Citation

Homer ML, Palmer NP, Fox KP, Armstrong J, Mandl KD. Am. J. Med. 2017; 130(6): 744.e17-744.e23.

Affiliation

Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA. Electronic address: Kenneth_mandl@harvard.edu.

Copyright

(Copyright © 2017, Elsevier Publishing)

DOI

10.1016/j.amjmed.2017.01.003

PMID

28111165

Abstract

BACKGROUND: Accidental falls among people aged 65 years and older caused approximately 2,700,000 injuries, 27,000 deaths, and cost more than 34 billion dollars in the United States annually in recent years. Here, we derive and validate a predictive model for falls based on a retrospective cohort of those 65 years and older.

METHODS: Insurance claims from a one year observational period were used to predict a fall-related claim in the following two years. The predictive model takes into account a person's age, sex, prescriptions, and diagnoses. Through random assignment, half of the people had their claims used to derive the model, while the remaining people had their claims used to validate the model.

RESULTS: Out of 120,881 individuals, with Aetna health insurance coverage, 12,431 (10.3%) members fell. During validation, people were risk stratified across 20 levels, where those in the highest risk stratum had 10.5 times the risk as those in the lowest stratum (33.1% vs. 3.1%).

CONCLUSIONS: Using only insurance claims, individuals in this large cohort at high risk of falls could be readily identified up to two years in advance. Although external validation is needed, the findings support the use of the model to better target interventions.

Copyright © 2017 Elsevier Inc. All rights reserved.

Language: en

Keywords

falls; population health; risk assessment