Defining Clinically Meaningful Subgroups for Risk Stratification in Patients Undergoing Revision Total Hip Arthroplasty: A Combined Unsupervised and Supervised Machine Learning Approach.

BACKGROUND: Studies developing predictive models from large datasets to risk stratify patients undergoing revision total hip arthroplasties (rTHA) are limited. We used machine learning (ML) to stratify patients undergoing rTHA into risk-based subgroups.

METHODS: Using a large national database from 2011 to 2018, we retrospectively identified 7,425 patients who underwent rTHA. An unsupervised random forest algorithm was used to partition patients into high- and low-risk strata based on similarities in rates of mortality, reoperation, and 25 other postoperative complications. A risk calculator was subsequently produced using a supervised ML algorithm to identify high-risk patients based on preoperative parameters.

RESULTS: There were 3,135 and 4,290 patients were identified in the high-risk and low-risk subgroups, respectively. Each group significantly differed by rate of 30-day mortalities, unplanned reoperations/readmissions, routine discharges, and hospital lengths of stay (P<0.05). The high-risk subgroup had a significantly increased rate of transfusions, surgical site infections, and other medical complications (P<0.05). A supervised Extreme Gradient Boosting algorithm outperformed a stepwise logistic regression (area under the receiver operating characteristics curve 86 vs. 83.6, respectively), and identified preoperative platelets <200, hematocrit >35 or <20, increasing age, albumin <3, international normalized ratio >2, body mass index >35, American Society of Anesthesia class ≥3, blood urea nitrogen >50 or <30, creatinine >1.5, diagnosis of hypertension or coagulopathy, and revision for periprosthetic fracture and infection as predictors of high-risk.

CONCLUSION: Clinically meaningful risk strata in patients undergoing rTHA were identified using a ML clustering approach. Routine preoperative laboratory workups, demographics, and surgical indications have the greatest impact on differentiating high versus low risk.