Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 3, 2026JCO Clinical Cancer Informatics

Rule-Based Algorithm to Identify Recurrent Non-Hodgkin Lymphoma in Electronic Health Data

View Full Paper
Ask AI
Bookmark
Share

Authors

MEMara M. EpsteinLSLaura SusickFLFeifan Liu

Discussion

Loading...

Member takes

Overview

Randomized trial develops a rule-based algorithm to identify recurrence in non-hodgkin lymphoma, highlighting potential for improved research.

Key Points

  • This research aims to create an algorithm to identify recurrent cases of non-Hodgkin lymphoma using electronic health data.
  • Identified incident cases of DLBCL and FL from 2000-2018 at two health plan sites.
  • Defined recurrent cases based on treatment initiation and gaps in treatment-related codes.
  • Validated algorithm performance through chart review and adjustments to reduce false-positive rates.
  • Baseline algorithm identified 42 recurrent cases of DLBCL and FL from 137 and 88 eligible cases respectively.
  • Revised algorithm (R2D-NHL) identified 60 recurrent cases with a 10% false-positive rate.
  • R2D-NHL exhibited a sensitivity of 74% and specificity of 90% after chart review.

Cite This Study

Epstein et al. (2026) studied this question.

synapsesocial.com/papers/6a4755345c29257aa257a671https://doi.org/10.1200/cci-25-00208
View Full Paper
Ask AI
Bookmark
Share