{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T17:40:32Z","timestamp":1789753232946,"version":"4.0.1"},"reference-count":36,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:00:00Z","timestamp":1760140800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background\/Objectives: Postoperative complications such as wound infections and sepsis are common in diabetic patients, often resulting in longer hospital stays and higher morbidity. This study hypothesizes that a Random Forest Classifier can accurately predict these complications, enabling early clinical interventions. The model utilizes ensemble learning to integrate diverse patient data and improve predictive accuracy beyond traditional risk assessments. Methods: A comprehensive retrospective analysis was performed using data extracted from the National Surgical Quality Improvement Program (NSQIP) database. The dataset encompassed a wide array of variables, including demographic factors, clinical markers, and detailed surgical data (specialty, type of anesthesia, duration of surgery). Each variable was meticulously encoded into numerical formats, with categorical variables transformed through one-hot encoding, and continuous variables were normalized. The dataset was partitioned into training (80%) and testing (20%) subsets, ensuring a balanced representation of the target outcomes. The Random Forest Classifier was selected due to its robustness in handling high-dimensional data and its ability to model complex interactions between variables. Results: The Random Forest model showed accuracy rates of 94.38% for wound infection and 94.94% for sepsis. Precision and recall metrics also exceeded 94%, highlighting the model\u2019s accuracy in identifying true positives and reducing false positives. ROC curve analysis yielded AUC values of 0.92 for wound infection and 0.95 for sepsis, indicating strong discriminative capability. Feature importance analysis further identified key predictors, including surgical duration, specific laboratory markers, and patient comorbidities. Conclusions: This study demonstrates the Random Forest Classifier\u2019s strong predictive ability for postoperative wound infections and sepsis in diabetic patients. The model\u2019s high-performance metrics indicate its potential for real-time risk stratification in clinical workflows. Future research should validate these findings in diverse populations and surgical settings. Incorporating this predictive model into clinical practice has the potential to significantly improve patient outcomes and reduce healthcare costs.<\/jats:p>","DOI":"10.3390\/jcm14207173","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T10:12:29Z","timestamp":1760523149000},"page":"7173","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["DiabCompSepsAI: Integrated AI Model for Early Detection and Prediction of Postoperative Complications in Diabetic Patients\u2014Using a Random Forest Classifier"],"prefix":"10.3390","volume":"14","author":[{"given":"Sri Harsha","family":"Boppana","sequence":"first","affiliation":[{"name":"Department of Internal Medicine, Nassau University Medical Center, East Meadow, NY 11554, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7431-1040","authenticated-orcid":false,"given":"Sachin Sravan Kumar","family":"Komati","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Florida International University, Miami, FL 33199, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raja Hamsa","family":"Chitturi","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, HCA Florida Ocala Hospital, Ocala, FL 34471, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ritwik","family":"Raj","sequence":"additional","affiliation":[{"name":"Zanvyl Krieger School of Arts and Sciences, Johns Hopkins University, Baltimore, MD 21218, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. David","family":"Mintz","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology & Critical Care Medicine, Johns Hopkins School of Medicine, Baltimore, MD 21205, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e316","DOI":"10.1016\/S2214-109X(15)70115-4","article-title":"Global access to surgical care: A modelling study","volume":"3","author":"Alkire","year":"2015","journal-title":"Lancet Glob. Health"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3256","DOI":"10.1097\/MS9.0000000000000866","article-title":"Delay in surgical treatment in low-income and middle-income countries: An editorial","volume":"85","author":"Aborode","year":"2023","journal-title":"Ann. Med. Surg."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1001\/jamasurg.2016.0773","article-title":"Hospital and payer costs associated with surgical complications","volume":"151","author":"Healy","year":"2016","journal-title":"JAMA Surg."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/j.jtcvs.2013.02.003","article-title":"High lactate levels are predictors of major complications after cardiac surgery","volume":"146","author":"Hajjar","year":"2013","journal-title":"J. Thorac. Cardiovasc. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.diabres.2011.10.040","article-title":"The International Diabetes Federation diabetes atlas methodology for estimating global and national prevalence of diabetes in adults","volume":"94","author":"Guariguata","year":"2011","journal-title":"Diabetes Res. Clin. Pract."},{"key":"ref_6","first-page":"289","article-title":"Boosting diabetes and pre-diabetes detection in rural Ghana","volume":"8","author":"Amoah","year":"2019","journal-title":"F1000Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1152\/physiol.00003.2018","article-title":"Circadian etiology of type 2 diabetes mellitus","volume":"33","author":"Javeed","year":"2018","journal-title":"Physiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.jtv.2023.03.002","article-title":"Use of honey in diabetic foot ulcer: Systematic review and meta-analysis","volume":"32","year":"2023","journal-title":"J. Tissue Viability"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1136\/bmj.2.351.246","article-title":"On the antiseptic principle in the practice of surgery","volume":"2","author":"Lister","year":"1867","journal-title":"Br. Med. J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1732","DOI":"10.1056\/NEJMoa1801550","article-title":"Changes in prevalence of health care\u2013associated infections in U.S. hospitals","volume":"379","author":"Magill","year":"2018","journal-title":"N. Engl. J. Med."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Spampinato, S.F., Caruso, G.I., De Pasquale, R., Sortino, M.A., and Merlo, S. (2020). The treatment of impaired wound healing in diabetes: Looking among old drugs. Pharmaceuticals, 13.","DOI":"10.3390\/ph13040060"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1055\/s-0038-1677001","article-title":"Predicting and preventing postoperative outcomes","volume":"32","author":"Lee","year":"2019","journal-title":"Clin. Colon. Rectal. Surg."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1097\/00000658-199908000-00016","article-title":"Risk factors for prolonged length of stay after major elective surgery","volume":"230","author":"Collins","year":"1999","journal-title":"Ann. Surg."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.jamcollsurg.2016.12.057","article-title":"An examination of American College of Surgeons NSQIP surgical risk calculator accuracy","volume":"224","author":"Cohen","year":"2017","journal-title":"J. Am. Coll. Surg."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1016\/j.surg.2018.07.002","article-title":"Eye of the beholder: Risk calculators and barriers to adoption in surgical trainees","volume":"164","author":"Leeds","year":"2018","journal-title":"Surgery"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1038\/s41598-023-27418-5","article-title":"Dynamic predictions of postoperative complications from explainable, uncertainty-aware, and multi-task deep neural networks","volume":"13","author":"Shickel","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_17","first-page":"516","article-title":"Machine Learning and Deep Learning Models for Early Sepsis Prediction: A Scoping Review","volume":"29","author":"Shanmugam","year":"2025","journal-title":"Indian J. Crit. Care Med. Peer-Rev. Off. Publ. Indian Soc. Crit. Care Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1038\/s41746-024-01419-8","article-title":"Multimodal machine learning to predict surgical site infection with healthcare workload impact assessment","volume":"8","author":"McLean","year":"2025","journal-title":"Npj Digit. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41746-025-01949-9","article-title":"Multicenter validation of a scalable, interpretable, multitask prediction model for multiple clinical outcomes","volume":"8","author":"Yoon","year":"2025","journal-title":"NPJ Digit. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e1259","DOI":"10.1097\/SLA.0000000000005696","article-title":"Operative time is associated with postoperative complications after pulmonary lobectomy","volume":"278","author":"Tan","year":"2023","journal-title":"Ann. Surg."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1177\/1758573219876573","article-title":"The effect of operative time on early postoperative complications in total shoulder arthroplasty: An analysis of the ACS-NSQIP database","volume":"13","author":"Wilson","year":"2021","journal-title":"Shoulder Elb."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.bjps.2023.07.048","article-title":"Prolonged operative time is a risk factor for adverse postoperative outcomes in the unilateral deep inferior epigastric perforator (DIEP) flap surgery: A retrospective cohort study","volume":"87","author":"Shtarbanov","year":"2023","journal-title":"J. Plast. Reconstr. Aesthet. Surg."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1089\/sur.2017.089","article-title":"Prolonged operative duration increases risk of surgical site infections: A systematic review","volume":"18","author":"Cheng","year":"2017","journal-title":"Surg. Infect."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"21S","DOI":"10.1177\/0148607113496117","article-title":"The surgically induced stress response","volume":"37","author":"Finnerty","year":"2013","journal-title":"JPEN J. Parenter. Enter. Nutr."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1097\/XCS.0000000000001079","article-title":"Impact of procedure risk vs frailty on outcomes of elderly patients undergoing emergency general surgery: Results of a national analysis","volume":"239","author":"Zakhary","year":"2024","journal-title":"J. Am. Coll. Surg."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.mpmed.2014.11.003","article-title":"Medical consequences of obesity","volume":"43","author":"Finer","year":"2015","journal-title":"Medicine"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.critrevonc.2008.01.013","article-title":"The changing prevalence of comorbidity across the age spectrum","volume":"67","author":"Piccirillo","year":"2008","journal-title":"Crit. Rev. Oncol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e000160","DOI":"10.1136\/tsaco-2017-000160","article-title":"Risk stratification tools in emergency general surgery","volume":"3","author":"Havens","year":"2018","journal-title":"Trauma Surg. Acute Care Open"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.jss.2021.02.045","article-title":"Machine learning and surgical outcomes prediction: A systematic review","volume":"264","author":"Elfanagely","year":"2021","journal-title":"J. Surg. Res."},{"key":"ref_30","first-page":"e50942","article-title":"Challenges and solutions in postoperative complications: A narrative review in general surgery","volume":"15","author":"Javed","year":"2023","journal-title":"Cureus"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: A framework for traditional and novel measures","volume":"21","author":"Steyerberg","year":"2010","journal-title":"Epidemiology"},{"key":"ref_32","first-page":"196","article-title":"Assessment of data quality variability across two EHR systems through a case study of post-surgical complications","volume":"2022","author":"Fu","year":"2022","journal-title":"AMIA Jt. Summits Transl. Sci. Proc."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1080\/12460125.2020.1819094","article-title":"Transparency and trust in artificial intelligence systems","volume":"29","author":"Schmidt","year":"2020","journal-title":"J. Decis. Syst."},{"key":"ref_34","first-page":"1073","article-title":"Interpreting medical information using machine learning and individual conditional expectation","volume":"216","author":"Nohara","year":"2015","journal-title":"Stud. Health Technol. Inform."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1016\/j.surg.2019.01.002","article-title":"Comparing clinical judgment with the MySurgeryRisk algorithm for preoperative risk assessment: A pilot usability study","volume":"165","author":"Brennan","year":"2019","journal-title":"Surgery"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Lee, T.C., Shah, N.U., Haack, A., and Baxter, S.L. (2020). Clinical implementation of predictive models embedded within electronic health record systems: A systematic review. Informatics, 7.","DOI":"10.3390\/informatics7030025"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/20\/7173\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T10:36:29Z","timestamp":1760524589000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/14\/20\/7173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,11]]},"references-count":36,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["jcm14207173"],"URL":"https:\/\/doi.org\/10.3390\/jcm14207173","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,11]]}}}