Artificial intelligence on the identification of risk groups for osteoporosis, a general review

High versus Low-Intensity Resistance Training on Bone Mineral Density and Content Acquisition by Postmenopausal Women with Osteopenia: A Randomized Controlled Trial

Background

The menopause stage in women reduces estrogen levels and bone indicators. This study compared the effects of high-intensity resistance training (HIRT) and low-intensity resistance training (LIRT) on bone mineral density (BMD) and bone mineral content (BMC), T-score, and Z-score in postmenopausal women with osteopenia.

Methods

A randomized controlled trial was conducted among 45 postmenopausal women, aged 50 to 60, who were randomly assigned into 3 parallel groups (n = 15 in each). The exercise program was performed by the interventional groups-the HIRT and LIRT groups-at 4 different intensities, 3 times a week for 24 weeks: 8 repetitions at 80% of 1 repetition maximum and 16 repetitions at 40% of 1 repetition maximum. The evaluated areas (BMD, BMC, T-score, and Z-score) included the lumbar spine (LS) and the femur neck (FN) using a DEXA machine. One-way analysis of covariance and Bonferroni's post hoc tests were used for data analysis.

Results

The results indicated significant differences in BMD, BMC, T-scores, and Z-scores between the means of the LS and the FN in all groups. In addition, significant differences were revealed in the BMC of the LS, the BMD, T-scores (P < 0.001), Z-scores (P = 0.001), and in the BMC of the FN (P < 0.001), the BMD (P = 0.001), T-scores, and Z-scores (P < 0.001), respectively. In addition, the HIRT group's bone indices were considerably greater than those of the LIRT group (P < 0.00). Nonetheless, LIRT was significantly greater than that of the control group (P > 0.00).

Conclusion

According to the current findings, HIRT seems to be the most effective training program compared with LIRT for bone indicators improvement in the femur neck and the lumbar spine among postmenopausal women with osteopenia.

A novel primary osteoporosis screening tool (POST) for adults aged 50 years and over

PURPOSE

This study aimed to develop and validate a simple primary osteoporosis screening tool (POST) based on adults aged 50 years and older.

METHODS

This study included participants aged ≥50 from the National Health and Nutrition Examination Survey. Osteoporosis was defined according to bone mineral density values. The POST was developed based on methods from previous studies. Moreover, we plotted the receiver operating characteristic curves to calculate the area under the curve (AUC) and determine the optimal cut-off value according to the weighted Youden index. In addition, we compared the performances in identifying individuals with osteoporosis between the POST and the Osteoporosis Self-assessment Tool (OST). Finally, we also assessed the performance of the POST in the Chinese population.

RESULTS

Finally, a total of 6665 individuals were included in this study. The AUC values of the POST for identifying individuals with osteoporosis in the development cohort and the validation cohort were 0.81 (95% CI: 0.79-0.83) and 0.81 (95% CI: 0.77-0.84), respectively. Moreover, a POST-score ≥7 was determined as the threshold to identify individuals with osteoporosis, in which the sensitivity was greater than 90%. In addition, the POST showed significantly higher sensitivity than the OST. Finally, the POST showed an AUC of 0.75 (95% CI: 0.65-0.85) among 94 Chinese subjects aged ≥50 years old.

CONCLUSIONS

POST is a convenient and effective tool for osteoporosis screening among adults aged 50 years and over, which might provide new methodological support for future osteoporosis screening.

Applications of Artificial Intelligence Methods for the Prediction of Osteoporotic Fractures

Background: Osteoporosis is a socio-economic problem of modern aging societies. Bone fractures and the related treatments generate the highest costs. The occurrence of osteoporotic fractures is a cause of chronic disability, many complications, reduced quality of life, and often premature death. Aim of the study: The aim of the study was to determine which of the patient's potential risk factors pertaining to various diseases and lifestyle have an essential impact on the occurrence of low-energy fractures and the hierarchy of these factors. Methods: The study was retrospective. The documentation of 222 patients (206 women and 16 men) from an osteoporosis treatment clinic in Łódź, Poland was analyzed. Each patient was described by a vector consisting of 27 features, where each feature was a different risk factor. Using artificial neural networks, an attempt was made to create a model that, based on the available data, would be able to predict whether the patient would be exposed to low-energy fractures. We developed a neural network model that achieved the best result for the testing data. In addition, we used other methods to solve the classification problem, i.e., correctly dividing patients into two groups: those with fractures and those without fractures. These methods were logistic regression, k-nearest neighbors and SVM. Results: The obtained results gave us the opportunity to assess the effectiveness of various methods and the importance of the features describing patients. Using logistic regression and the recursive elimination of features, a ranking of risk factors was obtained in which the most important were age, chronic kidney disease, neck T-score, and serum phosphate level. Then, we repeated the learning procedure of the neural network considering only these four most important features. The average mean squared error on the test set was about 27% for the best variant of the model. Conclusions: The comparison of the rankings with different numbers of patients shows that the applied method is very sensitive to changes in the considered data (adding new patients significantly changes the result). Further cohort studies with more patients and more advanced methods of machine learning may be needed to identify other significant risk factors and to develop a reliable fracture risk system. The obtained results may contribute to the improved identification patients at risk of low-energy fractures and early implementation of comprehensive treatment.

Osteoporosis screening using machine learning and electromagnetic waves

Osteoporosis is a disease characterized by impairment of bone microarchitecture that causes high socioeconomic impacts in the world because of fractures and hospitalizations. Although dual-energy X-ray absorptiometry (DXA) is the gold standard for diagnosing the disease, access to DXA in developing countries is still limited due to its high cost, being present only in specialized hospitals. In this paper, we analyze the performance of Osseus, a low-cost portable device based on electromagnetic waves that measures the attenuation of the signal that crosses the medial phalanx of a patient's middle finger and was developed for osteoporosis screening. The analysis is carried out by predicting changes in bone mineral density using Osseus measurements and additional common risk factors used as input features to a set of supervised classification models, while the results from DXA are taken as target (real) values during the training of the machine learning algorithms. The dataset consisted of 505 patients who underwent osteoporosis screening with both devices (DXA and Osseus), of whom 21.8% were healthy and 78.2% had low bone mineral density or osteoporosis. A cross-validation with k-fold = 5 was considered in model training, while 20% of the whole dataset was used for testing. The obtained performance of the best model (Random Forest) presented a sensitivity of 0.853, a specificity of 0.879, and an F1 of 0.859. Since the Random Forest (RF) algorithm allows some interpretability of its results (through the impurity check), we were able to identify the most important variables in the classification of osteoporosis. The results showed that the most important variables were age, body mass index, and the signal attenuation provided by Osseus. The RF model, when used together with Osseus measurements, is effective in screening patients and facilitates the early diagnosis of osteoporosis. The main advantages of such early screening are the reduction of costs associated with exams, surgeries, treatments, and hospitalizations, as well as improved quality of life for patients.

Development of Machine Learning Models for Predicting Osteoporosis in Patients with Type 2 Diabetes Mellitus-A Preliminary Study

Purpose

Diagnosing osteoporosis in T2DM based on bone mineral density (BMD) remains challenging. We sought to develop prediction models employing machine learning algorithms for use as screening instruments for osteoporosis in T2DM patients.

Patients and Methods

Data were collected from 433 participants and analyzed using nine categorical machine learning algorithms to select features based on demographic and clinical variables. Multiple classification models were compared using the area under the receiver operating characteristic curve (ROC-AUC), accuracy, sensitivity, specificity, the average precision (AP), precision, F1 score, precision-recall curves, calibration plots, and decision curve analysis (DCA) to determine the best model. In addition, 5-fold cross-validation was utilized to optimize the model, followed by an evaluation of feature significance using Shapley Additive exPlanations (SHAP). Using latent class analysis (LCA), distinct subpopulations were identified by constructing several discrete clusters.

Results

In this study, nine feature variables were identified to construct predictive models for osteoporosis in individuals with T2DM. The machine learning algorithms achieved an AP range of 0.444-1.000. The XGBoost model was selected as the final prediction model with an AUROC of 0.940 in the training set, 0.772 in the validation set for 5-fold cross-validation, and 0.872 in the test set. Using SHAP methodology, 25(OH)D was identified as the most important risk factor. Additionally, a 3-Class model was constructed using LCA, which categorized individuals into high, medium, and low-risk groups.

Conclusion

Our study developed a predictive model with high accuracy and clinical validity for predicting osteoporosis in type 2 diabetes patients. We also identified three subpopulations with varying osteoporosis risk using clustering. However, limited sample size warrants cautious interpretation of results, and validation in larger cohorts is needed.

Development and Validation of a New Clinical Diagnostic Screening Model for Osteoporosis in Postmenopausal Women

BACKGROUND

Age and weight are not only strong predictive parameters for osteoporosis diagnosis but can also be easily acquired from patients. This study aimed to develop and validate a new diagnostic screening model for postmenopausal osteoporosis that uses only 2 parameters, viz., age and weight. The discriminative ability of the model was analyzed and compared with that of the osteoporosis self-assessment tool for Asians (OSTA) index.

METHODS

The age-weight diagnostic screening model was developed using a retrospective chart review of postmenopausal women aged ≥50 years who underwent dual energy X-ray absorptiometry at a tertiary hospital from November 2017 to April 2022. Logistic regression analysis was used to derive a diagnostic screening model for osteoporosis.

RESULTS

A total of 533 postmenopausal women were included in the study. According to the highest Youden index value, a probability cut-off value of 0.298 was used in the diagnosis screening model at any site, which yielded a sensitivity of 84.3% and a specificity of 53.8%. For increased sensitivity as a screening tool, a cut-off value of 0.254 was proposed to obtain a sensitivity of 90.2% and a specificity of 42.2%. The area under receiver operating characteristic curves from all screening models were significantly higher than those from the OSTA index model (p<0.05).

CONCLUSIONS

This study showed the feasibility of a postmenopausal osteoporosis diagnostic screening model that uses 2 strong predictors for osteoporosis diagnosis: age and weight. This age-weight diagnostic model is a simple, effective option in postmenopausal osteoporosis screening.

Machine learning applied to HR-pQCT images improves fracture discrimination provided by DXA and clinical risk factors

BACKGROUND

Traditional analysis of High Resolution peripheral Quantitative Computed Tomography (HR-pQCT) images results in a multitude of cortical and trabecular parameters which would be potentially cumbersome to interpret for clinicians compared to user-friendly tools utilising clinical parameters. A computer vision approach (by which the entire scan is 'read' by a computer algorithm) to ascertain fracture risk, would be far simpler. We therefore investigated whether a computer vision and machine learning technique could improve upon selected clinical parameters in assessing fracture risk.

METHODS

Participants of the Hertfordshire Cohort Study (HCS) attended research visits at which height and weight were measured; fracture history was determined via self-report and vertebral fracture assessment. Bone microarchitecture was assessed via HR-pQCT scans of the non-dominant distal tibia (Scanco XtremeCT), and bone mineral density measurement and lateral vertebral assessment were performed using dual-energy X-ray absorptiometry (DXA) (Lunar Prodigy Advanced). Images were cropped, pre-processed and texture analysis was performed using a three-dimensional local binary pattern method. These image data, together with age, sex, height, weight, BMI, dietary calcium and femoral neck BMD, were used in a random-forest classification algorithm. Receiver operating characteristic (ROC) analysis was used to compare fracture risk identification methods.

RESULTS

Overall, 180 males and 165 females were included in this study with a mean age of approximately 76 years and 97 (28 %) participants had sustained a previous fracture. Using clinical risk factors alone resulted in an area under the curve (AUC) of 0.70 (95 % CI: 0.56-0.84), which improved to 0.71 (0.57-0.85) with the addition of DXA-measured BMD. The addition of HR-pQCT image data to the machine learning classifier with clinical risk factors and DXA-measured BMD as inputs led to an improved AUC of 0.90 (0.83-0.96) with a sensitivity of 0.83 and specificity of 0.74.

CONCLUSION

These results suggest that using a three-dimensional computer vision method to HR-pQCT scanning may enhance the identification of those at risk of fracture beyond that afforded by clinical risk factors and DXA-measured BMD. This approach has the potential to make the information offered by HR-pQCT more accessible (and therefore) applicable to healthcare professionals in the clinic if the technology becomes more widely available.

Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter Study

Although the number of patients with osteoporosis is increasing worldwide, diagnosis and treatment are presently inadequate. In this study, we developed a deep learning model to predict bone mineral density (BMD) and T-score from chest X-rays, which are one of the most common, easily accessible, and low-cost medical imaging examination methods. The dataset used in this study contained patients who underwent dual-energy X-ray absorptiometry (DXA) and chest radiography at six hospitals between 2010 and 2021. We trained the deep learning model through ensemble learning of chest X-rays, age, and sex to predict BMD using regression and T-score for multiclass classification. We assessed the following two metrics to evaluate the performance of the deep learning model: (1) correlation between the predicted and true BMDs and (2) consistency in the T-score between the predicted class and true class. The correlation coefficients for BMD prediction were hip = 0.75 and lumbar spine = 0.63. The areas under the curves for the T-score predictions of normal, osteopenia, and osteoporosis diagnoses were 0.89, 0.70, and 0.84, respectively. These results suggest that the proposed deep learning model may be suitable for screening patients with osteoporosis by predicting BMD and T-score from chest X-rays.

Osteoporosis in 10 years time: a glimpse into the future of osteoporosis

Patients living with osteoporosis are projected to increase dramatically in the next decade. Alongside the forecasted increased societal and economic burden, we will live a crisis of fractures. However, we will have novel pharmacological treatment to face this crisis and, more importantly, new optimized treatment strategies. Fracture liaison services will be probably implemented on a large scale worldwide, helping to prevent additional fractures in high-risk patients. In the next decade, novel advances in the diagnostic tools will be largely available. Moreover, new and more precise fracture risk assessment tools will change our ability to detect patients at high risk of fractures. Finally, big data and artificial intelligence will help us to move forward into the world of precision medicine. In the present review, we will discuss the future epidemiology and costs of osteoporosis, the advances in early and accurate diagnosis of osteoporosis, with a special focus on biomarkers and imaging tools. Then we will examine new and refined fracture risk assessment tools, the role of fracture liaison services, and a future perspective on osteoporosis treatment.

A hierarchical opportunistic screening model for osteoporosis using machine learning applied to clinical data and CT images

Background

Osteoporosis is a common metabolic skeletal disease and usually lacks obvious symptoms. Many individuals are not diagnosed until osteoporotic fractures occur. Bone mineral density (BMD) measured by dual-energy X-ray absorptiometry (DXA) is the gold standard for osteoporosis detection. However, only a limited percentage of people with osteoporosis risks undergo the DXA test. As a result, it is vital to develop methods to identify individuals at-risk based on methods other than DXA.

Results

We proposed a hierarchical model with three layers to detect osteoporosis using clinical data (including demographic characteristics and routine laboratory tests data) and CT images covering lumbar vertebral bodies rather than DXA data via machine learning. 2210 individuals over age 40 were collected retrospectively, among which 246 individuals’ clinical data and CT images are both available. Irrelevant and redundant features were removed via statistical analysis. Consequently, 28 features, including 16 clinical data and 12 texture features demonstrated statistically significant differences (p < 0.05) between osteoporosis and normal groups. Six machine learning algorithms including logistic regression (LR), support vector machine with radial-basis function kernel, artificial neural network, random forests, eXtreme Gradient Boosting and Stacking that combined the above five classifiers were employed as classifiers to assess the performances of the model. Furthermore, to diminish the influence of data partitioning, the dataset was randomly split into training and test set with stratified sampling repeated five times. The results demonstrated that the hierarchical model based on LR showed better performances with an area under the receiver operating characteristic curve of 0.818, 0.838, and 0.962 for three layers, respectively in distinguishing individuals with osteoporosis and normal BMD.

Conclusions

The proposed model showed great potential in opportunistic screening for osteoporosis without additional expense. It is hoped that this model could serve to detect osteoporosis as early as possible and thereby prevent serious complications of osteoporosis, such as osteoporosis fractures.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04596-z.

Application of Machine Learning to Identify Clinically Meaningful Risk Group for Osteoporosis in Individuals Under the Recommended Age for Dual-Energy X-Ray Absorptiometry

Dual-energy X-ray absorptiometry (DXA) is the gold standard for diagnosing osteoporosis; it is generally recommended in men ≥ 70 and women ≥ 65 years old. Therefore, assessment of clinical risk factors for osteoporosis is very important in individuals under the recommended age for DXA. Here, we examine the diagnostic performance of machine learning-based prediction models for osteoporosis in individuals under the recommended age for DXA examination. Data of 2210 men aged 50-69 and 1099 women aged 50-64 obtained from the Korea National Health and Nutrition Examination Survey IV-V were analyzed. Extreme gradient boosting (XGBoost) was used to find relevant clinical features and applied to three machine learning models: XGBoost, logistic regression, and a multilayer perceptron. For the prediction of osteoporosis, the XGBoost model using the top 20 features extracted from XGBoost showed the most reliable performance with area under the receiver operating characteristic curve (AUROC) of 0.73 and 0.79 in men and women, respectively. We compared the diagnostic accuracy of the Shapley additive explanation values based on a risk-score model obtained from XGBoost and conventional osteoporosis risk assessment tools for prediction of osteoporosis using optimal cut-off values for each model. We observed that a cut-off risk score of ≥ 28 in men and ≥ 47 in women was optimal to classify a positive screening for osteoporosis (an AUROC of 0.86 in men and 0.91 in women). The XGBoost-based osteoporosis-prediction model outperformed conventional risk assessment tools. Therefore, machine learning-based prediction models are a more suitable option than conventional risk assessment methods for screening osteoporosis in individuals under the recommended age for DXA examination.

The influence of antenna gain and beamwidth used in OSSEUS in the screening process for osteoporosis

Applications on electromagnetic waves in the field of biotelemetry have increased in the latest years, being used to prevent, diagnose, and treatment of several diseases. In this context, biotelemetry allows minimally invasive monitoring of the physiologic, improving comfort and patient care and significantly reducing hospital costs. Aiming to assist the mineral bone density classification, through a radio frequency signal (RF), for a later diagnosis of osteoporosis, Osseus was proposed in 2018. This equipment is a combination of the application of techniques and concepts of several areas such as software, electrical, electronic, computational, and biomedical engineering, developed at a low cost, with easy access to the population, and non-invasive. However, when placed on evaluation, potential improvements were identified to increase the stability of Osseus operation. It is proposed the implementation of improvements in the antennas used by Osseus, aiming its miniaturization, improvement in the reception of the RF signal, and better stability of the equipment's operation. Then, two antennas were built, one of which was used as a project for the second, which is an array. The array showed significant improvements in the radiation parameters relevant to the application, being a candidate to replace the antennas currently in use at Osseus.

Machine Learning to Predict the Progression of Bone Mass Loss Associated with Personal Characteristics and a Metabolic Syndrome Scoring Index

A relationship exists between metabolic syndrome (MetS) and human bone health; however, whether the combination of demographic, lifestyle, and socioeconomic factors that are associated with MetS development also simultaneously affects bone density remains unclear. Using a machine learning approach, the current study aimed to estimate the usefulness of predicting bone mass loss using these potentially related factors. The present study included a sample of 23,497 adults who routinely visited a health screening center at a large health center at least once during each of three 3-year stages (i.e., 2006–2008, 2009–2011, and 2012–2014). The demographic, socioeconomic, lifestyle characteristics, body mass index (BMI), and MetS scoring index recorded during the first 3-year stage were used to predict the subsequent occurrence of osteopenia using a non-concurrence design. A concurrent prediction was also performed using the features recorded from the same 3-year stage as the predicted outcome. Machine learning algorithms, including logistic regression (LR), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost), were applied to build predictive models using a unique feature set. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, and F1 score were used to evaluate the predictive performances of the models. The XGBoost model presented the best predictive performance among the non-concurrence models. This study suggests that the ensemble learning model with a MetS severity score can be used to predict the progression of osteopenia. The inclusion of an individual’s features into a predictive model over time is suggested for future studies.

Bone mineral density response prediction following osteoporosis treatment using machine learning to aid personalized therapy

Osteoporosis is a global health problem for ageing populations. The goals of osteoporosis treatment are to improve bone mineral density (BMD) and prevent fractures. One major obstacle that remains a great challenge to achieve the goals is how to select the best treatment regimen for individual patients. We developed a computational model from 8981 clinical variables, including demographic data, diagnoses, laboratory results, medications, and initial BMD results, taken from 10-year period of electronic medical records to predict BMD response after treatment. We trained 7 machine learning models with 13,562 osteoporosis treatment instances [comprising 5080 (37.46%) inadequate treatment responses and 8482 (62.54%) adequate responses] and selected the best model (Random Forests with area under the receiver operating curve of 0.70, accuracy of 0.69, precision of 0.70, and recall of 0.89) to individually predict treatment responses of 11 therapeutic regimens, then selected the best predicted regimen to compare with the actual regimen. The results showed that the average treatment response of the recommended regimens was 9.54% higher than the actual regimens. In summary, our novel approach using a machine learning-based decision support system is capable of predicting BMD response after osteoporosis treatment and personalising the most appropriate treatment regimen for an individual patient.

Application of artificial intelligence in diagnosis of osteoporosis using medical images: a systematic review and meta-analysis

Artificial intelligence (AI) is a potentially reliable assistant in the diagnosis of osteoporosis. This meta-analysis aims to assess the diagnostic accuracy of the AI-based systems using medical images. We searched PubMed and Web of Science from inception to June 15, 2020, for eligible articles that applied AI approaches to diagnosing osteoporosis using medical images. Quality and bias of the included studies were evaluated with the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. The main outcome was the sensitivity and specificity of the performance of the AI-based systems. The data analysis utilized the R Foundation packages of "meta" for univariate analysis and Stata for bivariate analysis. Random effects model was utilized. Seven studies with 3186 patients were included in the meta-analysis. The overall risk of bias of the included studies was assessed as low. The pooled sensitivity was 0.96 (95% CI 0.93-1.00), and the pooled specificity was 0.95 (95% CI 0.91-0.99). However, high heterogeneity was found in this meta-analysis. The results supported that the AI-based systems had good accuracy in diagnosing osteoporosis. However, the high risk of bias in patient selection and high heterogeneity in the meta-analysis made the conclusion less convincing. The application of AI-based systems in osteoporosis diagnosis needs to be further confirmed by more prospective studies in multi-centers including more random samples from complete patient types.

Comparison of cephalometric measurements between conventional and automatic cephalometric analysis using convolutional neural network

Objective

The rapid development of artificial intelligence technologies for medical imaging has recently enabled automatic identification of anatomical landmarks on radiographs. The purpose of this study was to compare the results of an automatic cephalometric analysis using convolutional neural network with those obtained by a conventional cephalometric approach.

Material and methods

Cephalometric measurements of lateral cephalograms from 35 patients were obtained using an automatic program and a conventional program. Fifteen skeletal cephalometric measurements, nine dental cephalometric measurements, and two soft tissue cephalometric measurements obtained by the two methods were compared using paired t test and Bland-Altman plots.

Results

A comparison between the measurements from the automatic and conventional cephalometric analyses in terms of the paired t test confirmed that the saddle angle, linear measurements of maxillary incisor to NA line, and mandibular incisor to NB line showed statistically significant differences. All measurements were within the limits of agreement based on the Bland-Altman plots. The widths of limits of agreement were wider in dental measurements than those in the skeletal measurements.

Conclusions

Automatic cephalometric analyses based on convolutional neural network may offer clinically acceptable diagnostic performance. Careful consideration and additional manual adjustment are needed for dental measurements regarding tooth structures for higher accuracy and better performance.

Machine Learning Solutions for Osteoporosis-A Review

Osteoporosis and its clinical consequence, bone fracture, is a multifactorial disease that has been the object of extensive research. Recent advances in machine learning (ML) have enabled the field of artificial intelligence (AI) to make impressive breakthroughs in complex data environments where human capacity to identify high-dimensional relationships is limited. The field of osteoporosis is one such domain, notwithstanding technical and clinical concerns regarding the application of ML methods. This qualitative review is intended to outline some of these concerns and to inform stakeholders interested in applying AI for improved management of osteoporosis. A systemic search in PubMed and Web of Science resulted in 89 studies for inclusion in the review. These covered one or more of four main areas in osteoporosis management: bone properties assessment (n = 13), osteoporosis classification (n = 34), fracture detection (n = 32), and risk prediction (n = 14). Reporting and methodological quality was determined by means of a 12-point checklist. In general, the studies were of moderate quality with a wide range (mode score 6, range 2 to 11). Major limitations were identified in a significant number of studies. Incomplete reporting, especially over model selection, inadequate splitting of data, and the low proportion of studies with external validation were among the most frequent problems. However, the use of images for opportunistic osteoporosis diagnosis or fracture detection emerged as a promising approach and one of the main contributions that ML could bring to the osteoporosis field. Efforts to develop ML-based models for identifying novel fracture risk factors and improving fracture prediction are additional promising lines of research. Some studies also offered insights into the potential for model-based decision-making. Finally, to avoid some of the common pitfalls, the use of standardized checklists in developing and sharing the results of ML models should be encouraged. © 2021 American Society for Bone and Mineral Research (ASBMR).

Predicting treatment recommendations in postmenopausal osteoporosis

We designed, implemented, and tested a clinical decision support system at the Research Center for the Study of Menopause and Osteoporosis within the University of Ferrara (Italy). As an independent module of our system, we implemented an original machine learning system for rule extraction, enriched with a hierarchical extraction methodology and a novel rule evaluation technique. Such a module is used in everyday operation protocol, and it allows physicians to receive suggestions for prevention and treatment of osteoporosis. In this paper, we design and execute an experiment based on two years of data, in order to evaluate and report the reliability of our suggestion system. Our results are encouraging, and in some cases reach expected accuracies of around 90%.

A feasibility study on microwave imaging of bone for osteoporosis monitoring

The dielectric properties of bones are found to be influenced by the demineralisation of bones. Therefore, microwave imaging (MWI) can be used to monitor in vivo dielectric properties of human bones and hence aid in the monitoring of osteoporosis. This paper presents the feasibility analysis of the MWI device for monitoring osteoporosis. Firstly, the dielectric properties of tissues present in the human heel are analysed. Secondly, a transmission line (TL) formalism approach is adopted to examine the feasible frequency band and the matching medium for MWI of trabecular bone. Finally, simplified numerical modelling of the human heel was set to monitor the penetration of E-field, the received signal strength, and the power loss in a numerical model of the human heel. Based on the TL formalism approach, 0.6-1.9-GHz frequency band is found to feasible for bone imaging purpose. The relative permittivity of the matching medium can be chosen between 15 and 40. The average percentage difference between the received signal for feasible and inconvenient frequency band was found to be 82%. The findings based on the dielectric contrast of tissues in the heel, the feasible frequency band, and the finite difference time domain simulations support the development of an MWI prototype for monitoring osteoporosis.

Deep Learning for Osteoporosis Classification Using Hip Radiographs and Patient Clinical Covariates

This study considers the use of deep learning to diagnose osteoporosis from hip radiographs, and whether adding clinical data improves diagnostic performance over the image mode alone. For objective labeling, we collected a dataset containing 1131 images from patients who underwent both skeletal bone mineral density measurement and hip radiography at a single general hospital between 2014 and 2019. Osteoporosis was assessed from the hip radiographs using five convolutional neural network (CNN) models. We also investigated ensemble models with clinical covariates added to each CNN. The accuracy, precision, recall, specificity, negative predictive value (npv), F1 score, and area under the curve (AUC) score were calculated for each network. In the evaluation of the five CNN models using only hip radiographs, GoogleNet and EfficientNet b3 exhibited the best accuracy, precision, and specificity. Among the five ensemble models, EfficientNet b3 exhibited the best accuracy, recall, npv, F1 score, and AUC score when patient variables were included. The CNN models diagnosed osteoporosis from hip radiographs with high accuracy, and their performance improved further with the addition of clinical covariates from patient records.

Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: A multicenter retrospective cohort study

Osteoporosis is a prevalent but underdiagnosed condition. As compared to dual-energy X-ray absorptiometry (DXA) measures, we aimed to develop a deep convolutional neural network (DCNN) model to classify osteopenia and osteoporosis with the use of lumbar spine X-ray images. Herein, we developed the DCNN models based on the training dataset, which comprising 1616 lumbar spine X-ray images from 808 postmenopausal women (aged 50 to 92 years). DXA-derived bone mineral density (BMD) measures were used as the reference standard. We categorized patients into three groups according to DXA BMD T-score: normal (T ≥ -1.0), osteopenia (-2.5 < T < -1.0), and osteoporosis (T ≤ -2.5). T-scores were calculated by using the BMD dataset of young Chinese female aged 20-40 years as a reference. A 3-class DCNN model was trained to classify normal BMD, osteoporosis, and osteopenia. Model performance was tested in a validation dataset (204 images from 102 patients) and two test datasets (396 images from 198 patients and 348 images from 147 patients respectively). Model performance was assessed by the receiver operating characteristic (ROC) curve analysis. The results showed that in the test dataset 1, the model diagnosing osteoporosis achieved an AUC of 0.767 (95% confidence interval [CI]: 0.701-0.824) with sensitivity of 73.7% (95% CI: 62.3-83.1), the model diagnosing osteopenia achieved an AUC of 0.787 (95% CI: 0.723-0.842) with sensitivity of 81.8% (95% CI: 67.3-91.8); In the test dataset 2, the model diagnosing osteoporosis yielded an AUC of 0.726 (95% CI: 0.646-0.796) with sensitivity of 68.4% (95% CI: 54.8-80.1), the model diagnosing osteopenia yielded an AUC of 0.810 (95% CI, 0.737-0.870) with sensitivity of 85.3% (95% CI, 68.9-95.0). Accordingly, a deep learning diagnostic network may have the potential in screening osteoporosis and osteopenia based on lumbar spine radiographs. However, further studies are necessary to verify and improve the diagnostic performance of DCNN models.

A novel computer navigation model guided unilateral percutaneous vertebroplasty for vertebral compression fracture: A case report

RATIONAL

Vertebral compression fracture (VCF) is one of the most common diseases in spinal surgery. Traditional percutaneous vertebroplasty (PVP) under fluoroscopy is an effective method to treat vertebral compression fracture. However, there is still a risk of vascular nerve injury and infection caused by inaccurate or repeated puncture. Therefore, the purpose of this paper was to assess the accuracy of unilateral PVP guided by screw view model of navigation (SVMN) for VCF.

PATIENT CONCERNS

A 59-year-old female patient suffered high falling injury, and with back pain as its main clinical symptom.

DIAGNOSES

The patient was diagnosed with a L1 VCF.

INTERVENTIONS

We placed the puncture needle under the guidance of SVMN to reach the ideal position designed before operation, and then injected the bone cement to complete the percutaneous kyphoplasty (PKP).

OUTCOMES

The operative time was 29.5 minutes, the puncture time was 1 time, the fluoroscopy time was 2.9 minutes, and the bone cement distribution was satisfactory. VAS and ODI scores were significant improved postoperatively. No surgical complications, including neurovascular injury and infection, were observed during 28-month follow up.

LESSONS

The SVMN guided percutaneous puncture needle insertion in PKP operation for VCF is an effective and safety technique. Besides, the SVMN has also been a contributor to reduce radiation doses and replace conventional fluoroscopy.

Artificial Intelligence, Real-World Automation and the Safety of Medicines

Despite huge technological advances in the capabilities to capture, store, link and analyse data electronically, there has been some but limited impact on routine pharmacovigilance. We discuss emerging research in the use of artificial intelligence, machine learning and automation across the pharmacovigilance lifecycle including pre-licensure. Reasons are provided on why adoption is challenging and we also provide a perspective on changes needed to accelerate adoption, and thereby improve patient safety. Last, we make clear that while technologies could be superimposed on existing pharmacovigilance processes for incremental improvements, these great societal advances in data and technology also provide us with a timely opportunity to reconsider everything we do in pharmacovigilance operations to maximise the benefit of these advances.

Chinese expert consensus on the diagnosis of osteoporosis by imaging and bone mineral density

With an aging society, osteoporosis is one of the most common diseases threatening the health of China's elderly population and is an issue that is raising increasing concern. Osteoporosis is characterized by bone loss and increased susceptibility to fragility fractures. Various imaging modalities such as X-ray, CT, MRI and nuclear medicine along with assessment of bone mineral density (BMD) play an important role in its diagnosis and management, and the treatment requires multidisciplinary teamwork. A lack of consensus in the approach to imaging and BMD measurement is hampering the quality of service and patient care in China. Therefore a panel of Chinese experts from the fields of radiology, orthopedics, endocrinology and nuclear medicine reviewed the international guidelines, consensus and literature with the most recent data from China and, taking account of current clinical practice in China, the panel reached this consensus to help guide the diagnosis of osteoporosis using imaging and BMD. This consensus report provides guidelines and standards for the imaging and BMD assessment of osteoporosis and criteria for the diagnosis of osteoporosis in China.

The Musculoskeletal Knowledge Portal: Making Omics Data Useful to the Broader Scientific Community

The development of high-throughput genotyping technologies and large biobank collections, complemented with rapid methodological advances in statistical genetics, has enabled hypothesis-free genome-wide association studies (GWAS), which have identified hundreds of genetic variants across many loci associated with musculoskeletal conditions. Similarly, basic scientists have valuable molecular cellular and animal data based on musculoskeletal disease that would be enhanced by being able to determine the human translation of their findings. By integrating these large-scale human genomic musculoskeletal datasets with complementary evidence from model organisms, new and existing genetic loci can be statistically fine-mapped to plausibly causal variants, candidate genes, and biological pathways. Genes and pathways identified using this approach can be further prioritized as drug targets, including side-effect profiling and the potential for new indications. To bring together these big data, and to realize the vision of creating a knowledge portal, the International Federation of Musculoskeletal Research Societies (IFMRS) established a working group to collaborate with scientists from the Broad Institute to create the Musculoskeletal Knowledge Portal (MSK-KP)(http://mskkp.org/). The MSK consolidates omics datasets from humans, cellular experiments, and model organisms into a central repository that can be accessed by researchers. The vision of the MSK-KP is to enable better understanding of the biological mechanisms underlying musculoskeletal disease and apply this knowledge to identify and develop new disease interventions. © 2020 American Society for Bone and Mineral Research (ASBMR).

Dielectric characterization of diseased human trabecular bones at microwave frequency

The objective of this study is to determine whether in vitro dielectric properties of human trabecular bones, can distinguish between osteoporotic and osteoarthritis patients' bone samples. Specifically this study enlightens intra-patient variation of trabecular bone microarchitecture and dielectric properties, inter-disease comparison of bone dielectric properties, and finally establishes the correlation to traditional bone histomorphometry parameter (bone volume fraction) for diseased bone tissue. Bone cores were obtained from osteoporotic and osteoarthritis patients (n = 12). These were scanned using microCT to examine bone volume fraction. An open-ended coaxial probe measurement technique was employed to measure dielectric properties over the 0.5 - 8.5 GHz frequency range. The dielectric properties of osteoarthritis patients are significantly higher than osteoporotic patients; with an increase of 41% and 45% for relative permittivity and conductivity respectively. The dielectric properties within each patient vary significantly, variation in relative permittivity and conductivity was found to be greater than 25% and 1.4% respectively. A weak correlation (r  =  0.5) is observed between relative permittivity and bone volume fraction. Osteoporotic and osteoarthritis bones can be differentiated based on difference of dielectric properties. Although these do not correlate strongly to bone volume fraction, it should be noted that bone volume fraction is a poor predictor of fracture risk. The dielectric properties of bones are found to be influenced by mineralization levels of bones. Therefore, dielectric properties of bones may have potential as a diagnostic measure of osteoporosis.

An integrated model using the Taguchi method and artificial neural network to improve artificial kidney solidification parameters

BACKGROUND

Hemodialysis mainly relies on the "artificial kidney," which plays a very important role in temporarily or permanently substituting for the kidney to carry out the exchange of waste and discharge of water. Nevertheless, a previous study on the artificial kidney has paid little attention to the optimization of factors and levels for reducing the solidification of the artificial kidney during the hemodialysis procedure. Thus, this study proposes an integrated model that uses the Taguchi method, omega formula, and back-propagation network to determine the optimal factors and levels for addressing this issue.

METHODS

First, we collected the recommendations of medical doctors and nursing staff through a small group discussion, and used the Taguchi method to analyze the key factors at different levels. Next, the omega formula was used to convert the analysis results from the Taguchi method to assess the defect rate. Finally, we utilized back-propagation network algorithms to predict the optimal factors and levels for artificial kidney solidification, in order to confirm that the key factors and levels identified can effectively improve the solidification rate of the artificial kidney and thereby enhance the effect of hemodialysis.

RESULTS

The research finding proposes the following as the optimal factors and levels for artificial kidney solidification: the amount of anticoagulation should be set at 500 units, the velocity of blood flow at 300 ml/min, the dehydration volume at 2.5 kg, and the vascular access type as autologous blood vessels. We obtained 270 sets of data from the patients of End Stage Renal Disease (ESRD) under the setting of the optimal combination of the factors at different levels; the defect rate of artificial kidney solidification is 12.9%, which is better than the defect rate of 32% in the original experiment. Meanwhile, the patient characteristics for physiological status in BMI, serum calcium, hematocrit, ferritin, and transferrin saturation percentage are improved by this study.

CONCLUSION

This conclusion validates the ability of the proposed model in this study to improve the solidification rate of the artificial kidney, thereby confirming the model's use as a standard operation procedure in the hemodialysis experiment. The ideas behind and the implications of the proposed model are further discussed in this study.

Osteoporosis and sport

Osteoporosis is common throughout the world. Complications include fragility fractures. In this paper I will describe the condition as it relates to athletes young and old. It will be seen that osteoporosis may result from poorly managed sporting activities at the same time it may be ameliorated by exercise in those susceptible to the disorder. I will discuss the epidemiology, the protective effect of exercise, the therapeutic benefits of sport and exercise in the older population with fragility fractures, the effects of weight limited sport and the severe risks to those who diet and exercise intensely at the same time. I will cover the range of diagnostic investigations including imaging and non-radiological techniques and focus on advice to the coach and athlete to maintain bone health throughout an athletic and sporting lifetime.