Artificial intelligence with temporal features outperforms machine learning in predicting diabetes

Diabetes mellitus type 2 is increasingly being called a modern preventable pandemic, as even with excellent available treatments, the rate of complications of diabetes is rapidly increasing. Predicting diabetes and identifying it in its early stages could make it easier to prevent, allowing enough time to implement therapies before it gets out of control. Leveraging longitudinal electronic medical record (EMR) data with deep learning has great potential for diabetes prediction. This paper examines the predictive competency of deep learning models in contrast to state-of-the-art machine learning models to incorporate the time dimension of risk. The proposed research investigates a variety of deep learning models and features for predicting diabetes. Model performance was appraised and compared in relation to predominant features, risk factors, training data density and visit history. The framework was implemented on the longitudinal EMR records of over 19K patients extracted from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Empirical findings demonstrate that deep learning models consistently outperform other state-of-the-art competitors with prediction accuracy of above 91%, without overfitting. Fasting blood sugar, hemoglobin A1c and body mass index are the key predictors of future onset of diabetes. Overweight, middle aged patients and patients with hypertension are more vulnerable to developing diabetes, consistent with what is already known. Model performance improves as training data density or the visit history of a patient increases. This study confirms the ability of the LSTM deep learning model to incorporate the time dimension of risk in its predictive capabilities.Author summary: Diabetes is a growing problem around the world and yet it is preventable. A small percentage of people are at higher risk of developing diabetes. Detecting those at highest risk early and offering them early treatment could go a long way to slowing down the growth of diabetes and reverse the trend of severe complications of diabetes. One of the barriers to early detection is our inability to take into account the risk that accumulates over time. Someone who has had elevated blood sugar for 5 years has more risk than someone who has only had it for 1 year, yet all current prediction models only take into account the blood sugar and not the time element. This paper reports on our research with artificial intelligence models that can take into account the time element of risk.