Assessing clinical decision support system tools in precision oncology: piloting ring testing
V Nygaard1, S Zhao1, D Tamborero2,3
1Department of Pathology, Division of Laboratory Medicine, Oslo University Hospital, Oslo, Norway.
A pilot study assessed clinical decision support systems (CDSS) for precision cancer medicine. Results showed variability in variant interpretation, highlighting the need for external quality assessment for CDSS tools.
Area of Science:
- Oncology
- Genomics
- Bioinformatics
Background:
- Precision cancer medicine relies on accurate molecular diagnostics and clinical decision support systems (CDSS).
- External quality assessment (EQA) is crucial for laboratory tests but lacking for CDSS tools.
- The EU4Health project PCM4EU initiative aims to enhance cancer patient survival and quality of life.
Purpose of the Study:
- To pilot an international ring test for evaluating CDSS performance in molecular cancer diagnostics.
- To document CDSS usage, performance, and manual interpretation in a real-world setting.
- To identify needs for structured EQA schemes for CDSS tools.
Main Methods:
- Generated 20 synthetic datasets mimicking variant call sets from a 500-gene panel.
- Distributed datasets to 8 laboratories across 7 countries for analysis.
- Collected results on variant interpretation and clinical significance using structured forms.
Main Results:
- Good agreement was observed for hotspot oncogenic variants across different CDSS tools.
- Variability was noted in the reporting of specific variants and their clinical interpretation.
- Eight laboratories participated, with 10 tumour-only cases analyzed.
Conclusions:
- Pilot ring test revealed clinically relevant discrepancies in CDSS interpretation.
- Emphasized the necessity for structured EQA schemes for CDSS tools.
- Identified challenges in synthetic data generation, reporting formats, and ground truth definition.
More Related Videos
05:18Radiation Planning Assistant - A Web-based Tool to Support High-quality Radiotherapy in Clinics with Limited Resources
Published on: October 6, 2023
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
