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

BACKGROUND: Identification of those at high risk before a fracture occurs is an essential part of osteoporosis management. This topic remains a significant challenge for researchers in the field, and clinicians worldwide. Although many algorithms have been developed to either identify those with a diagnosis of osteoporosis or predict their risk of fracture, concern remains regarding their accuracy and application. Scientific advances including machine learning methods are rapidly gaining appreciation as alternative techniques to develop or enhance risk assessment and current practice. Recent evidence suggests that these methods could play an important role in the assessment of osteoporosis and fracture risk. METHODS: Data used for this study included Dual-energy X-ray Absorptiometry (DXA) bone mineral density and T-scores, and multiple clinical variables drawn from a convenience cohort of adult patients scanned on one of 4 DXA machines across three hospitals in the West of Ireland between January 2000 and November 2018 (the DXA-Heath Informatics Prediction Cohort). The dataset was cleaned, validated and anonymized, and then split into an exploratory group (80%) and a development group (20%) using the stratified sampling method. We first established the validity of a simple tool, the Osteoporosis Self-assessment Tool Index (OSTi) to identify those classified as osteoporotic by the modified International Society for Clinical Densitometry DXA criteria. We then compared these results to seven machine learning techniques (MLTs): CatBoost, eXtreme Gradient Boosting, Neural network, Bagged flexible discriminant analysis, Random forest, Logistic regression and Support vector machine to enhance the discrimination of those classified as osteoporotic or not. The performance of each prediction model was measured by calculating the area under the curve (AUC) with 95% confidence interval (CI), and was compared against the OSTi. RESULTS: A cohort of 13,577 adults aged ≥40 yr at the age of their first scan was identified including 11,594 women and 1983 men. 2102 (18.13%) females and 356 (17.95%) males were identified with osteoporosis based on their lowest T-score. The OSTi performed well in our cohort in both men (AUC 0.723, 95% CI 0.659-0.788) and women (AUC 0.810, 95% CI 0.787-0.833). Four MLTs improved discrimination in both men and women, though the incremental benefit was small. eXtreme Gradient Boosting showed the most promising results: +4.5% (AUC 0.768, 95% CI 0.706-0.829) for men and +2.3% (AUC 0.833, 95% CI 0.812-0.853) for women. Similarly MLTs outperformed OSTi in sensitivity analyses-which excluded those subjects taking osteoporosis medications-though the absolute improvements differed. CONCLUSION: The OSTi retains an important role in identifying older men and women most likely to have osteoporosis by bone mineral density classification. MLTs could improve DXA detection of osteoporosis classification in older men and women. Further exploration of MLTs is warranted in other populations, and with additional data.

Utility of Osteoporosis Self-Assessment Tool as a Screening Tool for Osteoporosis in Irish Men and Women: Results of the DXA-HIP Project.

Many algorithms have been developed and publicised over the past 2 decades for identifying those most likely to have osteoporosis or low BMD, or at increased risk of fragility fracture. The Osteoporosis Self-assessment Tool index (OSTi) is one of the oldest, simplest, and widely used for identifying men and women with low BMD or osteoporosis. OSTi has been validated in many cohorts worldwide but large studies with robust analyses evaluating this or other algorithms in adult populations residing in the Republic of Ireland are lacking, where waiting times for public DXA facilities are long. In this study we evaluated the validity of OSTi in men and women drawn from a sampling frame of more than 36,000 patients scanned at one of 3 centres in the West of Ireland. 18,670 men and women aged 40 years and older had a baseline scan of the lumbar spine femoral neck and total hip available for analysis. 15,964 (86%) were female, 5,343 (29%) had no major clinical risk factors other than age, while 5,093 (27%) had a prior fracture. Approximately 2/3 had a T-score ≤-1.0 at one or more skeletal sites and 1/3 had a T-score ≤-1.0 at all 3 skeletal sites, while 1 in 5 had a DXA T-score ≤-2.5 at one or more skeletal sites and 5% had a T-score ≤-2.5 at all 3 sites. OSTi generally performed well in our population with area under the curve (AUC) values ranging from 0.581 to 0.881 in men and 0.701 to 0.911 in women. The performance of OSTi appeared robust across multiple sub-group analyses. AUC values were greater for women, proximal femur sites, those without prior fractures and those not taking osteoporosis medication. Optimal OSTi cut-points were '2' for men and '0' for women in our study population. OSTi is a simple and effective tool to aid identification of Irish men and women with low BMD or osteoporosis. Use of OSTi could improve the effectiveness of DXA screening programmes for older adults in Ireland.

Modelling future bone mineral density: Simplicity or complexity?

BACKGROUND: Osteoporotic fractures are a major global public health issue, leading to patient suffering and death, and considerable healthcare costs. Bone mineral density (BMD) measurement is important to identify those with osteoporosis and assess their risk of fracture. Both the absolute BMD and the change in BMD over time contribute to fracture risk. Predicting future fracture in individual patients is challenging and impacts clinical decisions such as when to intervene or repeat BMD measurement. Although the importance of BMD change is recognised, an effective way to incorporate this marginal effect into clinical algorithms is lacking. METHODS: We compared two methods using longitudinal DXA data generated from subjects with two or more hip DXA scans on the same machine between 2000 and 2018. A simpler statistical method (ZBM) was used to predict an individual's future BMD based on the mean BMD and the standard deviation of the reference group and their BMD measured in the latest scan. A more complex deep learning (DL)-based method was developed to cope with multidimensional longitudinal data, variables extracted from patients' historical DXA scan(s), as well as features drawn from the ZBM method. Sensitivity analyses of several subgroups was conducted to evaluate the performance of the derived models. RESULTS: 2948 white adults aged 40-90 years met our study inclusion: 2652 (90 %) females and 296 (10 %) males. Our DL-based models performed significantly better than the ZBM models in women, particularly our Hybrid-DL model. In contrast, the ZBM-based models performed as well or better than DL-based models in men. CONCLUSIONS: Deep learning-based and statistical models have potential to forecast future BMD using longitudinal clinical data. These methods have the potential to augment clinical decisions regarding when to repeat BMD testing in the assessment of osteoporosis.

An overview of the management of osteoporosis in the aging female population.

Osteoporosis is a systemic skeletal disease that is a cause of morbidity and mortality. It can affect all ages but most frequently postmenopausal women. It is a silent condition, however, osteoporotic fractures can lead to significant pain and disability. In this review article, we aim to review the clinical approach to the management of postmenopausal osteoporosis. We include risk assessment, investigations, and the various pharmacological and non-pharmacological options used in the treatment of osteoporosis. We have discussed the pharmacological options individually including their mechanism of action, safety profile, effects on bone mineral density and fracture risks, and duration of use. Potential new treatments are also discussed. The importance of sequence in the use of osteoporotic medicine is also highlighted in the article. An understanding of the different treatment options will hopefully help in the management of this very common and debilitating condition.

Prevalence of Low Bone Mass and Osteoporosis in Ireland: the Dual-Energy X-Ray Absorptiometry (DXA) Health Informatics Prediction (HIP) Project.

Osteoporosis is a common disease that has a significant impact on patients, healthcare systems, and society. World Health Organization (WHO) diagnostic criteria for postmenopausal women were established in 1994 to diagnose low bone mass (osteopenia) and osteoporosis using dual-energy X-ray absorptiometry (DXA)-measured bone mineral density (BMD) to help understand the epidemiology of osteoporosis, and identify those at risk for fracture. These criteria may also apply to men ≥50 years, perimenopausal women, and people of different ethnicity. The DXA Health Informatics Prediction (HIP) project is an established convenience cohort of more than 36,000 patients who had a DXA scan to explore the epidemiology of osteoporosis and its management in the Republic of Ireland where the prevalence of osteoporosis remains unknown. In this article we compare the prevalence of a DXA classification low bone mass (T-score < -1.0) and of osteoporosis (T-score ≤ -2.5) among adults aged ≥40 years without major risk factors or fractures, with one or more major risk factors, and with one or more major osteoporotic fractures. A total of 33,344 subjects met our study inclusion criteria, including 28,933 (86.8%) women; 9362 had no fractures or major risk factors, 14,932 had one or more major clinical risk factors, and 9050 had one or more major osteoporotic fractures. The prevalence of low bone mass and osteoporosis increased significantly with age overall. The prevalence of low bone mass and osteoporosis was significantly greater among men and women with major osteoporotic fractures than healthy controls or those with clinical risk factors. Applying our results to the national population census figure of 5,123,536 in 2022 we estimate between 1,039,348 and 1,240,807 men and women aged ≥50 years have low bone mass, whereas between 308,474 and 498,104 have osteoporosis. These data are important for the diagnosis of osteoporosis in clinical practice, and national policy to reduce the illness burden of osteoporosis. © 2023 The Authors. JBMR Plus published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research.

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

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.

How does proximal femur BMD of healthy Irish adults compare to NHANES III? Results of the DXA-HIP Project.

This study examines the distribution of proximal femur bone mineral density in a cohort of healthy Irish adults. These values are similar to those of the NHANES III Caucasian cohorts, supporting international recommendations to use this reference group for calculating DXA T-scores and Z-scores in Irish adults. INTRODUCTION: Bone mineral density (BMD) is widely used in the assessment and monitoring of osteoporosis. International guidelines recommend referencing proximal femur BMD measurements to NHANES III values to calculate T-scores and Z-scores, but their validity for the Irish population has not been established. In this study, we compare BMD values of healthy Irish Caucasian adults to those of Caucasian men and women in the NHANES III cohort study. METHODS: Men and women without bone disease and/or major risk factors for fracture, and/or not taking osteoporosis medication who had a screening DXA scan (GE Lunar, Madison, USA) at one of 3 centres in the West of Ireland were selected for this study. We calculated the mean and standard deviation (SD) used by GE for calculating white female NHANES III T-scores at the femoral neck and total hip sites, and used these values to calculate white female T-scores for men and women across each decade in our study sample. We calculated mean white female T-scores for each decade for both Caucasian men and women in the NHANES III cohort using the published data. Finally, we plotted these results against those of our study population. RESULTS: In total, 6729 (18.5%) of 36,321 adults were included in our analyses, including 5923 (88%) women. The majority of the study population were aged between 40 and 89 years. Our results show that the proximal femur BMD of healthy Irish men and women is broadly similar to that of the NHANES III reference population, especially middle-aged adults. Results differ for very young and very old adults, likely reflecting the small sample size and a referral bias. Further studies of these populations and other manufacturers could help clarify these uncertainties. CONCLUSIONS: Our results support using the NHANES III reference population to calculate proximal femur adult T-scores and Z-scores to establish the presence or prevalence of osteoporosis in Ireland.

The Irish dual-energy X-ray absorptiometry (DXA) Health Informatics Prediction (HIP) for Osteoporosis Project.

PURPOSE: The purpose of the Irish dual-energy X-ray absorptiometry (DXA) Health Informatics Prediction (HIP) for Osteoporosis Project is to create a large retrospective cohort of adults in Ireland to examine the validity of DXA diagnostic classification, risk assessment tools and management strategies for osteoporosis and osteoporotic fractures for our population. PARTICIPANTS: The cohort includes 36 590 men and women aged 4-104 years who had a DXA scan between January 2000 and November 2018 at one of 3 centres in the West of Ireland. FINDINGS TO DATE: 36 590 patients had at least 1 DXA scan, 6868 (18.77%) had 2 scans and 3823 (10.45%) had 3 or more scans. There are 364 unique medical disorders, 186 unique medications and 46 DXA variables identified and available for analysis. The cohort includes 10 349 (28.3%) individuals who underwent a screening DXA scan without a clear fracture risk factor (other than age), and 9947 (27.2%) with prevalent fractures at 1 of 44 skeletal sites. FUTURE PLANS: The Irish DXA HIP Project plans to assess current diagnostic classification and risk prediction algorithms for osteoporosis and fractures, identify the risk predictors for osteoporosis and develop novel, accurate and personalised risk prediction tools, by using the large multicentre longitudinal follow-up cohort. Furthermore, the dataset may be used to assess, and possibly support, multimorbidity management due to the large number of variables collected in this project.