Limestone: High-throughput candidate phenotype generation via tensor factorization
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
The rapidly increasing availability of electronic health records (EHRs) from multiple heterogeneous sources has spearheaded the adoption of data-driven approaches for improved clinical research, decision making, prognosis, and patient management. Unfortunately, EHR data do not always directly and reliably map to medical concepts that clinical researchers need or use. Some recent studies have focused on EHR-derived phenotyping, which aims at mapping the EHR data to specific medical concepts; however, most of these approaches require labor intensive supervision from experienced clinical professionals. Furthermore, existing approaches are often disease-centric and specialized to the idiosyncrasies of the information technology and/or business practices of a single healthcare organization. In this paper, we propose Limestone, a nonnegative tensor factorization method to derive phenotype candidates with virtually no human supervision. Limestone represents the data source interactions naturally using tensors (a generalization of matrices). In particular, we investigate the interaction of diagnoses and medications among patients. The resulting tensor factors are reported as phenotype candidates that automatically reveal patient clusters on specific diagnoses and medications. Using the proposed method, multiple phenotypes can be identified simultaneously from data. We demonstrate the capability of Limestone on a cohort of 31,815 patient records from the Geisinger Health System. The dataset spans 7 years of longitudinal patient records and was initially constructed for a heart failure onset prediction study. Our experiments demonstrate the robustness, stability, and the conciseness of Limestone-derived phenotypes. Our results show that using only 40 phenotypes, we can outperform the original 640 features (169 diagnosis categories and 471 medication types) to achieve an area under the receiver operator characteristic curve (AUC) of 0.720 (95% CI 0.715 to 0.725). Moreover, in consultation with a medical expert, we confirmed 82% of the top 50 candidates automatically extracted by Limestone are clinically meaningful.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Heart Disease and Stroke Statistics—2012 Update: A Report From the American Heart Association
Writing Group Members, Roger, V. L., Go, A. S., Lloyd-Jones, D. M., Benjamin, E. J., Berry, J. D., Borden, W. B., Bravata, D. M., Dai, S., Ford, E. S., et al. (2012) · Circulation · doi:10.1161/cir.0b013e31823ac046 · Cited by 7,333
Heidenreich, P. A., Trogdon, J. G., Khavjou, O. A., Butler, J., Dracup, K., Ezekowitz, M. D., Finkelstein, E. A., Hong, Y., Johnston, S. C., Khera, A., et al. (2011) · Circulation · doi:10.1161/cir.0b013e31820a55f5 · Cited by 3,208
Mining electronic health records: towards better research applications and clinical care
Jensen, P. B., Jensen, L. J., & Brunak, S. (2012) · Nature Reviews Genetics · doi:10.1038/nrg3208 · Cited by 1,680 · cited 1×
“While knowledge discovery in EHRs show great promise towards providing better quality of care at lower costs [13–15], the vast information captured pose difficulties for both medical practitioners and data analysts [16].”
BackgroundPheWAS: demonstrating the feasibility of a phenome-wide scan to discover gene–disease associations
Denny, J. C., Ritchie, M. D., Basford, M. A., Pulley, J. M., Bastarache, L., Brown-Gentry, K., Wang, D., Masys, D. R., Roden, D. M., & Crawford, D. C. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq126 · Cited by 1,219
Self-citationNext-generation phenotyping of electronic health records
Hripcsak, G., & Albers, D. J. (2013) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2012-001145 · Cited by 795 · cited 9×
“Data mining and machine learning tools have been utilized to automate the phenotype generation process [24,36,37,26].”
BackgroundMethodInfluentialUniqueness of medical data mining
Cios, K. J., & William Moore, G. (2002) · Artificial Intelligence in Medicine · doi:10.1016/s0933-3657(02)00049-0 · Cited by 639
Nguyen, H. B., Corbett, S. W., Steele, R., Banta, J., Clark, R. T., Hayes, S. R., Edwards, J., Cho, T. W., & Wittlake, W. A. (2007) · Critical Care Medicine · doi:10.1097/01.ccm.0000259463.33848.3d · Cited by 555
Validation of a common data model for active safety surveillance research
Overhage, J. M., Ryan, P. B., Reich, C. G., Hartzema, A. G., & Stang, P. E. (2012) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2011-000376 · Cited by 548 · cited 1×
“Examples of such large-scale phenotyping efforts are typ-ified by the Electronic Medical Records and Genomics (eMERGE) Network [34] and the Observational Medical Outcomes Partner-ship (OMOP) [35].”
Electronic Medical Records for Genetic Research: Results of the eMERGE Consortium
Kho, A. N., Pacheco, J. A., Peissig, P. L., Rasmussen, L., Newton, K. M., Weston, N., Crane, P. K., Pathak, J., Chute, C. G., Bielinski, S. J., et al. (2011) · Science Translational Medicine · doi:10.1126/scitranslmed.3001807 · Cited by 336
Self-citationUsing EHRs to integrate research with patient care: promises and challenges: Table 1
Weng, C., Appelbaum, P., Hripcsak, G., Kronish, I., Busacca, L., Davidson, K. W., & Bigger, J. T. (2012) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2012-000878 · Cited by 82 · cited 1×
“While knowledge discovery in EHRs show great promise towards providing better quality of care at lower costs [13–15], the vast information captured pose difficulties for both medical practitioners and data analysts [16].”
Background
Cited by
In silico methods for drug repurposing and pharmacology
Hodos, R. A., Kidd, B. A., Shameer, K., Readhead, B. P., & Dudley, J. T. (2016) · WIREs Systems Biology and Medicine · doi:10.1002/wsbm.1337 · Cited by 326
Mining Electronic Health Records (EHRs): A Survey
Yadav, P., Steinbach, M., Kumar, V., & Simon, G. (2018) · ACM Computing Surveys · doi:10.1145/3127881 · Cited by 299
Recommendations for Reporting Machine Learning Analyses in Clinical Research
Stevens, L. M., Mortazavi, B. J., Deo, R. C., Curtis, L., & Kao, D. P. (2020) · Circulation: Cardiovascular Quality and Outcomes · doi:10.1161/circoutcomes.120.006556 · Cited by 268
“25,26 In such cases, additional ML and statistical approaches such as traditional regression or survival methods, double ML, 21 and causal inference techniques 27,28 may be used in conjunction with or may be considered over unsupervised approaches.”
Clinical Data Reuse or Secondary Use: Current Status and Potential Future Progress
Meystre, S. M., Lovis, C., Bürkle, T., Tognola, G., Budrionis, A., & Lehmann, C. U. (2017) · Yearbook of Medical Informatics · doi:10.15265/iy-2017-007 · Cited by 204
Federated Tensor Factorization for Computational Phenotyping
Kim, Y., Sun, J., Yu, H., & Jiang, X. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098118 · Cited by 128
“Overcoming several disadvantages of the previous methods, tensor factorization methods have shown great potential in discovering meaningful phenotypes from complicated and heterogeneous health records [13, 14, 28].”
BackgroundMethodSelf-citation
Metadata
- Authors
- Ho, J. C., Ghosh, J., Steinhubl, S. R., Stewart, W. F., Denny, J. C., Malin, B. A., & Sun, J.
- Venue
- Journal of Biomedical Informatics
- Publisher
- Elsevier BV
- Published
- 2014-12
- Volume
- 52
- Pages
- 199-211
- ISSN
- 1532-0464 (ISSN-L)
- OpenAlex
- W2135496322
- Cited by
- 151
- References
- 10
- FWCI
- 14.85
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.