Related Experiment Video
Updated: Jul 2, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
A Data-Driven Model to Predict Delirium Based on Dynamic Patterns of Clinical Deterioration in Critically Ill
Ji-Sun Back1, Yinji Jin2, Taixian Jin3
1Department of Nursing, Dongnam Health University, Suwon, Gyeonggi-do, Republic of Korea.
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 (PaCO2 > 48 mmHg, OR: 1.45 [1.02-2.06]) and bicarbonate (HCO3 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.
