Analysis of machine learning algorithmic models for the prediction of vital status at six months after hip fracture in patients older than 74 years.

Abstract

Background and objective: The objective is to develop a model that predicts vital status six months after fracture as accurately as possible. For this purpose we will use five different data sources obtained through the National Hip Fracture Registry, the Health Management Unit and the Economic Management Department.

Material and methods: The study population is a cohort of patients over 74 years of age who suffered a hip fracture between May 2020 and December 2022. A warehouse is created from five different data sources with the necessary variables. An analysis of missing values and outliers as well as unbalanced classes of the target variable («vital status») is performed. Fourteen different algorithmic models are trained with the training. The model with the best performance is selected and a fine tuning is performed. Finally, the performance of the selected model is analyzed with test data.

Results: A data warehouse is created with 502 patients and 144 variables. The best performing model is Linear Regression. Sixteen of the 24 cases of deceased patients are classified as live, and 14 live patients are classified as deceased. A sensitivity of 31%, an accuracy of 34% and an area under the curve of 0.65 is achieved.

Conclusions: We have not been able to generate a model for the prediction of six-month survival in the current cohort. However, we believe that the method used for the generation of algorithms based on machine learning can serve as a reference for future works.