Graphical User Interface Development for a Hospital-Based Predictive Risk Tool: Protocol for a Co-Design Study
Bibliographic record
Abstract
BACKGROUND: This co-design research method details the iterative process developed to identify health professional recommendations for the graphical user interface (GUI) of an artificial intelligence (AI)-enabled risk prediction tool. Driving the decision to include a co-design process is the belief that choices regarding the aesthetic and functionality of an intervention are best made by its intended users and that engaging these users in its design will promote the tool's adoption and use. OBJECTIVE: The aim of this research is to identify health professional design and uptake recommendations for the GUI of an AI-enabled predictive risk tool. METHODS: We will hold 3 research phases, each consisting of 2 workshops with health professionals, between mid-2023 and mid-2024. A total of 6 health professionals will be sought per workshop, resulting in a total enrollment of 36 health professionals at the conclusion of the research. A total of 7 workshop activities have been scheduled across the 3 workshops; these include context of use, notifiers, format, AI survey-Likert, prototype, AI survey-written, and testing. The first 6 of these activities will be repeated in each workshop to enable the iterative development and refinement of GUI. The last activity (testing) will be performed in the final workshop to examine health professionals' thoughts on the final GUI iteration. Qualitative and quantitative results data will be produced from tasks in each research activity. Qualitative data will be examined through inductive thematic analysis or deductive thematic analysis in accordance with the Nonadoption, Abandonment, and Challenges to the Scale-up, Spread, and Sustainability (NASSS) framework; visual data will be examined in accordance with "framework of interactivity;" and quantitative data will be examined using descriptive statistics. RESULTS: Project registration with the Australia and New Zealand Clinical Trial Registry has been requested (#384098). Finalized design recommendations are expected in early to mid-2024, with a results manuscript to be submitted in mid-2024. This research method has human research ethics approval from the South Australian Department of Health and Wellbeing (#2022/HRE00131) as well as from the Human Research Ethics Committee of the University of South Australia (application ID#204143). CONCLUSIONS: Understanding whether an intervention is needed in a particular situation is just the start; designing an intervention so that it is used within that situation is paramount. This co-design process engages end users to create a GUI that includes the aesthetic and functional details they need in a manner that aligns with their existing work practices. Indeed, interventions that fail to do this may be disliked, and at worst, they may be dangerous. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/47717.
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 | 0.123 | 0.097 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.004 | 0.003 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.005 | 0.006 |
| Insufficient payload (model declined to judge) | 0.052 | 0.015 |
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".