CoChat
Sign Up
Cited by 10Machine Learning in HealthcareMedical Coding and Health InformationElectronic Health Records Systems

Impact of Diverse Data Sources on Computational Phenotyping

Open access
Wang, Liwei, Olson, Janet E., Bielinski, Suzette J., St. Sauver, Jennifer L., Fu, Sunyang, He, Huan, Cicek, Mine S., Hathcock, Matthew A. +2 more·2020·Frontiers in Genetics
DOI 10.3389/fgene.2020.00556PMC PMC7283539
Open this paper in CoChat — free account

Abstract

Electronic health records (EHRs) are widely adopted with a great potential to serve as a rich, integrated source of phenotype information. Computational phenotyping, which extracts phenotypes from EHR data automatically, can accelerate the adoption and utilization of phenotype-driven efforts to advance scientific discovery and improve healthcare delivery. A list of computational phenotyping algorithms has been published but data fragmentation, i.e., incomplete data within one single data source, has been raised as an inherent limitation of computational phenotyping. In this study, we investigated the impact of diverse data sources on two published computational phenotyping algorithms, rheumatoid arthritis (RA) and type 2 diabetes mellitus (T2DM), using Mayo EHRs and Rochester Epidemiology Project (REP) which links medical records from multiple health care systems. Results showed that both RA (less prevalent) and T2DM (more prevalent) case selections were markedly impacted by data fragmentation, with positive predictive value (PPV) of 91.4 and 92.4%, false-negative rate (FNR) of 26.6 and 14% in Mayo data, respectively, PPV of 97.2 and 98.3%, FNR of 5.2 and 3.3% in REP. T2DM controls also contain biases, with PPV of 91.2% and FNR of 1.2% for Mayo. We further elaborated underlying reasons impacting the performance.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3389/fgene.2020.00556

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

No references could be resolved yet.

Research works printed but not linked: 24

  1. Aletaha D. Neogi T. Silman A. J. Funovits J. Felson D. T. Bingham C. O. (2010). 2010 Rheumatoid arthritis classification criteria: an American College of Rheumatology/European League Against Rheumatism collaborative initiative. Arthr. Rheum 62 2569– 2581. 10.1002/art.27584 20872595 · DOI
  2. Bullard K. M. Cowie C. C. Lessem S. E. (2018). Prevalence of diagnosed diabetes in adults by diabetes type—United States, 2016. Morb. Mortal. Wkly Rep. 67: 359. 10.15585/mmwr.mm6712a2 29596402 PMC5877361 · DOI · Paper page
  3. Carroll R. J. Eyler A. E. Denny J. C. (2015). Intelligent use and clinical benefits of electronic health records in rheumatoid arthritis. Expert Rev. Clin. Immunol. 11 329– 337. 10.1586/1744666X.2015.1009895 25660652 PMC4518025 · DOI
  4. Carroll R. J. Thompson W. K. Eyler A. E. Mandelin A. M. Cai T. Zink R. M. (2012). Portability of an algorithm to identify rheumatoid arthritis in electronic health records. J. Am. Med. Inform. Assoc. 19 e162– e169. 10.1136/amiajnl-2011-000583 22374935 PMC3392871 · DOI
  5. Crawford D. C. Crosslin D. R. Tromp G. Kullo I. J. Kuivaniemi H. Hayes M. G. (2014). eMERGEing progress in genomics—the first seven years. Front. Genet. 5: 184. 10.3389/fgene.2014.00184 24987407 PMC4060012 · DOI
  6. Denny J. C. Crawford D. C. Ritchie M. D. Bielinski S. J. Basford M. A. Bradford Y. (2011). Variants near FOXE1 are associated with hypothyroidism and other thyroid conditions: using electronic medical records for genome-and phenome-wide studies. Am. J. Hum. Genet. 89 529– 542. 10.1016/j.ajhg.2011.09.008 21981779 PMC3188836 · DOI
  7. Gunasekar S. Ho J. C. Ghosh J. Kreml S. Kho A. N. Denny J. C. (2016). Phenotyping using Structured Collective Matrix Factorization of Multi–source EHR Data. arXiv [preprint]. Available online at: https://arxiv.org/abs/1609.04466 (accessed January 20, 2020). · arXiv
  8. Hirsch J. Nicola G. McGinty G. Liu R. W. Barr R. M. Chittle M. D. (2016). ICD-10: history and context. Am. J. Neuroradiol. 37 596– 599. 10.3174/ajnr.A4696 26822730 PMC7960170 · DOI
  9. Hunter T. M. Boytsov N. N. Zhang X. Schroeder K. Michaud K. Araujo A. B. (2017). Prevalence of rheumatoid arthritis in the United States adult population in healthcare claims databases, 2004–2014. Rheumatol. Int. 37 1551– 1557. 10.1007/s00296-017-3726-1 28455559 · DOI
  10. Kho A. N. Hayes M. G. Rasmussen-Torvik L. Pacheco J. A. Thompson W. K. Armstrong L. L. (2011). Use of diverse electronic medical record systems to identify genetic risk for type 2 diabetes within a genome-wide association study. J. Am. Med. Inform. Assoc. 19 212– 218. 10.1136/amiajnl-2011-000439 22101970 PMC3277617 · DOI
  11. Kullo I. J. Ding K. Jouni H. Smith C. Y. Chute C. G. (2010). A genome-wide association study of red blood cell traits using the electronic medical record. PLoS One 5: e13011. 10.1371/journal.pone.0013011 20927387 PMC2946914 · DOI
  12. Kurreeman F. Liao K. Chibnik L. Hickey B. Stahl E. Gainer V. (2011). Genetic basis of autoantibody positive and negative rheumatoid arthritis risk in a multi-ethnic cohort derived from electronic health records. Am. J. Hum. Genet. 88 57– 69. 10.1016/j.ajhg.2010.12.007 21211616 PMC3014362 · DOI
  13. Liao K. P. Cai T. Gainer V. (2010). Electronic medical records for discovery research in rheumatoid arthritis. Arthr. Care Res. 62 1120– 1127. 10.1002/acr.20184 20235204 PMC3121049 · DOI
  14. Newton K. M. Peissig P. L. Kho A. N. Bielinski S. J. Berg R. L. Choudhary V. (2013). Validation of electronic medical record-based phenotyping algorithms: results and lessons learned from the eMERGE network. J. Am. Med. Inform. Assoc. 20 e147– e154. 10.1136/amiajnl-2012-000896 23531748 PMC3715338 · DOI
  15. Olson J. E. Ryu E. Johnson K. J. (2013). The mayo clinic biobank: a building block for individualized medicine. Mayo Clin Proc. 88 952– 962. 10.1016/j.mayocp.2013.06.006 24001487 PMC4258707 · DOI
  16. Ostropolets A. Christian R. Patrick R. Ning S. George H. Chunhua W. (2020). Adapting electronic health records-derived phenotypes to claims data: Lessons learned in using limited clinical data for phenotyping. J. Biomed. Inform. 102: 103363. 10.1016/j.jbi.2019.103363 31866433 PMC7390483 · DOI
  17. Ritchie M. D. Denny J. C. Crawford D. C. Ramirez A. H. Weiner J. B. Pulley J. M. (2010). Robust replication of genotype-phenotype associations across multiple diseases in an electronic medical record. Am. J. Hum. Genet. 86 560– 572. 10.1016/j.ajhg.2010.03.003 20362271 PMC2850440 · DOI
  18. Robinson J. R. Wei W.-Q. Roden D. M. Denny J. C. (2018). Defining phenotypes from clinical data to drive genomic research. Annu. Rev. Biomed. Data Sci. 1 69– 92. PMC8186527 34109303
  19. Rocca W. A. Grossardt B. R. Brue S. M. Bock-Goodner C. M. Chamberlain A. M. Wilson P. M. (2018). Data resource profile: expansion of the Rochester epidemiology project medical records-linkage system (E-REP). Int. J. Epidemiol. 47 368– 368j. 10.1093/ije/dyx268 29346555 PMC5913632 · DOI
  20. Teixeira P. L. Wei W.-Q. Cronin R. M. Mo H. VanHouten J. P. Carroll R. J. (2016). Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals. J. Am. Med. Inform. Assoc. 24 162– 171. 10.1093/jamia/ocw071 27497800 PMC5201185 · DOI
  21. Wei W.-Q. Denny J. C. (2015). Extracting research-quality phenotypes from electronic health records to support precision medicine. Genome Med. 7: 41. 10.1186/s13073-015-0166-y 25937834 PMC4416392 · DOI
  22. Wei W.-Q. Leibson C. L. Ransom J. E. Kho A. N. Caraballo P. J. Chai H. S. (2012). Impact of data fragmentation across healthcare centers on the accuracy of a high-throughput clinical phenotyping algorithm for specifying subjects with type 2 diabetes mellitus. J. Am. Med. Inform. Assoc. 19 219– 224. 10.1136/amiajnl-2011-000597 22249968 PMC3277630 · DOI · Paper page
  23. Wei W.-Q. Leibson C. L. Ransom J. E. Kho A. N. Chute C. G. (2013). The absence of longitudinal data limits the accuracy of high-throughput clinical phenotyping for identifying type 2 diabetes mellitus subjects. Int. J. Med. Inform. 82 239– 247. 10.1016/j.ijmedinf.2012.05.015 22762862 PMC3478423 · DOI
  24. Wood G. C. Still C. D. Chu X. Susek M. Erdman R. Hartman C. (2008). Association of chromosome 9p21 SNPs with cardiovascular phenotypes in morbid obesity using electronic health record data. Genomic Med. 2 33– 43. 10.1007/s11568-008-9023-z 18716918 PMC2518660 · DOI

Cited by

Sorted by citations

Authors
Wang, L., Olson, J. E., Bielinski, S. J., St. Sauver, J. L., Fu, S., He, H., Cicek, M. S., Hathcock, M. A., Cerhan, J. R., & Liu, H.
Affiliations
Mayo Clinic (US)
Corresponding author
Liu, Hongfang
ORCID
Venue
Frontiers in Genetics
Publisher
Frontiers Media SA
Published
2020-06-03
Volume
11
Pages
556-556
ISSN
1664-8021 (ISSN-L)
DOI
10.3389/fgene.2020.00556
PMC
PMC7283539
OpenAlex
W3027096112
Cited by
10
References
0
Citations by year
2025: 4 · 2023: 2 · 2022: 2 · 2021: 2
FWCI
0.59
Type
journal article
Language
en
Open access
Licence
Locations
  • Frontiers in Genetics (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Mayo Clinic
  • National Institutes of Health (U01TR002062)
  • Center for Individualized Medicine, Mayo Clinic
  • National Institute on Aging (R01AG034676)
  • U.S. National Library of Medicine (R01LM011829)
  • National Center for Advancing Translational Sciences (U01TR02062)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Health Professions › Health Information Management › Medical Coding and Health Information
  • Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
Keywords
computational phenotyping, electronic health records, data fragmentation, rheumatoid arthritis, type 2 diabetes, Rochester Epidemiology Project, positive predictive value, false negative rate, case selection, control selection bias

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