Automated machine learning‐based model predicts postoperative delirium using readily extractable perioperative collected electronic data

Hu, Xiaoyi; Liu, He; Zhao, Xinghong; Sun, Xun; Zhou, Jian; Gao, Xing; Guan, Hui-Lian; Zhou, Yang; Zhao, Qiu; Han, Yuan; Cao, Jun-Li

doi:10.1111/cns.13758

Cited by 30 publications

(34 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Delirium is a common post operative neuropsychiatric complication in elderly hip fracture patients, which usually occurs from a few hours to a few days after surgery and is mainly manifested as attention disorders, a decline in consciousness, and thinking disorders (Hu et al, 2022 ). In elderly patients with hip fractures, the incidence of post operative delirium (POD) ranges from 13% to 70%, and POD has higher mortality within 6 months (Bruce et al, 2007 ; Mosk et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

“…Studies found that not all POD can be noticed in time. Hypoactive POD, which accounts for up to 71% of POD, is not easy to notice because of the non-typical symptoms (Hayhurst et al, 2020 ; Lee-Archer et al, 2021 ; Hu et al, 2022 ). Therefore, it is crucial to find an effective POD prediction method and early identification of elderly patients with hip fractures at high risk of POD.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development and Validation of a Nomogram for Predicting Postoperative Delirium in Patients With Elderly Hip Fracture Based on Data Collected on Admission

Yang

Wang

Guo

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

Delirium is a common postoperative complication in elderly hip fracture patients that seriously affects patients’ lives and health, and early delirium risk prediction, and targeted measures can significantly reduce the incidence of delirium. The purpose of this study was to develop and validate a nomogram for the prediction of postoperative delirium (POD) in elderly hip fracture patients. A total of 328 elderly patients with hip fractures enrolled retrospectively in department 1 of our hospital were randomly divided into the training set (n = 230) and the internal validation set (n = 98). The least absolute shrinkage and selection operator (LASSO) regression analysis was used for feature variable selection, and multivariate logistic regression with a backward stepwise method was used to construct a nomogram in the training set. The discrimination efficacy and calibration efficacy of the nomogram were evaluated through the receiver operating characteristic (ROC) curve and calibration curve, respectively. The clinical usefulness was estimated through decision curve analysis (DCA) and clinical impact curve (CIC) analysis. Another validation set from department 2 of our hospital, containing 76 elderly patients with hip fractures, was used for external validation of the nomogram. A total of 43 (13.1%) and 12 (15.8%) patients had POD in department 1 and department 2, respectively. The nomogram was constructed by three predictors, including dementia, chronic obstructive pulmonary disease (COPD), and albumin level. The nomogram showed good discrimination efficacy and calibration efficacy, with the AUC of 0.791 (95% CI, 0.708–0.873), 0.820 (95% CI, 0.676–0.964), and 0.841 (95% CI, 0.717–0.966) in the training set, the internal validation set, and the external validation set, respectively. Both DCA and CIC demonstrated that this nomogram has good clinical usefulness. The nomogram constructed by dementia, COPD, and albumin level can be conveniently used to predict POD in patients with elderly hip fractures.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Development and Validation of a Nomogram for Predicting Postoperative Delirium in Patients With Elderly Hip Fracture Based on Data Collected on Admission

Yang

Wang

Guo

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

show abstract

“…In another recent article, Palla et al ( 40 ) presented a model capable of predicting hypotension in post anesthesia care unit (PACU) using preoperative and intraoperative data of 88,446 surgical patients, with an AUROC of 0.82. The integration between the two data timings was also exploited to create effective automated ML prediction models of postoperative delirium ( 41 ). Different, but equally effective, example are the models of Xue et al ( 11 ), previously cited.…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence and anesthesia: a narrative review

Carnà¹,

Russo²,

Vincenzo³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

Background and Objective The aim of this narrative review is to analyze whether or not artificial intelligence (AI) and its subsets are implemented in current clinical anesthetic practice, and to describe the current state of the research in the field. AI is a general term which refers to all the techniques that enable computers to mimic human intelligence. AI is based on algorithms that gives machines the ability to reason and perform functions such as problem-solving, object and word recognition, inference of world states, and decision-making. It includes machine learning (ML) and deep learning (DL). Methods We performed a narrative review of the literature on Scopus, PubMed and Cochrane databases. The research string comprised various combinations of “artificial intelligence”, “machine learning”, “anesthesia”, “anesthesiology”. The databases were searched independently by two authors. A third reviewer would mediate any disagreement the results of the two screeners. Key Content and Findings The application of AI has shown excellent results in both anesthesia and in operating room (OR) management. In each phase of the perioperative process, pre-, intra- and postoperative ones, it is able to perform different and specific tasks, using various techniques. Conclusions Thanks to the use of these new technologies, even anesthesia, as it is happening for other disciplines, is going through a real revolution, called Anesthesia 4.0. However, AI is not free from limitations and open issues. Unfortunately, the models created, provided they have excellent performance, have not yet entered daily practice. Clinical impact analyzes and external validations are needed before this happens. Therefore, qualitative research will be needed to better understand the ethical, cultural, and societal implications of integrating AI into clinical workflows.

show abstract

“…The results were almost same with Hu's work. They achieved best AUC of 0.8 with logistic regression algorithm in a dataset of 531 patients under general anesthesia 35 . Compared to small‐scale dataset, it is difficult to predict POD in a big dataset.…”

Section: Discussionmentioning

confidence: 99%

Comparison of logistic regression and machine learning methods for predicting postoperative delirium in elderly patients: A retrospective study

et al. 2022

View full text Add to dashboard Cite

Aims:To compare the performance of logistic regression and machine learning methods in predicting postoperative delirium (POD) in elderly patients. Method:This was a retrospective study of perioperative medical data from patients undergoing non-cardiac and non-neurology surgery over 65 years old from January 2014 to August 2019. Forty-six perioperative variables were used to predict POD.A traditional logistic regression and five machine learning models (Random Forest, GBM, AdaBoost, XGBoost, and a stacking ensemble model) were compared by the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, and precision. Results:In total, 29,756 patients were enrolled, and the incidence of POD was 3.22% after variable screening. AUCs were 0.783 (0.765-0.8) for the logistic regression method, 0.78 for random forest, 0.76 for GBM, 0.74 for AdaBoost, 0.73 for XGBoost, and 0.77 for the stacking ensemble model. The respective sensitivities for the 6 aforementioned models were 74.

show abstract

Automated machine learning‐based model predicts postoperative delirium using readily extractable perioperative collected electronic data

Abstract: This is an open access article under the terms of the Creat ive Commo ns Attri bution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Cited by 30 publications

References 39 publications

Development and Validation of a Nomogram for Predicting Postoperative Delirium in Patients With Elderly Hip Fracture Based on Data Collected on Admission

Development and Validation of a Nomogram for Predicting Postoperative Delirium in Patients With Elderly Hip Fracture Based on Data Collected on Admission

Artificial intelligence and anesthesia: a narrative review

Comparison of logistic regression and machine learning methods for predicting postoperative delirium in elderly patients: A retrospective study

Contact Info

Product

Resources

About