Ensemble artificial neural networks applied to predict the key risk factors of hip bone fracture for elders

Ensemble-learning approach improves fracture prediction using genomic and phenotypic data

This study presents an innovative ensemble machine learning model integrating genomic and clinical data to enhance the prediction of major osteoporotic fractures in older men. The Super Learner (SL) model achieved superior performance (AUC = 0.76, accuracy = 95.6%, sensitivity = 94.5%, specificity = 96.1%) compared to individual models. Ensemble machine learning improves fracture prediction accuracy, demonstrating the potential for personalized osteoporosis management.

PURPOSE

Existing fracture risk models have limitations in their accuracy and in integrating genomic data. This study developed and validated an innovative ensemble machine learning (ML) model that combines multiple algorithms and integrates clinical, lifestyle, skeletal, and genomic data to enhance prediction for major osteoporotic fractures (MOF) in older men.

METHODS

This study analyzed data from 5130 participants in the Osteoporotic Fractures in Men cohort Study. The model incorporated 1103 individual genome-wide significant variants and conventional risk factors of MOF. The participants were randomly divided into training (80%) and testing (20%) sets. Seven ML algorithms were combined using the SL ensemble method with tenfold cross-validation MOF prediction. Model performance was evaluated on the testing set using the area under the curve (AUC), the area under the precision-recall curve, calibration, accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), and reclassification metrics. SL model performances were evaluated by comparison with baseline models and subgroup analyses by race.

RESULTS

The SL model demonstrated the best performance with an AUC of 0.76, accuracy of 95.6%, sensitivity of 94.5%, specificity of 96.1%, NPV of 95.1%, and PPV of 94.7%. Among the individual ML, gradient boosting performed optimally. The SL model outperformed baseline models, and it also achieved accuracies of 93.1% for Whites and 91.6% for Minorities, outperforming single ML in subgroup analysis.

CONCLUSION

The ensemble learning approach significantly improved fracture prediction accuracy and model performance compared to individual ML. Integrating genomic and phenotypic data via the SL approach represents a promising advancement for personalized osteoporosis management.

Artificial intelligence in fracture detection with different image modalities and data types: A systematic review and meta-analysis

Artificial Intelligence (AI), encompassing Machine Learning and Deep Learning, has increasingly been applied to fracture detection using diverse imaging modalities and data types. This systematic review and meta-analysis aimed to assess the efficacy of AI in detecting fractures through various imaging modalities and data types (image, tabular, or both) and to synthesize the existing evidence related to AI-based fracture detection. Peer-reviewed studies developing and validating AI for fracture detection were identified through searches in multiple electronic databases without time limitations. A hierarchical meta-analysis model was used to calculate pooled sensitivity and specificity. A diagnostic accuracy quality assessment was performed to evaluate bias and applicability. Of the 66 eligible studies, 54 identified fractures using imaging-related data, nine using tabular data, and three using both. Vertebral fractures were the most common outcome (n = 20), followed by hip fractures (n = 18). Hip fractures exhibited the highest pooled sensitivity (92%; 95% CI: 87-96, p< 0.01) and specificity (90%; 95% CI: 85-93, p< 0.01). Pooled sensitivity and specificity using image data (92%; 95% CI: 90-94, p< 0.01; and 91%; 95% CI: 88-93, p < 0.01) were higher than those using tabular data (81%; 95% CI: 77-85, p< 0.01; and 83%; 95% CI: 76-88, p < 0.01), respectively. Radiographs demonstrated the highest pooled sensitivity (94%; 95% CI: 90-96, p < 0.01) and specificity (92%; 95% CI: 89-94, p< 0.01). Patient selection and reference standards were major concerns in assessing diagnostic accuracy for bias and applicability. AI displays high diagnostic accuracy for various fracture outcomes, indicating potential utility in healthcare systems for fracture diagnosis. However, enhanced transparency in reporting and adherence to standardized guidelines are necessary to improve the clinical applicability of AI. Review Registration: PROSPERO (CRD42021240359).

The synergy of synchrotron imaging and convolutional neural networks towards the detection of human micro-scale bone architecture and damage

The growing health and economic burden of bone fractures, their intricate multiscale features and the existing knowledge gaps in the comprehension of micro-scale bone damage occurrence make fracture diagnosis a challenging issue. In this scenario, deep-learning and artificial intelligence embody the new frontier of healthcare system, by overcoming the subjectivity of clinicians in the analysis of medical images. However, the preliminary attempts in exploiting the power of machine learning algorithms such as neural networks are still limited to bone macro-scale, while there is an evident lack in their application to smaller scales, where damage starts nucleating. Currently, speculations at the micro-scale are only feasible with the aid of high-resolution imaging techniques, that are particularly time consuming in terms of output images analysis. In this context, this works aims at combining the visualization of the micro-crack propagation mechanism with the promising application of convolutional neural networks. The implemented artificial intelligence tool is based for the first time on a large number of human synchrotron images coming from healthy and osteoporotic femoral heads tested under micro-compression. The designed convolutional neural networks are able to automatically detect lacunae and micro-cracks at different compression levels with high accuracy levels; indeed, with the baseline setup, networks achieve more than 0.99 level of accuracy for both cracks and lacunae, and more than 0.87 of the meanIoU adopted as validation metric. This approach is particularly encouraging for the development of powerful recognition system to comprehend bone micro-damage initiation and propagation, paving the way to the application of machine learning studies to bone micromechanics. This could be additionally crucial for future patient specific micro-scale observations to be related to the clinical practice.

A method based on non-ionizing microwave radiation for ancillary diagnosis of osteoporosis: a pilot study

Background

Osteoporosis is a condition characterized by low bone mineral density, which typically leads to fractures and reduced quality of life. Currently, diagnostic devices used to assess this condition (e.g., dual-energy X-ray absorptiometry) are very costly, making it infeasible to meet the demand for testing in most countries. Therefore, we proposed a preclinical validation of a prototype called Osseus in an attempt to enhance osteoporosis screening tests and alleviate their costs. Osseus is a device developed to assist bone mineral density classification. It integrates a microcontroller into other peripheral devices to measure the attenuation at the middle phalanx of the middle finger, with two antennas operating at the 2.45 GHz frequency.

Results

We conducted tests with plaster, poultry, and porcine bones. A comparison of the measurements of the original and mechanically altered samples demonstrated that the device can handle the complexity of the tissues within the bone structure and characterize its microarchitecture.

Conclusions

Osseus is a device that has been preliminarily validated. Ionising radiation needed for DXA tests is replaced by non-ionising microwave electromagnetic radiation. Osseus enables early detection of osteoporosis, reduces costs, and optimizes high-complexity testing referrals. There is a lack of validation studies with the reference/gold standard that are currently under development.

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.

Application and Development of Artificial Intelligence and Intelligent Disease Diagnosis

With the continuous development of artificial intelligence (AI) technology, big data-supported AI technology with considerable computer and learning capacity has been applied in diagnosing different types of diseases. This study reviews the application of expert systems, neural networks, and deep learning used by AI technology in disease diagnosis. This paper also gives a glimpse of the intelligent diagnosis and treatment of digestive system diseases, respiratory system diseases, and osteoporosis by AI technology.

Computer-aided diagnosis systems for osteoporosis detection: a comprehensive survey

Computer-aided diagnosis (CAD) has revolutionized the field of medical diagnosis. They assist in improving the treatment potentials and intensify the survival frequency by early diagnosing the diseases in an efficient, timely, and cost-effective way. The automatic segmentation has led the radiologist to successfully segment the region of interest to improve the diagnosis of diseases from medical images which is not so efficiently possible by manual segmentation. The aim of this paper is to survey the vision-based CAD systems especially focusing on the segmentation techniques for the pathological bone disease known as osteoporosis. Osteoporosis is the state of the bones where the mineral density of bones decreases and they become porous, making the bones easily susceptible to fractures by small injury or a fall. The article covers the image acquisition techniques for acquiring the medical images for osteoporosis diagnosis. The article also discusses the advanced machine learning paradigms employed in segmentation for osteoporosis disease. Other image processing steps in osteoporosis like feature extraction and classification are also briefly described. Finally, the paper gives the future directions to improve the osteoporosis diagnosis and presents the proposed architecture. Graphical abstract.

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.

Intelligent Noninvasive Diagnosis of Aneuploidy: Raw Values and Highly Imbalanced Dataset

The objective of this paper is to introduce a noninvasive diagnosis procedure for aneuploidy and to minimize the social and financial cost of prenatal diagnosis tests that are performed for fetal aneuploidies in an early stage of pregnancy. We propose a method by using artificial neural networks trained with data from singleton pregnancy cases, while undergoing first trimester screening. Three different datasets¹ with a total of 122 362 euploid and 967 aneuploid cases were used in this study. The data for each case contained markers collected from the mother and the fetus. This study, unlike previous studies published by the authors for a similar problem differs in three basic principles: 1) the training of the artificial neural networks is done by using the markers' values in their raw form (unprocessed), 2) a balanced training dataset is created and used by selecting only a representative number of euploids for the training phase, and 3) emphasis is given to the financials and suggest hierarchy and necessity of the available tests. The proposed artificial neural networks models were optimized in the sense of reaching a minimum false positive rate and at the same time securing a 100% detection rate for Trisomy 21. These systems correctly identify other aneuploidies (Trisomies 13&18, Turner, and Triploid syndromes) at a detection rate greater than 80%. In conclusion, we demonstrate that artificial neural network systems can contribute in providing noninvasive, effective early screening for fetal aneuploidies with results that compare favorably to other existing methods.

A New Ensemble Classification System For Fracture Zone Prediction Using Imbalanced Micro-CT Bone Morphometrical Data

Trabecular bone fractures constitute a major health issue for the modern societies, with the currently established prediction methods of fracture risk, such as bone mineral density (BMD), resulting in errors up to 40%. Fracture-zone prediction based on bone's microstructure has been recently proposed as an alternative prediction method of fracture risk. In this paper, a classification system (CS) for the automatic fracture-zone prediction based on an Ensemble of Imbalanced Learning methods is proposed, following the observation that the percentage of the actual fractured bone area is significantly smaller than the intact bone in the case of a fracture event. The sample is divided into Volumes of Interest (VOIs) of specific size and 29 morphometrical parameters are calculated from each VOI, which serve as input features for the CS in order for it to separate the input patterns in to two classes: fractured and nonfractured. To this end, two well-established Imbalanced Learning methods, namely Random Undersampling and Synthetic Minority Oversampling, and two popular classification algorithms, namely Multilayer Perceptrons and Support Vector Machines, are tested and combined accordingly, to provide the best possible performance on a dataset that contains 45 specimens' pre- and postfailure scans. The best combination is then compared with three well-established Ensembles of Imbalanced Learning methods, namely RUSBoost, UnderBagging and SMOTEBagging. The experimental results clearly show that the proposed CS outperforms the competition, scoring in some occasions more than 90% in G-Mean and Area under Curve metrics. Finally, an investigation on the significance of the various trabecular bone's biomechanical parameters is made using the sequential forward floating selection technique, in order to identify possible biomarkers for fracture-zone prediction.