Electronic Health Record Phenotypes for Identifying Patients with Late-Stage Disease: a Method for Research and Clinical Application
Systematic identification of patients allows researchers and clinicians to test new models of care delivery. EHR phenotypes—structured algorithms based on clinical indicators from EHRs—can aid in such identification.
To develop EHR phenotypes to identify decedents with stage 4 solid-tumor cancer or stage 4–5 chronic kidney disease (CKD).
We developed two EHR phenotypes. Each phenotype included International Classification of Diseases (ICD)-9 and ICD-10 codes. We used natural language processing (NLP) to further specify stage 4 cancer, and lab values for CKD.
Decedents with cancer or CKD who had been admitted to an academic medical center in the last 6 months of life and died August 26, 2017–December 31, 2017.
We calculated positive predictive values (PPV), false discovery rates (FDR), false negative rates (FNR), and sensitivity. Phenotypes were validated by a comparison with manual chart review. We also compared the EHR phenotype results to those admitted to the oncology and nephrology inpatient services.
The EHR phenotypes identified 271 decedents with cancer, of whom 186 had stage 4 disease; of 192 decedents with CKD, 89 had stage 4–5 disease. The EHR phenotype for stage 4 cancer had a PPV of 68.6%, FDR of 31.4%, FNR of 0.5%, and 99.5% sensitivity. The EHR phenotype for stage 4–5 CKD had a PPV of 46.4%, FDR of 53.7%, FNR of 0.0%, and 100% sensitivity.
EHR phenotypes efficiently identified patients who died with late-stage cancer or CKD. Future EHR phenotypes can prioritize specificity over sensitivity, and incorporate stratification of high- and low-palliative care need. EHR phenotypes are a promising method for identifying patients for research and clinical purposes, including equitable distribution of specialty palliative care.
This work was supported by the North Carolina Translational and Clinical Sciences Institute (NC TraCS), Clinical and Translational Science Awards (CTSA) grant no. UL1TR002489.
Compliance with Ethical Standards
Conflict of Interest
The authors declare that they do not have a conflict of interest.
- 2.Institute of Medicine (US). Dying in America: Improving Quality and Honoring Individual Preferences Near the End of Life : Health and Medicine Division. 2015.Google Scholar
- 3.O’hare AM, Song M-K, Tamura MK, Moss AH. Priorities in Palliative Care Research II Research Priorities for Palliative Care for Older Adults with Advanced Chronic Kidney Disease.Google Scholar
- 7.Hanson LC, Gabriel S, Ernecoff NC, Wessell KL, Mitchell SL, Sachs G, et al. Triggered Palliative Care in Advanced Dementia: A Pilot Study. 2017.Google Scholar
- 8.Ernecoff NC, Wessell KL, Gabriel S, Carey TS, Hanson LC. A Novel Screening Method to Identify Late-Stage Dementia Patients for Palliative Care Research and Practice. J Pain Symptom Manage. 2018;Google Scholar
- 10.Conway M, Berg RL, Carrell D, Denny JC, Kho AN, Kullo IJ, et al. Analyzing the Heterogeneity and Complexity of Electronic Health Record Oriented Phenotyping Algorithms.Google Scholar
- 12.Lilley EJ, Lindvall ÃC, Lillemoe KD, Tulsky JA, Wiener DC, Cooper Z, et al. Measuring Processes of Care in Palliative Surgery A Novel Approach Using Natural Language Processing. 2017;XX(Xx):1–3.Google Scholar
- 13.I2b2. Informatics for Integrating Biology and Bedside. Boston, MA;Google Scholar
- 14.Hanauer DA, Mei Q, Law J, Khanna R, Zheng K. Supporting information retrieval from electronic health records: A report of University of Michigan’s nine-year experience in developing and using the Electronic Medical Record Search Engine (EMERSE). J Biomed Inform. 2015 Jun;55:290–300.CrossRefGoogle Scholar
- 15.Levey AS, Eckardt K-U, Tsukamoto Y, Levin A, Coresh J, Rossert J, et al. Definition and classification of chronic kidney disease: A position statement from Kidney Disease: Improving Global Outcomes (KDIGO). Vol. 67, Kidney International. 2005.Google Scholar
- 16.Zeng QT, Goryachev S, Weiss S, Sordo M, Murphy SN, Lazarus R. BMC Medical Informatics and Decision Making Extracting principal diagnosis, co-morbidity and smoking status for asthma research: evaluation of a natural language processing system. 2006;Google Scholar
- 17.Kelley AS, Morrison RS. Palliative Care for the Seriously Ill. Campion EW, editor. N Engl J Med. 2015 Aug 20;373(8):747–55.Google Scholar
- 21.American Academy of Family Physicians. A, Stoeckle J, Diaz V, Valko G, Arenson C. Family practice management. Vol. 24, Family Practice Management. American Academy of Family Physicians; 2017. 30–33 p.Google Scholar
- 22.Lofthus DM, Gadgil JY, De Lemos JA. Overriding Concerns: The Role of Electronic Medical Record-Based Best Practice Alerts in Reducing Unnecessary Laboratory Testing. 2014;Google Scholar
- 25.Navar AM, Peterson ED, Steen DL, Wojdyla DM, Sanchez RJ, Khan I, et al. Evaluation of Mortality Data from the Social Security Administration Death Master File for Clinical Research. JAMA Cardiol. 2019;Google Scholar
- 27.Weissman DE, Meier DE. Special Report Identifying Patients in Need of a Palliative Care Assessment in the Hospital Setting A Consensus Report from the Center to Advance Palliative Care.Google Scholar
- 28.Avati A, Jung K, Harman S, Downing L, Ng A, Shah NH. Improving palliative care with deep learning. In: 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE; 2017. p. 311–6.Google Scholar
- 29.Sahni N, Simon G, Arora R. Development and Validation of Machine Learning Models for Prediction of 1-Year Mortality Utilizing Electronic Medical Record Data Available at the End of Hospitalization in Multicondition Patients: a Proof-of-Concept Study. J Gen Intern Med. 2018;33(6):921–9.CrossRefGoogle Scholar
- 30.Cardona-Morrell M, Hillman K. Development of a tool for defining and identifying the dying patient in hospital: Criteria for Screening and Triaging to Appropriate aLternative care (CriSTAL).Google Scholar