Classification and Diagnostic Prediction of Colorectal Cancer Mortality Based on Machine Learning Algorithms: A Multicenter National Study

INTRODUCTION

Colorectal cancer (CRC) ranks as the second leading cause of cancer-related deaths. This study aimed to predict survival outcomes of CRC patients using machine learning (ML) methods.

MATERIAL AND METHODS

A retrospective analysis included 1853 CRC patients admitted to three prominent tertiary hospitals in Iran from October 2006 to July 2019. Six ML methods, namely logistic regression (LR), Naïve Bayes (NB), Support Vector Machine (SVM), Neural Network (NN), Decision Tree (DT), and Light Gradient Boosting Machine (LGBM), were developed with 10-fold cross-validation. Feature selection employed the Random Forest method based on mean decrease GINI criteria. Model performance was assessed using Area Under the Curve (AUC).

RESULTS

Time from diagnosis, age, tumor size, metastatic status, lymph node involvement, and treatment type emerged as crucial predictors of survival based on mean decrease GINI. The NB (AUC = 0.70, 95% Confidence Interval [CI] 0.65-0.75) and LGBM (AUC = 0.70, 95% CI 0.65-0.75) models achieved the highest predictive AUC values for CRC patient survival.

CONCLUSIONS

This study highlights the significance of variables including time from diagnosis, age, tumor size, metastatic status, lymph node involvement, and treatment type in predicting CRC survival. The NB model exhibited optimal efficacy in mortality prediction, maintaining a balanced sensitivity and specificity. Policy recommendations encompass early diagnosis and treatment initiation for CRC patients, improved data collection through digital health records and standardized protocols, support for predictive analytics integration in clinical decisions, and the inclusion of identified prognostic variables in treatment guidelines to enhance patient outcomes.

Prevalence and Mortality of Post-traumatic Acute Kidney Injury in Children; a Systematic Review and Meta-analysis

Introduction

Numerous studies on acute kidney injury (AKI) following trauma have been performed, and acceptable findings have been reported in the adult population. The present meta-analysis summarizes the studies performed on the pediatric population to evaluate the prevalence of AKI following trauma in this population.

Method

The Medline, Embase, Scopus and Web of Sciences databases were searched for articles published until the July, 31, 2021. Two independent reviewers screened observational studies performed on children with physical trauma and AKI related to it. The interested outcomes were the prevalence and mortality of trauma-related AKI in traumatized children.

Results

Data of 9 articles were included in the present meta-analysis. The prevalence of trauma-related AKI varied between 0% and 30.30% among included studies. Pooled analysis showed that the prevalence of trauma-related AKI was 9.86% (95% CI: 8.02 to 11.84%). The prevalence of AKI after exertional rhabdomyolysis, direct physical trauma, and earthquake related injuries was 0%, 12.64% and 24.60%, respectively. There was a significant relationship between the prevalence of AKI and trauma etiology (p = 0.038). Moreover, the occurrence of AKI in children with trauma was associated with an increased risk of mortality (OR = 5.55; 95% CI: 2.14 to 13.93).

Conclusion

The findings of the present study showed that 9.86% of children develop AKI following trauma, which may increase their risk of death by about 5.5 times. Nevertheless, since none of the studies had adjusted their analyzes for potential confounders, caution should be exercised in interpreting the relationship between trauma-related AKI and mortality.

Active and Passive Immunization with Myelin Basic Protein as a Method for Early Treatment of Traumatic Spinal Cord Injury; a Meta-Analysis

Introduction:

Traumatic spinal cord injury (SCI), as a dangerous central nervous system damage, continues to threaten communities by imposing various disabilities and costs. Early adjustment of the immune system response using Myelin Basic Protein (MBP) immunization may prevent the SCI-related secondary damages. As a result, the current study is designed to review and analyse the evidence on active and passive immunization with MBP for treatment of traumatic SCI.

Methods:

Medline, Embase, Scopus, and Web of Science databases were systematically searched until the end of 2020. Criteria for inclusion in the current study included pre-clinical studies, which performed passive (injection of MBP-activated T cells) or active (administration of MBP or MBP-modified peptides) immunization with MBP after traumatic SCI. Exclusion criteria was defined as lack of a non-treated SCI group, lack of evaluation of locomotion, review studies, and combination therapy. Finally, analyses were conducted using STATA software, and a standardized mean difference (SMD) with a 95% confidence interval (CI) were reported.

Results:

Data from 17 papers were included in the present study. Finally, analysis of these data showed that passive immunization (SMD=0.87; 95%CI: 0.19-1.55; p=0.012) and active immunization (SMD=2.08, 95%CI: 1.42-2.73; p<0.001) for/with MBP both have good efficacy in improving locomotion following traumatic SCI. However, significant heterogeneity was observed in both of them. The most important sources of heterogeneity in active immunization were differences in SCI models, route of administration, time interval between SCI and transplantation, and type of vaccine used. In passive immunization, however, these sources were the model of SCI and the time interval between SCI and transplantation. Although, there was substantial heterogeneity among studies, subgroup analysis showed that active immunization improved locomotion after traumatic SCI in all tested conditions (with differences in injury model, severity of injury, method of administration, different time interval between SCI to vaccination, etc.).

Conclusion:

The results of the present study demonstrated that immunization with MBP, especially in its active form, could significantly improve motor function following SCI in rats and mice. Therefore, it could be considered as a potential treatment in acute settings such as emergency departments. However, the safety of this method is still under debate. Therefore, it is recommended for future research to focus on the investigation of safety of MBP immunization in animal studies, before conducting human clinical trials.

The Value of Physiological Scoring Criteria in Predicting the In-Hospital Mortality of Acute Patients; a Systematic Review and Meta-Analysis

Introduction:

There is no comprehensive meta-analysis on the value of physiological scoring systems in predicting the mortality of critically ill patients. Therefore, the present study intended to conduct a systematic review and meta-analysis to collect the available clinical evidence on the value of physiological scoring systems in predicting the in-hospital mortality of acute patients.

Method:

An extensive search was performed on Medline, Embase, Scopus, and Web of Science databases until the end of year 2020. Physiological models included Rapid Acute Physiology Score (RAPS), Rapid Emergency Medicine Score (REMS), modified REMS (mREMS), and Worthing Physiological Score (WPS). Finally, the data were summarized and the findings were presented as summary receiver operating characteristics (SROC), sensitivity, specificity and diagnostic odds ratio (DOR).

Results:

Data from 25 articles were included. The overall analysis showed that the area under the SROC curve of REMS, RAPS, mREMS, and WPS criteria were 0.83 (95% CI: 0.79-0.86), 0.89 (95% CI: 0.86-0.92), 0.64 (95% CI: 0.60-0.68) and 0.86 (95% CI: 0.83-0.89), respectively. DOR for REMS, RAPS, mREMS and WPS models were 11 (95% CI: 8-16), 13 (95% CI: 4-41), 2 (95% CI: 2-4) and 17 (95% CI: 5-59) respectively. When analyses were limited to trauma patients, the DOR of the REMS and RAPS models were 112 and 431, respectively. Due to the lack of sufficient studies, it was not possible to limit the analyses for mREMS and WPS.

Conclusion:

The findings of the present study showed that three models of RAPS, REMS and WPS have a high predictive value for in-hospital mortality. In addition, the value of these models in trauma patients is much higher than other patient settings.