Improving Machine Learning Diabetes Prediction Models for the Utmost Clinical Effectiveness

PyCaret for Predicting Type 2 Diabetes: A Phenotype- and Gender-Based Approach with the "Nurses' Health Study" and the "Health Professionals' Follow-Up Study" Datasets

Predicting type 2 diabetes mellitus (T2DM) by using phenotypic data with machine learning (ML) techniques has received significant attention in recent years. PyCaret, a low-code automated ML tool that enables the simultaneous application of 16 different algorithms, was used to predict T2DM by using phenotypic variables from the "Nurses' Health Study" and "Health Professionals' Follow-up Study" datasets. Ridge Classifier, Linear Discriminant Analysis, and Logistic Regression (LR) were the best-performing models for the male-only data subset. For the female-only data subset, LR, Gradient Boosting Classifier, and CatBoost Classifier were the strongest models. The AUC, accuracy, and precision were approximately 0.77, 0.70, and 0.70 for males and 0.79, 0.70, and 0.71 for females, respectively. The feature importance plot showed that family history of diabetes (famdb), never having smoked, and high blood pressure (hbp) were the most influential features in females, while famdb, hbp, and currently being a smoker were the major variables in males. In conclusion, PyCaret was used successfully for the prediction of T2DM by simplifying complex ML tasks. Gender differences are important to consider for T2DM prediction. Despite this comprehensive ML tool, phenotypic variables alone may not be sufficient for early T2DM prediction; genotypic variables could also be used in combination for future studies.

Machine Learning Prediction of Autism Spectrum Disorder Through Linking Mothers' and Children's Electronic Health Record Data

Autism spectrum disorder (ASD) is a neurodevelopmental disorder typically diagnosed in children. Early detection of ASD, particularly in girls who are often diagnosed late, can aid long-term development for children. We aimed to develop machine learning models for predicting ASD diagnosis in children, both boys and girls, using child-mother linked electronic health records (EHRs) data from a large clinical research network. Model features were children and mothers' risk factors in EHRs, including maternal health factors. We tested XGBoost and logistic regression with Random Oversampling (ROS) and Random Undersampling (RUS) to address imbalanced data. Logistic regression with RUS considering a three-year observation window for children's risk factors achieved the best performance for predicting ASD among the overall study population (AUROC = 0.798), boys (AUROC = 0.786), and girls (AUROC = 0.791). We calculated SHAP values to quantify the impacts of important clinical and sociodemographic risk factors.

A Fair Individualized Polysocial Risk Score for Identifying Increased Social Risk in Type 2 Diabetes

Background

Racial and ethnic minority groups and individuals facing social disadvantages, which often stem from their social determinants of health (SDoH), bear a disproportionate burden of type 2 diabetes (T2D) and its complications. It is crucial to implement effective social risk management strategies at the point of care.

Objective

To develop an electronic health records (EHR)-based machine learning (ML) analytical pipeline to address unmet social needs associated with hospitalization risk in patients with T2D.

Methods

We identified real-world patients with T2D from the EHR data from University of Florida (UF) Health Integrated Data Repository (IDR), incorporating both contextual SDoH (e.g., neighborhood deprivation) and individual-level SDoH (e.g., housing instability). The 2015-2020 data were used for training and validation and 2021-2022 data for independent testing. We developed a machine learning analytic pipeline, namely individualized polysocial risk score (iPsRS), to identify high social risk associated with hospitalizations in T2D patients, along with explainable AI (XAI) and fairness optimization.

Results

The study cohort included 10,192 real-world patients with T2D, with a mean age of 59 years and 58% female. Of the cohort, 50% were non-Hispanic White, 39% were non-Hispanic Black, 6% were Hispanic, and 5% were other races/ethnicities. Our iPsRS, including both contextual and individual-level SDoH as input factors, achieved a C statistic of 0.72 in predicting 1-year hospitalization after fairness optimization across racial and ethnic groups. The iPsRS showed excellent utility for capturing individuals at high hospitalization risk because of SDoH, that is, the actual 1-year hospitalization rate in the top 5% of iPsRS was 28.1%, ~13 times as high as the bottom decile (2.2% for 1-year hospitalization rate).

Conclusion

Our ML pipeline iPsRS can fairly and accurately screen for patients who have increased social risk leading to hospitalization in real word patients with T2D.