Comparison of Machine Learning Techniques for Mortality Prediction in a Prospective Cohort of Older Adults

As global demographics change, ageing is a global phenomenon which is increasingly of interest in our modern and rapidly changing society. Thus, the application of proper prognostic indices in clinical decisions regarding mortality prediction has assumed a significant importance for personalized risk management (i.e., identifying patients who are at high or low risk of death) and to help ensure effective healthcare services to patients. Consequently, prognostic modelling expressed as all-cause mortality prediction is an important step for effective patient management. Machine learning has the potential to transform prognostic modelling. In this paper, results on the development of machine learning models for all-cause mortality prediction in a cohort of healthy older adults are reported. The models are based on features covering anthropometric variables, physical and lab examinations, questionnaires, and lifestyles, as well as wearable data collected in free-living settings, obtained for the “Healthy Ageing Initiative” study conducted on 2291 recruited participants. Several machine learning techniques including feature engineering, feature selection, data augmentation and resampling were investigated for this purpose. A detailed empirical comparison of the impact of the different techniques is presented and discussed. The achieved performances were also compared with a standard epidemiological model. This investigation showed that, for the dataset under consideration, the best results were achieved with Random UnderSampling in conjunction with Random Forest (either with or without probability calibration). However, while including probability calibration slightly reduced the average performance, it increased the model robustness, as indicated by the lower 95% confidence intervals. The analysis showed that machine learning models could provide comparable results to standard epidemiological models while being completely data-driven and disease-agnostic, thus demonstrating the opportunity for building machine learning models on health records data for research and clinical practice. However, further testing is required to significantly improve the model performance and its robustness.

SARS-CoV-2 infection and cardiovascular or pulmonary complications in ambulatory care: A risk assessment based on routine data

Background Risk factors of severe COVID-19 have mainly been investigated in the hospital setting. We investigated pre-defined risk factors for testing positive for SARS-CoV-2 infection and cardiovascular or pulmonary complications in the outpatient setting. Methods The present cohort study makes use of ambulatory claims data of statutory health insurance physicians in Bavaria, Germany, with polymerase chain reaction (PCR) test confirmed or excluded SARS-CoV-2 infection in first three quarters of 2020. Statistical modelling and machine learning were used for effect estimation and for hypothesis testing of risk factors, and for prognostic modelling of cardiovascular or pulmonary complications. Results A cohort of 99 811 participants with PCR test was identified. In a fully adjusted multivariable regression model, dementia (odds ratio (OR) = 1.36), type 2 diabetes (OR = 1.14) and obesity (OR = 1.08) were identified as significantly associated with a positive PCR test result. Significant risk factors for cardiovascular or pulmonary complications were coronary heart disease (CHD) (OR = 2.58), hypertension (OR = 1.65), tobacco consumption (OR = 1.56), chronic obstructive pulmonary disease (COPD) (OR = 1.53), previous pneumonia (OR = 1.53), chronic kidney disease (CKD) (OR = 1.25) and type 2 diabetes (OR = 1.23). Three simple decision rules derived from prognostic modelling based on age, hypertension, CKD, COPD and CHD were able to identify high risk patients with a sensitivity of 74.8% and a specificity of 80.0%. Conclusions The decision rules achieved a high prognostic accuracy non-inferior to complex machine learning methods. They might help to identify patients at risk, who should receive special attention and intensified protection in ambulatory care.

Clinical Features at Presentation for Glioblastoma Patients Impact Survival Predictions in a Machine Learning Model

Aims To generate an accurate prediction model for greater than median survival using Random Forest machine learning analysis and to compare the model to a traditional logistic regression analysis model on the same Glioblastoma Dataset. Method In this single centre retrospective cohort study, all patients with histologically diagnosed primary GB from October 2014 to April 2019 were included (n=466). Machine learning algorithms encompassing multiple logistic regression and a Random Forest, Gini index-based decision tree model with 100,000 trees were used. 17 clinical, molecular and treatment specific binarily categorised variables were used. The dataset was split 70:30 into training and validating sets. Results The dataset contained 466 patients. 326 patients made up the training set and 140 the validation set. The Random Forest model’s accuracy for predicting 18-month survival was 86.4% compared to the Logistic Regression model’s accuracy of 85.7%. The top 5 factors that the Random Forest model used to predict survival over 18 months were; mean MGMT status >10%, if the patient underwent gross total resection, whether the patient had adjuvant temozolomide, whether the patient had a neurological deficit on presentation, and the sex of the patient. Conclusion Machine learning can be applied in the context of GB prognostic modelling. The models show that as well as the known factors that affect GB survival, the presenting symptom may also have an impact on prognostication.