Using Machine Learning and Electronic Health Records to Identify Neuropsychiatric Risk Scores for Delirium in ICU and General Hospital Settings

Mariam Heikal,1 Halim Saad,2 Pia Maria Ghanime,3 Tarek Bou Dargham,4 Maya Bizri,5 Firas Kobeissy,6 Wassim El Hajj,1 Farid Talih2 1Department of Computer Science, American University of Beirut, Beirut, Lebanon; 2Department of Psychiatry, Faculty of Medicine, American University of Beirut, Beirut, Lebanon; 3Department of Psychiatry, Massachusetts General Hospital, Boston, MA, USA; 4Department of Neurosurgery, Duke University Medical Center, Durham, NC, USA; 5Department of Psychiatry and Psychology, Cleveland Clinic, Cleveland, OH, USA; 6Department of Neurobiology, Morehouse School of Medicine, Atlanta, GA, USACorrespondence: Mariam Heikal, Department of Computer Science, American University of Beirut, Beirut, Lebanon, Email mas177@mail.aub.eduObjective: Delirium is a common and acute neuropsychiatric syndrome that requires timely intervention to prevent its associated morbidity and mortality. Yet, its diagnosis and symptoms are often overlooked due to its variable clinical presentation and fluctuating nature. Thus, in this study, we address the barriers to delirium diagnosis by utilizing a machine learning-based predictive algorithm for incident delirium that relies on archived electronic health records (EHRs) data.Methods: We used the Medical Information Mart for Intensive Care (MIMIC) database to create a detailed dataset for identifying delirium in intensive care unit (ICU) patients. Our approach involved training machine learning models on this dataset to pinpoint critical clinical features for delirium detection. These features were then refined and applied to non-ICU patients using EHRs from the American University of Beirut Medical Center (AUBMC).Results: Our study assessed machine learning models like Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Classification and Regression Trees (CART), Random Forest (RF), Neural Oblivious Decision Ensembles (NODE), and Logistic Regression (LR), highlighting superior delirium detection in diverse clinical settings. The CatBoost model excelled in ICU environments with an F1 Score of 89.2%, while XGBoost performed best in general hospital settings with a 75.4% F1 Score. Interpretations using Tabular Local Interpretable Model-agnostic Explanations (LIME) revealed critical indicators such as prothrombin time and hematocrit levels, enhancing model transparency and clinical applicability. These clinical insights help differentiate the delirium predictors between ICU patients, who are often sensitive to various factors.Conclusion: The proposed predictive algorithm improves delirium detection rates and streamlines efficiency in hospital electronic systems, thereby enabling prompt interventions to prevent delirium progression and associated complications. The clinical indicators for delirium that we identified in general hospital settings and ICU can greatly help healthcare professionals identify potential causes of delirium and reduce misdiagnosis.Keywords: Delirium, ICU delirium, Hospital-acquired delirium, electronic health records, machine learning, clinical indicators