Related Experiment Video
Updated: Jul 1, 2025
08:55
Murine Model for Non-invasive Imaging to Detect and Monitor Ovarian Cancer Recurrence
Published on: November 2, 2014
12.3K
Development of an Automatic Rule-Based Algorithm for the Detection of Ovarian Cancer Recurrence From Electronic
Sanghee Lee1,2, Ji Hyun Kim3, Hyeong In Ha4
1Department of Cancer Control & Population Health, National Cancer Center Graduate School of Cancer Science and Policy, Goyang, Republic of Korea.
JCO Clinical Cancer Informatics
|March 5, 2024
Summary
An automated algorithm effectively detects ovarian cancer recurrence from electronic health records, significantly reducing manual review time and resources. This method closely matches traditional review accuracy for recurrence-free survival estimates.
Area of Science:
- Oncology
- Medical Informatics
- Health Services Research
Background:
- Detecting cancer recurrence from electronic health records (EHR) typically requires extensive manual chart review.
- This manual process is time-consuming and resource-intensive, hindering large-scale analysis.
Purpose of the Study:
- To develop an automated, rule-based algorithm for detecting ovarian cancer (OC) recurrence using EHR data.
- To assess the algorithm's performance against manual chart review methods.
Main Methods:
- Developed an automated rule-based recurrence detection algorithm (Auto-Recur) using image, biomarker (CA125), and treatment data from EHR.
- Evaluated Auto-Recur's sensitivity, specificity, and accuracy in detecting recurrence time.
- Compared estimated recurrence-free survival probabilities with retrospective chart review results.
Main Results:
- The Auto-Recur algorithm significantly reduced manual review time, saving approximately 1,340 days per 100,000 patients.
- The hybrid algorithm combining image, biomarker, and treatment data achieved high efficiency (sensitivity: 93.4%, specificity: 97.4%) with minimal time error (8.5 days).
- Estimated 3-year recurrence-free survival probability (44%) closely aligned with retrospective review estimates (45%).
Conclusions:
- The developed rule-based algorithm accurately identifies ovarian cancer recurrence from large-scale EHR data.
- This automated approach facilitates efficient EHR analysis and enhances opportunities for clinical research.
- The findings support the use of automated methods for cancer recurrence detection in clinical practice.
Related Concept Videos
01:21Cancer Survival Analysis
345
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
345
01:15Receiver Operating Characteristic Plot
167
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
167