The "Silent" Failures of Scoring CDSS: Challenge in Detecting Malfunctions
Bibliographic record
Abstract
Defective clinical decision support system (CDSS) could deliver wrong information to clinical workers, which lead wrong decisions during their patient cares and cause unintended adverse consequences. Change point detection methods, which focus on segmenting time series data and using statistical techniques to infer or detect change point locations, have been proposed to identify periods when a CDSS starts exhibiting abnormal behavior. However, we found it may not effectively capture scoring CDSS malfunctions, particularly when applied directly to the daily count of filed scores. For instance, using the Sequential Organ Failure Assessment (SOFA) score extracted from MIMIC-III clinical database as a case study, we observed that its malfunctions were not accurately detected because the scoring tool is designed to assume that missing data indicates a normal condition (assigning a sub score of 0), which may lead to an underestimation of the patient condition and potentially result in incorrect recommendations from downstream automated decision support systems. This malfunction could arise from various factors, such as missing or delayed data entries, inconsistencies in score calculation logic, or system integration errors affecting score transmission. In this study, we demonstrate the Poisson change point model was not able to detect the SOFA CDSS malfunction(s) by monitoring the daily count of SOFA scores. Further analytical approaches need to be explored to enable regular monitoring of this type of scoring CDSS, reducing the burden of manual malfunction detection and improving system robustness.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.073 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".