What is the clinical evidence from this study?

Study design: Systematic Review. Population: Perioperative risk (n=36). Intervention: Machine learning algorithms vs. Validated prognostic scores and traditional statistics. Primary outcome: Predictive performance (AUC) for perioperative outcomes.

January 15, 2022Journal of Anesthesia Analgesia and Critical Care86 citationsOpen Access

Machine learning in perioperative medicine: a systematic review

VBValentina BelliniUniversity of Parma MVMarina ValenteUniversity of Parma GBGiorgia BertorelliUniversity of Parma

Key Result

Machine learning algorithms, particularly gradient boosting and random forest, effectively predicted perioperative outcomes with high accuracy (AUC > 0.90), outperforming traditional scores.

Study Design

Type

Systematic Review (n=36)

Structured PICO

Do machine learning algorithms improve the prediction of perioperative outcomes compared to traditional prognostic scores in surgical patients?

Population

36 studies evaluating machine learning models in surgical settings for the prediction of perioperative risk

Intervention

Machine learning algorithms (e.g., gradient boosting, random forest, artificial neural networks, support vector machines) for perioperative risk assessment and outcome prediction

Comparator

Traditional statistics and validated prognostic scores (e.g., ASA physical status, APACHE-II, CARES model)

Outcome

Predictive performance (e.g., AUC) for perioperative outcomes including mortality, systemic complications, ICU admission, and length of hospital stay

Machine learning algorithms, particularly gradient boosting and random forest, demonstrate high accuracy in predicting perioperative outcomes and show potential to outperform traditional clinical risk scores.

Limitations

Heterogeneity of settings and difference in algorithms evaluated prevented a meta-analysis.
Lack of external validation in most of the included studies.
Limits of AUC as an evaluation criterion in the setting of AI, especially in case of unbalanced datasets.

Abstract

BACKGROUND: Risk stratification plays a central role in anesthetic evaluation. The use of Big Data and machine learning (ML) offers considerable advantages for collection and evaluation of large amounts of complex health-care data. We conducted a systematic review to understand the role of ML in the development of predictive post-surgical outcome models and risk stratification. METHODS: Following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines, we selected the period of the research for studies from 1 January 2015 up to 30 March 2021. A systematic search in Scopus, CINAHL, the Cochrane Library, PubMed, and MeSH databases was performed; the strings of research included different combinations of keywords: "risk prediction," "surgery," "machine learning," "intensive care unit (ICU)," and "anesthesia" "perioperative." We identified 36 eligible studies. This study evaluates the quality of reporting of prediction models using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) checklist. RESULTS: The most considered outcomes were mortality risk, systemic complications (pulmonary, cardiovascular, acute kidney injury (AKI), etc.), ICU admission, anesthesiologic risk and prolonged length of hospital stay. Not all the study completely followed the TRIPOD checklist, but the quality was overall acceptable with 75% of studies (Rev #2, comm #minor issue) showing an adherence rate to TRIPOD more than 60%. The most frequently used algorithms were gradient boosting (n = 13), random forest (n = 10), logistic regression (LR; n = 7), artificial neural networks (ANNs; n = 6), and support vector machines (SVM; n = 6). Models with best performance were random forest and gradient boosting, with AUC > 0.90. CONCLUSIONS: The application of ML in medicine appears to have a great potential. From our analysis, depending on the input features considered and on the specific prediction task, ML algorithms seem effective in outcomes prediction more accurately than validated prognostic scores and traditional statistics. Thus, our review encourages the healthcare domain and artificial intelligence (AI) developers to adopt an interdisciplinary and systemic approach to evaluate the overall impact of AI on perioperative risk assessment and on further health care settings as well.

问 AI

Bookmark

View Full Paper