Open AccessOsteoporotic hip fracture prediction from risk factors available in administrative claims data – A machine learning approach
Author(s) -
Alexander Engels,
K. Reber,
Ivonne Lindlbauer,
Kilian Rapp,
Gisela Büchele,
Jochen Klenk,
Andreas D. Meid,
Clemens Becker,
HansHelmut König
Publication year - 2020
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0232969
Subject(s) - machine learning , support vector machine , calibration , computer science , hip fracture , data set , artificial intelligence , set (abstract data type) , predictive modelling , mean squared error , health care , regression analysis , regression , data mining , statistics , medicine , osteoporosis , mathematics , economic growth , economics , programming language , endocrinology
Objective Hip fractures are among the most frequently occurring fragility fractures in older adults, associated with a loss of quality of life, high mortality, and high use of healthcare resources. The aim was to apply the superlearner method to predict osteoporotic hip fractures using administrative claims data and to compare its performance to established methods. Methods We devided claims data of 288,086 individuals aged 65 years and older without care level into a training (80%) and a validation set (20%). Subsequently, we trained a superlearner algorithm that considered both regression and machine learning algorithms (e.g., support vector machines, RUSBoost) on a large set of clinical risk factors. Mean squared error and measures of discrimination and calibration were employed to assess prediction performance. Results All algorithms used in the analysis showed similar performance with an AUC ranging from 0.66 to 0.72 in the training and 0.65 to 0.70 in the validation set. Superlearner showed good discrimination in the training set but poorer discrimination and calibration in the validation set. Conclusions The superlearner achieved similar predictive performance compared to the individual algorithms included. Nevertheless, in the presence of non-linearity and complex interactions, this method might be a flexible alternative to be considered for risk prediction in large datasets.