Development and Evaluation of a Standardized Tool to Measure the Quality of Clinician’s Interaction with AI-Enabled Systems
Bibliographic record
Abstract
INTRODUCTION Artificial intelligence (AI) has the potential to improve healthcare quality when thoughtfully integrated into clinical practice. However, many clinicians remain hesitant towards its adoption. Current evaluations of AI solutions tend to focus solely on model performance. There is a critical knowledge gap in the assessment of AI-clinician interactions. We aim to develop a standardized framework to measure the quality of clinician’s interaction with AI-enabled systems in healthcare. METHODS We performed a systematic review of published studies to June 2022 that reported elements of interactions involved in the relationship between clinicians and AI-enabled clinical decision support systems. We conducted semi-structured interviews to supplement the results obtained from the systematic review. Literature review and interview findings were utilized to develop a comprehensive list of interaction traits, which was then reduced and organized with scoring profiles through iterative cycles of expert consensus meetings and a feasibility assessment. We then arrived at a final version of the measurement framework. RESULTS We identified 105 unique interaction traits from the review and interviews and the most common interaction traits were usefulness, ease of use, trust, satisfaction, willingness to use, and usability. These traits were categorized into seven categories, each with various subcategories, based on their shared constructs. After the consensus meeting and feasibility assessment, the framework was finalized into eight categories: usability, workflow impact, system performance and technical integration, trust and acceptance, impact on patient outcomes and care delivery, clinician engagement, communication and collaboration, and ethical and professional concerns. CONCLUSION We developed a standardized framework to measure the quality of interaction between clinicians and AI systems that contained eight categories of interaction traits, each with its own scoring profile. To our knowledge, this is the first framework of its kind to assess the quality of AI- clinician interactions within clinical setting.
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 | 0.211 | 0.241 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.008 |
| Bibliometrics | 0.019 | 0.012 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.006 | 0.005 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 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".