Quantifying Healthcare Provider Perceptions of a Novel Deep Learning Algorithm to Predict Sepsis: Electronic Survey
Bibliographic record
Abstract
IMPORTANCE: Sepsis is a major cause of morbidity and mortality, with early intervention shown to improve outcomes. Predictive modeling and artificial intelligence (AI) can aid in early sepsis recognition, but there remains a gap between algorithm development and clinical use. Despite the importance of user experience in adopting clinical predictive models, few studies have focused on provider acceptance and feedback. OBJECTIVES: To evaluate healthcare worker perception and acceptance of a deep learning sepsis prediction model in the emergency department (ED). DESIGN, SETTING, AND PARTICIPANTS: COnformal Multidimensional Prediction Of SEpsis Risk (COMPOSER), a deep learning algorithm, is used at two EDs of a large academic medical center to predict sepsis before clear clinical presentation. An internally developed survey following the Checklist for Reporting Results of Internet E-Surveys was distributed to team members who received a COMPOSER alert. ANALYSIS: Mann-Whitney U testing was performed on results stratified by provider experience. RESULTS: A total of 114 responses were received: 76 from doctors of medicine/doctors of osteopathic medicine, 34 from registered nurses, and four from nurse practicioners/physician assistants. Of these, 53% were from providers with fewer than 5 years of experience. Seventy-seven percent of respondents had a positive or neutral perception of the alert's usefulness. Providers with 0-5 years of experience were more likely to expect sepsis after the alert (p = 0.021) and found the alert more useful (p = 0.016) compared with those with 6+ years of experience. Additionally, physicians with 0-5 years of experience were more likely to say the alert changed their patient management (p = 0.048). CONCLUSIONS: Less experienced providers were more likely to perceive benefit from the alert, which was overall received favorably. Future AI implementations might consider tailored alert patterns and education to enhance reception and reduce fatigue.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".