Development and validation of a machine learning-based fall-related injury risk prediction model using nationwide claims database in Korean community-dwelling older population

Abstract Background Falls impact over 25% of older adults annually, making fall prevention a critical public health focus. We aimed to develop and validate a machine learning-based prediction model for serious fall-related injuries (FRIs) among community-dwelling older adults, incorporating various...

Full description

Bibliographic Details
Main Authors: Kyu-Nam Heo, Jeong Yeon Seok, Young-Mi Ah, Kwang-il Kim, Seung-Bo Lee, Ju-Yeun Lee
Format: Article
Language:English
Published: BMC 2023-12-01
Series:BMC Geriatrics
Subjects:
Online Access:https://doi.org/10.1186/s12877-023-04523-8
_version_ 1797388045762166784
author Kyu-Nam Heo
Jeong Yeon Seok
Young-Mi Ah
Kwang-il Kim
Seung-Bo Lee
Ju-Yeun Lee
author_facet Kyu-Nam Heo
Jeong Yeon Seok
Young-Mi Ah
Kwang-il Kim
Seung-Bo Lee
Ju-Yeun Lee
author_sort Kyu-Nam Heo
collection DOAJ
description Abstract Background Falls impact over 25% of older adults annually, making fall prevention a critical public health focus. We aimed to develop and validate a machine learning-based prediction model for serious fall-related injuries (FRIs) among community-dwelling older adults, incorporating various medication factors. Methods Utilizing annual national patient sample data, we segmented outpatient older adults without FRIs in the preceding three months into development and validation cohorts based on data from 2018 and 2019, respectively. The outcome of interest was serious FRIs, which we defined operationally as incidents necessitating an emergency department visit or hospital admission, identified by the diagnostic codes of injuries that are likely associated with falls. We developed four machine-learning models (light gradient boosting machine, Catboost, eXtreme Gradient Boosting, and Random forest), along with a logistic regression model as a reference. Results In both cohorts, FRIs leading to hospitalization/emergency department visits occurred in approximately 2% of patients. After selecting features from initial set of 187, we retained 26, with 15 of them being medication-related. Catboost emerged as the top model, with area under the receiver operating characteristic of 0.700, along with sensitivity and specificity rates around 65%. The high-risk group showed more than threefold greater risk of FRIs than the low-risk group, and model interpretations aligned with clinical intuition. Conclusion We developed and validated an explainable machine-learning model for predicting serious FRIs in community-dwelling older adults. With prospective validation, this model could facilitate targeted fall prevention strategies in primary care or community-pharmacy settings.
first_indexed 2024-03-08T22:35:02Z
format Article
id doaj.art-20b9b06c4538442ead10583f9c9057ac
institution Directory Open Access Journal
issn 1471-2318
language English
last_indexed 2024-03-08T22:35:02Z
publishDate 2023-12-01
publisher BMC
record_format Article
series BMC Geriatrics
spelling doaj.art-20b9b06c4538442ead10583f9c9057ac2023-12-17T12:29:17ZengBMCBMC Geriatrics1471-23182023-12-0123111010.1186/s12877-023-04523-8Development and validation of a machine learning-based fall-related injury risk prediction model using nationwide claims database in Korean community-dwelling older populationKyu-Nam Heo0Jeong Yeon Seok1Young-Mi Ah2Kwang-il Kim3Seung-Bo Lee4Ju-Yeun Lee5College of Pharmacy and Research Institute of Pharmaceutical Sciences, Seoul National UniversityCollege of Pharmacy and Research Institute of Pharmaceutical Sciences, Seoul National UniversityCollege of Pharmacy, Yeungnam UniversityDepartment of Internal Medicine, Seoul National University Bundang HospitalDepartment of Medical Informatics, Keimyung University School of MedicineCollege of Pharmacy and Research Institute of Pharmaceutical Sciences, Seoul National UniversityAbstract Background Falls impact over 25% of older adults annually, making fall prevention a critical public health focus. We aimed to develop and validate a machine learning-based prediction model for serious fall-related injuries (FRIs) among community-dwelling older adults, incorporating various medication factors. Methods Utilizing annual national patient sample data, we segmented outpatient older adults without FRIs in the preceding three months into development and validation cohorts based on data from 2018 and 2019, respectively. The outcome of interest was serious FRIs, which we defined operationally as incidents necessitating an emergency department visit or hospital admission, identified by the diagnostic codes of injuries that are likely associated with falls. We developed four machine-learning models (light gradient boosting machine, Catboost, eXtreme Gradient Boosting, and Random forest), along with a logistic regression model as a reference. Results In both cohorts, FRIs leading to hospitalization/emergency department visits occurred in approximately 2% of patients. After selecting features from initial set of 187, we retained 26, with 15 of them being medication-related. Catboost emerged as the top model, with area under the receiver operating characteristic of 0.700, along with sensitivity and specificity rates around 65%. The high-risk group showed more than threefold greater risk of FRIs than the low-risk group, and model interpretations aligned with clinical intuition. Conclusion We developed and validated an explainable machine-learning model for predicting serious FRIs in community-dwelling older adults. With prospective validation, this model could facilitate targeted fall prevention strategies in primary care or community-pharmacy settings.https://doi.org/10.1186/s12877-023-04523-8FallFall-related injuryOlder adultsMachine-learningPrediction modelClaims data
spellingShingle Kyu-Nam Heo
Jeong Yeon Seok
Young-Mi Ah
Kwang-il Kim
Seung-Bo Lee
Ju-Yeun Lee
Development and validation of a machine learning-based fall-related injury risk prediction model using nationwide claims database in Korean community-dwelling older population
BMC Geriatrics
Fall
Fall-related injury
Older adults
Machine-learning
Prediction model
Claims data
title Development and validation of a machine learning-based fall-related injury risk prediction model using nationwide claims database in Korean community-dwelling older population
title_full Development and validation of a machine learning-based fall-related injury risk prediction model using nationwide claims database in Korean community-dwelling older population
title_fullStr Development and validation of a machine learning-based fall-related injury risk prediction model using nationwide claims database in Korean community-dwelling older population
title_full_unstemmed Development and validation of a machine learning-based fall-related injury risk prediction model using nationwide claims database in Korean community-dwelling older population
title_short Development and validation of a machine learning-based fall-related injury risk prediction model using nationwide claims database in Korean community-dwelling older population
title_sort development and validation of a machine learning based fall related injury risk prediction model using nationwide claims database in korean community dwelling older population
topic Fall
Fall-related injury
Older adults
Machine-learning
Prediction model
Claims data
url https://doi.org/10.1186/s12877-023-04523-8
work_keys_str_mv AT kyunamheo developmentandvalidationofamachinelearningbasedfallrelatedinjuryriskpredictionmodelusingnationwideclaimsdatabaseinkoreancommunitydwellingolderpopulation
AT jeongyeonseok developmentandvalidationofamachinelearningbasedfallrelatedinjuryriskpredictionmodelusingnationwideclaimsdatabaseinkoreancommunitydwellingolderpopulation
AT youngmiah developmentandvalidationofamachinelearningbasedfallrelatedinjuryriskpredictionmodelusingnationwideclaimsdatabaseinkoreancommunitydwellingolderpopulation
AT kwangilkim developmentandvalidationofamachinelearningbasedfallrelatedinjuryriskpredictionmodelusingnationwideclaimsdatabaseinkoreancommunitydwellingolderpopulation
AT seungbolee developmentandvalidationofamachinelearningbasedfallrelatedinjuryriskpredictionmodelusingnationwideclaimsdatabaseinkoreancommunitydwellingolderpopulation
AT juyeunlee developmentandvalidationofamachinelearningbasedfallrelatedinjuryriskpredictionmodelusingnationwideclaimsdatabaseinkoreancommunitydwellingolderpopulation