A data-driven approach to predicting diabetes and cardiovascular disease with machine learning

Abstract

BackgroundDiabetes and cardiovascular disease are two of the main causes of death in the United States. Identifying and predicting these diseases in patients is the first step towards stopping their progression. We evaluate the capabilities of machine learning models in detecting at-risk patients using survey data (and laboratory results), and identify key variables within the data contributing to these diseases among the patients.MethodsOur research explores data-driven approaches which utilize supervised machine learning models to identify patients with such diseases. Using the National Health and Nutrition Examination Survey (NHANES) dataset, we conduct an exhaustive search of all available feature variables within the data to develop models for cardiovascular, prediabetes, and diabetes detection. Using different time-frames and feature sets for the data (based on laboratory data), multiple machine learning models (logistic regression, support vector machines, random forest, and gradient boosting) were evaluated on their classification performance. The models were then combined to develop a weighted ensemble model, capable of leveraging the performance of the disparate models to improve detection accuracy. Information gain of tree-based models was used to identify the key variables within the patient data that contributed to the detection of at-risk patients in each of the diseases classes by the data-learned models.ResultsThe developed ensemble model for cardiovascular disease (based on 131 variables) achieved an Area Under - Receiver Operating Characteristics (AU-ROC) score of 83.1% using no laboratory results, and 83.9% accuracy with laboratory results. In diabetes classification (based on 123 variables), eXtreme Gradient Boost (XGBoost) model achieved an AU-ROC score of 86.2% (without laboratory data) and 95.7% (with laboratory data). For pre-diabetic patients, the ensemble model had the top AU-ROC score of 73.7% (without laboratory data), and for laboratory based data XGBoost performed the best at 84.4%. Top five predictors in diabetes patients were 1) waist size, 2) age, 3) self-reported weight, 4) leg length, and 5) sodium intake. For cardiovascular diseases the models identified 1) age, 2) systolic blood pressure, 3) self-reported weight, 4) occurrence of chest pain, and 5) diastolic blood pressure as key contributors.ConclusionWe conclude machine learned models based on survey questionnaire can provide an automated identification mechanism for patients at risk of diabetes and cardiovascular diseases. We also identify key contributors to the prediction, which can be further explored for their implications on electronic health records.

Machine learning for characterizing risk of type 2 diabetes mellitus in a rural Chinese population: the Henan Rural Cohort Study

“…In contrast to traditional methods, machine learning can learn the nonlinear interactions iteratively from large amounts of data using computer algorithms 13 , which have been applied in various fields, such as disease risk assessment and prediction 14,15 . Recent research shows that machine learning methods can describe patients' characteristics and identify patients at risk of developing T2DM 16,17 . A study illustrated the performance of support vector machine for detecting persons with diabetes and pre-diabetes 18 .…”

Comparison of ARIMA model and XGBoost model for prediction of human brucellosis in mainland China: a time-series study

“…The XGBoost model has achieved excellent performance in many fields of medical research. [23][24][25][26] Currently, no researchers have used the XGBoost model to predict the time series data of human brucellosis.…”

Diagnostic significance of C-reactive protein and hematological parameters in acute toxoplasmosis

“…The data analysis driven by ML is a quite new approach in medical care and complementary diagnosis (Heinrichs and Eickhoff 2020 ; Sidey-Gibbons and Sidey-Gibbons 2019 ; Watson et al 2019 ); however, in the last years, several studies have reported the use of ML with image data or clinical specimens (blood, stool, urine) to help in diagnose cancer (Kourou et al 2015 ; Podnar et al 2019 ; Salod and Singh 2019 ; Wu et al 2019 ), diabetes and cardiovascular disease (Dinh et al 2019 ; Kavakiotis et al 2017 ; Shameer et al 2018 ) among other conditions (Ayling et al 2019 ; Gunčar et al 2018 ; Poostchi et al 2018 ; Ullah et al 2019 ). Considering the infective diseases, ML techniques were used to identify dengue (Hair et al 2019 ), bacterial infections (Rawson et al 2019 ) and, more recently, COVID-19 (Banerjee et al 2020 ; Brinati et al 2020 ).…”