New strategies in hepatocellular carcinoma: genomic prognostic markers

Accurate prognosis prediction in oncology is critical. In patients with hepatocellular carcinoma (HCC), unlike most solid tumors, the coexistence of two life-threatening conditions, cancer and cirrhosis, makes prognostic assessments difficult. Despite the usefulness of clinical staging systems for HCC in routine clinical decision making (e.g., Barcelona-Clinic Liver Cancer algorithm), there is still a need to refine and complement outcome predictions. Recent data suggest the ability of gene signatures from the tumor (e.g., EpCAM signature) and adjacent tissue (e.g., poor-survival signature) to predict outcome in HCC (either recurrence or overall survival), although independent external validation is still required. In addition, novel information is being produced by alternative genomic sources such as microRNA (miRNA; e.g., miR-26a) or epigenomics, areas in which promising preliminary data are thoroughly explored. Prognostic models need to contemplate the impact of liver dysfunction and risk of subsequent de novo tumors in a patient's life expectancy. The challenge for the future is to precisely depict genomic predictors (e.g., gene signatures, miRNA, or epigenetic biomarkers) at each stage of the disease and their specific influence to determine patient prognosis.

The Risk of Deterioration in GCS13-15 Patients with Traumatic Brain Injury Identified by Computed Tomography Imaging: A Systematic Review and Meta-Analysis

The optimal management of mild traumatic brain injury (TBI) patients with injuries identified by computed tomography (CT) brain scan is unclear. Some guidelines recommend hospital admission for an observation period of at least 24 h. Others argue that selected lower-risk patients can be discharged from the Emergency Department (ED). The objective of our review and meta-analysis was to estimate the risk of death, neurosurgical intervention, and clinical deterioration in mild TBI patients with injuries identified by CT brain scan, and assess which patient factors affect the risk of these outcomes. A systematic review and meta-analysis adhering to PRISMA standards of protocol and reporting were conducted. Study selection was performed by two independent reviewers. Meta-analysis using a random effects model was undertaken to estimate pooled risks for: clinical deterioration, neurosurgical intervention, and death. Meta-regression was used to explore between-study variation in outcome estimates using study population characteristics. Forty-nine primary studies and five reviews were identified that met the inclusion criteria. The estimated pooled risk for the outcomes of interest were: clinical deterioration 11.7% (95% confidence interval [CI]: 11.7%-15.8%), neurosurgical intervention 3.5% (95% CI: 2.2%-4.9%), and death 1.4% (95% CI: 0.8%-2.2%). Twenty-one studies presented within-study estimates of the effect of patient factors. Meta-regression of study characteristics and pooling of within-study estimates of risk factor effect found the following factors significantly affected the risk for adverse outcomes: age, initial Glasgow Coma Scale (GCS), type of injury, and anti-coagulation. The generalizability of many studies was limited due to population selection. Mild TBI patients with injuries identified by CT brain scan have a small but clinically important risk for serious adverse outcomes. This review has identified several prognostic factors; research is needed to derive and validate a usable clinical decision rule so that low-risk patients can be safely discharged from the ED.

Whole-Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer

Background

In endometrial cancer (EC), preoperative pelvic MRI is recommended for local staging, while final tumor stage and grade are established by surgery and pathology. MRI‐based radiomic tumor profiling may aid in preoperative risk‐stratification and support clinical treatment decisions in EC.

Purpose

To develop MRI‐based whole‐volume tumor radiomic signatures for prediction of aggressive EC disease.

Study Type

Retrospective.

Population

A total of 138 women with histologically confirmed EC, divided into training (n_T = 108) and validation cohorts (n_V = 30).

Field Strength/Sequence

Axial oblique T₁‐weighted gradient echo volumetric interpolated breath‐hold examination (VIBE) at 1.5T (71/138 patients) and DIXON VIBE at 3T (67/138 patients) at 2 minutes postcontrast injection.

Assessment

Primary tumors were manually segmented by two radiologists with 4 and 8 years' of experience. Radiomic tumor features were computed and used for prediction of surgicopathologically‐verified deep (≥50%) myometrial invasion (DMI), lymph node metastases (LNM), advanced stage (FIGO III + IV), nonendometrioid (NE) histology, and high‐grade endometrioid tumors (E3). Corresponding analyses were also conducted using radiomics extracted from the axial oblique image slice depicting the largest tumor area.

Statistical Tests

Logistic least absolute shrinkage and selection operator (LASSO) was applied for radiomic modeling in the training cohort. The diagnostic performances of the radiomic signatures were evaluated by area under the receiver operating characteristic curve in the training (AUC_T) and validation (AUC_V) cohorts. Progression‐free survival was assessed using the Kaplan–Meier and Cox proportional hazard model.

Results

The whole‐tumor radiomic signatures yielded AUC_T/AUC_V of 0.84/0.76 for predicting DMI, 0.73/0.72 for LNM, 0.71/0.68 for FIGO III + IV, 0.68/0.74 for NE histology, and 0.79/0.63 for high‐grade (E3) tumor. Single‐slice radiomics yielded comparable AUC_T but significantly lower AUC_V for LNM and FIGO III + IV (both P < 0.05). Tumor volume yielded comparable AUC_T to the whole‐tumor radiomic signatures for prediction of DMI, LNM, FIGO III + IV, and NE, but significantly lower AUC_T for E3 tumors (P < 0.05). All of the whole‐tumor radiomic signatures significantly predicted poor progression‐free survival with hazard ratios of 4.6–9.8 (P < 0.05 for all).

Data Conclusion

MRI‐based whole‐tumor radiomic signatures yield medium‐to‐high diagnostic performance for predicting aggressive EC disease. The signatures may aid in preoperative risk assessment and hence guide personalized treatment strategies in EC.

Level of Evidence

4

Technical Efficacy Stage

2

Pitfalls of the concordance index for survival outcomes

Prognostic models are useful tools for assessing a patient's risk of experiencing adverse health events. In practice, these models must be validated before implementation to ensure that they are clinically useful. The concordance index (C-Index) is a popular statistic that is used for model validation, and it is often applied to models with binary or survival outcome variables. In this paper, we summarize existing criticism of the C-Index and show that many limitations are accentuated when applied to survival outcomes, and to continuous outcomes more generally. We present several examples that show the challenges in achieving high concordance with survival outcomes, and we argue that the C-Index is often not clinically meaningful in this setting. We derive a relationship between the concordance probability and the coefficient of determination under an ordinary least squares model with normally distributed predictors, which highlights the limitations of the C-Index for continuous outcomes. Finally, we recommend existing alternatives that more closely align with common uses of survival models.

The 3'UTR signature defines a highly metastatic subgroup of triple-negative breast cancer

Triple-negative breast cancer (TNBC) is a highly heterogeneous disease with an aggressive clinical course. Prognostic models are needed to chart potential patient outcomes. To address this, we used alternative 3′UTR patterns to improve postoperative risk stratification. We collected 327 publicly available microarrays and generated the 3′UTR landscape based on expression ratios of alternative 3′UTR. After initial feature filtering, we built a 17-3′UTR-based classifier using an elastic net model. Time-dependent ROC comparisons and Kaplan–Meier analyses confirmed an outstanding discriminating power of our prognostic model for TNBC patients. In the training cohort, 5-year event-free survival (EFS) was 78.6% (95% CI 71.2–86.0) for the low-risk group, and 16.3% (95% CI 2.3–30.4) for the high-risk group (log-rank p<0.0001; hazard ratio [HR] 8.29, 95% CI 4.78–14.4), In the validation set, 5-year EFS was 75.6% (95% CI 68.0–83.2) for the low-risk group, and 33.2% (95% CI 17.1–49.3) for the high-risk group (log-rank p<0.0001; HR 3.17, 95% CI 1.66–5.42). In conclusion, the 17-3′UTR-based classifier provides a superior prognostic performance for estimating disease recurrence and metastasis in TNBC patients and it may permit personalized management strategies.

Prognostic modeling of oral cancer by gene profiles and clinicopathological co-variables

Accurate staging and outcome prediction is a major problem in clinical management of oral cancer patients, hampering high precision treatment and adjuvant therapy planning. Here, we have built and validated multivariable models that integrate gene signatures with clinical and pathological variables to improve staging and survival prediction of patients with oral squamous cell carcinoma (OSCC). Gene expression profiles from 249 human papillomavirus (HPV)-negative OSCCs were explored to identify a 22-gene lymph node metastasis signature (LNMsig) and a 40-gene overall survival signature (OSsig). To facilitate future clinical implementation and increase performance, these signatures were transferred to quantitative polymerase chain reaction (qPCR) assays and validated in an independent cohort of 125 HPV-negative tumors. When applied in the clinically relevant subgroup of early-stage (cT1-2N0) OSCC, the LNMsig could prevent overtreatment in two-third of the patients. Additionally, the integration of RT-qPCR gene signatures with clinical and pathological variables provided accurate prognostic models for oral cancer, strongly outperforming TNM. Finally, the OSsig gene signature identified a subpopulation of patients, currently considered at low-risk for disease-related survival, who showed an unexpected poor prognosis. These well-validated models will assist in personalizing primary treatment with respect to neck dissection and adjuvant therapies.

Development of a Clinical Decision Rule for the Early Safe Discharge of Patients with Mild Traumatic Brain Injury and Findings on Computed Tomography Brain Scan: A Retrospective Cohort Study

International guidelines recommend routine hospital admission for all patients with mild traumatic brain injury (TBI) who have injuries on computed tomography (CT) brain scan. Only a small proportion of these patients require neurosurgical or critical care intervention. We aimed to develop an accurate clinical decision rule to identify low-risk patients safe for discharge from the emergency department (ED) and facilitate earlier referral of those requiring intervention. A retrospective cohort study of case notes of patients admitted with initial Glasgow Coma Scale 13-15 and injuries identified by CT was completed. Data on a primary outcome measure of clinically important deterioration (indicating need for hospital admission) and secondary outcome of neurosurgery, intensive care unit admission, or intubation (indicating need for neurosurgical admission) were collected. Multi-variable logistic regression was used to derive models and a risk score predicting deterioration using routinely reported clinical and radiological candidate variables identified in a systematic review. We compared the performance of this new risk score with the Brain Injury Guideline (BIG) criteria, derived in the United States. A total of 1699 patients were included from three English major trauma centers. A total of 27.7% (95% confidence interval [CI], 25.5-29.9) met the primary and 13.1% (95% CI, 11.6-14.8) met the secondary outcomes of deterioration. The derived clinical decision rule suggests that patients with simple skull fractures or intracranial bleeding <5 mm in diameter who are fully conscious could be safely discharged from the ED. The decision rule achieved a sensitivity of 99.5% (95% CI, 98.1-99.9) and specificity of 7.4% (95% CI, 6.0-9.1) to the primary outcome. The BIG criteria achieved the same sensitivity, but lower specificity (5%). Our empirical models showed good predictive performance and outperformed the BIG criteria. This would potentially allow ED discharge of 1 in 20 patients currently admitted for observation. However, prospective external validation and economic evaluation are required.

Reappraisal of the prognostic significance of mitotic rate supports its reincorporation into the melanoma staging system

BACKGROUND

Mitotic rate is a strong, independent prognostic factor in patients with melanoma. However, incorporating it into the melanoma staging system has proved challenging.

METHODS

The prognostic impact of mitotic rate was assessed in a melanoma cohort comprising 5050 patients from 2 geographically distinct populations. Computer-generated cut points for mitotic rate were constructed to determine its impact on melanoma-associated survival using Kaplan-Meier and multivariate regression analyses. The impact of mitotic rate also was assessed in randomly split training and validation sets.

RESULTS

Mitotic rate had a nonlinear impact on survival, as evidenced by unequally spaced cut points. An index incorporating these cut points that was constructed from one population produced significantly more accurate predictions of survival in the other population than using the entire scale of mitotic rate. An index constructed from the combined cohort was found to be independently predictive of survival, with an impact comparable to that of ulceration. Optimal high-versus-low cut points for mitotic rate were generated separately for each T category (<2 mitoses/mm² vs ≥2 mitoses/mm² for T1 melanoma, <4 mitoses/mm² vs ≥4 mitoses/mm² for T2 melanoma, <6 mitoses/mm² vs ≥6/mitoses/mm² for T3 melanoma, and <7 mitoses/mm² vs ≥7 mitoses/mm² for T4 melanoma). Using Kaplan-Meier analysis, elevated mitotic rate was found to have an impact on survival comparable to that of ulceration within each T category. Application of the index for mitotic rate that was constructed from the training data set demonstrated an independent impact in the validation data set, with a significance similar to that of ulceration.

CONCLUSIONS

The results of the current study demonstrated the comparable prognostic impact of mitotic rate and ulceration, providing support for its reincorporation into the T category.

Clinical Examination for the Prediction of Mortality in the Critically Ill: The Simple Intensive Care Studies-I

OBJECTIVES

Caregivers use clinical examination to timely recognize deterioration of a patient, yet data on the prognostic value of clinical examination are inconsistent. In the Simple Intensive Care Studies-I, we evaluated the association of clinical examination findings with 90-day mortality in critically ill patients.

DESIGN

Prospective single-center cohort study.

SETTING

ICU of a single tertiary care level hospital between March 27, 2015, and July 22, 2017.

PATIENTS

All consecutive adults acutely admitted to the ICU and expected to stay for at least 24 hours.

INTERVENTIONS

A protocolized clinical examination of 19 clinical signs conducted within 24 hours of admission.

MEASUREMENTS MAIN RESULTS

Independent predictors of 90-day mortality were identified using multivariable logistic regression analyses. Model performance was compared with established prognostic risk scores using area under the receiver operating characteristic curves. Robustness of our findings was tested by internal bootstrap validation and adjustment of the threshold for statistical significance. A total of 1,075 patients were included, of whom 298 patients (28%) had died at 90-day follow-up. Multivariable analyses adjusted for age and norepinephrine infusion rate demonstrated that the combination of higher respiratory rate, higher systolic blood pressure, lower central temperature, altered consciousness, and decreased urine output was independently associated with 90-day mortality (area under the receiver operating characteristic curves = 0.74; 95% CI, 0.71-0.78). Clinical examination had a similar discriminative value as compared with the Simplified Acute Physiology Score-II (area under the receiver operating characteristic curves = 0.76; 95% CI, 0.73-0.79; p = 0.29) and Acute Physiology and Chronic Health Evaluation-IV (using area under the receiver operating characteristic curves = 0.77; 95% CI, 0.74-0.80; p = 0.16) and was significantly better than the Sequential Organ Failure Assessment (using area under the receiver operating characteristic curves = 0.67; 95% CI, 0.64-0.71; p < 0.001).

CONCLUSIONS

Clinical examination has reasonable discriminative value for assessing 90-day mortality in acutely admitted ICU patients. In our study population, a single, protocolized clinical examination had similar prognostic abilities compared with the Simplified Acute Physiology Score-II and Acute Physiology and Chronic Health Evaluation-IV and outperformed the Sequential Organ Failure Assessment score.

Identification of an Immune-Related Prognostic Gene CLEC5A Based on Immune Microenvironment and Risk Modeling of Ovarian Cancer

Objective: To understand the immune characteristics of the ovarian cancer (OC) microenvironment and explore the differences of immune-related molecules and cells to establish an effective risk model and identify the molecules that significantly affected the immune response of OC, to help guide the diagnosis. Methods: First, we calculate the TMEscore which reflects the immune microenvironment, and then analyze the molecular differences between patients with different immune characteristics, and determine the prognostic genes. Then, the risk model was established by least absolute shrinkage and selection operator (LASSO) analysis and combined with clinical data into a nomogram for diagnosis and prediction. Subsequently, the potential gene CLEC5A influencing the immune response of OC was identified from the prognostic genes by integrative immune-stromal analysis. The genomic alteration was explored based on copy number variant (CNV) and somatic mutation data. Results: TMEscore was a prognostic indicator of OC. The prognosis of patients with high TMEscore was better. The risk model based on immune characteristics was a reliable index to predict the prognosis of patients, and the nomogram could comprehensively evaluate the prognosis of patients. Besides, CLEC5A was closely related to the abundance of immune cells, immune response, and the expression of immune checkpoints in the OC microenvironment. OC cells with high expression of CLEC5A increased the polarization of M2 macrophages. CLEC5A expression was significantly associated with TTN and CDK12 mutations and affected the copy number of tumor progression and immune-related genes. Conclusion: The study of immune characteristics in the OC microenvironment and the risk model can reveal the factors affecting the prognosis and guide the clinical hierarchical treatment. CLEC5A can be used as a potential key gene affecting the immune microenvironment remodeling of OC, which provides a new perspective for improving the effect of OC immunotherapy.

Screening Analysis of Platelet miRNA Profile Revealed miR-142-3p as a Potential Biomarker in Modeling the Risk of Acute Coronary Syndrome

Transcriptome analysis constitutes one of the major methods of elucidation of the genetic basis underlying the pathogenesis of various diseases. The post-transcriptional regulation of gene expression is mainly provided by microRNAs. Their remarkable stability in biological fluids and their high sensitivity to disease alteration indicates their potential role as biomarkers. Given the high mortality and morbidity of cardiovascular diseases, novel predictive biomarkers are sorely needed. Our study focuses for the first time on assessing potential biomarkers of acute coronary syndrome (ACS) based on the microRNA profiles of platelets. The study showed the overexpression of eight platelet microRNAs in ACS (miR-142-3p; miR-107; miR-338-3p, miR-223-3p, miR-21-5p, miR-130b-3p, miR-301a-3p, miR-221-3p) associated with platelet reactivity and functionality. Our results show that the combined model based on miR-142-3p and aspartate transaminase reached 82% sensitivity and 88% specificity in the differentiation of the studied groups. Furthermore, the analyzed miRNAs were shown to cluster into two orthogonal groups, regulated by two different biological factors. Bioinformatic analysis demonstrated that one group of microRNAs may be associated with the physiological processes of platelets, whereas the other group may be linked to platelet-vascular environment interactions. This analysis paves the way towards a better understanding of the role of platelet microRNAs in ACS pathophysiology and better modeling of the risk of ACS.

Predicting Neurological Recovery after Traumatic Brain Injury in Children: A Systematic Review of Prognostic Models

Predictive modeling is foundational to treatment and long-term management of children with traumatic brain injury (TBI). Assessment of injury severity in the acute-care setting enables early stratification of patients based on their risk of death, lifelong disability, or unfavorable outcome. This review evaluates predictive models that have been developed or validated for pediatric TBI patients. The predictive accuracy of these models, the outcomes and time points predicted, and the variables and statistical methods utilized in model development were compared. Embase, Scopus, MEDLINE^®, and Web of Science were searched for studies that developed statistical models for predicting patient outcomes following pediatric TBI. Studies were excluded if they focused on adults or non-traumatic brain injury, or if they did not assess classification accuracy. A total of 4538 entries were identified and screened, with 7 studies included for analysis. This included five studies in which adult predictive models were validated for use in the pediatric setting, and two in which new models were derived from a pediatric cohort. Trials of adult prediction tools in pediatric cohorts, including the International Mission for Prognosis and Analysis of Clinical Trials in TBI (IMPACT) and Corticoid Randomisation After Significant Head Injury (CRASH)-TBI models, showed comparable accuracy between classification of adults and children. Models derived from pediatric cohorts showed improved accuracy. Most studies solely focused on clinical variables, with two studies incorporating biochemical and imaging variables. Predictive models for pediatric TBI are primarily based on methods and variables identified in adult studies. Although adult models have proven effective in select pediatric cohorts, they may be suboptimal when compared with models derived or adjusted for children.

Using logistic regression to develop a diagnostic model for COVID-19: A single-center study

BACKGROUND

The main manifestations of coronavirus disease-2019 (COVID-19) are similar to the many other respiratory diseases. In addition, the existence of numerous uncertainties in the prognosis of this condition has multiplied the need to establish a valid and accurate prediction model. This study aimed to develop a diagnostic model based on logistic regression to enhance the diagnostic accuracy of COVID-19.

MATERIALS AND METHODS

A standardized diagnostic model was developed on data of 400 patients who were referred to Ayatollah Talleghani Hospital, Abadan, Iran, for the COVID-19 diagnosis. We used the Chi-square correlation coefficient for feature selection, and logistic regression in SPSS V25 software to model the relationship between each of the clinical features. Potentially diagnostic determinants extracted from the patient's history, physical examination, and laboratory and imaging testing were entered in a logistic regression analysis. The discriminative ability of the model was expressed as sensitivity, specificity, accuracy, and area under the curve, respectively.

RESULTS

After determining the correlation of each diagnostic regressor with COVID-19 using the Chi-square method, the 15 important regressors were obtained at the level of P < 0.05. The experimental results demonstrated that the binary logistic regression model yielded specificity, sensitivity, and accuracy of 97.3%, 98.8%, and 98.2%, respectively.

CONCLUSION

The destructive effects of the COVID-19 outbreak and the shortage of healthcare resources in fighting against this pandemic require increasing attention to using the Clinical Decision Support Systems equipped with supervised learning classification algorithms such as logistic regression.

Applied artificial intelligence in dentistry: emerging data modalities and modeling approaches

Artificial intelligence (AI) is increasingly applied across all disciplines of medicine, including dentistry. Oral health research is experiencing a rapidly increasing use of machine learning (ML), the branch of AI that identifies inherent patterns in data similarly to how humans learn. In contemporary clinical dentistry, ML supports computer-aided diagnostics, risk stratification, individual risk prediction, and decision support to ultimately improve clinical oral health care efficiency, outcomes, and reduce disparities. Further, ML is progressively used in dental and oral health research, from basic and translational science to clinical investigations. With an ML perspective, this review provides a comprehensive overview of how dental medicine leverages AI for diagnostic, prognostic, and generative tasks. The spectrum of available data modalities in dentistry and their compatibility with various methods of applied AI are presented. Finally, current challenges and limitations as well as future possibilities and considerations for AI application in dental medicine are summarized.

Multicenter Integration of MR Radiomics, Deep Learning, and Clinical Indicators for Predicting Hepatocellular Carcinoma Recurrence After Thermal Ablation

Background

To develop and validate an innovative predictive model that integrates multisequence magnetic resonance (MR) radiomics, deep learning features, and clinical indicators to accurately predict the recurrence of hepatocellular carcinoma (HCC) after thermal ablation.

Methods

This retrospective multicenter cohort study enrolled patients who were diagnosed with HCC and treated via thermal ablation. We extracted radiomic features from multisequence 3T MR images, analyzed these images using a 3D convolutional neural network (3D CNN), and incorporated clinical data into the model. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve.

Results

The study included 535 patients from three hospitals, comprising 462 males and 43 females. The RDC model, which stands for the Radiomics-Deep Learning-Clinical data model, demonstrated high predictive accuracy, achieving AUCs of 0.794 in the training set, 0.777 in the validation set, and 0.787 in the test set. Statistical analysis confirmed the model's robustness and the significant contribution of the integrated features to its predictive capabilities.

Conclusion

The RDC model effectively predicts HCC recurrence after thermal ablation by synergistically combining advanced imaging analysis and clinical parameters. This study highlights the potential of such integrative approaches to enhance prognostic assessments in HCC patients and offers a promising tool for clinical decision-making.

A three-range approach enhances the prognostic utility of CSF biomarkers in Alzheimer's disease

Introduction

Alzheimer's disease consensus recommends biomarker dichotomization, a practice with well-described clinical strengths and methodological limitations. Although neuroimaging studies have explored alternative biomarker interpretation strategies, a formally defined three-range approach and its prognostic impact remains under-explored for cerebrospinal fluid (CSF) biomarkers .

Methods

With two-graph receiver-operating characteristics based on different reference schemes, we derived three-range cut-points for CSF Elecsys biomarkers. According to baseline CSF status, we assessed the prognostic utility of this in predicting risk of clinical progression and longitudinal trajectories of cognitive decline and amyloid-beta (Aβ) positron emission tomography (PET) accumulation in non-demented individuals (Alzheimer's Disease Neuroimaging Initiative [ADNI]; n = 1246). In all analyses, we compared herein-derived three-range CSF cut-points to previously described binary ones.

Results

In our main longitudinal analyses, we highlight CSF p-tau181/Aβ1-42 three-range cut-points derived based on the cognitively normal Aβ-PET negative versus dementia Aβ-PET positive reference scheme for best depicting a prognostically relevant biomarker abnormality range. Longitudinally, our approach revealed a divergent intermediate cognitive trajectory undetected by dichotomization and a clearly abnormal group at higher risk for cognitive decline, with power analyses suggesting the latter group as potential trial enrichment candidates. Furthermore, we demonstrate that individuals with intermediate-range CSF status have similar rates of Aβ deposition to those in the clearly abnormal group.

Discussion

The proposed approach can refine clinico-biological prognostic assessment and potentially enhance trial recruitment, as it captures faster biomarker-related cognitive decline in comparison to binary cut-points. Although this approach has implications for trial recruitment and observational studies, further discussion is needed regarding clinical practice applications.

Perirenal Fat CT Radiomics-Based Survival Model for Upper Tract Urothelial Carcinoma: Integrating Texture Features with Clinical Predictors

Background: Upper tract urothelial carcinoma (UTUC) presents significant challenges in prognostication due to its rarity and complex anatomy. This study introduces a novel approach integrating perirenal fat (PRF) radiomics with clinical factors to enhance prognostic accuracy in UTUC. Methods: The study retrospectively analyzed 103 UTUC patients who underwent radical nephroureterectomy. PRF radiomics features were extracted from preoperative CT scans using a semi-automated segmentation method. Three prognostic models were developed: clinical, radiomics, and combined. Model performance was assessed using concordance index (C-index), time-dependent Area Under the Curve (AUC), and integrated Brier score. Results: The combined model demonstrated superior performance (C-index: 0.784, 95% CI: 0.707-0.861) compared to the radiomics (0.759, 95% CI: 0.678-0.840) and clinical (0.653, 95% CI: 0.547-0.759) models. Time-dependent AUC analysis revealed the radiomics model's particular strength in short-term prognosis (12-month AUC: 0.9281), while the combined model excelled in long-term predictions (60-month AUC: 0.8403). Key PRF radiomics features showed stronger prognostic value than traditional clinical factors. Conclusions: Integration of PRF radiomics with clinical data significantly improves prognostic accuracy in UTUC. This approach offers a more nuanced analysis of the tumor microenvironment, potentially capturing early signs of tumor invasion not visible through conventional imaging. The semi-automated PRF segmentation method presents advantages in reproducibility and ease of use, facilitating potential clinical implementation.

Prediction of Mental Health Complications Following Mild Traumatic Brain Injury

Prognostic models can support prevention of mental health complications after mild traumatic brain injury (mTBI). The present study aimed to identify risk factors and develop prognostic model(s) for mental health complications following mTBI. This secondary analysis of data from a randomized controlled trial included 513 adults presenting to emergency departments/urgent care centers. Candidate predictors were demographic, injury-related and health history information collected during medical chart review and eligibility screening, and scores on questionnaires completed at 2 weeks postinjury. The primary outcome was presence/absence of new or worsened major depressive disorder, anxiety disorders, and post-traumatic stress disorder (PTSD), determined with a structured psychodiagnostic interview (Mini International Neuropsychiatric Interview) at 3 and 6 months after mTBI. Logistic regression assessed the prognostic value of 22 pre-, peri-, and early postinjury factors. Least absolute shrinkage and selection operator (LASSO) was used to select predictors in prognostic model development. Younger age, identifying as a person of color, prior mTBI(s), maladaptive illness perceptions, and greater PTSD, and depression and anxiety symptom severity measured at 2 weeks postinjury were significant predictors of new/worsened mental health complications 3-6 months following mTBI. A comprehensive model (with 9 LASSO-selected predictors) showed strong discriminability for predicting mental health complications (optimism-corrected area under the receiver operating characteristic curve [AUC] = 0.80), outperforming a basic model that included only variables commonly collected as part of usual clinical care (optimism-corrected AUC = 0.71). Certain pre-injury and demographic characteristics are associated with increased risk of mental health complications after mTBI. Assessing for early postinjury illness beliefs and psychological symptoms can further improve prognostic accuracy.

[The Medical Social Characteristics of Women with Oncologic Diseases]

The oncologic pathology is covered by the group of socially significant diseases and ranks second position in the structure of population mortality in the Russian Federation, being one of the actual medical social problems of modern society. In the Russian Federation and all over the world, over last years, a steady rise of morbidity of malignant neoplasms is observed. At that, it is more intensive among female population. Both medical biological and social hygienic risk factors play a significant role in the development of these diseases. In this connection, significant interest represents study of individual medical social characteristics of females with oncologic pathology and their impact on health of this contingent and on development of disease itself. The medical social study, based on the developed program, covered 607 females with oncologic diseases and 605 females without this pathology (control group). The computer database was organized. To provide a possibility of in-death statistical processing of data, all qualitative indices were converted into number form using technology based on the expert appraisal. The technique of mathematical statistics was applied to analyze relationship of medical social characteristics. The functional dependences were built. The key risk factors were detected. The regression analysis was applied to develop mathematical models describing relationship between health of patients and their leaving on disability status and individual medical social risk factors. The testing confirmed efficiency of the developed models. The results of applied analysis and the developed prognostic models are proposed to be applied within the framework of stage-by-stage dispensary observation and control of health of females with oncologic diseases with the purpose of prevention at early stages and in case of complications of main and concomitant diseases.

Impact of anesthesia-related genes on prognosis and tumor microenvironment in hepatocellular carcinoma: A comprehensive analysis

Hepatocellular carcinoma (HCC), renowned for its bleak prognosis and high recurrence rates, necessitates innovative strategies for prognosis assessment and therapeutic intervention. In this pursuit, we systematically investigated the influence of anesthesia-related genes (ANARGs) on HCC outcomes. Leveraging data from The Cancer Genome Atlas (TCGA), our study scrutinized RNA sequencing data and clinical profiles from 374 HCC patients alongside 50 non-tumor liver samples to unravel ANARG expression patterns and their clinical relevance. Employing consensus clustering, we segregated HCC samples into two distinct subtypes based on ANARG profiles, unveiling significant survival disparities between them. Further differential expression analysis pinpointed pivotal genes and pathways distinguishing these subtypes, notably implicating lipid metabolism and the MTOR signaling pathway in HCC pathogenesis. A prognostic model, comprising five key ANARGs (DAGLA, CYP26B, HAVCR, G6PD and AKR1B), exhibited robust predictive capability for patient outcomes, validated across independent patient cohorts. Furthermore, immune infiltration analysis uncovered a nuanced interplay between ANARG expression and the tumor immune microenvironment, spotlighting variations in immune cell infiltration and function across the identified HCC subtypes. This comprehensive analysis underscores not only the prognostic significance of ANARGs in HCC but also their potential to modulate the tumor microenvironment, providing novel insights for tailoring anesthetic management and therapeutic strategies in HCC care. Our findings advocate for a more integrative approach to HCC management, amalgamating molecular profiling with traditional clinical parameters to refine patient stratification and personalize treatment strategies.

Evaluating generative AI models for explainable pathological feature extraction in lung adenocarcinoma grading assessment and prognostic model construction

BACKGROUND

Given the increasing prevalence of generative AI (GenAI) models, a systematically evaluation of their performance in lung adenocarcinoma histopathological assessment is crucial. This study aimed to evaluate and compare three visual-capable GenAI models (GPT-4o, Claude-3.5-Sonnet, and Gemini-1.5-Pro) for lung adenocarcinoma histological pattern recognition and grading, as well as to explore prognostic prediction models based on GenAI feature extraction.

MATERIALS AND METHODS

In this retrospective study, we analyzed 310 diagnostic slides from The Cancer Genome Atlas Lung Adenocarcinoma (TCGA-LUAD) database to evaluate GenAI models and to develop and internally validate machine learning-based prognostic models. For independent external validation, we utilized 95 and 87 slides from obtained different institutions. The primary endpoints comprised GenAI grading accuracy (area under the receiver operating characteristic curve, AUC) and stability (intraclass correlation coefficient, ICC). Secondary endpoints included developing and assessing machine learning-based prognostic models using GenAI-extracted features from the TCGA-LUAD dataset, evaluated by Concordance index (C-index).

RESULTS

Among the evaluated models, claude-3.5-Sonnet demonstrated the best overall performance, achieving high grading accuracy (average AUC = 0.823) with moderate stability (ICC = 0.585) The optimal machine learning-based prognostic model, developed using features extracted by Claude-3.5-Sonnet and integrating clinical variables, demonstrated good performance in both internal and external validations, yielding an average C-index of 0.715. Meta-analysis demonstrated that this prognostic model effectively stratified patients into risk groups, with the high-risk group showing significantly worse outcomes (Hazard ratio = 5.16, 95% confidence interval = 3.09-8.62).

CONCLUSION

GenAI models demonstrated significant potential in lung adenocarcinoma pathology, with Claude-3.5-Sonnet exhibiting superior performance in grading prediction and robust prognostic capabilities. These findings indicate promising applications of AI in lung adenocarcinoma diagnosis and clinical management.

Intracranial Densitometry-Augmented Machine Learning Enhances the Prognostic Value of Brain CT in Pediatric Patients With Traumatic Brain Injury: A Retrospective Pilot Study

Background: The inter- and intrarater variability of conventional computed tomography (CT) classification systems for evaluating the extent of ischemic-edematous insult following traumatic brain injury (TBI) may hinder the robustness of TBI prognostic models. Objective: This study aimed to employ fully automated quantitative densitometric CT parameters and a cutting-edge machine learning algorithm to construct a robust prognostic model for pediatric TBI. Methods: Fifty-eight pediatric patients with TBI who underwent brain CT were retrospectively analyzed. Intracranial densitometric information was derived from the supratentorial region as a distribution representing the proportion of Hounsfield units. Furthermore, a machine learning-based prognostic model based on gradient boosting (i.e., CatBoost) was constructed with leave-one-out cross-validation. At discharge, the outcome was assessed dichotomously with the Glasgow Outcome Scale (favorability: 1-3 vs. 4-5). In-hospital mortality, length of stay (>1 week), and need for surgery were further evaluated as alternative TBI outcome measures. Results: Densitometric parameters indicating reduced brain density due to subtle global ischemic changes were significantly different among the TBI outcome groups, except for need for surgery. The skewed intracranial densitometry of the unfavorable outcome became more distinguishable in the follow-up CT within 48 h. The prognostic model augmented by intracranial densitometric information achieved adequate AUCs for various outcome measures [favorability = 0.83 (95% CI: 0.72-0.94), in-hospital mortality = 0.91 (95% CI: 0.82-1.00), length of stay = 0.83 (95% CI: 0.72-0.94), and need for surgery = 0.71 (95% CI: 0.56-0.86)], and this model showed enhanced performance compared to the conventional CRASH-CT model. Conclusion: Densitometric parameters indicative of global ischemic changes during the acute phase of TBI are predictive of a worse outcome in pediatric patients. The robustness and predictive capacity of conventional TBI prognostic models might be significantly enhanced by incorporating densitometric parameters and machine learning techniques.

Machine learning models provide modest accuracy in predicting clinical impact of porcine reproductive and respiratory syndrome type 2 in Canadian sow herds

Objective

To determine the predictive potential of the open reading frame 5 nucleotide sequence of porcine reproductive and respiratory syndrome (PRRS) virus and the basic demographic data on the severity of the impact on selected production parameters during clinical PRRS outbreaks in Ontario sow herds.

Methods

A retrospective longitudinal study of clinical outbreaks in Ontario sow herds at various points between September 5, 2009, and February 5, 2019, was conducted using herds as units of analysis. Data were gathered from study sow farms in Ontario at the start of each clinical outbreak. Six machine learning models and 2 different genetic input structures of open reading frame 5 sequences were utilized to predict the impact on abortion and preweaning mortality.

Results

Extreme boosting machine learning models with genetic data represented through 2-dimensional multiple correspondence analysis had the highest accuracy when predicting clinical outcomes (60.8% [SD = 12.4%] and 74.4% [SD = 13.2%]) for abortion and preweaning mortality outcomes, respectively. The mean sensitivity of classifying outbreaks with a high impact on abortion was 50%, with a specificity of 89.2%. The mean sensitivity of classifying outbreaks with high preweaning mortality was 56.2%, with a specificity of 85.2%.

Conclusions

The data and methods utilized herein exhibited improvement in accuracy over the baseline; however, this increase was not sufficient to warrant field implementation.

Clinical Relevance

Predictive models based on observed data could assist practitioners in linking the genetics of the PRRS virus with clinical impact in clinical settings. Models trained in this study show promise for PRRS clinical impact prediction.

Unscheduled Hospital Admission as a Prognostic Factor in the Oncologic Patient: A Retrospective Study

Aims This research aimed to determine the correlation between survival, symptoms, and unscheduled admission in oncologic patients. Furthermore, this study aimed to develop a prognostic model that helps clinicians establish the indication of intervention by palliative care teams. Methodology A retrospective study of patients' digital clinical history registry was conducted to meet the two core objectives. The study population was patients with solid tumors undergoing unscheduled admissions to the oncology ward between January 1, 2018, and May 31, 2018. Demographic and clinical variables of those patients were analyzed. Specifically, the statistical analysis involved descriptive analysis, Kaplan-Meier curves, Log-Rank, and Chi-Squared Automatic Interaction Detection decision tree modeling. Results The results were obtained from 100 admissions of patients with an average age of 64. Of the patient cases examined, 67% (n = 67) were male. In 72% (n = 72) of the cases, patients presented with Stage IV tumors, and the most frequent primary tumor location among the admissions was lung, at 29% (n = 29). Intervention by the palliative care team occurred for 38% (n = 38) of patients. Mortality at 30, 90, 180, and 365 days was 34% (n = 34), 56% (n = 56), 71% (n = 71), and 78% (n = 78), respectively. Hepatic metastasis was the main predictor of mortality at 30 days (65%, n = 13) and at 90 days (90%, n = 18). In the absence of hepatic metastasis, the presence of more than one symptom predicted a mortality rate of 70% at 30 days. The main factor associated with mortality at 180 and 365 days was the tumor stage, with stage IV tumors having the highest mortality rate (84.7%, n = 61, and 90.3%, n = 65, respectively). Among the Stage IV population, the primary site shows a significant impact on survival, with colorectal/reproductive tumors being associated with decreased mortality. Conclusion Unscheduled admission is a negative prognostic factor in oncologic patients. An unscheduled admission can be expected to result in low survival in an oncologic patient, especially in those presenting with stage IV; involving non-colorectal/reproductive primaries; or presenting with pain, dyspnea, cachexia, or delirium.