Explore the vast range of titles available.

BackgroundNo data is available on delirium prediction models in the cardiac intensive care unit (CICU), although preexisting delirium prediction models [PREdiction of DELIRium in ICu patients (PRE-DELIRIC) and Early PREdiction of DELIRium in ICu patients (E-PRE-DELIRIC)] were developed and validated based on a population admitted to the general intensive care unit (ICU). Therefore, we externally validated the usefulness of the PRE-DELIRIC and E-PRE-DELIRIC models and compared their predictive performance in patients admitted to the CICU.MethodsA total of 2,724 patients admitted to the CICU were enrolled between September 2012 and December 2018. Delirium was defined as at least one positive Confusion Assessment Method for the ICU (CAM-ICU) which was screened at least once every 8 h. The PRE-DELIRIC value was calculated within 24 h of CICU admission, and the E-PRE-DELIRIC value was calculated at CICU admission. The predictive performance of the models was evaluated by using the area under the receiver operating characteristic (AUROC) curve, and the calibration slope was assessed graphically by plotting.ResultsDelirium occurred in 677 patients (24.8%) when the patients were assessed thrice daily until 7 days of the CICU stay. The AUROC curve for the prediction of delirium was significantly greater for PRE-DELIRIC values [0.84, 95% confidence interval (CI): 0.82–0.86] than for E-PRE-DELIRIC values (0.79, 95% CI: 0.77–0.80) [z score of −6.24 ( p < 0.001)]. Net reclassification improvement for the prediction of delirium increased by 0.27 (95% CI: 0.21–0.32, p < 0.001). Calibration was acceptable in the PRE-DELIRIC model (Hosmer-Lemeshow p = 0.170) but not in the E-PRE-DELIRIC model (Hosmer-Lemeshow p < 0.001).ConclusionAlthough both models have good predictive performance for the development of delirium, even in critically ill cardiac patients, the performance of the PRE-DELIRIC model might be superior to that of the E-PRE-DELIRIC model. Further studies are required to confirm our results and design a specific delirium prediction model for CICU patients.

To develop and validate a simple delirium-predicting scoring system in patients undergoing major abdominal surgery by incorporating preoperative risk factors and intraoperative surgical Apgar score (SAS). Observational retrospective cohort study. A tertiary general hospital in China. 1055 patients who received major abdominal surgery from January 2015 to December 2019. We collected data on preoperative and intraoperative variables, and postoperative delirium. A risk scoring system for postoperative delirium in patients after major open abdominal surgery was developed and validated based on traditional logistic regression model. The elastic net algorithm was further developed and evaluated. The incidence of postoperative delirium was 17.8% (188/1055) in these patients. They were randomly divided into the development (n = 713) and validation (n = 342) cohorts. Both the logistic regression model and the elastic net regression model identified that advanced age, arrythmia, hypoalbuminemia, coagulation dysfunction, mental illness or cognitive impairments and low surgical Apgar score are related with increased risk of postoperative delirium. The elastic net algorithm has an area under the receiver operating characteristic curve (AUROC) of 0.842 and 0.822 in the development and validation cohorts, respectively. A prognostic score was calculated using the following formula: Prognostic score = Age classification (0 to 3 points) + arrythmia + 2 * hypoalbuminemia + 2 * coagulation dysfunction + 4 * mental illness or cognitive impairments + (10-surgical Apgar score). The 22-point risk scoring system had good discrimination and calibration with an AUROC of 0.823 and 0.834, and a non-significant Hosmer-Lemeshow test P = 0.317 and P = 0.853 in the development and validation cohorts, respectively. The bootstrapping internal verification method (R = 1000) yielded a C-index of 0.822 (95% CI: 0.759–0.857). The prognostic scoring system, which used both preoperative risk factors and surgical Apgar score, serves as a good first step toward a clinically useful predictive model for postoperative delirium in patients undergoing major open abdominal surgery. •A postoperative delirium prediction scoring system for patients with major abdominal surgery was developed and validated.•This large-sample study found that low SAS was associated with increased risk for postoperative delirium.•The elastic net regression model with high significance was further established to predict postoperative delirium.

To develop and validate a pragmatic risk screening score for postoperative delirium (POD) based on routine preoperative data. Prospective observational monocentric trial. Preoperative data and POD assessment were collected from cardiac and non-cardiac surgical patients at a German university hospital. Data-driven modelling approaches (step-wise vs. component-wise gradient boosting on complete and restricted predictor set) were compared to predictor selection by experts (investigators vs. external Delphi survey). Inpatients (≥60 years) scheduled for elective surgery lasting more than 60 min. POD was assessed daily during first five postoperative or post-sedation days with confusion assessment method for intensive and standard care unit (CAM-ICU/CAM), 4 ‘A's test (4AT) and Delirium Observation Screening (DOS) scale. From 1023 enrolled patients, 978 completed observations were separated in development (n = 600; POD incidence 22.2%) and validation (n = 378; POD incidence 25.7%) cohorts. Data-driven approaches generated models containing laboratory values, surgical discipline and several items on cognitive and quality of life assessment, which are time consuming to collect. Boosting on complete predictor set yielded the highest bootstrapped prediction accuracy (AUC 0.767) by selecting 12 predictors, with substantial dependence on cardiac surgery. Investigators selected via univariate comparison age, ASA and NYHA classification, surgical risk as well as ´serial subtraction´ and ´sentence repetition´ of the Montreal Cognitive Assessment (MoCA) to enable rapid collection of their risk score for preoperative screening. This investigator model provided slightly lower bootstrapped prediction accuracy (AUC 0.746) but proved to have robust results on validation cohort (AUC 0.725) irrespective of surgical discipline. Simplification of the investigator model by scaling and rounding of regression coefficients into the PROPDESC score achieved a comparable precision on the validation cohort (AUC 0.729). The PROPDESC score showed promising performance on a separate validation cohort in predicting POD based on routine preoperative data. Suitability for universal screening needs to be shown in a large external validation. •PROPDESC score was developed for preoperative screening of POD risk.•Different modelling approaches with statistical and clinical input were investigated.•Prediction model development aimed to provide a pragmatic screening tool.•PROPDESC score predicts POD risk based on preoperative rapidly available parameters.•PROPDESC score provides POD prediction in various surgical disciplines.

Background Machine learning models have shown great potential in preventive medicine but require large datasets, which is a challenge due to strict privacy regulations in the healthcare sector. Federated learning is an approach that enables collaboration between institutions while preserving data privacy. The focus today in research is highly on developing federated learning methods using artificial neural networks. In this study, we aimed to contribute federated learning modelling methods applied for random forests with an use-case of predicting delirium in hospitalised patients using data from multiple hospitals. Methods We collected data from eleven hospitals, including 29,479 patients and 627 features. We developed individual random forest models for each hospital data and a general model using all data. We developed federated learning models by averaging the predictions of the individual hospital models, with different schemes based on the number of samples, positives cases, minority cases and maximum possible diversity and evaluated the models using area under the receiver operating characteristic curve (AUROC). Results The general model outperformed all the other models with an AUROC of 0.855 [0.845–0.865]. Models trained on data from single hospitals varied in performance with an AUROC ranging from 0.633 to 0.829. Models from hospitals with large datasets performed better than those of small hospitals. Federated learning models outperformed individual models. With an AUROC of 0.794 [0.782–0.806], unweighted averaging achieved the worst results. Among the weighting algorithms, the number of positive cases performed the best reaching an AUROC of 0.843 [0.832–0.854], followed by minority cases (AUROC = 0.841 [0.830–0.852]), maximum possible diversity (AUROC = 0.836 [0.825–0.847]) and number of samples (AUROC = 0.830 [0.819–0.841]). Conclusions Results show that federated learning models can perform better than hospital-specific models in some cases, especially hospitals with limited data. In case of datasets of different size, we suggest weighted averaging based on the number of samples. If the datasets are class imbalanced, minority cases or maximum possible diversity should also be considered. Additionally, federated learning models maintain consistency compared to hospital specific models. Clinical trial registration Not applicable.

Key summary points Aim To externally validate the performance of the SURGE-Ahead postoperative delirium (POD) prediction algorithm in older adults undergoing surgery. Findings The SURGE-Ahead POD algorithm showed excellent predictive ability (ROC AUC 0.86) and good calibration (Brier Score 0.14). Implication This validated algorithm can be readily accessed on GitHub, allowing for easy integration into various surgical environments to enhance patient care for hospitalized older adults. Purpose In this prospective external validation study, we examined the performance of the Supporting SURgery with GEriatric Co-Management and AI (SURGE-Ahead) postoperative delirium (POD) prediction algorithm. SURGE-Ahead is a collaborative project that aims to develop a clinical decision support system that uses predictive models to support geriatric co-management in surgical wards. Delirium is a common complication in older adults after surgery, leading to poor outcomes and increased healthcare costs. Early and accurate prediction of POD is crucial for timely intervention and prevention strategies. Methods The SURGE-Ahead algorithm utilizes a linear support vector machine model with a comprehensive set of 15 clinical and demographic features. In our validation, we analyzed 173 study participants, of which 50 developed POD. Results The study found that the SURGE-Ahead POD prediction algorithm yielded state-of-the-art performance, using only preoperative data, with a receiver operating characteristics area under the curve of 0.86. In addition, the SURGE-Ahead algorithm exhibited good calibration as shown by a Brier Score of 0.14. The algorithm is openly available on GitHub, facilitating its implementation and adaptation to different surgical settings. Conclusion Our findings contribute to the development of reliable POD prediction tools, ultimately supporting the improvement of patient care in hospitalized older adults.

In recent years, intensive care unit (ICU) doctors have paid more attention to delirium. ICU patients have a high risk of delirium. Delirium can lead to serious adverse outcomes, but early diagnosis and prediction of delirium are very difficult and lack effective assessment tools. The causes of delirium are many and complex, and there is no definite prediction model. To solve this problem, this paper proposes a delirium prediction model based on a hybrid cuckoo search algorithm with stochastic gradient descent—the adaptive-network-based fuzzy inference system (SGDCS-ANFIS) approach. Thirty-five relevant indicators of 1072 ICU cases (536 delirium cases and 536 nondelirium cases) were selected to establish a delirium prediction model to judge whether patients tended to experience delirium. The experiments show that the delirium prediction model based on the hybrid SGDCS-ANFIS approach has better performance than traditional classification and prediction machine learning approaches, and the accuracy is improved to 73.02%. It can provide some reference for the prediction of delirium, promote early diagnosis, and provide knowledge for early intervention to improve the prognosis of ICU patients. Adding this delirium prediction model to the ICU protocol will potentially improve the treatment outcome, quality, and cost. Doctors can manage sudden symptoms more calmly, and patients will also benefit. By collecting the real-time data commonly used in electronic medical records of ICUs, the proposed delirium prediction model can be easily applied in hospitals.Delirium can lead to serious adverse outcomes, but early diagnosis and prediction of delirium are very difficult and lack effective assessment tools. We propose a hybrid SGDCS-ANFIS approach to establish delirium prediction model to judge whether ICU patients tend to experience delirium. It can provide some reference for the prediction of delirium, promote early diagnosis, and provide knowledge for early intervention to improve the prognosis of ICU patients. By collecting the real-time data commonly used in electronic medical records of ICUs, the proposed delirium prediction model can be easily applied in hospitals.Fig. Development flow from raw data to the building of the delirium prediction model and model comparison.

Key summary points Aim Testing the role of the Multidimensional Prognostic Index (MPI), based on the Comprehensive Geriatric Assessment (CGA), in predicting the risk of incident delirium in hospitalized older patients with COVID-19. Findings The MPI showed a good accuracy in predicting incident delirium (AUC = 0.71). Its accuracy is higher than the ones of two validated predictive models (AWOL delirium risk-stratification score’s AUC = 0.63; Martinez Model’s AUC = 0.61; p < 0.0001 for both comparisons). Message The MPI is a sensitive tool for risk-stratification of the incident delirium in hospitalized older COVID-19 patients. Purpose Incident delirium is a frequent complication among hospitalized older people with COVID-19, associated with increased length of hospital stay, higher morbidity and mortality rates. Although delirium is preventable with early detection, systematic assessment methods and predictive models are not universally defined, thus delirium is often underrated. In this study, we tested the role of the Multidimensional Prognostic Index (MPI), a prognostic tool based on Comprehensive Geriatric Assessment, to predict the risk of incident delirium. Methods Hospitalized older patients (≥ 65 years) with COVID-19 infection were enrolled (n = 502) from ten centers across Europe. At hospital admission, the MPI was administered to all the patients and two already validated delirium prediction models were computed (AWOL delirium risk-stratification score and Martinez model). Delirium occurrence during hospitalization was ascertained using the 4A’s Test (4AT). Accuracy of the MPI and the other delirium predictive models was assessed through logistic regression models and the area under the curve (AUC). Results We analyzed 293 patients without delirium at hospital admission. Of them 33 (11.3%) developed delirium during hospitalization. Higher MPI score at admission (higher multidimensional frailty) was associated with higher risk of incident delirium also adjusting for the other delirium predictive models and COVID-19 severity (OR = 12.72, 95% CI = 2.11–76.86 for MPI-2 vs MPI-1, and OR = 33.44, 95% CI = 4.55–146.61 for MPI-3 vs MPI-1). The MPI showed good accuracy in predicting incident delirium (AUC = 0.71) also superior to AWOL tool, (AUC = 0.63) and Martinez model (AUC = 0.61) ( p  < 0.0001 for both comparisons). Conclusions The MPI is a sensitive tool for early identification of older patients with incident delirium.

Background Delirium, an acute and fluctuating neurocognitive disorder prevalent among hospitalized and geriatric surgical patients, remains a pervasive yet underrecognized clinical challenge. Leveraging Electronic Health Records (EHRs), Machine Learning (ML) models have emerged as promising tools for early prediction and intervention. This scoping review synthesizes the existing literature, identifies current research gaps, and outlines future directions to advance delirium prediction modeling. Methods Following the PRISMA Extension for Scoping Reviews (PRISMA-ScR) guidelines, literature from 2020 to 2025 was systematically searched across Google Scholar, EMBASE, PubMed, Scopus, and Web of Science using a comprehensive query strategy. Results The review highlights a significant reliance on structured preoperative and intraoperative EHR for delirium prediction, despite the existence of abundant and highly informative unstructured clinical narratives. Furthermore, a substantial heterogeneity exists in the utilized delirium identification methodologies (e.g. Nursing Delirium Screening Scale (Nu-DESC), Delirium Observation Screening Scale (DOSS), International Classification of Diseases (ICD) criteria, 4AT delirium detection, Confusion Assessment Method (CAM), Intensive Care Delirium Screening Checklist (ICDSC), Cornell Assessment of Pediatric Delirium (CAPD) Diagnostic and Statistical Manual of Mental Disorders 5th version (DSM-5), natural language processing (NLP) based analysis), alongside a focus on specific surgical subgroups. This limited data utilization and methodological variation pose challenges to ML model generalizability and robustness. The literature also showed a research emphasis on critically ill patients, potentially overlooking subtle delirium in low-severity cases. Conclusions Future research should focus on early risk stratification and prioritize four key areas: (1) expanded utilization of both tabular EHR and unstructured clinical notes; (2) development of integrated multimodal fusion models adaptable to dynamic patient states; (3) investigation of the temporal dynamics of delirium development using time-series analysis; and (4) application of causal inference methods to elucidate the relationships between risk factors and delirium. Superior prediction performance can be achieved by leveraging cutting-edge architectures (e.g. transformers) and parallel computing efficiencies to move beyond traditional machine learning. To enhance real-world adoption, future work should integrate Explainable AI tools such as Shapley Additive Explanations (SHAP) within EHR-based decision support systems, improving interpretability and mitigating subgroup disparities in localized risk assessment.