Assessing AI Explainability: A Usability Study Using a Novel Framework Involving Clinicians
Bibliographic record
Abstract
An AI design framework was developed based on three core principles, namely understandability, trust, and usability. The framework was conceptualized by synthesizing evidence from the literature and by consulting with experts. The initial version of the AI Explainability Framework was then validated based on an in-depth expert engagement and review process. For evaluation purposes, an AI-anchored prototype, incorporating novel explainability features, was built and deployed online via Google Cloud Platform. The primary function of the prototype was to predict the postpartum depression risk using analytics models. The development of the prototype was carried out in an iterative fashion, based on a pilot-level formative evaluation, followed by a round of refinement and summative evaluation. In the formative stage, the prototype was evaluated based on an internal pilot usability test involving a small number of clinicians (n=3). The prototype was updated based on the user’s feedback in the formative stage. The System Explainability Scale (SES) metric was developed to measure the individual and interacting influence of the three dimensions of the AI Explainability Framework. For the summative stage, a comprehensive usability test was conducted involving 20 clinicians, and the SES metric was used to assess clinicians’ satisfaction with the tool. On a 5-point rating system, the tool received high scores for usability dimension, followed by trust and understandability. The average explainability score was 4.56. In terms of understandability, trust and usability, the average score was 4.51, 4.53, and 4.71 respectively. Overall, the 13-item SES metric showed strong internal consistency with Cronbach’s alpha of 0.84 and a positive correlation coefficient (Spearman's rho = 0.81, p<0.001) between the composite SES score and explainability, indicating a positive trend in AI explainability. This study demonstrated the influence of understandability, trust, and usability on AI Explainability using a combination of a novel design and experimental approach. A major finding was that the AI Explainability Framework, combined with the SES usability metric, provides a straightforward yet effective approach for developing AI-based healthcare tools that lower the challenges associated with explainability.
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 | 0.097 | 0.157 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| 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".