Machine Learning Can Improve Clinical Detection of Low BMD: The DXA-HIP Study

Erjiang, E; Wang, Tingyan; Yang, Lan; Dempsey, Mary; Brennan, Attracta; Yu, Ming; Chan, Wing P.; Whelan, Bryan; Silke, Charlotte; O’Sullivan, Miriam; Rooney, Bridie; McPartland, Aoife; O'Malley, G; Carey, John J.

doi:10.1016/j.jocd.2020.10.004

Cited by 24 publications

(12 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1296 subjects had a VFA scan report and DXA information available for analysis including 1042 women and 254 men. Details of our entire cohort has previously been published [37,41], while a summary of the characteristics of this subgroup are shown in Table 1. The majority are female, with a mean age of 70 years, and a range of 40-94 years.…”

Section: Resultsmentioning

confidence: 99%

Vertebral Fractures in Ireland: A Sub-analysis of the DXA HIP Project

et al. 2021

Self Cite

View full text Add to dashboard Cite

Osteoporosis is an important global health problem resulting in fragility fractures. The vertebrae are the commonest site of fracture resulting in extreme illness burden, and having the highest associated mortality. International studies show that vertebral fractures (VF) increase in prevalence with age, similarly in men and women, but differ across different regions of the world. Ireland has one of the highest rates of hip fracture in the world but data on vertebral fractures are limited. In this study we examined the prevalence of VF and associated major risk factors, using a sample of subjects who underwent vertebral fracture assessment (VFA) performed on 2 dual-energy X-ray absorptiometry (DXA) machines. A total of 1296 subjects aged 40 years and older had a valid VFA report and DXA information available, including 254 men and 1042 women. Subjects had a mean age of 70 years, 805 (62%) had prior fractures, mean spine T-score was − 1.4 and mean total hip T-scores was − 1.2, while mean FRAX scores were 15.4% and 4.8% for major osteoporotic fracture and hip fracture, respectively. Although 95 (7%) had a known VF prior to scanning, 283 (22%) patients had at least 1 VF on their scan: 161 had 1, 61 had 2, and 61 had 3 or more. The prevalence of VF increased with age from 11.5% in those aged 40–49 years to > 33% among those aged ≥ 80 years. Both men and women with VF had significantly lower BMD at each measured site, and significantly higher FRAX scores, P < 0.01. These data suggest VF are common in high risk populations, particularly older men and women with low BMD, previous fractures, and at high risk of fracture. Urgent attention is needed to examine effective ways to identify those at risk and to reduce the burden of VF.

show abstract

Section: Resultsmentioning

confidence: 99%

Vertebral Fractures in Ireland: A Sub-analysis of the DXA HIP Project

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent decades, ML models, an AI-based approach, have been increasingly used to predict osteoporosis. In 2021, Wang et al [ 19 ] compared seven machine learning models to detect patients with or without osteoporosis. In 2021, Ou-Yang et al [ 20 ] implemented five ML models using 16 to 19 features (physical findings and blood tests) to identify the risk of osteoporosis in the population of Taiwan.…”

Section: Discussionmentioning

confidence: 99%

Screening for Osteoporosis from Blood Test Data in Elderly Women Using a Machine Learning Approach

et al. 2023

View full text Add to dashboard Cite

The diagnosis of osteoporosis is made by measuring bone mineral density (BMD) using dual-energy X-ray absorptiometry (DXA). Machine learning, one of the artificial intelligence methods, was used to predict low BMD without using DXA in elderly women. Medical records from 2541 females who visited the osteoporosis clinic were used in this study. As hyperparameters for machine learning, patient age, body mass index (BMI), and blood test data were used. As machine learning models, logistic regression, decision tree, random forest, gradient boosting trees, and lightGBM were used. Each model was trained to classify and predict low-BMD patients. The model performance was compared using a confusion matrix. The accuracy of each trained model was 0.772 in logistic regression, 0.739 in the decision tree, 0.775 in the random forest, 0.800 in gradient boosting, and 0.834 in lightGBM. The area under the curve (AUC) was 0.595 in the decision tree, 0.673 in logistic regression, 0.699 in the random forest, 0.840 in gradient boosting, and 0.961, which was the highest, in the lightGBM model. Important features were BMI, age, and the number of platelets. Shapley additive explanation scores in the lightGBM model showed that BMI, age, and ALT were ranked as important features. Among several machine learning models, the lightGBM model showed the best performance in the present research.

show abstract

“…Additionally, patients with osteoporosis and low BMD who should undergo DXA testing and/or treatment can be identified and treated. For example, in our previous research results, we proposed seven ML technologies which improve clinical detection of low BMD 27 and used OST model as a screening tool for osteoporosis in Irish men and women. 42 We also proposed and implemented a free online tool to assess the risk of osteoporosis, named DXA-HIP Osteoporosis Assessment Tool (https://dxa-hip.shinyapps.io/dxa-hip/).…”

Section: Discussionmentioning

confidence: 99%

“…In this study, we aim to address this limitation by proposing a DXA healthcare informatics prediction (HIP) system. 27,28 The DXA HIP system is designed for collecting, integrating and analysing healthcare data from multiple hospital systems and aims to improve fracture risk prediction, osteoporosis care and reduce healthcare cost. The DXA HIP system was applied in three healthcare centres in Ireland to validate and verify its usability and effectiveness.…”

Section: Introductionmentioning

confidence: 99%

Conceptual design of the dual X-ray absorptiometry health informatics prediction system for osteoporosis care

Erjiang

Carey

Wang

et al. 2022

Health Informatics J

Self Cite

View full text Add to dashboard Cite

Osteoporotic fractures are a major and growing public health problem, which is strongly associated with other illnesses and multi-morbidity. Big data analytics has the potential to improve care for osteoporotic fractures and other non-communicable diseases (NCDs), reduces healthcare costs and improves healthcare decision-making for patients with multi-disorders. However, robust and comprehensive utilization of healthcare big data in osteoporosis care practice remains unsatisfactory. In this paper, we present a conceptual design of an intelligent analytics system, namely, the dual X-ray absorptiometry (DXA) health informatics prediction (HIP) system, for healthcare big data research and development. Comprising data source, extraction, transformation, loading, modelling and application, the DXA HIP system was applied in an osteoporosis healthcare context for fracture risk prediction and the investigation of multi-morbidity risk. Data was sourced from four DXA machines located in three healthcare centres in Ireland. The DXA HIP system is novel within the Irish context as it enables the study of fracture-related issues in a larger and more representative Irish population than previous studies. We propose this system is applicable to investigate other NCDs which have the potential to improve the overall quality of patient care and substantially reduce the burden and cost of all NCDs.

show abstract

Machine Learning Can Improve Clinical Detection of Low BMD: The DXA-HIP Study

Cited by 24 publications

References 50 publications

Vertebral Fractures in Ireland: A Sub-analysis of the DXA HIP Project

Vertebral Fractures in Ireland: A Sub-analysis of the DXA HIP Project

Screening for Osteoporosis from Blood Test Data in Elderly Women Using a Machine Learning Approach

Conceptual design of the dual X-ray absorptiometry health informatics prediction system for osteoporosis care

Contact Info

Product

Resources

About