Derivation and validation of the CFracture competing risk fracture prediction tool compared with QFracture in older people and people with comorbidity: a population cohort study

Fully Automatic Deep Learning Model for Spine Refracture in Patients with OVCF: A Multi-Center Study

BACKGROUND

The reaserch of artificial intelligence (AI) model for predicting spinal refracture is limited to bone mineral density, X-ray and some conventional laboratory indicators, which has its own limitations. Besides, it lacks specific indicators related to osteoporosis and imaging factors that can better reflect bone quality, such as computed tomography (CT).

OBJECTIVE

To construct a novel predicting model based on bone turn-over markers and CT to identify patients who were more inclined to suffer spine refracture.

METHODS

CT images and clinical information of 383 patients (training set = 240 cases of osteoporotic vertebral compression fractures (OVCF), validation set = 63, test set = 80) were retrospectively collected from January 2015 to October 2022 at three medical centers. The U-net model was adopted to automatically segment ROI. Three-dimensional (3D) cropping of all spine regions was used to achieve the final ROI regions including 3D_Full and 3D_RoiOnly. We used the Densenet 121-3D model to model the cropped region and simultaneously build a T-NIPT prediction model. Diagnostics of deep learning models were assessed by constructing ROC curves. We generated calibration curves to assess the calibration performance. Additionally, decision curve analysis (DCA) was used to assess the clinical utility of the predictive models.

RESULTS

The performance of the test model is comparable to its performance on the training set (dice coefficients of 0.798, an mIOU of 0.755, an SA of 0.767, and an OS of 0.017). Univariable and multivariable analysis indicate that T_P1NT was an independent risk factor for refracture. The performance of predicting refractures in different ROI regions showed that 3D_Full model exhibits the highest calibration performance, with a Hosmer-Lemeshow goodness-of-fit (HL) test statistic exceeding 0.05. The analysis of the training and test sets showed that the 3D_Full model, which integrates clinical and deep learning results, demonstrated superior performance with significant improvement (p-value < 0.05) compared to using clinical features independently or using only 3D_RoiOnly.

CONCLUSION

T_P1NT was an independent risk factor of refracture. Our 3D-FULL model showed better performance in predicting high-risk population of spine refracture than other models and junior doctors do. This model can be applicable to real-world translation due to its automatic segmentation and detection.

Hip Fracture Risk Assessment Tools for Adults Aged 80 Years and Older

Importance

While adults aged 80 years and older account for 70% of hip fractures in the US, performance of fracture risk assessment tools in this population is uncertain.

Objective

To compare performance of the Fracture Risk Assessment Tool (FRAX), Garvan Fracture Risk Calculator, and femoral neck bone mineral density (FNBMD) alone in 5-year hip fracture prediction.

Design, Setting and Participants

Prognostic analysis of 3 prospective cohort studies including participants attending an index examination (1997 to 2016) at age 80 years or older. Data were analyzed from March 2023 to April 2024.

Main Outcomes and Measures

Participants contacted every 4 or 6 months after index examination to ascertain incident hip fractures and vital status. Predicted 5-year hip fracture probabilities calculated using FRAX and Garvan models incorporating FNBMD and FNBMD alone. Model discrimination assessed by area under receiver operating characteristic curve (AUC). Model calibration assessed by comparing observed vs predicted hip fracture probabilities within predicted risk quintiles.

Results

A total of 8890 participants were included, with a mean (SD) age at index examination of 82.6 (2.7) years; 4906 participants (55.2%) were women, 866 (9.7%) were Black, 7836 (88.1%) were White, and 188 (2.1%) were other races and ethnicities. During 5-year follow-up, 321 women (6.5%) and 123 men (3.1%) experienced a hip fracture; 818 women (16.7%) and 921 men (23.1%) died before hip fracture. Among women, AUC was 0.69 (95% CI, 0.67-0.72) for FRAX, 0.69 (95% CI, 0.66-0.72) for Garvan, and 0.72 (95% CI, 0.69-0.75) for FNBMD alone (FNBMD superior to FRAX, P = .01; and Garvan, P = .01). Among men, AUC was 0.71 (95% CI, 0.66-0.75) for FRAX, 0.76 (95% CI, 0.72-0.81) for Garvan, and 0.77 (95% CI, 0.72-0.81) for FNBMD alone (P < .001 Garvan and FNBMD alone superior to FRAX). Among both sexes, Garvan greatly overestimated hip fracture risk among individuals in upper quintiles of predicted risk, while FRAX modestly underestimated risk among those in intermediate quintiles of predicted risk.

Conclusions and Relevance

In this prognostic study of adults aged 80 years and older, FRAX and Garvan tools incorporating FNBMD compared with FNBMD alone did not improve 5-year hip fracture discrimination. FRAX modestly underpredicted observed hip fracture probability in intermediate-risk individuals. Garvan markedly overpredicted observed hip fracture probability in high-risk individuals. Until better prediction tools are available, clinicians should prioritize consideration of hip BMD, life expectancy, and patient preferences in decision-making regarding drug treatment initiation for hip fracture prevention in late-life adults.

Balancing fracture risk versus risk of mortality before fracture among women aged 80 years or older

BACKGROUND

Most fractures occur in women aged ≥80 years but competing mortality unrelated to fracture may limit the benefit of osteoporosis drug therapy for some women in late life. Our primary aim was to develop separate prediction models for non-spine fracture (NSF) and mortality before fracture to identify subsets of women with varying fracture versus mortality risks.

METHODS

Separate prediction models were developed for NSF and mortality before NSF for 4895 women aged ≥80 years enrolled in the Study of Osteoporotic Fractures (SOF) or the Health Aging and Body Composition (HABC) study. Proportional hazards models modified to account for competing mortality were used to identify candidate risk factors for each outcome. Predictors associated with NSF or mortality (p < 0.2) were included in separate competing risk models to estimate the cumulative incidence of NSF and mortality before NSF during 5 years of follow-up. This process was repeated to develop separate prediction models for hip fracture and mortality before hip fracture.

RESULTS

Significant predictors of NSF (race, total hip BMD, grip strength, prior fracture, falls, and use of selective serotonin reuptake inhibitors, benzodiazepines, or oral/transdermal estrogen) differed from predictors of mortality before NSF (age, walking speed, multimorbidity, weight change, shrinking, smoking, self-rated health, dementia, and use of warfarin). Within nine subsets of women defined by tertiles of risk, 5-year outcomes varied from 28% NSF and 8% mortality in the high-risk NSF/low-risk mortality subset, to 9% NSF and 22% mortality in the low-risk NSF/high-risk mortality subset. Similar results were seen for predictors of hip fracture and mortality before hip fracture.

CONCLUSION

Considerable variation in 5-year competing mortality risk is present among women in late life with similar 5-year NSF risk. Both fracture risk and life expectancy should inform shared clinical decision-making regarding initiation or continuation of osteoporosis drug therapy for women aged ≥80 years.

The implications of competing risks and direct treatment disutility in cardiovascular disease and osteoporotic fracture: risk prediction and cost effectiveness analysis

Background

Clinical guidelines commonly recommend preventative treatments for people above a risk threshold. Therefore, decision-makers must have faith in risk prediction tools and model-based cost-effectiveness analyses for people at different levels of risk. Two problems that arise are inadequate handling of competing risks of death and failing to account for direct treatment disutility (i.e. the hassle of taking treatments). We explored these issues using two case studies: primary prevention of cardiovascular disease using statins and osteoporotic fracture using bisphosphonates.

Objectives

Externally validate three risk prediction tools [QRISK®3, QRISK®-Lifetime, QFracture-2012 (ClinRisk Ltd, Leeds, UK)]; derive and internally validate new risk prediction tools for cardiovascular disease [competing mortality risk model with Charlson Comorbidity Index (CRISK-CCI)] and fracture (CFracture), accounting for competing-cause death; quantify direct treatment disutility for statins and bisphosphonates; and examine the effect of competing risks and direct treatment disutility on the cost-effectiveness of preventative treatments.

Design, participants, main outcome measures, data sources

Discrimination and calibration of risk prediction models (Clinical Practice Research Datalink participants: aged 25-84 years for cardiovascular disease and aged 30-99 years for fractures); direct treatment disutility was elicited in online stated-preference surveys (people with/people without experience of statins/bisphosphonates); costs and quality-adjusted life-years were determined from decision-analytic modelling (updated models used in National Institute for Health and Care Excellence decision-making).

Results

CRISK-CCI has excellent discrimination, similar to that of QRISK3 (Harrell's c = 0.864 vs. 0.865, respectively, for women; and 0.819 vs. 0.834, respectively, for men). CRISK-CCI has systematically better calibration, although both models overpredict in high-risk subgroups. People recommended for treatment (10-year risk of ≥ 10%) are younger when using QRISK-Lifetime than when using QRISK3, and have fewer observed events in a 10-year follow-up (4.0% vs. 11.9%, respectively, for women; and 4.3% vs. 10.8%, respectively, for men). QFracture-2012 underpredicts fractures, owing to under-ascertainment of events in its derivation. However, there is major overprediction among people aged 85-99 years and/or with multiple long-term conditions. CFracture is better calibrated, although it also overpredicts among older people. In a time trade-off exercise (n = 879), statins exhibited direct treatment disutility of 0.034; for bisphosphonates, it was greater, at 0.067. Inconvenience also influenced preferences in best-worst scaling (n = 631). Updated cost-effectiveness analysis generates more quality-adjusted life-years among people with below-average cardiovascular risk and fewer among people with above-average risk. If people experience disutility when taking statins, the cardiovascular risk threshold at which benefits outweigh harms rises with age (≥ 8% 10-year risk at 40 years of age; ≥ 38% 10-year risk at 80 years of age). Assuming that everyone experiences population-average direct treatment disutility with oral bisphosphonates, treatment is net harmful at all levels of risk.

Limitations

Treating data as missing at random is a strong assumption in risk prediction model derivation. Disentangling the effect of statins from secular trends in cardiovascular disease in the previous two decades is challenging. Validating lifetime risk prediction is impossible without using very historical data. Respondents to our stated-preference survey may not be representative of the population. There is no consensus on which direct treatment disutilities should be used for cost-effectiveness analyses. Not all the inputs to the cost-effectiveness models could be updated.

Conclusions

Ignoring competing mortality in risk prediction overestimates the risk of cardiovascular events and fracture, especially among older people and those with multimorbidity. Adjustment for competing risk does not meaningfully alter cost-effectiveness of these preventative interventions, but direct treatment disutility is measurable and has the potential to alter the balance of benefits and harms. We argue that this is best addressed in individual-level shared decision-making.

Study registration

This study is registered as PROSPERO CRD42021249959.

Funding

This award was funded by the National Institute for Health and Care Research (NIHR) Health and Social Care Delivery Research programme (NIHR award ref: 15/12/22) and is published in full in Health and Social Care Delivery Research; Vol. 12, No. 4. See the NIHR Funding and Awards website for further award information.

A Risk Assessment Tool for Predicting Fragility Fractures in People with HIV: Derivation and Internal Validation of the FRESIA Model

People with HIV have a higher risk of fracture than the general population. Because of the low performance of the existing prediction tools, there is controversy surrounding fracture risk estimation in this population. The aim of the study was to develop a model for predicting the long-term risk of fragility fractures in people with HIV. We included 11,899 individuals aged ≥30 years from the Spanish HIV/AIDS research network cohort. We identified incident fragility fractures from medical records, defined as nontraumatic or those occurring after a casual fall, at major osteoporotic sites (hip, clinical spine, forearm, proximal humerus). Our model accounted for the competing risk of death and included 12 candidate predictors to estimate the time to first fragility fracture. We assessed the discrimination and calibration of the model and compared it with the FRAX tool. The incidence rate of fragility fractures was 4.34 (95% CI 3.61 to 5.22) per 1000 person-years. The final prediction model included age, chronic kidney disease, and chronic obstructive pulmonary disease as significant predictors. The model accurately predicted the 5- and 10-year risk of fragility fractures, with an area under the receiving operator characteristic curve of 0.768 (95% CI 0.722 to 0.814) and agreement between the observed and expected probabilities. Furthermore, it demonstrated better discrimination and calibration than the FRAX tool, improving the classification of over 35% of individuals with fragility fractures compared to FRAX. Our prediction model demonstrated accuracy in predicting the long-term risk of fragility fractures. It can assist in making personalized intervention decisions for individuals with HIV and could potentially replace the current tools recommended for fracture risk assessment in this population. © 2023 The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR).