Applications of Machine Learning in Bone and Mineral Research

Kong, Sung Hye; Shin, Chan Soo

doi:10.3803/enm.2021.1111

Cited by 19 publications

(8 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML essentially means that the computer itself learns patterns in the data and makes predictions on future data based on the patterns obtained. Current studies have shown that ML methods can be used to predict osteoporosis, and ML algorithms for osteoporotic risk assessment have shown the advantages of high accuracy and simplicity [ [51] , [52] , [53] , [54] , [55] ]. However, most of these studies have focused on predicting osteoporosis in older adults and postmenopausal women, and few reports have emerged to demonstrate the risk factors for diabetes-related fractures in China using ML algorithms.…”

Section: Discussionmentioning

confidence: 99%

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

Chu¹,

Jiang²,

Chen³

et al. 2023

Heliyon

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

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

Chu¹,

Jiang²,

Chen³

et al. 2023

Heliyon

View full text Add to dashboard Cite

“…A particular interest is observed in the field of total joint arthroplasty, where ML has been effectively employed in the analysis of tabular data, processing of medical imagery, and the interpretation of natural language. ML models are proficient in identifying fractures, classifying implant types in radiographic images, and discerning osteoarthritis stages through gait analysis [ 31 ]. Despite these promising developments and growing adoption of ML in orthopedics, several challenges persist.…”

Section: Reviewmentioning

confidence: 99%

Leveraging Artificial Intelligence and Machine Learning in Regenerative Orthopedics: A Paradigm Shift in Patient Care

Jeyaraman,

Ratna,

Jeyaraman

et al. 2023

Cureus

View full text Add to dashboard Cite

The integration of artificial intelligence (AI) and machine learning (ML) into regenerative orthopedics heralds a paradigm shift in clinical methodologies and patient management. This review article scrutinizes AI's role in augmenting diagnostic accuracy, refining predictive models, and customizing patient care in orthopedic medicine. Focusing on innovations such as KeyGene and CellNet, we illustrate AI's adeptness in navigating complex genomic datasets, cellular differentiation, and scaffold biodegradation, which are critical components of tissue engineering. Despite its transformative potential, AI's clinical adoption remains in its infancy, contending with challenges in validation, ethical oversight, and model training for clinical relevance. This review posits AI as a vital complement to human intelligence (HI), advocating for an interdisciplinary approach that merges AI's computational prowess with medical expertise to fulfill precision medicine's promise. By analyzing historical and contemporary developments in AI, from the foundational theories of McCullough and Pitts to sophisticated neural networks, the paper emphasizes the need for a synergistic alliance between AI and HI. This collaboration is imperative for improving surgical outcomes, streamlining therapeutic modalities, and enhancing the quality of patient care. Our article calls for robust interdisciplinary strategies to overcome current obstacles and harness AI's full potential in revolutionizing patient outcomes, thereby significantly contributing to the advancement of regenerative orthopedics and the broader field of scientific research.

show abstract

“…23 Most studies using machine learning are cross sectional and examine the ability to identify persons with prevalent fractures or osteoporosis (BMD T-Score ≤ -2.5 SD). [24][25][26][27] This is the first prospective study using deep learning to derive an algorithm that identifies women having incident fractures during five years. The algorithm was developed by interrogating the three-dimensional images of bone and soft tissue, no other information was used.…”

Section: Many Qualities Of Bone Not Captured By Bmd But Not Yet Quant...mentioning

confidence: 99%

“…Application of Deep Learning to medical imaging 24 facilitates the investigation of bone's multilayered qualities and has been reported to identify patients with prevalent fractures or osteoporosis in cross sectional studies. [25][26][27] However, no prospective studies have applied deep learning using only the high resolution 3-dimensional images of bone and soft tissue to determine whether an algorithm, a Structural Fragility Score derived by Artificial Intelligence (SFS-AI), might capture deteriorated bone qualities and soft tissue.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Using High-Resolution Images of Forearm Predicts Fracture

Chapurlat

Ferrari

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

Importance Fragility fractures are a public health problem. Over 70% of women having fractures have osteopenia or normal BMD, but they remain unidentified and untreated because the definition of ‘osteoporosis’, a bone mineral density (BMD) T-Score ≤ -2.5SD, is often used to signal bone fragility.Objective As deep learning facilitates investigation of bone’s multi-level hierarchical structure and soft tissue, we tested whether this approach might better identify women at risk of fracture before fracture.Design We pooled data from three French and Swiss prospective population-based cohorts (OFELY, QUALYOR, GERICO) that collected clinical risk factors for fracture, areal BMD and distal radius measurements with high resolution peripheral quantitative tomography (HRpQCT). Using only three-dimensional images of the distal radius, ulna and soft tissue acquired by HRpQCT, an algorithm, a Structural Fragility Score-Artificial Intelligence (SFS-AI), was trained to distinguish 277 women having fractures from 1401 remaining fracture-free during 5 years and then was tested in a validation cohort of 422 women.Setting European postmenopausal womenParticipants We have studied postmenopausal women considered as representative of the general population, who were followed for a median 9.4 years in OFELY, 5.4 years in QUALYOR and 5.7 years in GERICO.Main outcome and measure All types of incident fragility fracturesResults We used data from 2666 postmenopausal women, with age range of 42-94. In women ≥ 65 years having ‘All Fragility Fractures’ or ‘Major Fragility Fractures’, SFS-AI generated an AUC of 66-70%, sensitivities of 60-68% and specificity of 71%. Sensitivities were greater than achieved by the fracture risk assessment (FRAX) with BMD or BMD (6.7-26.7%) with lower specificities than these diagnostics (~95%).Conclusion The SFS-AI is a holistic surrogate of fracture risk that pre-emptively identifies most women needing prompt treatment to avert a first fracture.

show abstract

Applications of Machine Learning in Bone and Mineral Research

Cited by 19 publications

References 71 publications

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

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

Leveraging Artificial Intelligence and Machine Learning in Regenerative Orthopedics: A Paradigm Shift in Patient Care

Deep Learning Using High-Resolution Images of Forearm Predicts Fracture

Contact Info

Product

Resources

About