The development of early warning scores or alerting systems for the prediction of adverse events in psychiatric patients: a scoping review
Bibliographic record
Abstract
BACKGROUND: Adverse events in psychiatric settings present ongoing challenges for both patients and staff. Despite advances in psychiatric interventions and treatments, research on early warning scores and tools to predict patient deterioration is limited. This review provides a summary of the few tools that have been developed in a psychiatric setting, comparing machine learning (ML) and nonmachine learning/traditional methodologies. The outcomes of interest include the selected key variables that contribute to adverse events and the performance and validation measures of the predictive models. METHODS: Three databases, Ovid MEDLINE, PsycINFO, and Embase, were searched between February 2023 and April 2023 to identify all relevant studies that included a combination of (and were not limited to) the following search terms: "Early warning," "Alerting tool," and "Psychiatry". Peer-reviewed primary research publications were included without imposing any date restrictions. A total of 1,193 studies were screened. A total of 9 studies met the inclusion and exclusion criteria and were included in this review. The PICOS model, the Joanna Briggs Institute (JBI) Reviewer's Manual, and PRISMA guidelines were applied. RESULTS: This review identified nine studies that developed predictive models for adverse events in psychiatric settings. Encompassing 41,566 participants across studies that used both ML and non-ML algorithmic approaches, performance metrics, primarily AUC ROC, varied among studies between 0.62 and 0.95. The best performing model that had also been validated was the random forest (RF) ML model, with a score of 0.87 and a high sensitivity of 74% and a specificity of 88%. CONCLUSION: Currently, few predictive models have been developed for adverse events and patient deterioration in psychiatric settings. The findings of this review suggest that the use of ML and non-ML algorithms show moderate to good performance in predicting adverse events at the hospitals/units where the tool was developed. Understanding these models and the methodology of the studies is crucial for enhancing patient care as well as staff and patient safety research. Further research on the development and implementation of predictive tools in psychiatry should be carried out to assess the feasibility and efficacy of the tool in psychiatric patients.
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) | 0.002 | 0.001 |
| 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".