Creating a Learning Health System in a Cancer Center: Generalizability of an Electronic Health Record Phenotype for Advanced Solid Cancer

Anne M Walling; Karl A Lorenz; Anita Yuan; Claire E O'Hanlon; Michael McClean; Benjamin Fayyazuddin Ljungberg; Karleen F Giannitrapani; Selen Bozkurt; Sidharth Anand; John Glaspy; Neil S Wenger; Charlotta Lindvall

doi:10.1200/OP.24.00389

Creating a Learning Health System in a Cancer Center: Generalizability of an Electronic Health Record Phenotype for Advanced Solid Cancer

JCO Oncol Pract. 2024 Oct 10:OP2400389. doi: 10.1200/OP.24.00389. Online ahead of print.

Authors

Anne M Walling^{1

2

3}, Karl A Lorenz^{3

4

5}, Anita Yuan¹, Claire E O'Hanlon^{1

3}, Michael McClean¹, Benjamin Fayyazuddin Ljungberg⁶, Karleen F Giannitrapani^{4

5}, Selen Bozkurt⁷, Sidharth Anand¹, John Glaspy¹, Neil S Wenger¹, Charlotta Lindvall^{6

8

9}

Affiliations

¹ VA Greater Los Angeles Health System, Los Angeles, CA.
² Department of Medicine, University of California, Los Angeles, Los Angeles, CA.
³ RAND, Santa Monica, CA.
⁴ Center for Innovation and Implementation, VA Palo Alto Health Care System, Menlo Park, CA.
⁵ Stanford University School of Medicine, Stanford, CA.
⁶ Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, MA.
⁷ Department of Biomedical Informatics, Emory University, Atlanta, GA.
⁸ Department of Medicine, Brigham and Women's Hospital, Boston, MA.
⁹ Harvard Medical School, Boston, MA.

PMID: 39388652
DOI: 10.1200/OP.24.00389

Abstract

Purpose: To test the generalizability of an electronic health record (EHR) phenotype for patients with advanced solid cancer, which was previously developed in a single cancer center.

Methods: We compared an algorithm to identify patients with advanced solid cancer from a random sample of patients with active cancer in the Veterans Health Administration (VA) and an academic cancer center with a human-coded reference standard between January 1, 2016, and December 31, 2019.

Results: Compared with the human-coded reference standard, the algorithm had high specificity (93%; 95% CI, 87 to 99 and 97%; 95% CI, 93 to 100) and reasonable sensitivity (85%; 95% CI, 76 to 94 and 87%; 95% CI, 77 to 97) in the VA and academic cancer center populations, respectively. Patients with advanced cancer (compared with those with active nonadvanced cancer) had higher mortality at the VA and academic cancer center (29.2% and 17.0% 6-month mortality v 6.8% and 3.5%), respectively.

Conclusion: This EHR phenotype can be used to measure and improve the quality of palliative care for patients with advanced cancer within and across health care settings.