Development and Portability of a Text Mining Algorithm for Capturing Disease Progression in Electronic Health Records of Patients With Stage IV Non–Small Cell Lung Cancer

JCO Clinical Cancer Informatics, vol. 8, pp. e2400053

Abstract

PURPOSE: The objective was to develop and evaluate the portability of a text mining algorithm for prospectively capturing disease progression in electronic health record (EHR) data of patients with metastatic non-small cell lung cancer (mNSCLC) treated with immunochemotherapy. METHODS: This study used EHR data from patients with mNSCLC receiving immunochemotherapy (between October 1, 2018, and December 31, 2022) in four Dutch hospitals. A text mining algorithm for capturing disease progression was developed in hospitals 1 and 2 and then transferred to hospitals 3 and 4 to evaluate portability. Performance metrics were calculated by comparing its outcomes with manual chart review. In addition, data were simulated to come available over time to assess performance in real-time applications. Median progression-free survival (PFS) was calculated using the Kaplan-Meier method to compare text mining with manual chart review. RESULTS: During development and portability, the text mining algorithm performed well in capturing disease progression, with all performance scores >90%. When real-time performance was simulated, the performance scores in all four hospitals exceeded 90% from week 15 after the start of follow-up. Although the exact progression dates varied in 46 patients of 157 patients with progressive disease, the number of patients labeled with progression too early (n = 24) and too late (n = 22) was well balanced with discrepancies ranging from -116 to 384 days. Nevertheless, the PFS curves constructed with text mining and manual chart review were highly similar for each hospital. CONCLUSION: In this study, an accurate text mining algorithm for capturing disease progression in the EHR data of patients with mNSCLC was developed. The algorithm was portable across different hospitals, and the performance over time was good, making this an interesting approach for prospective follow-up of multicenter cohorts.

Authors 9

1. Marjon V. Verschueren

   Utrecht University

   Affiliation as printed

   Department of Clinical Pharmacy, St Antonius Hospital, Utrecht, the Netherlands

   Division of Pharmacoepidemiology and Clinical Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht University, Utrecht, the Netherlands

2. Hanieh Abedian Kalkhoran Aachen Department of Clinical Pharmacy and Toxicology

   Leiden University Medical Center · Haga Hospital

   Affiliation as printed

   Department of Clinical Pharmacy and Toxicology, Leiden University Medical Center, Leiden, the Netherlands

   Department of Pharmacy, Haga Teaching Hospital, The Hague, the Netherlands

3. Maarten J. Deenen Aachen Department of Clinical Pharmacy and Toxicology

   Leiden University Medical Center · Catharina Ziekenhuis

   Affiliation as printed

   Department of Clinical Pharmacy and Toxicology, Leiden University Medical Center, Leiden, the Netherlands

   Department of Clinical Pharmacy, Catharina Hospital, Eindhoven, the Netherlands

4. Ben E.E.M. van den Borne

   Catharina Ziekenhuis

   Affiliation as printed

   Department of Respiratory Medicine, Catharina Hospital, Eindhoven, the Netherlands

5. J. Zwaveling Aachen Department of Clinical Pharmacy and Toxicology

   Leiden University Medical Center

   Affiliation as printed

   Department of Clinical Pharmacy and Toxicology, Leiden University Medical Center, Leiden, the Netherlands

6. Loes E. Visser

   Erasmus MC · Haga Hospital

   Affiliation as printed

   Department of Epidemiology, Erasmus Medical Centre, Rotterdam, the Netherlands

   Department of Hospital Pharmacy, Erasmus Medical Centre, Rotterdam, the Netherlands

   Department of Pharmacy, Haga Teaching Hospital, The Hague, the Netherlands

7. Lourens T. Bloem

   Utrecht University

   Affiliation as printed

   Division of Pharmacoepidemiology and Clinical Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht University, Utrecht, the Netherlands

8. Bas J.M. Peters
   Affiliation as printed

   Department of Clinical Pharmacy, St Antonius Hospital, Utrecht, the Netherlands

9. Ewoudt M.W. van de Garde

   Utrecht University

   Affiliation as printed

   Department of Clinical Pharmacy, St Antonius Hospital, Utrecht, the Netherlands

   Division of Pharmacoepidemiology and Clinical Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht University, Utrecht, the Netherlands