Deep representation learning of electronic health records to unlock patient stratification at scale

Abstract

Deriving disease subtypes from electronic health records (EHRs) can guide next-generation personalized medicine. However, challenges in summarizing and representing patient data prevent widespread practice of scalable EHR-based stratification analysis. Here we present an unsupervised framework based on deep learning to process heterogeneous EHRs and derive patient representations that can efficiently and effectively enable patient stratification at scale. We considered EHRs of 1,608,741 patients from a diverse hospital cohort comprising a total of 57,464 clinical concepts. We introduce a representation learning model based on word embeddings, convolutional neural networks, and autoencoders (i.e., ConvAE) to transform patient trajectories into lowdimensional latent vectors. We evaluated these representations as broadly enabling patient stratification by applying hierarchical clustering to different multi-disease and disease-specific patient cohorts. ConvAE significantly outperformed several baselines in a clustering task to identify patients with different complex conditions, with 2.61 entropy and 0.31 purity average scores. When applied to stratify patients within a certain condition, ConvAE led to various clinically relevant subtypes for different disorders, including type 2 diabetes, Parkinson's disease, and Alzheimer's disease, largely related to comorbidities, disease progression, and symptom severity. With these results, we demonstrate that ConvAE can generate patient representations that lead to clinically meaningful insights. This scalable framework can help better understand varying etiologies in heterogeneous sub-populations and unlock patterns for EHR-based research in the realm of personalized medicine.

A 5-min Cognitive Task With Deep Learning Accurately Detects Early Alzheimer's Disease

“…Deep learning can also help to identify features that are important for disease progression or serve as markers for clinical trials (Ithapu et al, 2015 ). In addition to harvesting brain imaging data [especially the multimodality imaging data from the public ADNI database ( http://adni.loni.usc.edu/ )], deep learning has been applied to biospecimens (Lee et al, 2019b ; Lin et al, 2020 ), electronic health records (Landi et al, 2020 ; Nori et al, 2020 ), speech (Lopez-de-Ipina et al, 2018 ), neuropsychological data (Choi et al, 2018 ; Kang et al, 2019 ), and a combination of MRI and neuropsychological data (Qiu et al, 2018 ; Duc et al, 2020 ). By contrast, few studies have applied deep learning to cognitive task data, which – by design – is supposed to be more sensitive to detect early and mild neurocognitive impairment (Locascio et al, 1995 ; Perry and Hodges, 1999 ).…”

Machine Learning Applied to Clinical Laboratory Data Predicts Patient-Specific, Near-Term Relapse in Patients in Medication for Opioid Use Disorder Treatment

“…This data could be amenable to machine learning and data science methods now being applied in other areas of medicine (7; 8; 9; 10) , being tempered with the knowledge of how the underlying testing works, and the insights into patient behavior provided by expert clinicians.…”

An Ensemble Learning Approach for Enhanced Classification of Patients With Hepatitis and Cirrhosis

“…Such data-driven paradigm -opposite to the classical ruleor formula-based -has been boosted by the recent introduction of electronic health records (EHRs). In fact, EHRs play nowadays a major role as a data source, not only for standard shallow computational intelligence approaches but also for the growing literature trend associated with the quick development of novel deep learning algorithms [58], applied also imaging data [59], [60]. Although more classical data sources are still used (for example, insurance claims [61]), EHRs represent now a solid base for building learning models upon, both for diagnostic purposes in chronic hepatitis C [9], [62]- [64] and in derived diseases such as liver cancer [65].…”