Development and validation of a machine learning ASA-score to identify candidates for comprehensive preoperative screening and risk stratification - 26/04/23
, Boudewijn Aasman, BSc c , Shweta Garg, MS c , Annika S. Witt, BSc a , Arshia A. Harandi a , Omid Azimaraghi, MD a , Parsa Mirhaji, MD, PhD c , Selvin Soby, PharmD c , Preeti Anand, MD a , Carina P. Himes, MD a , Richard V. Smith, MD d , Peter Santer, MD, PhD e , Jeffrey Freda, MD f , Matthias Eikermann, MD, PhD a, g, ⁎ , Priya Ramaswamy, MD h Abstract |
Objective |
The ASA physical status (ASA-PS) is determined by an anesthesia provider or surgeon to communicate co-morbidities relevant to perioperative risk. Assigning an ASA-PS is a clinical decision and there is substantial provider-dependent variability. We developed and externally validated a machine learning-derived algorithm to determine ASA-PS (ML-PS) based on data available in the medical record.
Design |
Retrospective multicenter hospital registry study.
Setting |
University-affiliated hospital networks.
Patients |
Patients who received anesthesia at Beth Israel Deaconess Medical Center (Boston, MA, training [n = 361,602] and internal validation cohorts [n = 90,400]) and Montefiore Medical Center (Bronx, NY, external validation cohort [n = 254,412]).
Measurements |
The ML-PS was created using a supervised random forest model with 35 preoperatively available variables. Its predictive ability for 30-day mortality, postoperative ICU admission, and adverse discharge were determined by logistic regression.
Main results |
The anesthesiologist ASA-PS and ML-PS were in agreement in 57.2% of the cases (moderate inter-rater agreement). Compared with anesthesiologist rating, ML-PS assigned more patients into extreme ASA-PS (I and IV), (p < 0.01), and less patients in ASA II and III (p < 0.01). ML-PS and anesthesiologist ASA-PS had excellent predictive values for 30-day mortality, and good predictive values for postoperative ICU admission and adverse discharge. Among the 3594 patients who died within 30 days after surgery, net reclassification improvement analysis revealed that using the ML-PS, 1281 (35.6%) patients were reclassified into the higher clinical risk category compared with anesthesiologist rating. However, in a subgroup of multiple co-morbidity patients, anesthesiologist ASA-PS had a better predictive accuracy than ML-PS.
Conclusions |
We created and validated a machine learning physical status based on preoperatively available data. The ability to identify patients at high risk early in the preoperative process independent of the provider's decision is a part of the process we use to standardize the stratified preoperative evaluation of patients scheduled for ambulatory surgery.
Le texte complet de cet article est disponible en PDF.Highlights |
• | ASA Physical Status (PS) is used for resource allocation, risks prediction, and reimbursement. |
• | We created and validated a machine learning PS (ML-PS) using preoperative data. |
• | ML-PA and anesthesiologists' PS predict comparable 30-day mortality. |
• | ML-PS can be used to automatically classify patients' PS using EHR data. |
Keywords : Machine learning, Machine learning prediction, ASA classification, Mortality, Telehealth
Plan
Vol 87
Article 111103- août 2023 Retour au numéro
Article précédent
- All intraoperative hypotension is not created equal – A call for an individualized approach
- Ashish K. Khanna, Alexander Zarbock, Matthieu Legrand
- Intraoperative renal desaturation and postoperative acute kidney injury in older patients undergoing liver resection: A prospective cohort study
- Yao Yu, Haotian Wu, Chang Liu, Changsheng Zhang, Yuxiang Song, Yulong Ma, Hao Li, Jingsheng Lou, Yanhong Liu, Jiangbei Cao, Huan Zhang, Zhipeng Xu, Roger G. Evans, Chongyang Duan, Weidong Mi
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?