Osteoporosis risk prediction for bone mineral density assessment of postmenopausal women using machine learning

Sarcopenic obesity and osteoporosis: Research progress and hot spots

Sarcopenic obesity (SO) and osteoporosis (OP) are associated with aging and obesity. The pathogenesis of SO is complex, including glucolipid and skeletal muscle metabolic disorders caused by inflammation, insulin resistance, and other factors. Growing evidence links muscle damage to bone loss. Muscle-lipid metabolism disorders of SO disrupt the balance between bone formation and bone resorption, increasing the risk of OP. Conversely, bones also play a role in fat and muscle metabolism. In the context of aging and obesity, the comprehensive review focuses on the effects of mechanical stimulation, mesenchymal stem cells (MSCs), chronic inflammation, myokines, and adipokines on musculoskeletal, at the same time, the impact of osteokines on muscle-lipid metabolism were also analyzed. So far, exercise combined with diet therapy is the most effective strategy for increasing musculoskeletal mass. A holistic treatment of musculoskeletal diseases is still in the preliminary exploration stage. Therefore, this article aims to improve the understanding of musculoskeletal -fat interactions in SO and OP, explores targets that can provide holistic treatment for SO combined with OP, and discusses current limitations and challenges. We hope to provide relevant ideas for developing specific therapies and improving disease prognosis in the future.

Preventive machine learning models incorporating health checkup data and hair mineral analysis for low bone mass identification

Machine learning (ML) models have been increasingly employed to predict osteoporosis. However, the incorporation of hair minerals into ML models remains unexplored. This study aimed to develop ML models for predicting low bone mass (LBM) using health checkup data and hair mineral analysis. A total of 1206 postmenopausal women and 820 men aged 50 years or older at a health promotion center were included in this study. LBM was defined as a T-score below - 1 at the lumbar, femur neck, or total hip area. The proportion of individuals with LBM was 59.4% (n = 1205). The features used in the models comprised 50 health checkup items and 22 hair minerals. The ML algorithms employed were Extreme Gradient Boosting (XGB), Random Forest (RF), Gradient Boosting (GB), and Adaptive Boosting (AdaBoost). The subjects were divided into training and test datasets with an 80:20 ratio. The area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and an F1 score were evaluated to measure the performances of the models. Through 50 repetitions, the mean (standard deviation) AUROC for LBM was 0.744 (± 0.021) for XGB, the highest among the models, followed by 0.737 (± 0.023) for AdaBoost, and 0.733 (± 0.023) for GB, and 0.732 (± 0.021) for RF. The XGB model had an accuracy of 68.7%, sensitivity of 80.7%, specificity of 51.1%, PPV of 70.9%, NPV of 64.3%, and an F1 score of 0.754. However, these performance metrics did not demonstrate notable differences among the models. The XGB model identified sulfur, sodium, mercury, copper, magnesium, arsenic, and phosphate as crucial hair mineral features. The study findings emphasize the significance of employing ML algorithms for predicting LBM. Integrating health checkup data and hair mineral analysis into these models may provide valuable insights into identifying individuals at risk of LBM.

Osteoporosis Prediction Using Machine-Learned Optical Bone Densitometry Data

Optical bone densitometry (OBD) has been developed for the early detection of osteoporosis. In recent years, machine learning (ML) techniques have been actively implemented for the areas of medical diagnosis and screening with the goal of improving diagnostic accuracy. The purpose of this study was to verify the feasibility of using the combination of OBD and ML techniques as a screening tool for osteoporosis. Dual energy X-ray absorptiometry (DXA) and OBD measurements were performed on 203 Thai subjects. From the OBD measurements and readily available demographic data, machine learning techniques were used to predict the T-score measured by the DXA. The T-score predicted using the Ridge regressor had a correlation of r = 0.512 with respect to the reference value. The predicted T-score also showed an AUC of 0.853 for discriminating individuals with osteoporosis. The results obtained suggest that the developed model is reliable enough to be used for screening for osteoporosis.

Artificial intelligence applications in bone fractures: A bibliometric and science mapping analysis

Background

Bone fractures are a common medical issue worldwide, causing a serious economic burden on society. In recent years, the application of artificial intelligence (AI) in the field of fracture has developed rapidly, especially in fracture diagnosis, where AI has shown significant capabilities comparable to those of professional orthopedic surgeons. This study aimed to review the development process and applications of AI in the field of fracture using bibliometric analysis, while analyzing the research hotspots and future trends in the field.

Materials and methods

Studies on AI and fracture were retrieved from the Web of Science Core Collections since 1990, a retrospective bibliometric and visualized study of the filtered data was conducted through CiteSpace and Bibliometrix R package.

Results

A total of 1063 publications were included in the analysis, with the annual publication rapidly growing since 2017. China had the most publications, and the United States had the most citations. Technical University of Munich, Germany, had the most publications. Doornberg JN was the most productive author. Most research in this field was published in Scientific Reports. Doi K's 2007 review in Computerized Medical Imaging and Graphics was the most influential paper.

Conclusion

AI application in fracture has achieved outstanding results and will continue to progress. In this study, we used a bibliometric analysis to assist researchers in understanding the basic knowledge structure, research hotspots, and future trends in this field, to further promote the development of AI applications in fracture.

A machine learning-based online web calculator to aid in the diagnosis of sarcopenia in the US community

Background

Sarcopenia places a heavy healthcare burden on individuals and society. Recognizing sarcopenia and intervening at an early stage is critical. However, there is no simple and easy-to-use prediction tool for diagnosing sarcopenia. The aim of this study was to construct a well-performing online web calculator based on a machine learning approach to predict the risk of low lean body mass (LBM) to assist in the diagnosis of sarcopenia.

Methods

Data from the National Health and Nutritional Examination Surveys 1999-2004 were selected for model construction, and the included data were randomly divided into training and validation sets in the ratio of 75:25. Six machine learning methods- Classification and Regression Trees, Logistic Regression, Neural Network, Random Forest, Support Vector Machine, and Extreme Gradient Boosting (XGBoost)-were used to develop the model. They are screened for features and evaluated for performance. The best-performing models were further developed as an online web calculator for clinical applications.

Results

There were 3046 participants enrolled in the study and 815 (26.8%) participants with LBM. Through feature screening, height, waist circumference, race, and age were used as machine learning features to construct the model. After performance evaluation and sensitivity analysis, the XGBoost-based model was determined to be the best model with better discriminative performance, clinical utility, and robustness.

Conclusion

The XGBoost-based model in this study has excellent performance, and the online web calculator based on it can easily and quickly predict the risk of LBM to aid in the diagnosis of sarcopenia in adults over the age of 60.

Application of machine learning algorithms to predict osteoporosis in postmenopausal women with type 2 diabetes mellitus

PURPOSE

The screening and diagnosis of osteoporosis in patients with type 2 diabetes mellitus (T2DM) based on bone mineral density remains challenging because of the limited availability and accessibility of dual-energy X-ray absorptiometry. We aimed to develop and validate models to predict the risk of osteoporosis in postmenopausal women with T2DM based on machine learning (ML) algorithms.

METHODS

This retrospective study included 303 postmenopausal women with T2DM. To develop prediction models for osteoporosis, we applied nine ML algorithms combined with demographic, clinical, and laboratory data. The least absolute shrinkage and selection operator were used to perform feature selection. We used the bootstrap resampling technique for model training and validation. To test the performance of the models, we calculated indices including the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, calibration curve, and decision curve analysis. Furthermore, we conducted fivefold cross-validation for parameter optimization and model validation. Feature importance was assessed using the SHapley additive explanation (SHAP).

RESULTS

We identified 10 independent predictors as the most valuable features. An AUROC of 0.616-1.000 was observed for nine ML algorithms. The extreme gradient boosting (XGBoost) model exhibited the best performance, outperforming conventional risk assessment tools and registering 0.993 in the training set, 0.798 in the validation set, and 0.786 in the test set for fivefold cross-validation. Using SHAP, we found that the explanatory variables contributed to the model and their relationship with osteoporosis occurrence. Furthermore, we developed a user-friendly tool for calculating the risk of osteoporosis.

CONCLUSIONS

With the integration of demographic and clinical risk factors, ML algorithms can accurately predict osteoporosis. The XGBoost model showed ideal performance. With the incorporation of these models in the clinic, patients may benefit from early osteoporosis diagnosis and treatment.

A decision support system for osteoporosis risk prediction using machine learning and explainable artificial intelligence

Osteoporosis is a metabolic bone condition that occurs when bone mineral density and mass decrease. This makes the bones weak and brittle. The disorder is often undiagnosed and untreated due to its asymptomatic nature until the manifestation of a fracture. Machine Learning (ML) is extensively used in diverse healthcare domains to analyze precise outcomes, provide timely risk scores, and allocate resources. Hence, we have designed multiple heterogeneous machine-learning frameworks to predict the risk of Osteoporosis. An open-source dataset of 1493 patients containing bone density, blood, and physical tests is utilized. Thirteen distinct feature selection techniques were leveraged to extract the most salient parameters. The best-performing pipeline consisted of a Forward Feature Selection algorithm followed by a custom multi-level ensemble learning-based stack, which achieved an accuracy of 89 %. Deploying a layer of explainable artificial intelligence using tools such as SHAP (SHapley Additive Values), LIME (Local Interpretable Model Explainer), ELI5, Qlattice, and feature importance provided interpretability and rationale behind classifier prediction. With this study, we aim to provide the holistic risk prediction of Osteoporosis and concurrently present a system for automated screening to assist physicians in making diagnostic decisions.

Artificial Intelligence Applications for Osteoporosis Classification Using Computed Tomography

Osteoporosis, marked by low bone mineral density (BMD) and a high fracture risk, is a major health issue. Recent progress in medical imaging, especially CT scans, offers new ways of diagnosing and assessing osteoporosis. This review examines the use of AI analysis of CT scans to stratify BMD and diagnose osteoporosis. By summarizing the relevant studies, we aimed to assess the effectiveness, constraints, and potential impact of AI-based osteoporosis classification (severity) via CT. A systematic search of electronic databases (PubMed, MEDLINE, Web of Science, ClinicalTrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 39 articles were retrieved from the databases, and the key findings were compiled and summarized, including the regions analyzed, the type of CT imaging, and their efficacy in predicting BMD compared with conventional DXA studies. Important considerations and limitations are also discussed. The overall reported accuracy, sensitivity, and specificity of AI in classifying osteoporosis using CT images ranged from 61.8% to 99.4%, 41.0% to 100.0%, and 31.0% to 100.0% respectively, with areas under the curve (AUCs) ranging from 0.582 to 0.994. While additional research is necessary to validate the clinical efficacy and reproducibility of these AI tools before incorporating them into routine clinical practice, these studies demonstrate the promising potential of using CT to opportunistically predict and classify osteoporosis without the need for DEXA.

A Machine Learning-Based Preclinical Osteoporosis Screening Tool (POST): Model Development and Validation Study

Background

Identifying persons with a high risk of developing osteoporosis and preventing the occurrence of the first fracture is a health care priority. Most existing osteoporosis screening tools have high sensitivity but relatively low specificity.

Objective

We aimed to develop an easily accessible and high-performance preclinical risk screening tool for osteoporosis using a machine learning-based method among the Hong Kong Chinese population.

Methods

Participants aged 45 years or older were enrolled from 6 clinics in the 3 major districts of Hong Kong. The potential risk factors for osteoporosis were collected through a validated, self-administered questionnaire and then filtered using a machine learning-based method. Bone mineral density was measured with dual-energy x-ray absorptiometry at the clinics; osteoporosis was defined as a t score of -2.5 or lower. We constructed machine learning models, including gradient boosting machines, support vector machines, and naive Bayes, as well as the commonly used logistic regression models, for the prediction of osteoporosis. The best-performing model was chosen as the final tool, named the Preclinical Osteoporosis Screening Tool (POST). Model performance was evaluated by the area under the receiver operating characteristic curve (AUC) and other metrics.

Results

Among the 800 participants enrolled in this study, the prevalence of osteoporosis was 10.6% (n=85). The machine learning-based Boruta algorithm identified 15 significantly important predictors from the 113 potential risk factors. Seven variables were further selected based on their accessibility and convenience for daily self-assessment and health care practice, including age, gender, education level, decreased body height, BMI, number of teeth lost, and the intake of vitamin D supplements, to construct the POST. The AUC of the POST was 0.86 and the sensitivity, specificity, and accuracy were all 0.83. The positive predictive value, negative predictive value, and F1-score were 0.41, 0.98, and 0.56, respectively.

Conclusions

The machine learning-based POST was conveniently accessible and exhibited accurate discriminative capabilities for the prediction of osteoporosis; it might be useful to guide population-based preclinical screening of osteoporosis and clinical decision-making.

Comparison between linear regression and four different machine learning methods in selecting risk factors for osteoporosis in a Chinese female aged cohort

BACKGROUND

Population aging is emerging as an increasingly acute challenge for countries around the world. One particular manifestation of this phenomenon is the impact of osteoporosis on individuals and national health systems. Previous studies of risk factors for osteoporosis were conducted using traditional statistical methods, but more recent efforts have turned to machine learning approaches. Most such efforts, however, treat the target variable (bone mineral density [BMD] or fracture rate) as a categorical one, which provides no quantitative information. The present study uses five different machine learning methods to analyze the risk factors for T-score of BMD, seeking to (1) compare the prediction accuracy between different machine learning methods and traditional multiple linear regression (MLR) and (2) rank the importance of 25 different risk factors.

METHODS

The study sample includes 24 412 women older than 55 years with 25 related variables, applying traditional MLR and five different machine learning methods: classification and regression tree, Naïve Bayes, random forest, stochastic gradient boosting, and eXtreme gradient boosting. The metrics used for model performance comparisons are the symmetric mean absolute percentage error, relative absolute error, root relative squared error, and root mean squared error.

RESULTS

Machine learning approaches outperformed MLR for all four prediction errors. The average importance ranking of each factor generated by the machine learning methods indicates that age is the most important factor determining T-score, followed by estimated glomerular filtration rate (eGFR), body mass index (BMI), uric acid (UA), and education level.

CONCLUSION

In a group of women older than 55 years, we demonstrated that machine learning methods provide superior performance in estimating T-Score, with age being the most important impact factor, followed by eGFR, BMI, UA, and education level.

Penicopeptide A (PPA) from the deep-sea-derived fungus promotes osteoblast-mediated bone formation and alleviates ovariectomy-induced bone loss by activating the AKT/GSK-3β/β-catenin signaling pathway

The potential of marine natural products as effective drugs for osteoporosis treatment is an understudied area. In this study, we investigated the ability of lead compounds from deep-sea-derived Penicillium solitum MCCC 3A00215 to promote bone formation in vitro and in vivo. We found that penicopeptide A (PPA) promoted osteoblast mineralization among bone marrow mesenchymal stem cells (BMSCs) in a concentration-dependent manner, and thus, we selected this natural peptide for further testing. Our further experiments showed that PPA significantly promoted the osteogenic differentiation of BMSCs while inhibiting their adipogenic differentiation and not affecting their chondrogenic differentiation. Mechanistic studies showed that PPA binds directly to the AKT and GSK-3β and activates phosphorylation of AKT and GSK-3β, resulting in the accumulation of β-catenin. We also evaluated the therapeutic potential of PPA in a female mouse model of ovariectomy-induced systemic bone loss. In this model, PPA treatment prevented decreases in bone volume and trabecular thickness. In conclusion, our in vitro and in vivo results demonstrated that PPA could promote osteoblast-related bone formation via the AKT, GSK-3β, and β-catenin signaling pathways, indicating the clinical potential of PPA as a candidate compound for osteoporosis prevention.

Screening for Osteoporosis Risk Among Community-Dwelling Older Adults: A Scoping Review

BACKGROUND AND PURPOSE

Due to potential health-related consequences of osteoporosis (OP), health care providers who do not order imaging, such as physical therapists, should be aware of OP screening tools that identify individuals who need medical and rehabilitation care. However, current knowledge and guidance on screening tools is limited. Therefore, we explored OP screening tools that are appropriate and feasible for physical therapy practice, and evaluated tools' effectiveness by examining their clinimetric properties.

METHODS

A systematic search of the following databases was performed: PubMed, PEDro, PsycINFO, CINAHL, and Web of Science. Articles were included if the study population was 50 years and older, had a diagnosis of OP, if the screening tool was within the scope of physical therapy practice, and was compared to either a known diagnosis of OP or bone densitometry scan results. Included articles underwent multiple reviews for inclusion and exclusion, with each review round having a different randomly selected pair of reviewers. Data were extracted from included articles for participant demographics, outcome measures, cut-off values, and clinimetric properties. Results were categorized with positive and negative likelihood ratios (+LR/-LR) based on the magnitude of change in the probability of having or not having OP.

RESULTS

+LRs ranged from 0.15 to 20.21, with the Fracture Risk Assessment Tool (FRAX) and Study of Osteoporotic Fractures (SOF) having a large shift in posttest probability. -LRs ranged from 0.03 to 1.00, with the FRAX, Male Osteoporosis Risk Estimation Scores, Osteoporosis Self-Assessment Tool (OST), and Simple Calculated Osteoporosis Risk Estimation having a large shift in posttest probability.

CONCLUSION

Tools with moderate-large shift for both +LR and -LR recommended for use are: (1) OST; (2) FRAX; and (3) SOF. The variability in cut-off scores and clinimetric properties based on gender, age, and race/ethnicities made it impossible to provide one specific recommendation for an OP screening tool. Future research should focus on OP risk prediction among males and racial and ethnic groups.

Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary Study

Purpose

There remains a lack of a machine learning (ML) model incorporating body composition to assess the risk of bone mineral density (BMD) decreases in type 2 diabetes mellitus (T2DM) patients. We aimed to use ML algorithms and the traditional multivariate logistic regression to establish prediction models for BMD decreases in T2DM patients over 50 years of age, and compare the performance of the two methods.

Patients and Methods

This cross-sectional study was conducted among 450 patients with T2DM from 1 August 2016 to 31 December 2022. The participants were divided into a normal BMD group and a decreased BMD group. Traditional multivariate logistic regression and six ML algorithms were selected to construct male and female models. Two nomograms were constructed to evaluate the risk of BMD decreases in the male and female T2DM patients, respectively. The ML models with the highest area under the curve (AUC) were compared with the traditional multivariate logistic regression models in terms of discriminant ability and clinical applicability.

Results

The optimal ML model was the extreme gradient boost (XGBoost) model. The AUCs of the traditional multivariate logistic regression and the XGBoost models were 0.722 and 0.800 in the male testing dataset, respectively, and 0.876 and 0.880 in the female testing dataset, respectively. The decision curve analysis results suggested that using the XGBoost models to predict the risk of BMD decreases obtained more net benefits compared with the traditional models in both sexes.

Conclusion

We preliminarily proved that the XGBoost models outperformed most other ML models in both sexes and achieved higher accuracy than traditional analyses. Due to the limited sample size in the study, it is necessary to validate our findings in larger prospective cohort studies.

Retrospective study: risk assessment model for osteoporosis-a detailed exploration involving 4,552 Shanghai dwellers

Background

Osteoporosis, a prevalent orthopedic issue, significantly influences patients' quality of life and results in considerable financial burden. The objective of this study was to develop and validate a clinical prediction model for osteoporosis risk, utilizing computer algorithms and demographic data.

Method

In this research, a total of 4,552 residents from Shanghai were retrospectively included. LASSO regression analysis was executed on the sample's basic characteristics, and logistic regression was employed for analyzing clinical characteristics and building a predictive model. The model's diagnostic capacity for predicting osteoporosis risk was assessed using R software and computer algorithms.

Results

The predictive nomogram model for bone loss risk, derived from the LASSO analysis, comprised factors including BMI, TC, TG, HDL, Gender, Age, Education, Income, Sleep, Alcohol Consumption, and Diabetes. The nomogram prediction model demonstrated impressive discriminative capability, with a C-index of 0.908 (training set), 0.908 (validation set), and 0.910 (entire cohort). The area under the ROC curve (AUC) of the model was 0.909 (training set), 0.903 (validation set), and applicable to the entire cohort. The decision curve analysis further corroborated that the model could efficiently predict the risk of bone loss in patients.

Conclusion

The nomogram, based on essential demographic and health factors (Body Mass Index, Total Cholesterol, Triglycerides, High-Density Lipoprotein, Gender, Age, Education, Income, Sleep, Alcohol Consumption, and Diabetes), offered accurate predictions for the risk of bone loss within the studied population.

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.

A clinical prediction model for 10-year risk of self-reported osteoporosis diagnosis in pre- and perimenopausal women

A machine learning model using clinical, laboratory, and imaging data was developed to predict 10-year risk of menopause-related osteoporosis. The resulting predictions, which are sensitive and specific, highlight distinct clinical risk profiles that can be used to identify patients most likely to be diagnosed with osteoporosis.

PURPOSE

The aim of this study was to incorporate demographic, metabolic, and imaging risk factors into a model for long-term prediction of self-reported osteoporosis diagnosis.

METHODS

This was a secondary analysis of 1685 patients from the longitudinal Study of Women's Health Across the Nation using data collected between 1996 and 2008. Participants were pre- or perimenopausal women between 42 and 52 years of age. A machine learning model was trained using 14 baseline risk factors-age, height, weight, body mass index, waist circumference, race, menopausal status, maternal osteoporosis history, maternal spine fracture history, serum estradiol level, serum dehydroepiandrosterone level, serum thyroid-stimulating hormone level, total spine bone mineral density, and total hip bone mineral density. The self-reported outcome was whether a doctor or other provider had told participants they have osteoporosis or treated them for osteoporosis.

RESULTS

At 10-year follow-up, a clinical osteoporosis diagnosis was reported by 113 (6.7%) women. Area under the receiver operating characteristic curve of the model was 0.83 (95% confidence interval, 0.73-0.91) and Brier score was 0.054 (95% confidence interval, 0.035-0.074). Total spine bone mineral density, total hip bone mineral density, and age had the largest contributions to predicted risk. Using two discrimination thresholds, stratification into low, medium, and high risk, respectively, was associated with likelihood ratios of 0.23, 3.2, and 6.8. At the lower threshold, sensitivity was 0.81, and specificity was 0.82.

CONCLUSION

The model developed in this analysis integrates clinical data, serum biomarker levels, and bone mineral densities to predict 10-year risk of osteoporosis with good performance.

Machine learning algorithms are comparable to conventional regression models in predicting distant metastasis of follicular thyroid carcinoma

OBJECTIVE

Distant metastasis often indicates a poor prognosis, so early screening and diagnosis play a significant role. Our study aims to construct and verify a predictive model based on machine learning (ML) algorithms that can estimate the risk of distant metastasis of newly diagnosed follicular thyroid carcinoma (FTC).

DESIGN

This was a retrospective study based on the Surveillance, Epidemiology, and End Results (SEER) database from 2004 to 2015.

PATIENTS

A total of 5809 FTC patients were included in the data analysis. Among them, there were 214 (3.68%) cases with distant metastasis.

METHOD

Univariate and multivariate logistic regression (LR) analyses were used to determine independent risk factors. Seven commonly used ML algorithms were applied for predictive model construction. We used the area under the receiver-operating characteristic (AUROC) curve to select the best ML algorithm. The optimal model was trained through 10-fold cross-validation and visualized by SHapley Additive exPlanations (SHAP). Finally, we compared it with the traditional LR method.

RESULTS

In terms of predicting distant metastasis, the AUROCs of the seven ML algorithms were 0.746-0.836 in the test set. Among them, the Extreme Gradient Boosting (XGBoost) had the best prediction performance, with an AUROC of 0.836 (95% confidence interval [CI]: 0.775-0.897). After 10-fold cross-validation, its predictive power could reach the best [AUROC: 0.855 (95% CI: 0.803-0.906)], which was slightly higher than the classic binary LR model [AUROC: 0.845 (95% CI: 0.818-0.873)].

CONCLUSIONS

The XGBoost approach was comparable to the conventional LR method for predicting the risk of distant metastasis for FTC.

Value of machine learning algorithms for predicting diabetes risk: A subset analysis from a real-world retrospective cohort study

AIMS/INTRODUCTION

To compare the application value of different machine learning (ML) algorithms for diabetes risk prediction.

MATERIALS AND METHODS

This is a 3-year retrospective cohort study with a total of 3,687 participants being included in the data analysis. Modeling variable screening and predictive model building were carried out using logistic regression (LR) analysis and 10-fold cross-validation, respectively. In total, six different ML algorithms, including random forests, light gradient boosting machine, extreme gradient boosting, adaptive boosting (AdaBoost), multi-layer perceptrons and gaussian naive bayes were used for model construction. Model performance was mainly evaluated by the area under the receiver operating characteristic curve. The best performing ML model was selected for comparison with the traditional LR model and visualized using Shapley additive explanations.

RESULTS

A total of eight risk factors most associated with the development of diabetes were identified by univariate and multivariate LR analysis, and they were visualized in the form of a nomogram. Among the six different ML models, the random forests model had the best predictive performance. After 10-fold cross-validation, its optimal model has an area under the receiver operating characteristic value of 0.855 (95% confidence interval [CI] 0.823-0.886) in the training set and 0.835 (95% CI 0.779-0.892) in the test set. In the traditional LR model, its area under the receiver operating characteristic value is 0.840 (95% CI 0.814-0.866) in the training set and 0.834 (95% CI 0.785-0.884) in the test set.

CONCLUSIONS

In the real-world epidemiological research, the combination of traditional variable screening and ML algorithm to construct a diabetes risk prediction model has satisfactory clinical application value.

Decision Tree Modeling for Osteoporosis Screening in Postmenopausal Thai Women

Osteoporosis is still a serious public health issue in Thailand, particularly in postmenopausal women; meanwhile, new effective screening tools are required for rapid diagnosis. This study constructs and confirms an osteoporosis screening tool-based decision tree (DT) model. Four DT algorithms, namely, classification and regression tree; chi-squared automatic interaction detection (CHAID); quick, unbiased, efficient statistical tree; and C4.5, were implemented on 356 patients, of whom 266 were abnormal and 90 normal. The investigation revealed that the DT algorithms have insignificantly different performances regarding the accuracy, sensitivity, specificity, and area under the curve. Each algorithm possesses its characteristic performance. The optimal model is selected according to the performance of blind data testing and compared with traditional screening tools: Osteoporosis Self-Assessment for Asians and the Khon Kaen Osteoporosis Study. The Decision Tree for Postmenopausal Osteoporosis Screening (DTPOS) tool was developed from the best performance of CHAID’s algorithms. The age of 58 years and weight at a cutoff of 57.8 kg were the essential predictors of our tool. DTPOS provides a sensitivity of 92.3% and a positive predictive value of 82.8%, which might be used to rule in subjects at risk of osteopenia and osteoporosis in a community-based screening as it is simple to conduct.

Current Applications of Machine Learning in Spine: From Clinical View

STUDY DESIGN

Narrative review.

OBJECTIVES

This review aims to present current applications of machine learning (ML) in spine domain to clinicians.

METHODS

We conducted a comprehensive PubMed search of peer-reviewed articles that were published between 2006 and 2020 using terms (spine, spinal, lumbar, cervical, thoracic, machine learning) to examine ML in spine. Then exclude research of other domain, case report, review or meta-analysis, and which without available abstract or full text.

RESULTS

Total 1738 articles were retrieved from database, and 292 studies were finally included. Key findings of current applications were compiled and summarized in this review. Main clinical applications of those techniques including image processing, diagnosis, decision supporting, operative assistance, rehabilitation, surgery outcomes, complications, hospitalization and cost.

CONCLUSIONS

ML had achieved excellent performance and hold immense potential in spine. ML could help clinical staff to improve medical level, enhance work efficiency, and reduce adverse events. However more randomized controlled trials and improvement of interpretability are essential to clinicians accepting models' assistance in real work.

Surgical Methods and Social Factors Are Associated With Long-Term Survival in Follicular Thyroid Carcinoma: Construction and Validation of a Prognostic Model Based on Machine Learning Algorithms

Background

This study aimed to establish and verify an effective machine learning (ML) model to predict the prognosis of follicular thyroid cancer (FTC), and compare it with the eighth edition of the American Joint Committee on Cancer (AJCC) model.

Methods

Kaplan-Meier method and Cox regression model were used to analyze the risk factors of cancer-specific survival (CSS). Propensity-score matching (PSM) was used to adjust the confounding factors of different surgeries. Nine different ML algorithms,including eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Random Forests (RF), Logistic Regression (LR), Adaptive Boosting (AdaBoost), Gaussian Naive Bayes (GaussianNB), K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP),were used to build prognostic models of FTC.10-fold cross-validation and SHapley Additive exPlanations were used to train and visualize the optimal ML model.The AJCC model was built by multivariate Cox regression and visualized through nomogram. The performance of the XGBoost model and AJCC model was mainly assessed using the area under the receiver operating characteristic (AUROC).

Results

Multivariate Cox regression showed that age, surgical methods, marital status, T classification, N classification and M classification were independent risk factors of CSS. Among different surgeries, the prognosis of one-sided thyroid lobectomy plus isthmectomy (LO plus IO) was the best, followed by total thyroidectomy (hazard ratios: One-sided thyroid LO plus IO, 0.086[95% confidence interval (CI),0.025-0.290], P<0.001; total thyroidectomy (TT), 0.490[95%CI,0.295-0.814], P=0.006). PSM analysis proved that one-sided thyroid LO plus IO, TT, and partial thyroidectomy had no significant differences in long-term prognosis. Our study also revealed that married patients had better prognosis than single, widowed and separated patients (hazard ratios: single, 1.686[95%CI,1.146-2.479], P=0.008; widowed, 1.671[95%CI,1.163-2.402], P=0.006; separated, 4.306[95%CI,2.039-9.093], P<0.001). Among different ML algorithms, the XGBoost model had the best performance, followed by Gaussian NB, RF, LR, MLP, LightGBM, AdaBoost, KNN and SVM. In predicting FTC prognosis, the predictive performance of the XGBoost model was relatively better than the AJCC model (AUROC: 0.886 vs. 0.814).

Conclusion

For high-risk groups, effective surgical methods and well marital status can improve the prognosis of FTC. Compared with the traditional AJCC model, the XGBoost model has relatively better prediction accuracy and clinical usage.

Osteoporosis Pre-Screening Using Ensemble Machine Learning in Postmenopausal Korean Women

As osteoporosis is a degenerative disease related to postmenopausal aging, early diagnosis is vital. This study used data from the Korea National Health and Nutrition Examination Surveys to predict a patient’s risk of osteoporosis using machine learning algorithms. Data from 1431 postmenopausal women aged 40–69 years were used, including 20 features affecting osteoporosis, chosen by feature importance and recursive feature elimination. Random Forest (RF), AdaBoost, and Gradient Boosting (GBM) machine learning algorithms were each used to train three models: A, checkup features; B, survey features; and C, both checkup and survey features, respectively. Of the three models, Model C generated the best outcomes with an accuracy of 0.832 for RF, 0.849 for AdaBoost, and 0.829 for GBM. Its area under the receiver operating characteristic curve (AUROC) was 0.919 for RF, 0.921 for AdaBoost, and 0.908 for GBM. By utilizing multiple feature selection methods, the ensemble models of this study achieved excellent results with an AUROC score of 0.921 with AdaBoost, which is 0.1–0.2 higher than those of the best performing models from recent studies. Our model can be further improved as a practical medical tool for the early diagnosis of osteoporosis after menopause.

Serum biomarker-based osteoporosis risk prediction and the systemic effects of Trifolium pratense ethanolic extract in a postmenopausal model

Background

Recent years, a soaring number of marketed Trifolium pratense (red clover) extract products have denoted that a rising number of consumers are turning to natural alternatives to manage postmenopausal symptoms. T. pratense ethanolic extract (TPEE) showed immense potential for their uses in the treatment of menopause complications including osteoporosis and hormone dependent diseases. Early diagnosis of osteoporosis can increase the chance of efficient treatment and reduce fracture risks. Currently, the most common diagnosis of osteoporosis is performed by using dual-energy x-ray absorptiometry (DXA). However, the major limitation of DXA is that it is inaccessible and expensive in rural areas to be used for primary care inspection. Hence, serum biomarkers can serve as a meaningful and accessible data for osteoporosis diagnosis.

Methods

The present study systematically elucidated the anti-osteoporosis and estrogenic activities of TPEE in ovariectomized (OVX) rats by evaluating the bone microstructure, uterus index, serum and bone biomarkers, and osteoblastic and osteoclastic gene expression. Leverage on a pool of serum biomarkers obtained from this study, recursive feature elimination with a cross-validation method (RFECV) was used to select useful biomarkers for osteoporosis prediction. Then, using the key features extracted, we employed five classification algorithms: extreme gradient boosting (XGBoost), random forest, support vector machine, artificial neural network, and decision tree to predict the bone quality in terms of T-score.

Results

TPEE treatments down-regulated nuclear factor kappa-B ligand, alkaline phosphatase, and up-regulated estrogen receptor β gene expression. Additionally, reduced serum C-terminal telopeptides of type 1 collagen level and improvement in the estrogen dependent characteristics of the uterus on the lining of the lumen were observed in the TPEE intervention group. Among the tested classifiers, XGBoost stood out as the best performing classification model with the highest F1-score and lowest standard deviation.

Conclusions

The present study demonstrates that TPEE treatment showed therapeutic benefits in the prevention of osteoporosis at the transcriptional level and maintained the estrogen dependent characteristics of the uterus. Our study revealed that, in the case of limited number of features, RFECV paired with XGBoost model could serve as a powerful tool to readily evaluate and diagnose postmenopausal osteoporosis.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13020-022-00622-7.

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.

Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis

Background and Objectives: A few deep learning studies have reported that combining image features with patient variables enhanced identification accuracy compared with image-only models. However, previous studies have not statistically reported the additional effect of patient variables on the image-only models. This study aimed to statistically evaluate the osteoporosis identification ability of deep learning by combining hip radiographs with patient variables. Materials andMethods: We collected a dataset containing 1699 images from patients who underwent skeletal-bone-mineral density measurements and hip radiography at a general hospital from 2014 to 2021. Osteoporosis was assessed from hip radiographs using convolutional neural network (CNN) models (ResNet18, 34, 50, 101, and 152). We also investigated ensemble models with patient clinical variables added to each CNN. Accuracy, precision, recall, specificity, F1 score, and area under the curve (AUC) were calculated as performance metrics. Furthermore, we statistically compared the accuracy of the image-only model with that of an ensemble model that included images plus patient factors, including effect size for each performance metric. Results: All metrics were improved in the ResNet34 ensemble model compared with the image-only model. The AUC score in the ensemble model was significantly improved compared with the image-only model (difference 0.004; 95% CI 0.002–0.0007; p = 0.0004, effect size: 0.871). Conclusions: This study revealed the additional effect of patient variables in identification of osteoporosis using deep CNNs with hip radiographs. Our results provided evidence that the patient variables had additive synergistic effects on the image in osteoporosis identification.

A Machine Learning-Based Fall Risk Assessment Model for Inpatients

Falls are one of the most common accidents among inpatients and may result in extended hospitalization and increased medical costs. Constructing a highly accurate fall prediction model could effectively reduce the rate of patient falls, further reducing unnecessary medical costs and patient injury. This study applied data mining techniques on a hospital's electronic medical records database comprising a nursing information system to construct inpatient-fall-prediction models for use during various stages of inpatient care. The inpatient data were collected from 15 inpatient wards. To develop timely and effective fall prediction models for inpatients, we retrieved the data of multiple-time assessment variables at four points during hospitalization. This study used various supervised machine learning algorithms to build classification models. Four supervised learning and two classifier ensemble techniques were selected for model development. The results indicated that Bagging+RF classifiers yielded optimal prediction performance at all four points during hospitalization. This study suggests that nursing personnel should be aware of patients' risk factors based on comprehensive fall risk assessment and provide patients with individualized fall prevention interventions to reduce inpatient fall rates.

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.

Application of machine learning approaches for osteoporosis risk prediction in postmenopausal women

Many predictive tools have been reported for assessing osteoporosis risk. The development and validation of osteoporosis risk prediction models were supported by machine learning.

INTRODUCTION

Osteoporosis is a silent disease until it results in fragility fractures. However, early diagnosis of osteoporosis provides an opportunity to detect and prevent fractures. We aimed to develop machine learning approaches to achieve high predictive ability for osteoporosis risk that could help primary care providers identify which women are at increased risk of osteoporosis and should therefore undergo further testing with bone densitometry.

METHODS

We included all postmenopausal Korean women from the Korea National Health and Nutrition Examination Surveys (KNHANES V-1, V-2) conducted in 2010 and 2011. Machine learning models using methods such as the k-nearest neighbors (KNN), decision tree (DT), random forest (RF), gradient boosting machine (GBM), support vector machine (SVM), artificial neural networks (ANN), and logistic regression (LR) were developed to predict osteoporosis risk. We analyzed the effect of applying the machine learning algorithms to the raw data and featuring the selected data only where the statistically significant variables were included as model inputs. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) were used to evaluate performance among the seven models.

RESULTS

A total of 1792 patients were included in this study, of which 613 had osteoporosis. The raw data consisted of 19 variables and achieved performances (in terms of AUROCs) of 0.712, 0.684, 0.727, 0.652, 0.724, 0.741, and 0.726 for KNN, DT, RF, GBM, SVM, ANN, and LR with fivefold cross-validation, respectively. The feature selected data consisted of nine variables and achieved performances (in terms of AUROCs) of 0.713, 0.685, 0.734, 0.728, 0.728, 0.743, and 0.727 for KNN, DT, RF, GBM, SVM, ANN, and LR with fivefold cross-validation, respectively.

CONCLUSION

In this study, we developed and compared seven machine learning models to accurately predict osteoporosis risk. The ANN model performed best when compared to the other models, having the highest AUROC value. Applying the ANN model in the clinical environment could help primary care providers stratify osteoporosis patients and improve the prevention, detection, and early treatment of osteoporosis.

Prediction of lumbar vertebral strength of elderly men based on quantitative computed tomography images using machine learning

The parameters extracted from quantitative computed tomography (QCT) images were used to predict vertebral strength through machine learning models, and the highly accurate prediction indicated that it may be a promising approach to assess fracture risk in clinics.

INTRODUCTION

Vertebral fracture is common in elderly populations. The main factor contributing to vertebral fracture is the reduced vertebral strength. This study aimed to predict vertebral strength based on clinical QCT images by using machine learning.

METHODS

Eighty subjects with QCT data of lumbar spine were randomly selected from the MrOS cohorts. L1 vertebral strengths were computed by QCT-based finite element analysis. A total of 58 features of each L1 vertebral body were extracted from QCT images, including grayscale distribution, grayscale values of 39 partitioned regions, BMD_QCT, structural rigidity, axial rigidity, and BMD_QCTA_min. Feature selection and dimensionality reduction were used to simplify the 58 features. General regression neural network and support vector regression models were developed to predict vertebral strength. Performance of prediction models was quantified by the mean squared error, the coefficient of determination, the mean bias, and the SD of bias.

RESULTS

The 58 parameters were simplified to five features (grayscale value of the 60% percentile, grayscale values of three specific partitioned regions, and BMD_QCTA_min) and nine principal components (PCs). High accuracy was achieved by using the five features or the nine PCs to predict vertebral strength.

CONCLUSIONS

This study provided an effective approach to predict vertebral strength and showed that it may have great potential in clinical applications for noninvasive assessment of vertebral fracture risk.

Machine learning classification models for fetal skeletal development performance prediction using maternal bone metabolic proteins in goats

Background

In developing countries, maternal undernutrition is the major intrauterine environmental factor contributing to fetal development and adverse pregnancy outcomes. Maternal nutrition restriction (MNR) in gestation has proven to impact overall growth, bone development, and proliferation and metabolism of mesenchymal stem cells in offspring. However, the efficient method for elucidation of fetal bone development performance through maternal bone metabolic biochemical markers remains elusive.

Methods

We adapted goats to elucidate fetal bone development state with maternal serum bone metabolic proteins under malnutrition conditions in mid- and late-gestation stages. We used the experimental data to create 72 datasets by mixing different input features such as one-hot encoding of experimental conditions, metabolic original data, experimental-centered features and experimental condition probabilities. Seven Machine Learning methods have been used to predict six fetal bone parameters (weight, length, and diameter of femur/humerus).

Results

The results indicated that MNR influences fetal bone development (femur and humerus) and fetal bone metabolic protein levels (C-terminal telopeptides of collagen I, CTx, in middle-gestation and N-terminal telopeptides of collagen I, NTx, in late-gestation), and maternal bone metabolites (low bone alkaline phosphatase, BALP, in middle-gestation and high BALP in late-gestation). The results show the importance of experimental conditions (ECs) encoding by mixing the information with the serum metabolic data. The best classification models obtained for femur weight (Fw) and length (FI), and humerus weight (Hw) are Support Vector Machines classifiers with the leave-one-out cross-validation accuracy of 1. The rest of the accuracies are 0.98, 0.946 and 0.696 for the diameter of femur (Fd), diameter and length of humerus (Hd, Hl), respectively. With the feature importance analysis, the moving averages mixed ECs are generally more important for the majority of the models. The moving average of parathyroid hormone (PTH) within nutritional conditions (MA-PTH-experim) is important for Fd, Hd and Hl prediction models but its removal for enhancing the Fw, Fl and Hw model performance. Further, using one feature models, it is possible to obtain even more accurate models compared with the feature importance analysis models. In conclusion, the machine learning is an efficient method to confirm the important role of PTH and BALP mixed with nutritional conditions for fetal bone growth performance of goats. All the Python scripts including results and comments are available into an open repository at https://gitlab.com/muntisa/goat-bones-machine-learning.

Artificial neural network optimizes self-examination of osteoporosis risk in women

Objective

This study aimed to investigate the application of an artificial neural network (ANN) in optimizing the Osteoporosis Self-Assessment Tool for Asians (OSTA) score.

Methods

OSTA score was calculated for each female participant that underwent dual-energy X-ray absorptiometry examination in two hospitals (one in each of two Chinese cities, Harbin and Ningbo). An ANN model was built using age and weight as input and femoral neck T-score as output. Osteoporosis risk screening by joint application of ANN and OSTA score was evaluated by receiver operating characteristic curve analysis.

Results

Nearly 90% of women with dual-energy X-ray absorptiometry-determined femoral neck osteoporosis were ≥60 years old. The ANN with age and weight as input and OSTA score both identified osteoporosis, with respective accuracy rates of 78.8% and 78.3%. However, both methods failed to identify osteoporosis in women < 60 years old. Compared with OSTA score alone, combined use of the two tools increased the rate of osteoporosis recognition among women > 80 years old.

Conclusions

OSTA score-mediated osteoporosis risk screening should be restricted to women ≥60 years old. Joint application of ANN and OSTA improved osteoporosis risk screening among Chinese women > 80 years old.

Machine Learning in Orthopedics: A Literature Review

In this paper we present the findings of a systematic literature review covering the articles published in the last two decades in which the authors described the application of a machine learning technique and method to an orthopedic problem or purpose. By searching both in the Scopus and Medline databases, we retrieved, screened and analyzed the content of 70 journal articles, and coded these resources following an iterative method within a Grounded Theory approach. We report the survey findings by outlining the articles' content in terms of the main machine learning techniques mentioned therein, the orthopedic application domains, the source data and the quality of their predictive performance.

ATLS Hypovolemic Shock Classification by Prediction of Blood Loss in Rats Using Regression Models

In our previous study, our input data set consisted of 78 rats, the blood loss in percent as a dependent variable, and 11 independent variables (heart rate, systolic blood pressure, diastolic blood pressure, mean arterial pressure, pulse pressure, respiration rate, temperature, perfusion index, lactate concentration, shock index, and new index (lactate concentration/perfusion)). The machine learning methods for multicategory classification were applied to a rat model in acute hemorrhage to predict the four Advanced Trauma Life Support (ATLS) hypovolemic shock classes for triage in our previous study. However, multicategory classification is much more difficult and complicated than binary classification. We introduce a simple approach for classifying ATLS hypovolaemic shock class by predicting blood loss in percent using support vector regression and multivariate linear regression (MLR). We also compared the performance of the classification models using absolute and relative vital signs. The accuracies of support vector regression and MLR models with relative values by predicting blood loss in percent were 88.5% and 84.6%, respectively. These were better than the best accuracy of 80.8% of the direct multicategory classification using the support vector machine one-versus-one model in our previous study for the same validation data set. Moreover, the simple MLR models with both absolute and relative values could provide possibility of the future clinical decision support system for ATLS classification. The perfusion index and new index were more appropriate with relative changes than absolute values.

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

INTRODUCTION

The goal of this paper is to present a critical review on the main systems that use artificial intelligence to identify groups at risk for osteoporosis or fractures. The systems considered for this study were those that fulfilled the following requirements: range of coverage in diagnosis, low cost and capability to identify more significant somatic factors.

METHODS

A bibliographic research was done in the databases, PubMed, IEEExplorer Latin American and Caribbean Center on Health Sciences Information (LILACS), Medical Literature Analysis and Retrieval System Online (MEDLINE), Cumulative Index to Nursing and Allied Health Literature (CINAHL), Scopus, Web of Science, and Science Direct searching the terms "Neural Network", "Osteoporosis Machine Learning" and "Osteoporosis Neural Network". Studies with titles not directly related to the research topic and older data that reported repeated strategies were excluded. The search was carried out with the descriptors in German, Spanish, French, Italian, Mandarin, Portuguese and English; but only studies written in English were found to meet the established criteria. Articles covering the period 2000-2017 were selected; however, articles prior to this period with great relevance were included in this study.

DISCUSSION

Based on the collected research, it was identified that there are several methods in the use of artificial intelligence to help the screening of risk groups of osteoporosis or fractures. However, such systems were limited to a specific ethnic group, gender or age. For future research, new challenges are presented.

CONCLUSIONS

It is necessary to develop research with the unification of different databases and grouping of the various attributes and clinical factors, in order to reach a greater comprehensiveness in the identification of risk groups of osteoporosis. For this purpose, the use of any predictive tool should be performed in different populations with greater participation of male patients and inclusion of a larger age range for the ones involved. The biggest challenge is to deal with all the data complexity generated by this unification, developing evidence-based standards for the evaluation of the most significant risk factors.

Approaches to Predicting Outcomes in Patients with Acute Kidney Injury

Despite recognition that Acute Kidney Injury (AKI) leads to substantial increases in morbidity, mortality, and length of stay, accurate prognostication of these clinical events remains difficult. It remains unclear which approaches to variable selection and model building are most robust. We used data from a randomized trial of AKI alerting to develop time-updated prognostic models using stepwise regression compared to more advanced variable selection techniques. We randomly split data into training and validation cohorts. Outcomes of interest were death within 7 days, dialysis within 7 days, and length of stay. Data elements eligible for model-building included lab values, medications and dosages, procedures, and demographics. We assessed model discrimination using the area under the receiver operator characteristic curve and r-squared values. 2241 individuals were available for analysis. Both modeling techniques created viable models with very good discrimination ability, with AUCs exceeding 0.85 for dialysis and 0.8 for death prediction. Model performance was similar across model building strategies, though the strategy employing more advanced variable selection was more parsimonious. Very good to excellent prediction of outcome events is feasible in patients with AKI. More advanced techniques may lead to more parsimonious models, which may facilitate adoption in other settings.

Reoperation rates of anterior cervical discectomy and fusion versus posterior laminoplasty for multilevel cervical degenerative diseases: a population-based cohort study in Taiwan

BACKGROUND CONTEXT

The reoperation (reop) rate is a crucial indicator of the efficacy of an operation; however, studies on the reop rates of anterior cervical discectomy and fusion (ACDF) or posterior laminoplasty (LMP) for treating multilevel cervical degenerative diseases (MCDDs) are scant.

PURPOSE

This study aimed to compare the reop rates and safety of ACDF and LMP for MCDD treatment.

STUDY DESIGN

This is a retrospective population-based cohort study.

PATIENT SAMPLE

Our sample consists of patients who underwent ACDF and LMP treatment.

OUTCOME MEASURES

Reop rate, risk of pneumonia, sepsis, surgery-related complications, and death.

METHODS

A total of 6,605 patients who underwent ACDF and 1,578 patients who underwent LMP for MCDD treatment from 2001 to 2011 were selected from the Taiwan National Health Insurance Research Database. Cox proportional hazard models were performed to compare the clinical outcomes of the patients who underwent ACDF with those of the patients who underwent LMP.

RESULTS

Long-term reop rates (per 100 person-month) were slightly Anterior cervical discectomy and fusion; in the patients who underwent ACDF (0.04 [95% confidence interval, CI: 0.03-0.05]) than in those who underwent LMP (0.06 [95% CI: 0.04-0.08]), with adjusted hazard ratio (HR) of 1.43 (95% CI: 0.96-2.11, p=.08), although short-term reop rates were significantly higher in the LMP group (0.41 [95% CI: 0.33-0.51]) than in the ACDF group (0.09 [95% CI: 0.07-0.11]), with adjusted HR of 4.81 (95% CI: 3.46-6.69, p<.001). Patients who underwent LMP had a lower risk of pneumonia, sepsis, surgery-related complications, and death than did those who underwent ACDF within a year of follow-up. The results after adjustment for all covariates showed that osteoarthritis (adjusted HR=2.07, 95% CI: 1.40-3.06, p<.01) was associated with reop risk in the patients who underwent ACDF, and diabetes (adjusted HR=3.27, 95% CI: 1.12-9.54, p=.03) was associated with reop risk in the patients who underwent LMP.

CONCLUSIONS

There was no significantly higher incidence rate of reop between the patients who underwent LMP and those who underwent ACDF after 1-year follow-up; however, ACDF was associated with a higher rate of 1-year complications and mortality compared with LMP. LMP might be considered as a treatment option for MCDD but could not be appropriate for patients with cervical kyphotic deformity.

Prediction of ATLS hypovolemic shock class in rats using the perfusion index and lactate concentration

It is necessary to quickly and accurately determine Advanced Trauma Life Support (ATLS) hemorrhagic shock class for triage in cases of acute hemorrhage caused by trauma. However, the ATLS classification has limitations, namely, with regard to primary vital signs. This study identified the optimal variables for appropriate triage of hemorrhage severity, including the peripheral perfusion index and serum lactate concentration in addition to the conventional primary vital signs. To predict the four ATLS classes, three popular machine learning algorithms with four feature selection methods for multicategory classification were applied to a rat model of acute hemorrhage. A total of 78 anesthetized rats were divided into four groups for ATLS classification based on blood loss (in percent). The support vector machine one-versus-one model with the Kruskal-Wallis feature selection method performed best, with 80.8% accuracy, relative classifier information of 0.629, and a kappa index of 0.732. The new hemorrhage-induced severity index (lactate concentration/perfusion index), diastolic blood pressure, mean arterial pressure, and the perfusion index were selected as the optimal variables for predicting the four ATLS classes by support vector machine one-versus-one with the Kruskal-Wallis method. These four variables were also selected for binary classification to predict ATLS classes I and II versus III and IV for blood transfusion requirement. The suggested ATLS classification system would be helpful to first responders by indicating the severity of patients, allowing physicians to prepare suitable resuscitation before hospital arrival, which could hasten treatment initiation.

Development and validation of osteoporosis prescreening model for Iranian postmenopausal women

Background

Studies have indicated that the commonly used osteoporosis prescreening tools are not appropriate for use in every nation. This study was designed to develop and validate a prescreening model for bone mineral densitometry among Iranian postmenopausal women.

Methods

From 13613 individuals who were referred for bone mineral densitometry in Shariati hospital in Tehran, 8644 postmenopausal women were considered for the study after excluding men and premenopausal women. Questionnaires regarding the risk factors for osteoporosis were filled for each individual. Bone mineral density at the lumbar vertebrae (L2-L4), femoral neck and total femur was measured by dual X-ray absorptiometry. Using holdout validation, the study sample was divided into two parts; training set (5705) and test set (2939). Logistic regression analysis was performed on the training set. A scoring model was developed and tested in the test set.

Results

Based on the training set, a seven-variable model named OPMIP (Osteoporosis Prescreening Model for Iranian Postmenopausal women) was developed with C statistics (area under curve) of 0.72. Using a cut-off of -2.5 for the model, the sensitivity, specificity, positive predictive value and negative predictive value were 72%, 59.5%, 64% and 69% respectively. The model performance was tested in the test set. OPMIP correctly classified 67.10% of cases with a sensitivity and specificity of 73.2% and 61%.

Conclusions

In order to appropriately refer patients for a bone mineral densitometry, OPMIP can be used as a prescreening tool in Iranian Postmenopausal women.

Screening for pre-diabetes using support vector machine model

The global prevalence of diabetes is rapidly increasing. Studies support screening and interventions for pre-diabetes, which results in serious complications and diabetes. This study aimed at developing an intelligence-based screening model for pre-diabetes that could assist with decreasing the prevalence of diabetes through early identification and subsequent interventions. Data from the Korean National Health and Nutrition Examination Survey (KNHANES) were used, excluding subjects with diabetes. The KNHANES 2010 data (n = 4,685) were used for training and internal validation, while data from KNHANES 2011 (n = 4,566) were used for external validation. We developed a model to screen for pre-diabetes using support vector machine (SVM), and performed a systematic evaluation of the SVM model using internal and external validation. We compared the performance of the SVM model with that of a screening score model based on logistic regression analysis for pre-diabetes that had been developed previously. Backward elimination logistic regression resulted in associations between pre-diabetes and age, sex, waist circumference, body mass index, alcohol intake, family history of diabetes, and hypertension. The areas under the curves (AUCs) for the SVM model in the internal and external datasets were 0.761 and 0.731, respectively, while the AUCs for the screening score model were 0.734 and 0.712, respectively. The SVM model developed in this study performed better than the screening score model that had been developed previously and may be more effective for pre-diabetes screening.

Screening for prediabetes using machine learning models

The global prevalence of diabetes is rapidly increasing. Studies support the necessity of screening and interventions for prediabetes, which could result in serious complications and diabetes. This study aimed at developing an intelligence-based screening model for prediabetes. Data from the Korean National Health and Nutrition Examination Survey (KNHANES) were used, excluding subjects with diabetes. The KNHANES 2010 data (n = 4685) were used for training and internal validation, while data from KNHANES 2011 (n = 4566) were used for external validation. We developed two models to screen for prediabetes using an artificial neural network (ANN) and support vector machine (SVM) and performed a systematic evaluation of the models using internal and external validation. We compared the performance of our models with that of a screening score model based on logistic regression analysis for prediabetes that had been developed previously. The SVM model showed the areas under the curve of 0.731 in the external datasets, which is higher than those of the ANN model (0.729) and the screening score model (0.712), respectively. The prescreening methods developed in this study performed better than the screening score model that had been developed previously and may be more effective method for prediabetes screening.