Machine learning-based prediction of short- and long-term mortality for shared decision-making in older hip fracture patients: the Dutch Hip Fracture Audit algorithms in 74,396 cases

Abstract

Background and purpose: Treatment-related shared decision-making (SDM) in older adults with hip fractures is complex due to the need to balance patient-specific factors such as life goals, frailty, and surgical risks. It includes considerations such as prognosis and decisions concerning whether to operate or not on frail, life-limited patients. We aimed to develop machine learning (ML)-driven prediction models for short- and long-term mortality in a large cohort of patients with hip fractures.

Methods: In this national registry-based retrospective cohort study, patients aged ≥ 70 years registered in the nationwide Dutch Hip Fracture Audit from 2018-2023 were included. Predictive variables were selected based on the literature and/or clinical relevance. 6 ML algorithms, including logistic regression, were trained with internal cross-validation and evaluated on discrimination (c-statistic), sensitivity, specificity, calibration, and interpretability.

Results: 74,396 patients (median age 84, IQR 78-89; 68% female) were analyzed. Most patients lived at home (69%) and high malnutrition risk was seen in 10%. 18% had dementia. Mortality rates were 9.1% (30-day), 15% (90-day), and 26% (1-year). Logistic regression performed comparably to other algorithms, but was chosen as the preferred algorithm due to its superior interpretability (c-statistic: 30-day 0.82, 90-day 0.81, 1-year 0.80).

Conclusion: We developed and validated ML algorithms, including logistic regression, for mortality prediction in older hip fracture patients with adequate performance. This information may inform SDM.

Figure 1

(A) Receiver operating characteristic curves per algorithm showing the area under the curve (AUC) for each algorithm, for the outcome 30-day mortality. (B) Calibration curve for the logistic regression algorithm for the outcome 30-day mortality. (C) Variable importance for 30-day mortality using the preferred algorithm (preferred based on transparency), logistic regression. Absolute coefficient = the absolute values of the standardized regression coefficients (|β|) from a logistic regression model, making the importances comparable across the variables.

Figure 2

(A) Receiver operating characteristic curves per algorithm showing the area under the curve (AUC) for each algorithm, for the outcome 90-day mortality. (B) Calibration curve for the logistic regression algorithm for the outcome 90-day mortality. (C) Variable importance for 90-day mortality using the preferred algorithm (preferred based on transparency), logistic regression. Absolute coefficient = the absolute values of the standardized regression coefficients (|β|) from a logistic regression model, making the importances comparable across the variables.

Figure 3

(A) Receiver operating characteristic curves per algorithm showing the area under the curve (AUC) for each algorithm, for the outcome 90-day mortality. (B) Calibration curve for the logistic regression algorithm for the outcome 90-day mortality. (C) Variable importance for 1-year mortality using the preferred algorithm (preferred based on transparency), logistic regression. Absolute coefficient = the absolute values of the standardized regression coefficients (|β|) from a logistic regression model, making the importances comparable across the variables.