Performance of the Garvan Fracture Risk Calculator in Individuals with Diabetes: A Registry-Based Cohort Study

Naïve Bayes is an interpretable and predictive machine learning algorithm in predicting osteoporotic hip fracture in-hospital mortality compared to other machine learning algorithms

Osteoporotic hip fractures (HFs) in the elderly are a pertinent issue in healthcare, particularly in developed countries such as Australia. Estimating prognosis following admission remains a key challenge. Current predictive tools require numerous patient input features including those unavailable early in admission. Moreover, attempts to explain machine learning [ML]-based predictions are lacking. Seven ML prognostication models were developed to predict in-hospital mortality following minimal trauma HF in those aged ≥ 65 years of age, requiring only sociodemographic and comorbidity data as input. Hyperparameter tuning was performed via fractional factorial design of experiments combined with grid search; models were evaluated with 5-fold cross-validation and area under the receiver operating characteristic curve (AUROC). For explainability, ML models were directly interpreted as well as analysed with SHAP values. Top performing models were random forests, naïve Bayes [NB], extreme gradient boosting, and logistic regression (AUROCs ranging 0.682-0.696, p>0.05). Interpretation of models found the most important features were chronic kidney disease, cardiovascular comorbidities and markers of bone metabolism; NB also offers direct intuitive interpretation. Overall, NB has much potential as an algorithm, due to its simplicity and interpretability whilst maintaining competitive predictive performance.

Chronic Kidney Disease in Patients with Hip Fracture: Prevalence and Outcomes

Objective. Although the association between chronic kidney disease (CKD) and osteoporotic fractures is well established, data on CKD combined with hip fracture (HF) are scarce and controversial. We aimed to assess in patients with HF the prevalence of CKD, its impact on hospital mortality and length of stay (LOS) and to determine the prognostic value of CKD to predict hospital outcomes. Methods. Prospectively collected clinical data were analysed in 3623 consecutive HF patients aged ≥65 years (mean age 83.4 ± 7.50 [standard deviation] years; 74.4% females). Results. CKD among older patients with HF is highly prevalent (39.9%), has different clinical characteristics, a 2.5-fold higher mortality rate, and 40% greater risk of prolonged LOS. The strongest risk for a poor outcome was advanced age (>80 years). The risk of death substantially increases in combination with chronic disorders, especially coronary artery disease, anaemia, hyperparathyroidism, and atrial fibrillation; models based only on three variables—CKD stage, age >80, and presence of a specific chronic condition—predicted in-hospital death with good discrimination capability (AUC ≥ 0.700) and reasonable accuracy, the number needed to predict ranged between 5.7 and 14.5. Only 12% of HF patients received osteoporotic drugs prefracture. Conclusion. In HF patients with CKD, the risk of adverse outcomes largely increases in parallel with worsening kidney function and, especially, in combination with comorbidities; models based on three admission variables predict a fatal outcome. Assessment of renal function is essential to preventing osteoporotic fractures.

Diagnosing Osteoporosis in Diabetes-A Systematic Review on BMD and Fractures

PURPOSE OF REVIEW

Recently, the American Diabetes Association updated the 2024 guidelines for Standards of Care in Diabetes and recommend that a T-score of - 2.0 in patients with diabetes should be interpreted as equivalent to - 2.5 in people without diabetes. We aimed to evaluate the most recent findings concerning the bone mineral density (BMD)-derived T-score and risk of fractures related to osteoporosis in subjects with diabetes.

RECENT FINDINGS

The dual-energy X-ray absorptiometry (DXA) scan is the golden standard for evaluating BMD. The BMD-derived T-score is central to fracture prediction and signifies both diagnosis and treatment for osteoporosis. However, the increased fracture risk in diabetes is not sufficiently explained by the T-score, complicating the identification and management of fracture risk in these patients. Recent findings agree that subjects with type 2 diabetes (T2D) have a higher T-score and higher fracture risk compared with subjects without diabetes. However, the actual number of studies evaluating the direct association of higher fracture risk at higher T-score levels is scant. Some studies support the adjustment based on the 0.5 BMD T-score difference between subjects with T2D and subjects without diabetes. However, further data from longitudinal studies is warranted to validate if the T-score treatment threshold necessitates modification to prevent fractures in subjects with diabetes.

Femoral bone mineral density at the time of hip fracture is higher in women with versus without type 2 diabetes mellitus: a cross-sectional study

PURPOSE

To compare femoral bone mineral density (BMD) levels in hip-fracture women with versus without type 2 diabetes mellitus (T2DM). We hypothesized that BMD levels could be higher in the women with T2DM than in controls and we aimed to quantify the BMD discrepancy associated with the presence of T2DM.

METHODS

At a median of 20 days after the occurrence of an original hip fracture due to fragility we measured BMD by dual-energy x-ray absorptiometry at the non-fractured femur.

RESULTS

We studied 751 women with subacute hip fracture. Femoral BMD was significantly higher in the 111 women with T2DM than in the 640 without diabetes: mean T-score between-group difference was 0.50, (95% CI from 0.30 to 0.69, P < 0.001). The association between the presence of T2DM and femoral BMD persisted after adjustment for age, body mass index, hip-fracture type, neurologic diseases, parathyroid hormone, 25-hydroxyvitamin D and estimated glomerular filtration rate (P < 0.001). For a woman without versus with T2DM, the adjusted odds ratio to have a femoral BMD T-score below the threshold of - 2.5 was 2.13 (95% CI from 1.33 to 3.42, P = 0.002).

CONCLUSIONS

Fragility fractures of the hip occurred in women with T2DM at a femoral BMD level higher than in control women. In the clinical assessment of fracture risk, we support the adjustment based on the 0.5 BMD T-score difference between women with and without T2DM, although further data from robust longitudinal studies is needed to validate the BMD-based adjustment of fracture risk estimation.

AI algorithms for accurate prediction of osteoporotic fractures in patients with diabetes: an up-to-date review

Osteoporotic fractures impose a substantial burden on patients with diabetes due to their unique characteristics in bone metabolism, limiting the efficacy of conventional fracture prediction tools. Artificial intelligence (AI) algorithms have shown great promise in predicting osteoporotic fractures. This review aims to evaluate the application of traditional fracture prediction tools (FRAX, QFracture, and Garvan FRC) in patients with diabetes and osteoporosis, review AI-based fracture prediction achievements, and assess the potential efficiency of AI algorithms in this population. This comprehensive literature search was conducted in Pubmed and Web of Science. We found that conventional prediction tools exhibit limited accuracy in predicting fractures in patients with diabetes and osteoporosis due to their distinct bone metabolism characteristics. Conversely, AI algorithms show remarkable potential in enhancing predictive precision and improving patient outcomes. However, the utilization of AI algorithms for predicting osteoporotic fractures in diabetic patients is still in its nascent phase, further research is required to validate their efficacy and assess the potential advantages of their application in clinical practice.

Machine learning algorithms for predicting the risk of fracture in patients with diabetes in China

Background

Patients with diabetes are more likely to be predisposed to fractures compared to those without diabetes. In clinical practice, predicting fracture risk in diabetics is still difficult because of the limited availability and accessibility of existing fracture prediction tools in the diabetic population. The purpose of this study was to develop and validate models using machine learning (ML) algorithms to achieve high predictive power for fracture in patients with diabetes in China.

Methods

In this study, the clinical data of 775 hospitalized patients with diabetes was analyzed by using Decision Tree (DT), Gradient Boosting Decision Tree (GBDT), Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost) and Probabilistic Classification Vector Machines (PCVM) algorithms to construct risk prediction models for fractures. Moreover, the risk factors for diabetes-related fracture were identified by the feature selection algorithms.

Results

The ML algorithms extracted 17 most relevant factors from raw clinical data to maximize the accuracy of the prediction results, including bone mineral density, age, sex, weight, high-density lipoprotein cholesterol, height, duration of diabetes, total cholesterol, osteocalcin, N-terminal propeptide of type I, diastolic blood pressure, and body mass index. The 7 ML models including LR, SVM, RF, DT, GBDT, XGBoost, and PCVM had f1 scores of 0.75, 0.83, 0.84, 0.85, 0.87, 0.88, and 0.97, respectively.

Conclusions

This study identified 17 most relevant risk factors for diabetes-related fracture using ML algorithms. And the PCVM model proved to perform best in predicting the fracture risk in the diabetic population. This work proposes a cheap, safe, and extensible ML algorithm for the precise assessment of risk factors for diabetes-related fracture.

Fracture prediction tools in diabetes

PURPOSE OF REVIEW

Type 1 (T1D) and 2 diabetes (T2D) are associated with increased risk of fracture independent of bone mineral density (BMD). Fracture risk prediction tools can identify individuals at highest risk, and therefore, most likely to benefit from antifracture therapy. This review summarizes recent advances in fracture prediction tools as applied to individuals with diabetes.

RECENT FINDINGS

The Fracture Risk Assessment (FRAX) tool, Garvan Fracture Risk Calculator (FRC), and QFracture tool are validated tools for fracture risk prediction. FRAX is most widely used internationally, and considers T1D (but not T2D) under secondary osteoporosis disorders. FRAX underestimates fracture risk in both T1D and T2D. Trabecular bone score and other adjustments for T2D-associated risk improve FRAX-based estimations. Similar adjustments for T1D are not identified. Garvan FRC does not incorporate diabetes as an input but does includes falls. Garvan FRC slightly underestimates osteoporotic fracture risk in women with diabetes. QFracture incorporates both T1D and T2D and falls as input variables, but has not been directly validated in individuals with diabetes.

SUMMARY

Further research is needed to validate and compare available fracture prediction tools and their performance in individuals with diabetes.