Evaluating a Clinical Decision Support Tool for Cancer Risk Assessment in Primary Care: Simulation Study of Unintended Weight Loss
Bibliographic record
Abstract
Background: Early cancer detection is crucial, but recognizing the significance of associated symptoms such as unintended weight loss in primary care remains challenging. Clinical decision support systems (CDSSs) can aid cancer detection but face implementation barriers and low uptake in real-world settings. To address these issues, simulation environments offer a controlled setting to study CDSS usage and improve their design for better adoption in clinical practice. Objective: This study aimed to evaluate a CDSS integrated within general practice electronic health records aimed at identifying patients at risk of undiagnosed cancer. Methods: The evaluation of a CDSS to identify patients with unintended weight loss was conducted in a simulated primary care environment where general practitioners (GPs) interacted with the CDSS in simulated clinical consultations. There were four possible clinical scenarios based on patient gender and risk of cancer. Data collection included interviews with GPs, cancer survivors (lived-experience community advocates), and patient actors, as well as video analysis of GP-CDSS interactions. Two theoretical frameworks were employed for thematic interpretation of the data. Results: We recruited 10 GPs and 6 community advocates, conducting 20 simulated consultations with 2 patient actors (2 consultations per GP: 1 high-risk consultation and 1 low-risk consultation). All participants found the CDSS acceptable and unobtrusive. GPs utilized CDSS recommendations in three distinct ways: as a communication aid when discussing follow-up with the patient, as a reminder for differential diagnoses and recommended investigations, and as an aid to diagnostic decision-making without sharing with patients. The CDSS's impact on patient-doctor communication varied, facilitating and hindering interactions depending on the GP's communication style. Conclusions: We developed and evaluated a CDSS for identifying cancer risk in patients with unintended weight loss in a simulated environment, revealing its potential to aid clinical decision-making and communication while highlighting implementation challenges and the need for context-sensitive application.
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 | 0.009 | 0.035 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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".