A Novel Information Retrieval Tool to Find Hospital Care Team Members: Development and Usability Study
Bibliographic record
Abstract
BACKGROUND: Hospital communication among members of a patient's care team is a central part of clinical workflow and consumes a large amount of a health care provider's time. Oftentimes the complexity of hospital care leads to difficulty in finding the appropriate contact, which can lead to inefficiencies and frustration. Squire is a Web-based information retrieval app created to improve the speed and efficiency in reaching the appropriate team member during the care of a hospitalized patient. OBJECTIVE: The objective of the study was to design and develop Squire and to evaluate the usage, usability, and perceived effect of the app on finding the correct contact within a hospital. METHODS: We used a mixed-methods design using a before-after survey methodology combined with one-on-one interviews to understand the perceived effect of Squire. The study took place at an academic medical center with internal medicine resident physicians. We surveyed residents on demographics, as well as time and efficiency of hospital communication before and after the use of Squire. After using Squire, participants were also asked to evaluate Squire's Net Promoter Score (NPS). A subset of voluntary participants participated in one-on-one interviews and completed the System Usability Scale (SUS). We performed descriptive statistics on participant characteristics, app usage data, and responses to surveys. Survey results were compared before and after Squire adoption using the Wilcoxon rank-sum test and a general linear model. Interview data were analyzed using content analysis with a qualitative description approach to review and categorize feedback from participants. RESULTS: There was a 67.9% (74/109) response rate to the pre-Squire survey and 89.9% (98/109) response rate to the post-Squire survey. At baseline, there was an average of 22.2 (95% CI 18.4-26.0) minutes/day spent searching for the right contact, and this decreased to 16.3 (95% CI 13.9-18.7) minutes/day after Squire was launched (P=.01). There were favorable usability scores, with an average SUS of 84.7, and a marginal NPS of +6.1. Overall, the use of Squire included 22,283 page views, most commonly to contact the admissions office or portable chest x-ray technician. Interviews highlighted common benefits of Squire, including decreased perceived time spent on hold with operators and improvement in connecting with the appropriate contact in specialized, complex departments. Future opportunities were also identified to improve Squire including adding a two-way communication between physician and nursing staff and providing offline access. CONCLUSIONS: Squire decreased the perceived time required to find an appropriate contact and had a favorable usability score; however, the NPS was marginal and several opportunities were identified to improve Squire for future use.
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 | 0.012 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".