An ensemble machine learning approach to predict postoperative mortality in older patients undergoing emergency surgery

Abstract

Background: Prediction of preoperative frailty risk in the emergency setting is a challenging issue because preoperative evaluation cannot be done sufficiently. In a previous study, the preoperative frailty risk prediction model used only diagnostic and operation codes for emergency surgery and found poor predictive performance. This study developed a preoperative frailty prediction model using machine learning techniques that can be used in various clinical settings with improved predictive performance.

Methods: This is a national cohort study including 22,448 patients who were older than 75 years and visited the hospital for emergency surgery from the cohort of older patients among the retrieved sample from the Korean National Health Insurance Service. The diagnostic and operation codes were one-hot encoded and entered into the predictive model using the extreme gradient boosting (XGBoost) as a machine learning technique. The predictive performance of the model for postoperative 90-day mortality was compared with those of previous frailty evaluation tools such as Operation Frailty Risk Score (OFRS) and Hospital Frailty Risk Score (HFRS) using the receiver operating characteristic curve analysis.

Results: The predictive performance of the XGBoost, OFRS, and HFRS for postoperative 90-day mortality was 0.840, 0.607, and 0.588 on a c-statistics basis, respectively.

Conclusions: Using machine learning techniques, XGBoost to predict postoperative 90-day mortality, using diagnostic and operation codes, the prediction performance was improved significantly over the previous risk assessment models such as OFRS and HFRS.

Keywords: Emergency surgery; Hospital frailty risk score; Machine learning; Operation frailty risk score; Postoperative mortality; Preoperative frailty.

Fig. 1

Flow chart showing the data retrieving procedures. HFRS: Hospital Frailty Risk Score, OFRS: Operation Frailty Risk Score

Fig. 2

The performance of different predictive models by the receiver operating characteristic curve. XGBoost: Extreme Gradient Boosting, HFRS: Hospital Frailty Risk Score, OFRS: Operation Frailty Risk Score

Fig. 3

Feature of importance in the predictive model using machine learning method (XGBoost). XGBoost: Extreme Gradient Boosting, DX: Diagnostic code, OP: Operation code, E83: Disorders of mineral metabolism, L08: Other local infections of skin and subcutaneous tissue, R11: Nausea, and vomiting, O1502: Irrigation of empyema cavity, M81: Osteoporosis without current pathological fracture, M6730: Percutaneous gastrostomy, M15: Polyosteoarthritis, A04: Other bacterial intestinal infections, L89: Pressure ulcer, O1264: Operation of vocal cord paralysis, UX044: Temporomandibular joint arthrocentesis, W19: Unspecified fall, M6650: Percutaneous installation of inferior vena cava filter, O2004: Implantation of internal pulse generator by thoracotomy, G30: Alzheimer’s disease, M41L: Scoliosis, S32: Fracture of lumbar spine and pelvis, E16: Other disorders of pancreatic internal secretion