知镜 Cognispect · 医学文献与研究工作台

Rule-Based Identification of a Reliable Real-World Cancer Recurrence Endpoint.

Lavery JA, Brown S, Nichols C, Jolissaint JS, Deng Y, Lee J, Shah NJ, Bahadur N, Niederhausern A, Philip J, Kehl KL, Schrag D, Panageas KS.
Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology · 2026-11-01 · PMID 42606327

文献摘要

Background Recurrence is a key oncologic endpoint but is difficult to automatically capture from electronic health records (EHR). Methods We evaluated rule-based algorithms to detect recurrence and its timing using a publicly available clinicogenomic database of patients with breast, colorectal, non-small cell lung, or pancreatic cancers. Algorithms evaluated varying anchor dates, defined as the time at which patients were assumed eligible to recur for the purposes of the algorithm, including diagnosis and 4, 6, and 12 months after diagnosis, as well as varying criteria for subsequent evidence of cancer from radiology, pathology, medical oncology assessments, or cancer-directed regimen initiation. Algorithm-derived recurrence results were compared with manually curated institutional data. Performance was measured by sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and concordance of recurrence timing. Results The best algorithms, anchored at 6 months after diagnosis and requiring two reports, demonstrated high sensitivity (≥0.95), PPV (≥0.81), NPV (≥0.84), reasonable specificity (≥0.75), and estimated recurrence within a median of 1 month of institutional reference data. Conclusions This scalable method enables the derivation of real-world endpoints from EHR-based data. Impact The algorithm may be used to characterize outcomes for patients treated outside of prospective clinical trials and may inform the creation of synthetic control cohorts to support regulatory approvals for new drugs in rare tumor or biomarker-defined populations.

在知镜精读原文来源DOI 原文

知镜提供医学文献检索、阅读笔记、人体图谱、统计绘图与研究复现工具。