with interstitial pneumonia with autoimmune features (IPAF).

METHODS

We performed a retrospective cohort study of adults with IPAF at an academic medical centre. The primary outcome was a composite of lung transplantation or death. We applied the patient data to the previously described Gender-Age-Physiology (GAP) and ILD-GAP models to determine the ability of these models to predict the composite outcome. Model discrimination was assessed using the c-index, and model calibration was determined by comparing the incidence ratios of observed vs expected deaths.

RESULTS

Ninety-four patients with IPAF were included. Mean (s.d.) age was 58 (13.5) years and the majority were female (62%). The majority met serologic and morphologic criteria for IPAF (94% and 91%, respectively). The GAP model had a c-index of 0.664 (95% CI 0.547-0.781), while the ILD-GAP model had a c-index of 0.569 (95% CI 0.440-0.697). In those with GAP stage 1 or GAP stage 2 disease, calibration of the GAP model was satisfactory at 2 and 3 years for the cumulative end point of lung transplantation or death.

CONCLUSION

In patients with IPAF, the GAP model performed well as a predictor of lung transplantation or death at 2 years and 3 years from ILD diagnosis in patients with GAP stage 1 and GAP stage 2 disease.

Nomogram to Predict 90-Day All-Cause Mortality in Acute Ischemic Stroke Patients after Endovascular Thrombectomy

OBJECTIVE

Although Endovascular Thrombectomy (EVT) significantly improves the prognosis of Acute Ischemic Stroke (AIS) patients with large vessel occlusion, the mortality rate remains higher. This study aimed to construct and validate a nomogram for predicting 90-day all-cause mortality in AIS patients with large vessel occlusion and who have undergone EVT.

METHODS

AIS patients with large vessel occlusion in the anterior circulation who underwent EVT from May 2017 to December 2022 were included. 430 patients were randomly split into a training group (N=302) and a test group (N=128) for the construction and validation of our nomogram. In the training group, multivariate logistic regression analysis was performed to determine the predictors of 90-day all-cause mortality. The C-index, calibration plots, and decision curve analysis were applied to evaluate the nomogram performance.

RESULTS

Multivariate logistic regression analysis revealed neurological deterioration during hospitalization, age, baseline National Institutes of Health Stroke Scale (NIHSS) score, occlusive vessel location, malignant brain edema, and Neutrophil-to-lymphocyte Ratio (NLR) as the independent predictors of 90-day all-cause mortality (all p ≤ 0.039). The C-index of the training and test groups was 0.891 (95%CI 0.848-0.934) and 0.916 (95% CI: 0.865-0.937), respectively, showing the nomogram to be well distinguished. The Hosmer-Lemeshow goodness-of-fit test revealed the p-values for both the internal and external verification datasets to be greater than 0.5.

CONCLUSION

Our nomogram has incorporated relevant clinical and imaging features, including neurological deterioration, age, baseline NIHSS score, occlusive vessel location, malignant brain edema, and NLR ratio, to provide an accurate and reliable prediction of 90-day all-cause mortality in AIS patients undergoing EVT.

Comparative Analysis of Three Atherosclerotic Cardiovascular Disease Risk Prediction Models in Individuals Aged 75 and Older

Purpose

To evaluate the performance of the Framingham cardiovascular risk score (FRS)/pooled cohort equations (PCE)/China prediction for atherosclerotic cardiovascular disease (ASCVD) risk (China-PAR model) in a prospective cohort of Chinese older adults.

Patients and Methods

We assessed 717 older adults aged 75-85 years without ASCVD at the baseline from the Sichuan province of China. The participants were followed annually from 2011 to 2021. We obtained the participants' information through the medical records of physical examination and evaluated their 10-year ASCVD risk using FRS, PCE, and China-PAR. We further evaluated the predictive abilities of three assessment models.

Results

During the 10-year follow-up, 206 participants developed ASCVD, with an incidence rate of 28.73%. The FRS and China-PAR moderately underestimated the risk of ASCVD (22.1% and 12.4%, respectively), but while PCE overestimated the risk (36.1%). FRS and China-PAR were found to underestimate the risk of ASCVD (26% and 63%, respectively) for men, while PCE overestimated the risk by 8%; For women, FRS and China-PAR were found to underestimate the risk of ASCVD (14% and 35%, respectively), while PCE overestimated the risk by 88%.

Conclusion

The 10-year ASCVD risk was found to be overestimated by PCE. China-PAR had the most accurate predictions in women, while FRS was particularly well-calibrated in males. All three risk models have good discrimination, with FRS and PCE being well-calibrated in men and all three being well-calibrated in women. Therefore, accurate risk models are warranted to facilitate the prevention of ASCVD at the baseline among Chinese older adults.

Establishment and evaluation of a nomogram for in-hospital new-onset atrial fibrillation after percutaneous coronary intervention for acute myocardial infarction

Background

New-onset atrial fibrillation (NOAF) is prognostic in acute myocardial infarction (AMI). The timely identification of high-risk patients is essential for clinicians to improve patient prognosis.

Methods

A total of 333 AMI patients were collected who underwent percutaneous coronary intervention (PCI) at Zhejiang Provincial People's Hospital between October 2019 and October 2020. Least absolute shrinkage and selection operator regression (Lasso) and multivariate logistic regression analysis were applied to pick out independent risk factors. Secondly, the variables identified were utilized to establish a predicted model and then internally validated by 10-fold cross-validation. The discrimination, calibration, and clinical usefulness of the prediction model were evaluated using the receiver operating characteristic (ROC) curve, calibration curve, Hosmer-Lemeshow test decision curve analyses, and clinical impact curve.

Result

Overall, 47 patients (14.1%) developed NOAF. Four variables, including left atrial dimension, body mass index (BMI), CHA2DS2-VASc score, and prognostic nutritional index, were selected to construct a nomogram. Its area under the curve is 0.829, and internal validation by 10-fold cross-folding indicated a mean area under the curve is 0.818. The model demonstrated good calibration according to the Hosmer-Lemeshow test (P = 0.199) and the calibration curve. It showed satisfactory clinical practicability in the decision curve analyses and clinical impact curve.

Conclusion

This study established a simple and efficient nomogram prediction model to assess the risk of NOAF in patients with AMI who underwent PCI. This model could assist clinicians in promptly identifying high-risk patients and making better clinical decisions based on risk stratification.

Prediction of vascular complications in free flap reconstruction with machine learning

OBJECTIVE

This study aims to explore the risk factors of vascular complications following free flap reconstruction and to develop a clinical auxiliary assessment tool for predicting vascular complications in patients undergoing free flap reconstruction leveraging machine learning methods.

METHODS

We reviewed the medical data of patients who underwent free flap reconstruction at the Affiliated Hospital of Zunyi Medical University retrospectively from January 1, 2019, to December 31, 2021. Statistical analysis was used to screen risk factors. A training data set was generated and augmented using the synthetic minority oversampling technique. Logistic regression, random forest and neural network, models were trained, using this dataset. The performance of these three predictive models was then evaluated and compared using a test set, with four metrics, area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

RESULTS

A total of 570 patients who underwent free flap reconstruction were included in this study, 46 of whom developed postoperative vascular complications. Among the models tested, the neural network model exhibited superior performance on the test set, achieving an AUC of 0.828. Multivariate logistic regression analysis identified that preoperative hemoglobin levels, preoperative fibrinogen levels, operation duration, smoking history, the number of anastomoses, and peripheral vascular injury as statistically significant independent risk factors for vascular complications post-free flap reconstruction. The top five predictive factors in the neural network were fibrinogen content, operation duration, donor site, body mass index (BMI), and platelet count.

CONCLUSION

Hemoglobin levels, fibrinogen levels, operation duration, smoking history, and anastomotic veins are independent risk factors for vascular complications following free flap reconstruction. These risk factors enhance the ability of machine learning models to predict the occurrence of vascular complications and identify high-risk patients. The neural network model outperformed the logistic regression and random forest models, suggesting its potential to aid clinicians in early identification of high-risk patients thereby mitigating patient suffering and improving 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%.

Application of deep neural survival networks to the development of risk prediction models for diabetes mellitus, hypertension, and dyslipidemia

OBJECTIVES

: Although numerous risk prediction models have been proposed, few such models have been developed using neural network-based survival analysis. We developed risk prediction models for three cardiovascular disease risk factors (diabetes mellitus, hypertension, and dyslipidemia) among a working-age population in Japan using DeepSurv, a deep feed-forward neural network.

METHODS

: Data were obtained from the Japan Epidemiology Collaboration on Occupational Health Study. A total of 51 258, 44 197, and 31 452 individuals were included in the development of risk models for diabetes mellitus, hypertension, and dyslipidemia, respectively; two-thirds of whom were used to develop prediction models, and the rest were used to validate the models. We compared the performances of DeepSurv-based models with those of prediction models based on the Cox proportional hazards model.

RESULTS

: The area under the receiver-operating characteristic curve was 0.878 [95% confidence interval (CI) = 0.864-0.892] for diabetes mellitus, 0.835 (95% CI = 0.826-0.845) for hypertension, and 0.826 (95% CI = 0.817-0.835) for dyslipidemia. Compared with the Cox proportional hazards-based models, the DeepSurv-based models had better reclassification performance [diabetes mellitus: net reclassification improvement (NRI) = 0.474, P  ≤ 0.001; hypertension: NRI = 0.194, P  ≤ 0.001; dyslipidemia: NRI = 0.397, P  ≤ 0.001] and discrimination performance [diabetes mellitus: integrated discrimination improvement (IDI) = 0.013, P  ≤ 0.001; hypertension: IDI = 0.007, P  ≤ 0.001; and dyslipidemia: IDI = 0.043, P  ≤ 0.001].

CONCLUSION

: This study suggests that DeepSurv has the potential to improve the performance of risk prediction models for cardiovascular disease risk factors.

Risk prediction models of mortality after hip fracture surgery in older individuals: a systematic review

OBJECTIVE

This study aimed to critically assess existing risk prediction models for postoperative mortality in older individuals with hip fractures, with the objective of offering substantive insights for their clinical application.

DESIGN

A comprehensive search was conducted across prominent databases, including PubMed, Embase, Cochrane Library, SinoMed, CNKI, VIP, and Wanfang, spanning original articles in both Chinese and English up until 1 December 2023. Two researchers independently extracted pertinent research characteristics, such as predictors, model performance metrics, and modeling methodologies. Additionally, the bias risk and applicability of the incorporated risk prediction models were systematically evaluated using the Prediction Model Risk of Bias Assessment Tool (PROBAST).

RESULTS

Within the purview of this investigation, a total of 21 studies were identified, constituting 21 original risk prediction models. The discriminatory capacity of the included risk prediction models, as denoted by the minimum and maximum areas under the subject operating characteristic curve, ranged from 0.710 to 0.964. Noteworthy predictors, recurrent across various models, included age, sex, comorbidities, and nutritional status. However, among the models assessed through the PROBAST framework, only one was deemed to exhibit a low risk of bias. Beyond this assessment, the principal limitations observed in risk prediction models pertain to deficiencies in data analysis, encompassing insufficient sample size and suboptimal handling of missing data.

CONCLUSION

Subsequent research endeavors should adopt more stringent experimental designs and employ advanced statistical methodologies in the construction of risk prediction models. Moreover, large-scale external validation studies are warranted to rigorously assess the generalizability and clinical utility of existing models, thereby enhancing their relevance as valuable clinical references.

Development and validation of the ASGARD risk score for safe monitoring in asymptomatic nonsevere aortic stenosis

AIMS

Current guidelines recommend serial echocardiography at minimum 1-2 year intervals for monitoring patients with nonsevere aortic valve stenosis (AS), which is costly and often clinically inconsequential.We aimed to develop and test whether the biomarker-based ASGARD risk score (Aortic Valve Stenosis Guarded by Amplified Risk Determination) can guide the timing of echocardiograms in asymptomatic patients with nonsevere AS.

METHODS

The development cohort comprised 1,093 of 1,589 (69%) asymptomatic patients with mild-to-moderate AS who remained event-free one year after inclusion into the SEAS trial. Cox regression landmark analyses with a 2-year follow-up identified the model (ASGARD) with the lowest Akaike information criterion for association to AS-related composite outcome (heart failure hospitalization, aortic valve replacement, or cardiovascular death). Fine-Gray analyses provided cumulative event rates by ASGARD score quartiles. The ASGARD score was internally validated in the remaining 496 patients (31%) from the SEAS-cohort and externally in 71 asymptomatic outpatients with nonsevere AS from six Copenhagen hospitals.

RESULTS

The ASGARD score comprises updated measurements of heart rate and age- and sex-adjusted N-terminal pro-brain natriuretic peptide upon transaortic maximal velocity (Vmax) from the previous year. The ASGARD score had high predictive accuracy across all cohorts (external validation: area under the curve: 0.74 [95% CI, 0.62-0.86]), and similar to an updated Vmax measurement. An ASGARD score ≤50% was associated with AS-related event rates ≤5% for a minimum of 15 months.

CONCLUSION

The ASGARD score could provide a personalized and safe surveillance alternative to routinely planned echocardiograms, so physicians can prioritize echocardiograms for high-risk patients.

Derivation and validation of a quantitative risk prediction model for weaning and extubation in neurocritical patients

Background

Patients with severe neurological conditions are at high risk during withdrawal and extubation, so it is important to establish a model that can quantitatively predict the risk of this procedure.

Methods

By analyzing the data of patients with traumatic brain injury and tracheal intubation in the ICU of the affiliated hospital of Hangzhou Normal University, a total of 200 patients were included, of which 140 were in the modeling group and 60 were in the validation group. Through binary logistic regression analysis, 8 independent risk factors closely related to the success of extubation were screened out, including age ≥ 65 years old, APACHE II score ≥ 15 points, combined chronic pulmonary disease, GCS score < 8 points, oxygenation index <300, cough reflex, sputum suction frequency, and swallowing function.

Results

Based on these factors, a risk prediction scoring model for extubation was constructed with a critical value of 18 points. The AUC of the model was 0.832, the overall prediction accuracy was 81.5%, the specificity was 81.6%, and the sensitivity was 84.1%. The data of the validation group showed that the AUC of the model was 0.763, the overall prediction accuracy was 79.8%, the specificity was 84.8%, and the sensitivity was 64.0%.

Conclusion

These results suggest that the extubation risk prediction model constructed through quantitative scoring has good predictive accuracy and can provide a scientific basis for clinical practice, helping to assess and predict extubation risk, thereby improving the success rate of extubation and improving patient prognosis.

Risk prediction model construction for asthma after allergic rhinitis by blood immune T effector cells

BACKGROUND

Allergic rhinitis (AR) and asthma (AS) are prevalent and frequently co-occurring respiratory diseases, with mutual influence on each other. They share similar etiology, pathogenesis, and pathological changes. Due to the anatomical continuity between the upper and lower respiratory tracts, allergic inflammation in the nasal cavity can readily propagate downwards, leading to bronchial inflammation and asthma. AR serves as a significant risk factor for AS by potentially inducing airway hyperresponsiveness in patients. Currently, there is a lack of reliable predictors for the progression from AR to AS.

METHODS

In this exhaustive investigation, we reexamined peripheral blood single cell RNA sequencing datasets from patients with AS following AR and healthy individuals. In addition, we used the bulk RNA sequencing dataset as a validation lineup, which included AS, AR, and healthy controls. Using marker genes of related cell subtype, signatures predicting the progression of AR to AS were generated.

RESULTS

We identified a subtype of immune-activating effector T cells that can distinguish patients with AS after AR. By combining specific marker genes of effector T cell subtype, we established prediction models of 16 markers. The model holds great promise for assessing AS risk in individuals with AR, providing innovative avenues for clinical diagnosis and treatment strategies.

CONCLUSION

Subcluster T effector cells may play a key role in post-AR AS. Notably, ACTR3 and HSPA8 genes were significantly upregulated in the blood of AS patients compared to healthy patients.

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.

Validation in type 2 diabetes of a metabolomic signature of all-cause mortality

CONTEXT

Mortality in type 2 diabetes is twice that of the normoglycemic population. Unravelling biomarkers that identify high-risk patients for referral to the most aggressive and costly prevention strategies is needed.

OBJECTIVE

To validate in type 2 diabetes the association with all-cause mortality of a 14-metabolite score (14-MS) previously reported in the general population and whether this score can be used to improve well-established mortality prediction models.

METHODS

This is a sub-study consisting of 600 patients from the "Sapienza University Mortality and Morbidity Event Rate" (SUMMER) study in diabetes, a prospective multicentre investigation on all-cause mortality in patients with type 2 diabetes. Metabolic biomarkers were quantified from serum samples using high-throughput proton nuclear magnetic resonance metabolomics.

RESULTS

In type 2 diabetes, the 14-MS showed a significant (p < 0.0001) association with mortality, which was lower (p < 0.0001) than that reported in the general population. This difference was mainly due to two metabolites (histidine and ratio of polyunsaturated fatty acids to total fatty acids) with an effect size that was significantly (p = 0.01) lower in diabetes than in the general population. A parsimonious 12-MS (i.e. lacking the 2 metabolites mentioned above) improved patient discrimination and classification of two well-established mortality prediction models (p < 0.0001 for all measures).

CONCLUSIONS

The metabolomic signature of mortality in the general population is only partially effective in type 2 diabetes. Prediction markers developed and validated in the general population must be revalidated if they are to be used in patients with diabetes.

EXIST: EXamining rIsk of excesS adiposiTy-Machine learning to predict obesity-related complications

Background

Obesity is associated with an increased risk of multiple conditions, ranging from heart disease to cancer. However, there are few predictive models for these outcomes that have been developed specifically for people with overweight/obesity.

Objective

To develop predictive models for obesity-related complications in patients with overweight and obesity.

Methods

Electronic health record data of adults with body mass index 25-80 kg/m2 treated in primary care practices between 2000 and 2019 were utilized to develop and evaluate predictive models for nine long-term clinical outcomes using a) Lasso-Cox models and b) a machine-learning method random survival forests (RSF). Models were trained on a training dataset and evaluated on a test dataset over 100 replicates. Parsimonious models of <10 variables were also developed using Lasso-Cox.

Results

Over a median follow-up of 5.6 years, study outcome incidence in the cohort of 433,272 patients ranged from 1.8% for knee replacement to 11.7% for atherosclerotic cardiovascular disease. Harrell C-index averaged over replicates ranged from 0.702 for liver outcomes to 0.896 for death for RSF, and from 0.694 for liver outcomes to 0.891 for death for Lasso-Cox. The Harrell C-index for parsimonious models ranged from 0.675 for liver outcomes to 0.850 for knee replacement.

Conclusions

Predictive modeling can identify patients at high risk of obesity-related complications. Interpretable Cox models achieve results close to those of machine learning methods and could be helpful for population health management and clinical treatment decisions.

A systematic review of risk prediction model of venous thromboembolism for patients with lung cancer

BACKGROUND

Venous thromboembolism (VTE) increases the risk of death or adverse outcomes in patients with lung cancer. Therefore, early identification and treatment of high-risk groups of VTE have been the research focus. In this systematic review, the risk assessment tools of VTE in patients with lung cancer were systematically analyzed and evaluated to provide a reference for VTE management.

METHODS

Relevant studies were retrieved from major English databases (The Cochrane Library, Embase, Web of Science, PubMed, Scopus, Medline) and Chinese databases (China National Knowledge Infrastructure [CNKI] and WanFang Data) until July 2023 and extracted by two researchers. This systematic review was registered at PROSPERO (no. CRD42023409748).

RESULTS

Finally, two prospective cohort studies and four retrospective cohort studies were included from 2019. There was a high risk of bias in all included studies according to the Prediction Model Risk of Bias Assessment tool (PROBAST). In the included studies, Cox and logistic regression were used to construct models. The area under the receiver operating characteristic curve (AUC) of the model ranged from 0.670 to 0.904, and the number of predictors ranged from 4 to 11. The D-dimer index was included in five studies, but significant differences existed in optimal cutoff values from 0.0005 mg/L to 2.06 mg/L. Then, three studies validated the model externally, two studies only validated the model internally, and only one study validated the model using a combination of internal and external validation.

CONCLUSION

VTE risk prediction models for patients with lung cancer have received attention for no more than 5 years. The included model shows a good predictive effect and may help identify the risk population of VTE at an early stage. In the future, it is necessary to improve data modeling and statistical analysis methods, develop predictive models with good performance and low risk of bias, and focus on external validation and recalibration of models.

Development and internal validation of a risk prediction model for stress urinary incontinence throughout pregnancy: A multicenter retrospective longitudinal study in Indonesia

BACKGROUND

This study aimed to develop a risk prediction model for stress urinary incontinence (SUI) throughout pregnancy in Indonesian women.

METHODS

We conducted a multicenter retrospective longitudinal study involving pregnant women in Indonesia, who sought care at obstetrics clinics from January 2023 to March 2023, encompassing all stages of pregnancy. We collected data on their predictive factors and SUI outcome. SUI was diagnosed based on responses to the "leaks when you are physically active/exercising" criterion in the ICIQ-UI-SF questionnaire during our investigation of the participants. The models underwent internal validation using a bootstrapping method with 1000 resampling iterations to assess discrimination and calibration.

RESULTS

A total of 660 eligible pregnant women were recruited from the two study centers, with an overall SUI prevalence of 39% (258/660). The final model incorporated three predictive factors: BMI during pregnancy, constipation, and previous delivery mode. The area under the curve (AUROC) was 0.787 (95% CI: 0.751-0.823). According to the max Youden index, the optimal cut-off point was 44.6%, with a sensitivity of 79.9% and specificity of 65.9%. A discrimination slope of 0.213 was found.

CONCLUSION

The developed risk prediction model for SUI in pregnant women offers a valuable tool for early identification and intervention among high-risk SUI populations in Indonesian pregnant women throughout their pregnancies. These findings challenge the assumption that a high BMI and multiple previous deliveries are predictors of SUI in Indonesian women. Further research is recommended to validate the model in diverse populations and settings.

Exploring KRAS-mutant pancreatic ductal adenocarcinoma: a model validation study

Introduction

Pancreatic ductal adenocarcinoma (PDAC) has the highest mortality rate among all solid tumors. Tumorigenesis is promoted by the oncogene KRAS, and KRAS mutations are prevalent in patients with PDAC. Therefore, a comprehensive understanding of the interactions between KRAS mutations and PDAC may expediate the development of therapeutic strategies for reversing the progression of malignant tumors. Our study aims at establishing and validating a prediction model of KRAS mutations in patients with PDAC based on survival analysis and mRNA expression.

Methods

A total of 184 and 412 patients with PDAC from The Cancer Genome Atlas (TCGA) database and the International Cancer Genome Consortium (ICGC), respectively, were included in the study.

Results

After tumor mutation profile and copy number variation (CNV) analyses, we established and validated a prediction model of KRAS mutations, based on survival analysis and mRNA expression, that contained seven genes: CSTF2, FAF2, KIF20B, AKR1A1, APOM, KRT6C, and CD70. We confirmed that the model has a good predictive ability for the prognosis of overall survival (OS) in patients with KRAS-mutated PDAC. Then, we analyzed differential biological pathways, especially the ferroptosis pathway, through principal component analysis, pathway enrichment analysis, Gene Ontology (GO) enrichment analysis, and gene set enrichment analysis (GSEA), with which patients were classified into low- or high-risk groups. Pathway enrichment results revealed enrichment in the cytokine-cytokine receptor interaction, metabolism of xenobiotics by cytochrome P450, and viral protein interaction with cytokine and cytokine receptor pathways. Most of the enriched pathways are metabolic pathways predominantly enriched by downregulated genes, suggesting numerous downregulated metabolic pathways in the high-risk group. Subsequent tumor immune infiltration analysis indicated that neutrophil infiltration, resting CD4 memory T cells, and resting natural killer (NK) cells correlated with the risk score. After verifying that the seven gene expression levels in different KRAS-mutated pancreatic cancer cell lines were similar to that in the model, we screened potential drugs related to the risk score.

Discussion

This study established, analyzed, and validated a model for predicting the prognosis of PDAC based on risk stratification according to KRAS mutations, and identified differential pathways and highly effective drugs.

PAGE-B incorporating moderate HBV DNA levels predicts risk of HCC among patients entering into HBeAg-positive chronic hepatitis B

BACKGROUND & AIMS

Recent studies reported that moderate HBV DNA levels are significantly associated with hepatocellular carcinoma (HCC) risk in hepatitis B e antigen (HBeAg)-positive, non-cirrhotic patients with chronic hepatitis B (CHB). We aimed to develop and validate a new risk score to predict HCC development using baseline moderate HBV DNA levels in patients entering into HBeAg-positive CHB from chronic infection.

METHODS

This multicenter cohort study recruited 3,585 HBeAg-positive, non-cirrhotic patients who started antiviral treatment with entecavir or tenofovir disoproxil fumarate at phase change into CHB from chronic infection in 23 tertiary university-affiliated hospitals of South Korea (2012-2020). A new HCC risk score (PAGED-B) was developed (training cohort, n = 2,367) based on multivariable Cox models. Internal validation using bootstrap sampling and external validation (validation cohort, n = 1,218) were performed.

RESULTS

Sixty (1.7%) patients developed HCC (median follow-up, 5.4 years). In the training cohort, age, gender, platelets, diabetes and moderate HBV DNA levels (5.00-7.99 log10 IU/ml) were independently associated with HCC development; the PAGED-B score (based on these five predictors) showed a time-dependent AUROC of 0.81 for the prediction of HCC development at 5 years. In the validation cohort, the AUROC of PAGED-B was 0.85, significantly higher than for other risk scores (PAGE-B, mPAGE-B, CAMD, and REAL-B). When stratified by the PAGED-B score, the HCC risk was significantly higher in high-risk patients than in low-risk patients (sub-distribution hazard ratio = 8.43 in the training and 11.59 in the validation cohorts, all p <0.001).

CONCLUSIONS

The newly established PAGED-B score may enable risk stratification for HCC at the time of transition into HBeAg-positive CHB.

IMPACT AND IMPLICATIONS

In this study, we developed and validated a new risk score to predict hepatocellular carcinoma (HCC) development in patients entering into hepatitis B e antigen (HBeAg)-positive chronic hepatitis B (CHB) from chronic infection. The newly established PAGED-B score, which included baseline moderate HBV DNA levels (5-8 log10 IU/ml), improved on the predictive performance of prior risk scores. Based on a patient's age, gender, diabetic status, platelet count, and moderate DNA levels (5-8 log10 IU/ml) at the phase change into CHB from chronic infection, the PAGED-B score represents a reliable and easily available risk score to predict HCC development during the first 5 years of antiviral treatment in HBeAg-positive patients entering into CHB. With a scoring range from 0 to 12 points, the PAGED-B score significantly differentiated the 5-year HCC risk: low <7 points and high ≥7 points.

Recalibration of a Non-Laboratory-Based Risk Model to Estimate Pre-Diabetes/Diabetes Mellitus Risk in Primary Care in Hong Kong

INTRODUCTION/OBJECTIVES

A non-laboratory-based pre-diabetes/diabetes mellitus (pre-DM/DM) risk prediction model developed from the Hong Kong Chinese population showed good external discrimination in a primary care (PC) population, but the estimated risk level was significantly lower than the observed incidence, indicating poor calibration. This study explored whether recalibrating/updating methods could improve the model's accuracy in estimating individuals' risks in PC.

METHODS

We performed a secondary analysis on the model's predictors and blood test results of 919 Chinese adults with no prior DM diagnosis recruited from PC clinics from April 2021 to January 2022 in HK. The dataset was randomly split in half into a training set and a test set. The model was recalibrated/updated based on a seven-step methodology, including model recalibrating, revising and extending methods. The primary outcome was the calibration of the recalibrated/updated models, indicated by calibration plots. The models' discrimination, indicated by the area under the receiver operating characteristic curves (AUC-ROC), was also evaluated.

RESULTS

Recalibrating the model's regression constant, with no change to the predictors' coefficients, improved the model's accuracy (calibration plot intercept: -0.01, slope: 0.69). More extensive methods could not improve any further. All recalibrated/updated models had similar AUC-ROCs to the original model.

CONCLUSION

The simple recalibration method can adapt the HK Chinese pre-DM/DM model to PC populations with different pre-test probabilities. The recalibrated model can be used as a first-step screening tool and as a measure to monitor changes in pre-DM/DM risks over time or after interventions.

Three molecular subtypes and a five-gene signature for hepatocellular carcinoma based on m7G-related classification

BACKGROUND

The current research investigated the heterogeneity of hepatocellular carcinoma (HCC) based on the expression of N7-methylguanosine (m7G)-related genes as a classification model and developed a risk model predictive of HCC prognosis, key pathological behaviors and molecular events of HCC.

METHODS

The RNA sequencing data of HCC were extracted from The Cancer Genome Atlas (TCGA)-live cancer (LIHC) database, hepatocellular carcinoman database (HCCDB) and Gene Expression Omnibus database, respectively. According to the expression level of 29 m7G-related genes, a consensus clustering analysis was conducted. The least absolute shrinkage and selection operator (LASSO) regression analysis and COX regression algorithm were applied to create a risk prediction model based on normalized expression of five characteristic genes weighted by coefficients. Tumor microenvironment (TME) analysis was performed using the MCP-Counter, TIMER, CIBERSORT and ESTIMATE algorithms. The Tumor Immune Dysfunction and Exclusion algorithm was applied to assess the responses to immunotherapy in different clusters and risk groups. In addition, patient sensitivity to common chemotherapeutic drugs was determined by the biochemical half-maximal inhibitory concentration using the R package pRRophetic.

RESULTS

Three molecular subtypes of HCC were defined based on the expression level of m7G-associated genes, each of which had its specific survival rate, genomic variation status, TME status and immunotherapy response. In addition, drug sensitivity analysis showed that the C1 subtype was more sensitive to a number of conventional oncolytic drugs (including paclitaxel, imatinib, CGP-082996, pyrimethamine, salubrinal and vinorelbine). The current five-gene risk prediction model accurately predicted HCC prognosis and revealed the degree of somatic mutations, immune microenvironment status and specific biological events.

CONCLUSION

In this study, three heterogeneous molecular subtypes of HCC were defined based on m7G-related genes as a classification model, and a five-gene risk prediction model was created for predicting HCC prognosis, providing a potential assessment tool for understanding the genomic variation, immune microenvironment status and key pathological mechanisms during HCC development.

Risk prediction of poor wound healing in patients with thoracoscopic lung cancer resection with drainage tube

This work established a risk prediction (RP) model for poor wound healing (PWH) in patients with thoracoscopic lung cancer (LC) resection (TLCR) after drainage tube placement to explore its application effect. 359 patients with TLCR were categorized into a good wound healing group (GWH group, 275 cases) and a poor wound healing group (PWH group, 84 cases) based on incision healing condition. The independent prediction risk factors (IPRFs) of PWH were analyzed and a RP model was constructed. 70% of the patients were classified as the model group (Mod group) and 30% were in the validation group (Val group). Resolution of the RP model was evaluated by the area under receiver operating characteristic (ROC) curve (AUC). The Hosmer-Lemeshow goodness of fit (HLGF) test was employed to evaluate the calibration of RP model. Results from the multivariate logistic regression analysis (MLRA) showed that age, preoperative albumin levels, diabetes history, dressing change frequency, and type of wound cleaning fluid were independent risk factors (IRFs) for postoperative PWH (P<0.05). In the Mod group, AUC=0.758 (P<0.05, 95% CI=0.712-0.806), and HLGF test showed P=0.493. In the Val group, AUC=0.783 (P<0.05, 95% CI=0.675-0.834), and HLGF test showed P=0.189. In conclusion, the constructed model was convenient, feasible, and demonstrates good predictive performance for postoperative incision healing issue, holding practical value and applicability.