Machine learning-based delirium prediction in surgical in-patients: a prospective validation study

• Published in: JAMIA open 2024-10, Vol.7 (3), p.ooae091
• Main Authors: Jauk, Stefanie, Kramer, Diether, Sumerauer, Stefan, Veeranki, Sai Pavan Kumar, Schrempf, Michael, Puchwein, Paul
• Format: Article
• Language: English
• Subjects: Algorithms; Analysis; Data mining; Delirium; Hospital patients; Machine learning; Medical records; Medical research; Medicine, Experimental; Nursing; Research and Applications
• ISSN: 2574-2531; 2574-2531
• DOI: 10.1093/jamiaopen/ooae091

Objective Delirium is a syndrome that leads to severe complications in hospitalized patients, but is considered preventable in many cases. One of the biggest challenges is to identify patients at risk in a hectic clinical routine, as most screening tools cause additional workload. The aim of this study was to validate a machine learning (ML)-based delirium prediction tool on surgical in-patients undergoing a systematic assessment of delirium. Materials and Methods 738 in-patients of a vascular surgery, a trauma surgery and an orthopedic surgery department were screened for delirium using the DOS scale twice a day over their hospital stay. Concurrently, delirium risk was predicted by the ML algorithm in real-time for all patients at admission and evening of admission. The prediction was performed automatically based on existing EHR data and without any additional documentation needed. Results 103 patients (14.0%) were screened positive for delirium using the DOS scale. Out of them, 85 (82.5%) were correctly identified by the ML algorithm. Specificity was slightly lower, detecting 463 (72.9%) out of 635 patients without delirium. The AUROC of the algorithm was 0.883 (95% CI, 0.8523-0.9147). Discussion In this prospective validation study, the implemented machine-learning algorithm was able to detect patients with delirium in surgical departments with high discriminative performance. Conclusion In future, this tool or similar decision support systems may help to replace time-intensive screening tools and enable efficient prevention of delirium. Lay Summary Delirium is one of the major complications following surgery in hospitalized patients. Early detection of at-risk patients is a significant challenge in the hectic clinical routine, and screening is often inconsistent. Machine learning (ML)-based prediction models have become a popular alternative, allowing for automated and comprehensive screening. We prospectively validated an ML-based tool for predicting delirium at hospital admission using existing data only. A total of 738 in-patients from the vascular surgery, trauma surgery, and orthopedic surgery departments were screened with the Delirium Observation Screening (DOS) scale twice daily throughout their hospital stay. Delirium risk was predicted in real-time in the background using diagnoses, lab values, nursing assessments, procedures, and medication data. A total of 103 patients (14.0%) were screened positive for delirium; the algorithm successfully