Categories
Nevin Manimala Statistics

POL-RISK: an algorithm for 10-year fracture risk prediction in the postmenopausal women from the RAC-OST-POL Study

Pol Arch Intern Med. 2023 Jan 4:16395. doi: 10.20452/pamw.16395. Online ahead of print.

ABSTRACT

INTRODUCTION: The fracture risk assessment is essential for the diagnostic process in osteoporosis.

OBJECTIVE: The aim of the study was to develop an algorithm for fracture risk prediction.

PATIENTS AND METHODS: Bone status was investigated in a population-based cohort of postmenopausal women, their mean age being 66.4 (SD=7.8) years. After that all the participants were invited by phone once a year (for 10 consecutive years) to update their history of fractures. At the end of the 10-year observation period the number of the study participants was 640 women, out of whom, 129 women presented the history of 190 osteoporotic fractures, recorded during the study period. Statistical analysis included multistep data preprocessing, feature selection, identification of fracture risk factors, and a final model design. Logistic regression models were fitted and used for evaluation of variables from determined feature sets, including global fit measures, as well as individual parameters, such as the Wald statistic and P-value, the odds ratio, and the confidence interval.

RESULTS: The 10-year any fracture risk depended on the age of the study subjects, the number of recorded fractures after the age of 40 years, femoral neck bone mass values, and the fact of falls in the past year. The equation is as follows: Risk of fracture=1/(1+e^(-(-3.336+0.019*AGE+0.437*NUMBER_OF_PRIOR_FRACTURES-0.258*FN_T_score+0.508*PRIOR_FALLS)). The algorithm is available at www.fracture-risk.pl.

CONCLUSION: A fracture prediction algorithm was developed in a longitudinal study to calculate 10-year fracture risk. The identification of patients at high fracture risk should be followed by a treatment strategy to reduce the number of future fractures.

PMID:36601872 | DOI:10.20452/pamw.16395

By Nevin Manimala

Portfolio Website for Nevin Manimala