Classification Performance of Neural Networks Versus Logistic Regression Models: Evidence From Healthcare Practice

Applying machine learning to construct an association model for lung cancer and environmental hormone high-risk factors and nursing assessment reconstruction

INTRODUCTION

To utilize machine learning techniques to develop an association model linking lung cancer and environmental hormones to enhance the understanding of potential lung cancer risk factors and refine current nursing assessments for lung cancer.

DESIGN

This study is exploratory in nature. In Stage 1, data were sourced from a biological database, and machine learning methods, including logistic regression and neural-like networks, were employed to construct an association model. Results indicate significant associations between lung cancer and blood cadmium, urine cadmium, urine cadmium/creatinine, and di(2-ethylhexyl) phthalate. In Stage 2, 128 lung adenocarcinoma patients were recruited through convenience sampling, and the model was validated using a questionnaire assessing daily living habits and exposure to environmental hormones.

RESULTS

Analysis reveals correlations between the living habits of patients with lung adenocarcinoma and exposure to blood cadmium, urine cadmium, urine cadmium/creatinine, polyaromatic hydrocarbons, diethyl phthalate, and di(2-ethylhexyl) phthalate.

CONCLUSIONS

According to the World Health Organization's global statistics, lung cancer claims approximately 1.8 million lives annually, with more than 50% of patients having no history of smoking or non-traditional risk factors. Environmental hormones have garnered significant attention in recent years in pathogen exploration. However, current nursing assessments for lung cancer risk have not incorporated environmental hormone-related factors. This study proposes reconstructing existing lung cancer nursing assessments with a comprehensive evaluation of lung cancer risks.

CLINICAL RELEVANCE

The findings underscore the importance of future studies advocating for public screening of environmental hormone toxins to increase the sample size and validate the model externally. The developed association model lays the groundwork for advancing cancer risk nursing assessments.

A machine learning approach towards assessing consistency and reproducibility: an application to graft survival across three kidney transplantation eras

Background

In South Africa, between 1966 and 2014, there were three kidney transplant eras defined by evolving access to certain immunosuppressive therapies defined as Pre-CYA (before availability of cyclosporine), CYA (when cyclosporine became available), and New-Gen (availability of tacrolimus and mycophenolic acid). As such, factors influencing kidney graft failure may vary across these eras. Therefore, evaluating the consistency and reproducibility of models developed to study these variations using machine learning (ML) algorithms could enhance our understanding of post-transplant graft survival dynamics across these three eras.

Methods

This study explored the effectiveness of nine ML algorithms in predicting 10-year graft survival across the three eras. We developed and internally validated these algorithms using data spanning the specified eras. The predictive performance of these algorithms was assessed using the area under the curve (AUC) of the receiver operating characteristics curve (ROC), supported by other evaluation metrics. We employed local interpretable model-agnostic explanations to provide detailed interpretations of individual model predictions and used permutation importance to assess global feature importance across each era.

Results

Overall, the proportion of graft failure decreased from 41.5% in the Pre-CYA era to 15.1% in the New-Gen era. Our best-performing model across the three eras demonstrated high predictive accuracy. Notably, the ensemble models, particularly the Extra Trees model, emerged as standout performers, consistently achieving high AUC scores of 0.95, 0.95, and 0.97 across the eras. This indicates that the models achieved high consistency and reproducibility in predicting graft survival outcomes. Among the features evaluated, recipient age and donor age were the only features consistently influencing graft failure throughout these eras, while features such as glomerular filtration rate and recipient ethnicity showed high importance in specific eras, resulting in relatively poor historical transportability of the best model.

Conclusions

Our study emphasises the significance of analysing post-kidney transplant outcomes and identifying era-specific factors mitigating graft failure. The proposed framework can serve as a foundation for future research and assist physicians in identifying patients at risk of graft failure.

Development and Validation of Two Prediction Models for 72-Hour Mortality in High-Risk Trauma Patients Using a Benchmark Dataset: A Comparative Study of Logistic Regression and Neural Networks Models

Background Many studies have been conducted to develop scoring systems for trauma patients, with the majority using logistic regression (LR) models. Neural networks (NN), which is a machine learning algorithm, has a potential to increase the performance of these models. Objectives The aim of this study was to develop and validate two separate prediction models for 72-hour mortality of high-risk trauma patients using LR and NN and to compare the performances of these models in detail. We also aimed to share the SPSS calculators for our models. Materials and methods This is a retrospective, single-center study conducted using a benchmark dataset where the patients were retrospectively gathered from a level 1 trauma center. Patients older than 18 years of age, who had multiple injuries, and were treated at the University Hospital Zurich between January 1, 1996, and January 1, 2013, were included. Patients with a condition that may have an impact on the musculoskeletal system, with Injury Severity Score<16, and with missing outcome data were excluded. Results A total of 3,075 patients were included in the analysis. The area under the curve values of the LR and NN models for predicting 72-hour mortality in patients with high-risk trauma in the hold-out cohort were 0.859 (95% CI=0.836 to 0.883) and 0.856 (95% CI=0.831 to 0.880), respectively. There was no statistically significant difference in the performance of the models (p = 0.554, DeLong's test). Conclusion Both of the models showed good discrimination. Our study suggests that the NN and LR models we developed hold promise as screening tools for predicting 72-hour mortality in high-risk trauma patients. These models were made available to clinicians as clinical prediction tools via SPSS calculators. However, further external validation studies in diverse populations are necessary to substantiate their clinical utility. Moreover, in subsequent studies, it would be beneficial to derive NN models with substantial events per predictor variable to attain more robust and greater predictive accuracy. If the dataset is relatively limited, using LR seems to be a viable alternative.