{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T21:27:16Z","timestamp":1790630836689,"version":"4.1.0"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T00:00:00Z","timestamp":1747353600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["203145Z\/16\/Z"],"award-info":[{"award-number":["203145Z\/16\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["NS\/A000050\/1"],"award-info":[{"award-number":["NS\/A000050\/1"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Accurate preoperative risk assessment is of great value to both patients and clinical teams. Several risk scores have been developed but are often not calibrated to the local institution, limited in terms of data input into the underlying models, and\/or lack individual precision. Machine Learning (ML) models have the potential to address limitations in existing scoring systems. A database of 1190 elderly patients who underwent major elective surgery was analyzed retrospectively. Preoperative cardiorespiratory fitness data from cardiopulmonary exercise testing (CPET), demographic and clinical data were extracted and integrated into advanced machine learning (ML) algorithms. Multi-Objective-Symbolic-Regression (MOSR), a novel algorithm utilizing Genetic Programming to generate mathematical formulae for learning tasks, was employed to predict patient morbidity at Postoperative Day 3, as defined by the PostOperative Morbidity Survey (POMS). Shapley-Additive-exPlanations (SHAP) was subsequently used to analyze feature contributions. Model performance was benchmarked against existing risk prediction scores, namely the Portsmouth-Physiological-and-Operative-Severity-Score-for-the-Enumeration-of-Mortality-and-Morbidity (PPOSSUM) and the Duke-Activity-Status-Index, as well as linear regression using CPET features. A model was also developed for the same task using data directly extracted from the CPET time-series. The incorporation of cardiorespiratory fitness data enhanced the performance of all models for predicting postoperative morbidity by 20% compared to sole reliance on clinical data. Cardiorespiratory fitness features demonstrated greater importance than clinical features in the SHAP analysis. Models utilizing data taken directly from the CPET time-series demonstrated a 12% improvement over the cardiorespiratory fitness models. MOSR model surpassed all other models in every experiment, demonstrating excellent robustness and generalization capabilities. Integrating cardiorespiratory fitness data with ML models enables improved preoperative prediction of postoperative morbidity in elective surgical patients. The MOSR model stands out for its capacity to pinpoint essential features and build models that are both simple and accurate, showing excellent generalizability.<\/jats:p>","DOI":"10.1371\/journal.pdig.0000851","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T16:01:53Z","timestamp":1747411313000},"page":"e0000851","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Assessing perioperative risks in a mixed elderly surgical population using machine learning: A multi-objective symbolic regression approach to cardiorespiratory fitness derived from cardiopulmonary exercise testing"],"prefix":"10.1371","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2080-5274","authenticated-orcid":true,"given":"Pietro","family":"Arina","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2365-4157","authenticated-orcid":true,"given":"Davide","family":"Ferrari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maciej R.","family":"Kaczorek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas","family":"Tetlow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amy","family":"Dewar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Stephens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Martin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramani","family":"Moonesinghe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mervyn","family":"Singer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3859-679X","authenticated-orcid":true,"given":"John","family":"Whittle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelos B.","family":"Mazomenos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,5,16]]},"reference":[{"key":"pdig.0000851.ref001","doi-asserted-by":"crossref","DOI":"10.1016\/S2214-109X(15)70087-2","article-title":"Estimated need for surgery worldwide based on prevalence of diseases: a modelling strategy for the WHO Global Health Estimate","volume":"3","author":"J Rose","year":"2015","journal-title":"Lancet Glob Health"},{"issue":"1","key":"pdig.0000851.ref002","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1038\/s41746-022-00625-6","article-title":"Multi-center validation of machine learning model for preoperative prediction of postoperative mortality","volume":"5","author":"SW Lee","year":"2022","journal-title":"NPJ Digit Med"},{"issue":"1","key":"pdig.0000851.ref003","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1186\/s12893-021-01392-z","article-title":"Postoperative complications: an observational study of trends in the United States from 2012 to 2018","volume":"21","author":"EE Dencker","year":"2021","journal-title":"BMC Surg"},{"issue":"14","key":"pdig.0000851.ref004","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1200\/JCO.2011.40.3568","article-title":"Influence of major postoperative complications on health-related quality of life among long-term survivors of esophageal cancer surgery","volume":"30","author":"M Derogar","year":"2012","journal-title":"J Clin Oncol"},{"issue":"6","key":"pdig.0000851.ref005","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1093\/bja\/aeu224","article-title":"Survival after postoperative morbidity: a longitudinal observational cohort study","volume":"113","author":"SR Moonesinghe","year":"2014","journal-title":"Br J Anaesth"},{"key":"pdig.0000851.ref006","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.jclinane.2018.06.025","article-title":"Perioperative mortality related to anesthesia within 48\u00a0h and up to 30\u00a0days following surgery: A retrospective cohort study of 11,562 anesthetic procedures","volume":"49","author":"LC Stefani","year":"2018","journal-title":"J Clin Anesth"},{"issue":"11","key":"pdig.0000851.ref007","doi-asserted-by":"crossref","first-page":"2581","DOI":"10.1007\/s00268-016-3600-4","article-title":"Perioperative Complications are Associated With Adverse Long-Term Prognosis and Affect the Cause of Death After General Surgery","volume":"40","author":"EKM Tjeertes","year":"2016","journal-title":"World J Surg"},{"issue":"1","key":"pdig.0000851.ref008","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1097\/00005650-200201000-00003","article-title":"Effect of definition of mortality on hospital profiles","volume":"40","author":"ML Johnson","year":"2002","journal-title":"Med Care"},{"issue":"9","key":"pdig.0000851.ref009","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1046\/j.1365-2168.1998.00840.x","article-title":"POSSUM and Portsmouth POSSUM for predicting mortality. Physiological and Operative Severity Score for the enUmeration of Mortality and morbidity","volume":"85","author":"DR Prytherch","year":"1998","journal-title":"Br J Surg"},{"issue":"2","key":"pdig.0000851.ref010","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.bjae.2018.09.009","article-title":"Clinical risk assessment tools in anaesthesia","volume":"19","author":"J Stones","year":"2019","journal-title":"BJA Educ"},{"issue":"13","key":"pdig.0000851.ref011","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1016\/j.jacc.2017.08.012","article-title":"Cardiopulmonary exercise testing: what is its value?","volume":"70","author":"M Guazzi","year":"2017","journal-title":"J Am Coll Cardiol"},{"issue":"8","key":"pdig.0000851.ref012","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1113\/EP090156","article-title":"\u201cFit for surgery\u201d: the relationship between cardiorespiratory fitness and postoperative outcomes","volume":"107","author":"GA Rose","year":"2022","journal-title":"Exp Physiol"},{"issue":"2","key":"pdig.0000851.ref013","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.bja.2022.10.039","article-title":"Physiological relationship between cardiorespiratory fitness and fitness for surgery: a narrative review","volume":"130","author":"BH Roxburgh","year":"2023","journal-title":"Br J Anaesth"},{"key":"pdig.0000851.ref014","article-title":"Clinician approach to cardiopulmonary exercise testing for exercise prescription in patients at risk of and with cardiovascular disease","author":"F D\u2019Ascenzi","year":"2022","journal-title":"Br J Sports Med"},{"issue":"1","key":"pdig.0000851.ref015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40140-020-00373-x","article-title":"Cardiopulmonary exercise testing for preoperative evaluation: what does the future hold?","volume":"10","author":"JM Otto","year":"2020","journal-title":"Curr Anesthesiol Rep"},{"key":"pdig.0000851.ref016","volume-title":"Cardiopulmonary Exercise Test: Interpretation and Application in Perioperative Medicine","author":"O Quick","year":"2022"},{"issue":"13","key":"pdig.0000851.ref017","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1056\/NEJMra2302038","article-title":"Artificial Intelligence and Machine Learning in Clinical Medicine, 2023","volume":"388","author":"CJ Haug","year":"2023","journal-title":"N Engl J Med"},{"issue":"1","key":"pdig.0000851.ref018","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1097\/ALN.0000000000004764","article-title":"Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools","volume":"140","author":"P Arina","year":"2024","journal-title":"Anesthesiology"},{"key":"pdig.0000851.ref019","first-page":"945","volume-title":"Multi-Objective Symbolic Regression for Data-Driven Scoring System Management. In: 2022 IEEE International Conference on Data Mining (ICDM)","author":"D Ferrari","year":"2022"},{"key":"pdig.0000851.ref020","first-page":"442","article-title":"Multi-objective Symbolic Regression to Generate Data-driven, Non-fixed Structure and Intelligible Mortality Predictors using EHR: Binary Classification Methodology and Comparison with State-of-the-art","volume":"2022","author":"D Ferrari","year":"2023","journal-title":"AMIA Annu Symp Proc"},{"issue":"3","key":"pdig.0000851.ref021","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1016\/j.bja.2017.10.020","article-title":"Perioperative cardiopulmonary exercise testing (CPET): consensus clinical guidelines on indications, organization, conduct, and physiological interpretation","volume":"120","author":"DZH Levett","year":"2018","journal-title":"Br J Anaesth"},{"issue":"9","key":"pdig.0000851.ref022","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1016\/j.jclinepi.2006.12.003","article-title":"The Postoperative Morbidity Survey was validated and used to describe morbidity after major surgery","volume":"60","author":"MPW Grocott","year":"2007","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"pdig.0000851.ref023","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1093\/bja\/aex117","article-title":"Predicting postoperative morbidity in adult elective surgical patients using the Surgical Outcome Risk Tool (SORT)","volume":"119","author":"DJN Wong","year":"2017","journal-title":"Br J Anaesth"},{"issue":"7825","key":"pdig.0000851.ref024","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"CR Harris","year":"2020","journal-title":"Nature"},{"key":"pdig.0000851.ref025","volume-title":"PyCaret: An open source, low","author":"M Ali","year":"Apr 2020"},{"issue":"4","key":"pdig.0000851.ref026","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2018-025611","article-title":"Uniformity in measuring adherence to reporting guidelines: the example of TRIPOD for assessing completeness of reporting of prediction model studies","volume":"9","author":"P Heus","year":"2019","journal-title":"BMJ Open"},{"issue":"1","key":"pdig.0000851.ref027","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1009736","article-title":"Positional SHAP (PoSHAP) for Interpretation of machine learning models trained from biological sequences","volume":"18","author":"Q Dickinson","year":"2022","journal-title":"PLoS Comput Biol"},{"issue":"10","key":"pdig.0000851.ref028","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1007\/s10822-020-00314-0","article-title":"Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions","volume":"34","author":"R Rodr\u00edguez-P\u00e9rez","year":"2020","journal-title":"J Comput Aided Mol Des"},{"issue":"4","key":"pdig.0000851.ref029","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1093\/bja\/aes225","article-title":"Cardiopulmonary exercise testing predicts postoperative outcome in patients undergoing gastric bypass surgery","volume":"109","author":"PJ Hennis","year":"2012","journal-title":"Br J Anaesth"},{"issue":"6","key":"pdig.0000851.ref030","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1002\/bjs.10112","article-title":"Validation of preoperative cardiopulmonary exercise testing-derived variables to predict in-hospital morbidity after major colorectal surgery","volume":"103","author":"MA West","year":"2016","journal-title":"Br J Surg"},{"issue":"14","key":"pdig.0000851.ref031","doi-asserted-by":"crossref","DOI":"10.14814\/phy2.14174","article-title":"Cardiopulmonary fitness predicts postoperative major morbidity after esophagectomy for patients with cancer","volume":"7","author":"N Patel","year":"2019","journal-title":"Physiol Rep"},{"key":"pdig.0000851.ref032","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.bja.2019.11.025","article-title":"Integration of the Duke Activity Status Index into preoperative risk evaluation: a multicentre prospective cohort study","volume":"124","author":"DN Wijeysundera","year":"2020","journal-title":"Br J Anaesth"},{"issue":"2","key":"pdig.0000851.ref033","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0226480","article-title":"Performance of cardiopulmonary exercise testing for the prediction of post-operative complications in non cardiopulmonary surgery: A systematic review","volume":"15","author":"DJ Stubbs","year":"2020","journal-title":"PLoS One"},{"issue":"5","key":"pdig.0000851.ref034","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1111\/anae.15988","article-title":"Performance and usability of pre-operative prediction models for 30-day peri-operative mortality risk: a systematic review","volume":"78","author":"JEM Vernooij","year":"2023","journal-title":"Anaesthesia"},{"key":"pdig.0000851.ref035","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.ijsu.2016.03.005","article-title":"Comparison of the risk prediction systems POSSUM and P-POSSUM with the Surgical Risk Scale: a prospective cohort study of 721 patients","volume":"29","author":"S Gonz\u00e1lez-Mart\u00ednez","year":"2016","journal-title":"Int J Surg"},{"issue":"1","key":"pdig.0000851.ref036","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s12893-022-01466-6","article-title":"The impact of obesity on surgical outcomes in patients undergoing emergency laparotomy for high-risk abdominal emergencies","volume":"22","author":"WT Kassahun","year":"2022","journal-title":"BMC Surg"},{"key":"pdig.0000851.ref037","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.2147\/CIA.S258659","article-title":"Application of POSSUM and P-POSSUM in Surgical Risk Assessment of Elderly Patients Undergoing Hepatobiliary and Pancreatic Surgery","volume":"15","author":"Z-W Hu","year":"2020","journal-title":"Clin Interv Aging"},{"issue":"6","key":"pdig.0000851.ref038","article-title":"Use of POSSUM (Physiologic and Operative Severity Score for the Study of Mortality and Morbidity) and Portsmouth-POSSUM for Surgical Assessment in Patients Undergoing Emergency Abdominal Surgeries","volume":"15","author":"N Shekar","year":"2023","journal-title":"Cureus"},{"issue":"12","key":"pdig.0000851.ref039","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1111\/anae.16118","article-title":"The Duke Activity Status Index compared with cardiopulmonary exercise testing in patients undergoing pre-operative assessment for cancer surgery","volume":"78","author":"A Dewar","year":"2023","journal-title":"Anaesthesia"},{"issue":"1","key":"pdig.0000851.ref040","doi-asserted-by":"crossref","DOI":"10.1136\/openhrt-2015-000268","article-title":"Sympathetic autonomic dysfunction and impaired cardiovascular performance in higher risk surgical patients: implications for perioperative sympatholysis","volume":"2","author":"J Whittle","year":"2015","journal-title":"Open Heart"},{"issue":"8","key":"pdig.0000851.ref041","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0221277","article-title":"Heart rate recovery and morbidity after noncardiac surgery: Planned secondary analysis of two prospective, multi-centre, blinded observational studies","volume":"14","author":"GL Ackland","year":"2019","journal-title":"PLoS One"},{"key":"pdig.0000851.ref042","first-page":"1","volume-title":"Death After Liver Transplantation: Mining Interpretable Risk Factors for Survival Prediction. In: 2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)","author":"V Guidetti","year":"2023"},{"issue":"9847","key":"pdig.0000851.ref043","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1016\/S0140-6736(12)61148-9","article-title":"Mortality after surgery in Europe: a 7 day cohort study","volume":"380","author":"RM Pearse","year":"2012","journal-title":"Lancet"},{"issue":"10","key":"pdig.0000851.ref044","first-page":"558","article-title":"A comprehensive estimation of the costs of 30-day postoperative complications using actual costs from multiple, diverse hospitals","volume":"46","author":"RP Merkow","year":"2020","journal-title":"Jt Comm J Qual Patient Saf"},{"issue":"2","key":"pdig.0000851.ref045","doi-asserted-by":"crossref","DOI":"10.1097\/SLA.0000000000004966","article-title":"Looking beyond perioperative morbidity and mortality as measures of surgical quality","volume":"275","author":"RP Merkow","year":"2022","journal-title":"Ann Surg"},{"issue":"1","key":"pdig.0000851.ref046","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40140-021-00493-y","article-title":"The hidden pandemic: the cost of postoperative complications","volume":"12","author":"GL Ludbrook","year":"2022","journal-title":"Curr Anesthesiol Rep"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T16:02:12Z","timestamp":1747411332000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000851"}},"subtitle":[],"editor":[{"given":"Dhiya","family":"Al-Jumeily OBE","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,5,16]]},"references-count":46,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0000851","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,16]]}}}