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 framew...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2020-07-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-020-0301-z |
| _version_ | 1797643144174501888 |
|---|---|
| author | Isotta Landi Benjamin S. Glicksberg Hao-Chih Lee Sarah Cherng Giulia Landi Matteo Danieletto Joel T. Dudley Cesare Furlanello Riccardo Miotto |
| author_facet | Isotta Landi Benjamin S. Glicksberg Hao-Chih Lee Sarah Cherng Giulia Landi Matteo Danieletto Joel T. Dudley Cesare Furlanello Riccardo Miotto |
| author_sort | Isotta Landi |
| collection | DOAJ |
| description | 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 low-dimensional 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. |
| first_indexed | 2024-03-11T14:10:24Z |
| format | Article |
| id | doaj.art-a3c812cf99b140a5b237ea6ab049acf1 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-11T14:10:24Z |
| publishDate | 2020-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-a3c812cf99b140a5b237ea6ab049acf12023-11-02T00:11:59ZengNature Portfolionpj Digital Medicine2398-63522020-07-013111110.1038/s41746-020-0301-zDeep representation learning of electronic health records to unlock patient stratification at scaleIsotta Landi0Benjamin S. Glicksberg1Hao-Chih Lee2Sarah Cherng3Giulia Landi4Matteo Danieletto5Joel T. Dudley6Cesare Furlanello7Riccardo Miotto8Bruno Kessler InstituteHasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount SinaiInstitute for Next Generation Healthcare, Icahn School of Medicine at Mount SinaiInstitute for Next Generation Healthcare, Icahn School of Medicine at Mount SinaiDepartment of Mental Health and Pathological Addiction, Azienda USL Centro “Santi”Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount SinaiInstitute for Next Generation Healthcare, Icahn School of Medicine at Mount SinaiBruno Kessler InstituteHasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount SinaiAbstract 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 low-dimensional 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.https://doi.org/10.1038/s41746-020-0301-z |
| spellingShingle | Isotta Landi Benjamin S. Glicksberg Hao-Chih Lee Sarah Cherng Giulia Landi Matteo Danieletto Joel T. Dudley Cesare Furlanello Riccardo Miotto Deep representation learning of electronic health records to unlock patient stratification at scale npj Digital Medicine |
| title | Deep representation learning of electronic health records to unlock patient stratification at scale |
| title_full | Deep representation learning of electronic health records to unlock patient stratification at scale |
| title_fullStr | Deep representation learning of electronic health records to unlock patient stratification at scale |
| title_full_unstemmed | Deep representation learning of electronic health records to unlock patient stratification at scale |
| title_short | Deep representation learning of electronic health records to unlock patient stratification at scale |
| title_sort | deep representation learning of electronic health records to unlock patient stratification at scale |
| url | https://doi.org/10.1038/s41746-020-0301-z |
| work_keys_str_mv | AT isottalandi deeprepresentationlearningofelectronichealthrecordstounlockpatientstratificationatscale AT benjaminsglicksberg deeprepresentationlearningofelectronichealthrecordstounlockpatientstratificationatscale AT haochihlee deeprepresentationlearningofelectronichealthrecordstounlockpatientstratificationatscale AT sarahcherng deeprepresentationlearningofelectronichealthrecordstounlockpatientstratificationatscale AT giulialandi deeprepresentationlearningofelectronichealthrecordstounlockpatientstratificationatscale AT matteodanieletto deeprepresentationlearningofelectronichealthrecordstounlockpatientstratificationatscale AT joeltdudley deeprepresentationlearningofelectronichealthrecordstounlockpatientstratificationatscale AT cesarefurlanello deeprepresentationlearningofelectronichealthrecordstounlockpatientstratificationatscale AT riccardomiotto deeprepresentationlearningofelectronichealthrecordstounlockpatientstratificationatscale |