Home › Research › Digital health tools
Deep representation learning of electronic health records to unlock patient stratification at scale
Landi I, Glicksberg BS, Lee HC, Cherng S, Landi G, Danieletto M, Dudley JT, Furlanello C et al.. NPJ digital medicine, 2020-07-17
Topic: Genetics and APOE
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.
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
APA 7th
Landi, I., Glicksberg, B. S., Lee, H. C., Cherng, S., Landi, G., Danieletto, M., et al. (2020). Deep representation learning of electronic health records to unlock patient stratification at scale. NPJ digital medicine. https://doi.org/10.1038/s41746-020-0301-z
Vancouver
Landi I, Glicksberg BS, Lee HC, Cherng S, Landi G, Danieletto M, et al. Deep representation learning of electronic health records to unlock patient stratification at scale. NPJ digital medicine. 2020. doi:10.1038/s41746-020-0301-z. PMID: 32699826.
BibTeX
@article{landi2020-32699826,
author = {Landi, I. and Glicksberg, B. S. and Lee, H. C. and Cherng, S. and Landi, G. and Danieletto, M. and Dudley, J. T. and Furlanello, C. and others},
title = {{Deep representation learning of electronic health records to unlock patient stratification at scale}},
journal = {NPJ digital medicine},
year = {2020},
doi = {10.1038/s41746-020-0301-z},
pmid = {32699826},
url = {https://doi.org/10.1038/s41746-020-0301-z}
}
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. The record's author list ends in “et al.”, so not every author is named. Check the citation against the original before you use it.
Key findings
- 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.
- With these results, we demonstrate that ConvAE can generate patient representations that lead to clinically meaningful insights.
New to this subject? Start with our plain-English guide: Digital health →
Study details
- Participants1,608,741
- Evidence strengthModerate
How this study scored 57/100
Published in a peer-reviewed journal. Scored zero for study design, effect reported and randomized / blinded because the record does not state it. We have no data on journal's citation record, times cited, citations per year, impact for its field and year, cited by studies here, still being cited, senior author's track record, institution's track record and multicenter collaboration, so those were left out: it earned 33 of the 58 points we could judge it on, which is 57 out of 100.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (NPJ digital medicine) |
| Journal's citation record | — / 4 | No journal record from OpenAlex — left out of this score |
| Study design | 0 / 12 | No study design recorded — scores zero, not guessed (not stated in the record — scored 0) |
| Strength of evidence | 3 / 5 | Rated “moderate” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 2 / 5 | 2020 — within 10 year(s) of the newest study here |
| Sample size | 4 / 4 | 1,608,741 participants |
| Effect reported | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomized / blinded | 0 / 2 | No randomization or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | — / 7 | No citation count (not found in OpenAlex) — left out of this score |
| Citations per year | — / 5 | No citation count or no year — left out of this score |
| Impact for its field and year | — / 6 | No field-weighted citation impact (OpenAlex has none yet) — left out of this score |
| Cited by studies here | — / 6 | Not yet checked against this library's citation graph — left out of this score |
| Still being cited | — / 4 | No yearly citation counts — left out of this score |
| Senior author's track record | — / 4 | Senior author's record not available — left out of this score |
| Institution's track record | — / 3 | No institution listed in OpenAlex — left out of this score |
| Multicenter collaboration | — / 3 | Institutions not listed — left out of this score |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 32699826) |
| Free to read | 2 / 2 | Free to read |
| Points | 33 / 58 | Scored on 11 of 20 parts. We have no data for the rest, so they are left out: 33 of the 58 points we could judge it on is 57 out of 100. |
| Total | 57 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
Free copy unknown: no free-copy check has an answer for this record yet. That does not mean it is paywalled.
Related
Studies in the library that share something with this one. The line above each title says what.
Related studies in Digital health tools
Also tagged “convolutional”
205 studies in the library carry the topic tag “convolutional”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 205 tagged studies.