A Data‐Driven Model to Predict Delirium Based on Dynamic Patterns of Clinical Deterioration in Critically Ill Patients
Bibliographic record
Abstract
ABSTRACT Background Although many risk factors for delirium have been identified, the contribution of dynamic patterns of clinical deterioration remains underexplored. Aims To explore the risk of delirium based on changes in clinical parameters. Study Design A retrospective study based on electronic health records (EHRs) was conducted. The EHRs of 3600 patients, including 827 with delirium and 2773 without delirium, who were admitted to the medical and surgical intensive care unit (ICU) between January 2017 and February 2020, were analysed. Data involving changes in clinical parameters recorded from admission until the day before the onset of delirium were categorised as ‘worsen to or persist worsen’ or ‘recovered to or persist normal.’ Logistic regression was conducted to identify the significant risk factors for delirium development. Results The model’s C‐statistic, which is equivalent to the area under the ROC curve (AUC) in this context, was 0.88, suggesting excellent ability to discriminate patients who developed delirium. Among 14 variables, 8 were associated with changes in patient conditions: diastolic blood pressure (< 60 mmHg, OR: 2.01 [1.68–2.48]), heart rate (> 100/min, OR: 1.55 [1.23–1.95]), respiratory rate (> 25/min, OR: 1.26 [0.92–1.72]), partial pressure of carbon dioxide (PaCO 2 > 48 mmHg, OR: 1.45 [1.02–2.06]) and bicarbonate (HCO 3 level > 28 mEq/L, OR: 0.77 [0.57–1.04]), albumin (< 3 g/dL, OR: 2.27 [1.60–3.20]), blood urea nitrogen (> 20 mg/dL, OR: 1.45 [1.18–1.78]) and sodium levels (> 146 mmol/L, OR: 2.06 [1.41–3.02]). Conclusions Persistent or worsening physiological derangements were significantly associated with delirium onset in critically ill patients. Relevance to Clinical Practice Recognising and concurrently addressing worsening clinical trends such as haemodynamic instability, acid–base imbalance and electrolyte disturbance can support earlier, tailored interventions to prevent delirium in high‐risk ICU 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 | 0.000 | 0.087 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".