Predicting hypertension onset from longitudinal electronic health records with deep learning. Issue 4 (25th November 2022)

• Record Type: Journal Article
• Authors: Datta, Suparno; Morassi Sasso, Ariane; Kiwit, Nina; Bose, Subhronil; Nadkarni, Girish; Miotto, Riccardo; Böttinger, Erwin P
• Is Part Of: JAMIA open. Volume 5:Issue 4(2022)
• Publication Date: 2022-11-25
• Subjects: machine learning -- electronic health records -- deep learning -- hypertension; Medical informatics -- Periodicals; 610.285
• DOI: 10.1093/jamiaopen/ooac097
• Languages: English
• ISSNs: 2574-2531

Abstract

Abstract: Objective: Hypertension has long been recognized as one of the most important predisposing factors for cardiovascular diseases and mortality. In recent years, machine learning methods have shown potential in diagnostic and predictive approaches in chronic diseases. Electronic health records (EHRs) have emerged as a reliable source of longitudinal data. The aim of this study is to predict the onset of hypertension using modern deep learning (DL) architectures, specifically long short-term memory (LSTM) networks, and longitudinal EHRs. Materials and Methods: We compare this approach to the best performing models reported from previous works, particularly XGboost, applied to aggregated features. Our work is based on data from 233 895 adult patients from a large health system in the United States. We divided our population into 2 distinct longitudinal datasets based on the diagnosis date. To ensure generalization to unseen data, we trained our models on the first dataset (dataset A "train and validation") using cross-validation, and then applied the models to a second dataset (dataset B "test") to assess their performance. We also experimented with 2 different time-windows before the onset of hypertension and evaluated the impact on model performance. Results: With the LSTM network, we were able to achieve an area under the receiver operating characteristic curve value of 0.98 in the "train and validation" dataset A and 0.94 in the "test" dataset B for a prediction time window of 1 year. Lipid disorders, type 2 diabetes, and renal disorders are found to be associated with incident hypertension. Conclusion: These findings show that DL models based on temporal EHR data can improve the identification of patients at high risk of hypertension and corresponding driving factors. In the long term, this work may support identifying individuals who are at high risk for developing hypertension and facilitate earlier intervention to prevent the future development of hypertension. Lay Summary: Hypertension or high blood pressure is a chronic medical condition which can lead to severe health complications and increases the risk of cardiovascular diseases such as stroke, heart attack, and heart failure. In this study, we aim to predict the onset of hypertension using electronic health records (EHR) data and different machine learning (ML) and deep learning (DL) models. We used a specific DL model, called long short-term memory (LSTM) networks which not only considers the individual clinical events from a patient's history but also takes into account the sequence in which they occur. The models were trained and validated using data from 233 895 adult patients belonging to a large health system in the United States. While both types of models perform well on the task, the LSTM model achieved better prediction performance when compared with the other ML models. A further analysis of the models showed that lipid disorders, type 2 diabetes, and renal disorders were associated with an onset of hypertension. As such, this study suggests that ML and DL models are useful tools for identifying underlying patterns and risk factors in EHR leading to a diagnosis of hypertension.