A Two-Phase Framework Leveraging User Feedback and Systemic Validation to Improve Post-Live Clinical Decision Support
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Despite the benefits of clinical decision support (CDS), concerns of potential risks arise amidst increasing reports of CDS malfunctions. Without objective and standardized methods to evaluate CDS in the post-live stage, CDS performance in a dynamic healthcare environment remains a black box from the user's perspective. In this study, we proposed a comprehensive framework to identify and evaluate post-live CDS malfunctions from the perspective of healthcare settings.We developed a two-phase framework to identify and evaluate post-live CDS system malfunctions: (1) real-time feedback from users in healthcare settings; (2) systematic validation through the use of databases that involve fundamental data flow validation and knowledge and rules validation. Identity, completeness, plausibility, and consistency across locations and time patterns were included as measures for systematic validation. We applied this framework to a commercial CDS system in 14 acute care facilities in Canada in a 2-year period.During this study, seven types of malfunctions were identified. The general rate of malfunctions was below 2%. In addition, an increase in CDS malfunctions was found during the electronic health record upgrade and implementation periods.This framework can be used to comprehensively evaluate CDS performance for healthcare settings. It provides objective insights into the extent of CDS issues, with the ability to capture low-prevalence malfunctions. Applying this framework to CDS evaluation can help improve CDS performance from the perspective of healthcare settings.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.012 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.000 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it