Christian Kruse

Continuous and long-term treatment is more important than dosage for the protective effect of thiazide use on bone metabolism and fracture risk

Data from observational studies have suggested that thiazide diuretics protect against fractures. Few studies have investigated time frames from initiation of treatment to fracture occurrence.

Predicting mortality and incident immobility in older Belgian men by characteristics related to sarcopenia and frailty

SummaryThere is an increasing awareness of sarcopenia in older people. We applied machine learning principles to predict mortality and incident immobility in older Belgian men through sarcopenia and frailty characteristics. Mortality could be predicted with good accuracy. Serum 25-hydroxyvitamin D and bone mineral density scores were the most important predictors.IntroductionMachine learning principles were used to predict 5-year mortality and 3-year incident severe immobility in a population of older men by frailty and sarcopenia characteristics.MethodsUsing prospective data from 1997 on 264 older Belgian men (n = 152 predictors), 29 statistical models were developed and tuned on 75% of data points then validated on the remaining 25%. The model with the highest test area under the curve (AUC) was chosen as the best. From these, ranked predictor importance was extracted.ResultsFive-year mortality could be predicted with good accuracy (test AUC of .85 [.73; .97], sensitivity 78%, specificity 89% at a probability cut-off of 22.3%) using a Bayesian generalized linear model. Three-year incident severe immobility could be predicted with fair accuracy (test AUC .74 [.57; .91], sensitivity 67%, specificity 78% at a probability cut-off of 14.2%) using a multivariate adaptive regression splines model. Serum 25-hydroxyvitamin D levels and hip bone mineral density scores were the most important predictors of mortality, while biochemical androgen markers and Short-Form 36 Physical Domain questions were the most important predictors of immobility. Sarcopenia assessed by lean mass estimates was relevant to mortality prediction but not immobility prediction.ConclusionsUsing advanced statistical models and a machine learning approach 5-year mortality can be predicted with good accuracy using a Bayesian generalized linear model and 3-year incident severe immobility with fair accuracy using a multivariate adaptive regression splines model.

The New Possibilities from “Big Data” to Overlooked Associations Between Diabetes, Biochemical Parameters, Glucose Control, and Osteoporosis

Purpose of ReviewTo review current practices and technologies within the scope of “Big Data” that can further our understanding of diabetes mellitus and osteoporosis from large volumes of data. “Big Data” techniques involving supervised machine learning, unsupervised machine learning, and deep learning image analysis are presented with examples of current literature.Recent FindingsSupervised machine learning can allow us to better predict diabetes-induced osteoporosis and understand relative predictor importance of diabetes-affected bone tissue. Unsupervised machine learning can allow us to understand patterns in data between diabetic pathophysiology and altered bone metabolism. Image analysis using deep learning can allow us to be less dependent on surrogate predictors and use large volumes of images to classify diabetes-induced osteoporosis and predict future outcomes directly from images.Summary“Big Data” techniques herald new possibilities to understand diabetes-induced osteoporosis and ascertain our current ability to classify, understand, and predict this condition.

Associations between trabecular bone score and biochemistry in surgically vs conservatively treated outpatients with primary hyperparathyroidism: A retrospective cohort study

Purpose Trabecular Bone Score (TBS) is a software-based method for indirect assessment of trabecular bone structure of the spine, based on analysis of pixels in dual energy x-ray absorptiometry (DXA) images. Few studies describe the use of TBS in patients with primary hyperparathyroidism (PHPT). This study aimed at further describing this relationship, investigating possible correlations between biochemistry, body mass index (BMI), fracture incidence and TBS. Methods Cross-sectional study of 195 patients with verified PHPT, surgically (27) or conservatively (168) treated at the Department of Endocrinology, Aalborg University Hospital. TBS was acquired by reanalyzing DXA-images of the included subjects from the outpatient clinic. Biochemical variables were obtained from clinical routine blood samples taken in relation to the DXA-scans. History of fractures and medical history was obtained from radiology reports and medical charts. Results Patients with active PHPT had a TBS-score signifying a partly degraded bone structure, whereas surgically treated patients had a normal bone structure as judged by TBS, though the difference in TBS-score was not statistically significant. Use of antiresorptive treatment was negatively associated with BMD but not TBS. No correlations between the biochemical variables and TBS were found. A negative correlation between TBS and BMI in patients with PHPT was present. Patients experiencing a fragility fracture had a significantly lowered TBS, BMD and T-Score. Conclusion Biochemistry does not seem to predict bone status in terms of TBS in patients with PHPT. TBS is negatively correlated to BMI, which is also seen in patients not suffering from PHPT. The lack of a predictive value for antiresorptive treatment for TBS may raise concern. TBS appears to have a predictive value when assessing risk of fracture in patients with PHPT. Mini abstract This cross-sectional study investigates possible correlations between biochemical variables, body mass index (BMI) and trabecular bone score (TBS) in 195 patients with primary hyperparathyroidism. It finds no correlation between biochemical variables and TBS, but finds a negative correlation between TBS and BMI and a clear association between fracture incidence and low TBS-score.