A machine‐learning approach for decision support and risk stratification of pediatric perioperative patients based on the APRICOT dataset

Abstract

Background Pediatric anesthesia has evolved to a high level of patient safety, yet a small chance remains for serious perioperative complications, even in those traditionally considered at low risk. In practice, prediction of at‐risk patients currently relies on the American Society of Anesthesiologists Physical Status (ASA‐PS) score, despite reported inconsistencies with this method. Aims The goal of this study was to develop predictive models that can classify children as low risk for anesthesia at the time of surgical booking and after anesthetic assessment on the procedure day. Methods Our dataset was derived from APRICOT, a prospective observational cohort study conducted by 261 European institutions in 2014 and 2015. We included only the first procedure, ASA‐PS classification I to III, and perioperative adverse events not classified as drug errors, reducing the total number of records to 30 325 with an adverse event rate of 4.43%. From this dataset, a stratified train:test split of 70:30 was used to develop predictive machine learning algorithms that could identify children in ASA‐PS class I to III at low risk for severe perioperative critical events that included respiratory, cardiac, allergic, and neurological complications. Results Our selected models achieved accuracies of >0.9, areas under the receiver operating curve of 0.6–0.7, and negative predictive values >95%. Gradient boosting models were the best performing for both the booking phase and the day‐of‐surgery phase. Conclusions This work demonstrates that prediction of patients at low risk of critical PAEs can be made on an individual, rather than population‐based, level by using machine learning. Our approach yielded two models that accommodate wide clinical variability and, with further development, are potentially generalizable to many surgical centers.

Advances in pediatric perioperative care using artificial intelligence

“…Nasr et al [10] developed a predictive model for perioperative morbidity such as cardiac arrest, acute respiratory failure within 48 h postop or unplanned ICU transfer within 72 h postop in children undergoing noncardiac surgical procedures. Similarly, Gray et al [11 ▪▪ ] developed a risk stratification model using data from the APRICOT dataset to prospectively classify American Society of Anesthesiologists Physical Status (ASA-PS) I–III pediatric patients’ risk for perioperative adverse events on the day of surgery. In comparison to commonly used clinical risk classification scores (such as the ASA-OS score), their model enables risk prediction for adverse events at an individual level rather than at a population level, which may ultimately improve the reliability of risk estimation [11 ▪▪ ].…”

“…Similarly, Gray et al [11 ▪▪ ] developed a risk stratification model using data from the APRICOT dataset to prospectively classify American Society of Anesthesiologists Physical Status (ASA-PS) I–III pediatric patients’ risk for perioperative adverse events on the day of surgery. In comparison to commonly used clinical risk classification scores (such as the ASA-OS score), their model enables risk prediction for adverse events at an individual level rather than at a population level, which may ultimately improve the reliability of risk estimation [11 ▪▪ ]. Additional AI applications enable prediction of a specific adverse event occurring, rather than composite adverse event risk estimation.…”

“…Continued) patients' risk for perioperative adverse events on the day of surgery. In comparison to commonly used clinical risk classification scores (such as the ASA-OS score), their model enables risk prediction for adverse events at an individual level rather than at a population level, which may ultimately improve the reliability of risk estimation[11 …”

Taking a byte out of APRICOT to predict which children are at low risk for critical perioperative events

“…2 InthisissueofPediatricAnesthesia,Gray etal.,sharetheirfindingsafterapplyingamachinelearningapproach todatafromtheEuropeanmulti-institutionalAnesthesiaPRacticeIn ChildrenObservationalTrial(APRICOT). 3 Theauthors'goalwasto develop predictive machine learning algorithms to assist clinicians indetermininglow-riskstatusinchildrenusingonlytheinformation thatwouldbeavailableatthetimeofmodeluse.…”

Novel Preoperative Risk Stratification Using Digital Phenotyping Applying a Scalable Machine-Learning Approach

“…11–15 However, to date, most studies have presented models with supervised learning trained to predict specific postoperative complications, including mortality, cardiorespiratory adverse events, allergic reaction, as well as the ASA score itself. 16–18…”