Authors : Lakshminarayanan S.; Gopika Shri G. S.; Dr. Gopalakrishnan G.; Dr. Junior Sundresh N.

Volume/Issue : Volume 11 - 2026, Issue 7 - July

Google Scholar : https://tinyurl.com/3w3exhnp

Scribd : https://tinyurl.com/yc2c5s8v

DOI : https://doi.org/10.38124/ijisrt/26jul1868

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Background: Post-surgical complications play a major role in causing patient morbidity, prolonged hospital stay, and increased healthcare costs. Traditional monitoring systems tend to miss cases of early clinical deterioration because of their dependence on pre-set cut-off values and periodic assessment. On the other hand, machine learning (ML) offers an evidence-based method of increasing the efficiency of postoperative risks prediction and improving patient outcomes.  Objective: Machine learning models development and evaluation for predicting post-operative adverse events and proposal of a data driven safety protocol.  Methods: A retrospective cohort study that involved the use of clinical, demographic, laboratory, and surgical information related to post-surgery patients hospitalized in Government Cuddalore Medical College and Hospital was conducted. The data were processed and analyzed using Orange Data Mining software. Three classification models based on logistic regression, random forest, and gradient boosting (XGBoost) techniques were constructed and assessed by classification measures (accuracy, precision, recall, F1-score), and ROC curves.  Results: ML algorithms proved their ability to detect the presence of adverse events following surgery. Moreover, the ensemble algorithms showed better predictive performance than traditional models. The main predictors included demographic, laboratory, surgical, and comorbidity factors. The predictive models were able to differentiate patients according to their risk of developing complications after surgery.  Conclusion: Machine learning algorithms can be used to increase postoperative patient safety by detecting complications before their occurrence and helping clinicians make informed decisions about patient management.

Keywords : Machine Learning, Post-Surgical Care, Patient Safety, Predictive Analytics, Postoperative Complications, Risk Stratification.

References :

1. Weiser TG, Haynes AB, Molina G, Lipsitz SR, Esquivel MM, Uribe-Leitz T, et al. Size and distribution of the global volume of surgery in 2012. Bull World Health Organ. 2016;94(3):201-209F. doi:10.2471/BLT.15.159293.
2. Shrime MG, Bickler SW, Alkire BC, Mock C. Global burden of surgical disease: an estimation from the provider perspective. Lancet Glob Health. 2015;3 Suppl 2:S8-S9.
3. Ghaferi AA, Birkmeyer JD, Dimick JB. Complications, failure to rescue, and mortality with major inpatient surgery in Medicare patients. Ann Surg. 2009;250(6):1029-1034.
4. Royal College of Physicians. National Early Warning Score (NEWS) 2: Standardising the assessment of acute-illness severity in the NHS. Updated report of a working party. London: Royal College of Physicians; 2017.
5. Smith GB, Prytherch DR, Schmidt PE, Featherstone PI. Review and performance evaluation of aggregate weighted “track and trigger” systems. Resuscitation. 2008;77(2):170-179. doi:10.1016/j.resuscitation.2007.12.004.
6. Churpek MM, Yuen TC, Edelson DP. Risk stratification of hospitalized patients on the wards. Chest. 2013;143(6):1758-1765.
7. Bates DW, Saria S, Ohno-Machado L, Shah A, Escobar G. Big data in health care: using analytics to identify and manage high-risk and high-cost patients. Health Aff (Millwood). 2014;33(7):1123-1131.
8. Obermeyer Z, Emanuel EJ. Predicting the future—big data, machine learning, and clinical medicine. N Engl J Med. 2016;375(13):1216-1219.
9. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230-243. doi:10.1136/svn-2017-000101.
10. Hosmer DW Jr, Lemeshow S, Sturdivant RX. Applied Logistic Regression. 3rd ed. Hoboken, NJ: John Wiley & Sons; 2013.
11. Breiman L. Random forests. Mach Learn. 2001;45:5-32.
12. Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29(5):1189-1232.
13. Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N, Hardt M, et al. Scalable and accurate deep learning with electronic health records. NPJ Digit Med. 2018;1:18. doi:10.1038/s41746-018-0029-1.
14. Futoma J, Morris J, Lucas J. A comparison of models for predicting early hospital readmissions. J Biomed Inform. 2015;56:229-238.
15. Escobar GJ, Liu VX, Schuler A, Lawson B, Greene JD, Kipnis P. Automated identification of adults at risk for in-hospital clinical deterioration. N Engl J Med. 2020;383(20):1951-1960. doi:10.1056/NEJMsa2001090.
16. Xie F, Chakraborty B, Ong MEH, Goldstein BA, Liu N. AutoScore: a machine learning-based automatic clinical score generator and its application to mortality prediction using electronic health records. JMIR Med Inform. 2020;8(10):e21798.
17. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765-4774.
18. Topol EJ. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. New York: Basic Books; 2019.
19. Sendak MP, D’Arcy J, Kashyap S, Gao M, Nichols M, Corey K, et al. A path for translation of machine learning products into healthcare delivery. EMJ Innov. 2020;4(1):19-26.
20. Wiens J, Saria S, Sendak M, Ghassemi M, Liu VX, Doshi-Velez F, et al. Do no harm: a roadmap for responsible machine learning for health care. Nat Med. 2019;25(9):1337-1340. doi:10.1038/s41591-019-0548-6.