An Expert Knowledge Algorithm and Model Predicting Wound Healing Trends for a Decision Support System for Pressure Injury Management in Home Care Nursing: Development and Validation Study
Bibliographic record
Abstract
Background: Home-visiting nurses have difficulty selecting appropriate pressure injury (PI) management despite using clinical practice guidelines in various home-visiting settings. Clinical decision support systems can help home-visiting nurses' decision-making. Objective: This study aimed to develop a care algorithm reflecting the expertise of a wound expert nurse and a predictive model for the change of PI severity to inform home-visiting nurses to receive actual consultation. Methods: First, an existing algorithm was modified by semistructured interviews with a certified wound expert nurse. Case information was input into both base and high-expertise algorithms, which provided care recommendations across 9 fields: (1) pressure relief; (2) nutritional management; (3) shear relief; (4) moisture management; (5) wound dressing use; (6) care for physical factors including bone prominence, obesity, joint contractures, and periwound edema; (7) care for systemic disorder; (8) selection of wound dressings, ointments, and negative pressure wound therapy; and (9) wound cleansing. An expert interviewee assessed the high-expertise algorithm's recommendations on a 5-point scale, comparing them to the base algorithm and their own clinical judgment. To measure the algorithm's applicability, agreement proportions were calculated as the number of vignettes where the care recommendation was considered appropriate or total number of vignettes. To measure the algorithm's alignment, improvement proportions were calculated as the number of vignettes where the care recommendation improved or total number of vignettes excluding vignettes when the existing and high-expertise algorithm both showed an appropriate recommendation. Expected healing levels were evaluated by a 4-point scale where 4 indicates the high-expertise algorithm can "much improve" the case. Second, predictive distributions of changes in DESIGN-R 2020 score, PI severity score, were estimated with a hierarchical Bayesian model. The best model determined using training data (n=42) calculated coverage probabilities of 90% prediction interval in test data (n=34). The coverage probability of a 90% prediction interval was defined as follows: the number of times when actual scores were within the 90% prediction interval or the number of assessments when the prediction was conducted. Results: The agreement proportions were 0.92 (33/36), 0.75 (27/36), and 0.89 (32/36) for each round. The improvement proportions were 0.73 (8/11), 0.25 (3/12), and 0.76 (13/17), respectively. The expected healing level was 2.67, 3.00, and 3.25, respectively. Coverage probabilities of 90% prediction interval in the test data were 0.67 (4/6), 0.83 (5/6), 0.86 (6/7), and 0.80 (8/10), respectively. Conclusions: This study developed an algorithm reflecting the expertise and a model to estimate predictive distributions of changes of DESIGN-R 2020 score for developing clinically applicable clinical decision support systems for home-visiting nurses providing appropriate PI management.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 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".