The diagnostic accuracy of AI-driven opportunistic osteoporosis screening based on routine non-contrast CT DOI Creative Commons

Baolian Zhao,

Ke Sun, Qianhui Shen

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 17, 2024

Abstract Background The diagnosis of osteoporosis is great clinical significance for the prevention fracture. To evaluate performance an artificial intelligence (AI) software opportunistic screening using non-contrast computed tomography (NCCT) compared to dual-energy X-ray absorptiometry (DXA). Methods This retrospective study included 518 patients who underwent both DXA and lumbar NCCT (LNCCT). Bone quality was classified into three groups—normal, osteopenia, osteoporosis—based on DXA. Commercially available AI used automatically segment vertebrae extract volumetric bone mineral density (vBMD) values from T12 L2 (thoracic 12 2) LNCCT. Four classification methods were devised AI-based vBMD assessment: method1 (average (avg) vBMD(T12+L1+L2)), method2 (avg vBMD(T12+L1)), method3 vBMD(T12+L2)), method4 vBMD(L1+L2)). Agreements among analyzed intraclass correlation coefficients (ICCs), Bland-Altman analysis, Linear Cohen’s weighted kappa statistics. Multi-categorical logistic regression receiver operating characteristic (ROC) curves employed estimate diagnostic four methods. A p-value less than 0.05 considered statistically significant. Results showed reasonable agreement with one another (ICC [95% confidence interval, CI]: 0.909[0.893–0.923]). between 1–4 good [95%CI]: 0.689[0.641,0.732], 0.649[0.594,0.698], 0.666[0.616,0.712], 0.680[0.631,0.724], respectively). decision function exhibited promising performance, precision 0.834 recall 0.735 diagnosing in those normal osteopenic conditions. Conclusions all found be when Among these methods, avg vBMD(T12+L1+L2) (method 1) best performance.

Language: Английский

Osteoporosis and reproductive health DOI Creative Commons

Danijela Ristovski-Kornic,

Mirela Matejić

Arhiv za farmaciju, Journal Year: 2025, Volume and Issue: 75(1), P. 15 - 31

Published: Jan. 1, 2025

Osteoporosis is a prevalent issue among menopausal women; however, the number of women with risk factors across all age groups increasing. This trend can lead to development osteopenia or osteoporosis at younger age, significantly impacting women's physical, emotional, and mental well-being. review aims evaluate current literature on prevalence its most common groups. It serves as an updated reference for readers, helping understand fundamental pathophysiological mechanisms disease, diagnostic methods, role medications lifestyle in prevention. Some authors suggest that dominant mechanism bone mass loss slowed osteoblastic formation, while others highlight increased breakdown matrix more prominent skeletal damage, depending underlying cause osteoporosis. Increased fragility higher tendency towards pathological fractures impact both quality life expectancy women. Therefore, it recommended osteological screening fracture assessment become mandatory component individualized care The focus health has shifted from postmenopausal treatment preventative care.

Language: Английский

Citations

0
Osteoporosis Risk Assessment and Individualized Feature Analysis Using Interpretable XAI and RAI Techniques DOI Open Access
Shivam Rajput, Rishabha Malviya, Sathvik Belagodu Sridhar

et al.

Published: March 3, 2025

Language: Английский

Citations

0
Exploring the Impact of Artificial Intelligence on Patient Care: A Comprehensive Review of Healthcare Advancements DOI Open Access

Sharmila Nirojini P,

K Kanaga,

S.V. Devika

et al.

Scholars Academic Journal of Pharmacy, Journal Year: 2024, Volume and Issue: 13(02), P. 67 - 81

Published: Feb. 28, 2024

Artificial Intelligence (AI) is revolutionizing healthcare by transforming disease identification, treatment, and management. Healthcare organizations are rapidly adopting AI technologies to improve patient outcomes, streamline operations, optimize costs. Utilizing a broad toolkit comprising Robotics, Computer Vision, Natural Language Processing, Machine Learning, has made significant advancements across various domains. AI-driven diagnostic systems showcased for their precision in analyzing medical images, enabling early detection of diseases such as cancer. Personalized treatment plans preventive treatments possible predictive analytics, which uses large amounts data predict the course identify those who at risk. This leads an improvement care. Beyond clinical applications, reshaping delivery through solutions like telemedicine, virtual consultations, remote monitoring. Virtual Health Assistants, empowered AI, deliver personalized health information, medication reminders, lifestyle guidance, enhancing engagement adherence. Telemedicine employ algorithms enhance resource allocation, expedite appointment scheduling, supply superior services isolated populations. Hence, AI’s potential productivity, encourage creativity, solve difficult problems sophisticated analysis automation what it so important many sectors.

Language: Английский

Citations

3
Diagnostic accuracy of chest X-ray and CT using artificial intelligence for osteoporosis: systematic review and meta-analysis DOI
Norio Yamamoto, Akihiro Shiroshita, Ryota Kimura

et al.

Journal of Bone and Mineral Metabolism, Journal Year: 2024, Volume and Issue: 42(5), P. 483 - 491

Published: Aug. 21, 2024

Language: Английский

Citations

3
Relationship of Chronic Stress and Hypertension with Bone Resorption DOI Creative Commons
M. Paulini,

Mariangeles Aimone,

Sara Feldman

et al.

Journal of Functional Morphology and Kinesiology, Journal Year: 2025, Volume and Issue: 10(1), P. 21 - 21

Published: Jan. 4, 2025

Background/Objectives: Chronic exposure to stress has been considered a risk factor for hypertension, which is also associated with increased bone resorption. This review aimed investigate the effect of acute and chronic stress, on skeletal system. Methods: A comprehensive search was conducted across multiple databases, focusing peer-reviewed articles published in English. We include experimental, clinical, studies focused relationship between Searches were MEDLINE via PubMed, Embase Scopus, last completed 10 September 2024. Results: The main topics situations that favor loss, such as psychological can lead osteoporotic fractures through immunological endocrine mechanisms. loss density, osteoporosis, occurs due reduction number osteoblasts balance physiological formation/resorption. Conclusions: significantly affects cardiovascular health narrative study highlights vulnerability system, along prolonged emphasizing need multidisciplinary strategies preventing stress-related conditions. Effective management help reduce risks disease resorption, their role care.

Language: Английский

Citations

0
Artificial intelligence—based diagnosis of oral leukoplakia using deep convolutional neural networks Xception and MobileNet-v2 DOI Creative Commons
Ramesh Eluri, Anuradha Ganesan,

Krithika Chandrasekar Lakshmi

et al.

Frontiers in Oral Health, Journal Year: 2025, Volume and Issue: 6

Published: March 21, 2025

Objective The present study aims to employ and compare the artificial intelligence (AI) convolutional neural networks (CNN) Xception MobileNet-v2 for diagnosis of Oral leukoplakia (OL) differentiate its clinical types from other white lesions oral cavity. Materials methods Clinical photographs non-oral were gathered SRM Dental College archives. An aggregate 659 photos, based on convenience sampling included archive in dataset. Around 202 pictures while 457 lesions. Lesions considered differential like frictional keratosis, candidiasis, lichen planus, lichenoid reactions, mucosal burns, pouch carcinoma under subset. A total 261 images constituting test sample, arbitrarily selected collected dataset, whilst remaining served as training validation datasets. dataset engaged data augmentation enhance quantity variation. Performance metrics accuracy, precision, recall, f1_score incorporated CNN model. Results models both MobileNetV2 able diagnose OL using photographs. In terms F1-score overall MobilenetV2 model performed noticeably better than Conclusion We demonstrate that are capable 89%–92% accuracy can be best used discern

Language: Английский

Citations

0
AI in Orthopedic Research: A Comprehensive Review DOI
Abdülhamit Mısır, Ali Yüce

Journal of Orthopaedic Research®, Journal Year: 2025, Volume and Issue: unknown

Published: May 26, 2025

ABSTRACT Artificial intelligence (AI) is revolutionizing orthopedic research and clinical practice by enhancing diagnostic accuracy, optimizing treatment strategies, streamlining workflows. Recent advances in deep learning have enabled the development of algorithms that detect fractures, grade osteoarthritis, identify subtle pathologies radiographic magnetic resonance images with performance comparable to expert clinicians. These AI‐driven systems reduce missed diagnoses provide objective, reproducible assessments facilitate early intervention personalized planning. Moreover, AI has made significant strides predictive analytics integrating diverse patient data—including gait imaging features—to forecast surgical outcomes, implant survivorship, rehabilitation trajectories. Emerging applications robotics, augmented reality, digital twin technologies, exoskeleton control promise further transform preoperative planning intraoperative guidance. Despite these promising developments, challenges such as data heterogeneity, algorithmic bias, “black box” nature many models—as well issues robust validation—remain. This comprehensive review synthesizes current critically examines limitations, outlines future directions for into musculoskeletal care.

Language: Английский

Citations

0
Automated deep learning-based bone mineral density assessment for opportunistic osteoporosis screening using various CT protocols with multi-vendor scanners DOI Creative Commons
Heejun Park, Woo Young Kang, Ok Hee Woo

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 23, 2024

This retrospective study examined the diagnostic efficacy of automated deep learning-based bone mineral density (DL-BMD) measurements for osteoporosis screening using 422 CT datasets from four vendors in two medical centers, encompassing 159 chest, 156 abdominal, and 107 lumbar spine datasets. DL-BMD values on L1 L2 vertebral bodies were compared with manual BMD (m-BMD) Pearson's correlation intraclass coefficients. Strong agreement was found between m-BMD total scans (r = 0.953, p < 0.001). The performance assessed receiver operating characteristic analysis low by dual-energy x-ray absorptiometry (DXA) m-BMD. Compared to DXA, demonstrated an AUC 0.790 (95% CI 0.733-0.839) 0.769 0.710-0.820) osteoporosis, sensitivity, specificity, accuracy 80.8% 74.2-86.3%), 56.3% 43.4-68.6%), 74.3% 68.3-79.7%) 65.4% 50.9-78.0%), 70.9% 63.8-77.3%), 69.7% 63.5-75.4%) respectively. m-BMD, showed 0.983 0.973-0.993) 0.972 0.958-0.987) 97.3% 94.5-98.9%), 85.2% 78.8-90.3%), 92.7% 89.7-95.0%) 94.4% 88.3-97.9%), 89.5% 85.6-92.7%), 90.8% 87.6-93.4%) DL-based method can provide accurate reliable assessments across diverse protocols scanners.

Language: Английский

Citations

2
Orthopädie und Unfallchirurgie im digitalen Zeitalter DOI
Sebastian Kühn, Johannes Knitza

Deleted Journal, Journal Year: 2024, Volume and Issue: 53(5), P. 327 - 335

Published: March 27, 2024

Die digitale Transformation prägt die Zukunft der Orthopädie und Unfallchirurgie maßgeblich. Telemedizin, Gesundheitsanwendungen, elektronische Patientenakten künstliche Intelligenz spielen dabei eine zentrale Rolle. Diese Technologien haben das Potenzial, medizinische Versorgung zu verbessern, individualisierte Behandlungspläne ermöglichen den Behandlungsprozess entlasten. Allerdings bestehen aktuell Herausforderungen in Bereichen Infrastruktur, Regulatorik, Erstattung Datenschutz. Eine effektive erfordert ein tiefgreifendes Verständnis sowohl Technologie als auch klinischen Praxis. Orthopäden Unfallchirurgen müssen Führungsrolle übernehmen, indem sie sich aktiv mit neuen auseinandersetzen, neue Behandlungsabläufe gestalten ihre medizinischen Kompetenzen durch KI-Kompetenzen erweitern. Integration digitaler Aus- fachärztliche Weiter‑/Fortbildung wird entscheidend sein für aktive Gestaltung digitalen Nutzung ihres vollen Potenzials.

Citations

1
Gene expression and hormonal signaling in osteoporosis: from molecular mechanisms to clinical breakthroughs DOI
Gurinderdeep Singh,

Ronald Darwin,

Krishna Chandra Panda

et al.

Journal of Biomaterials Science Polymer Edition, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 36

Published: Dec. 27, 2024

Osteoporosis is well noted to be a universal ailment that realization impaired bone mass and micro architectural deterioration thus enhancing the probability of fracture. Despite its high incidence, management remains highly demanding because multifactorial pathophysiology disease. This review highlights recent findings in osteoporosis particularly, gene expression hormonal control. Some newest approaches regarding subject are described, including single-cell RNA sequencing long non-coding RNAs. Also, reflects new on signaling estrogen parathyroid hormone; patient-specific due genetic variation. Potential biomarkers AI comprised as factors for improving ability anticipate manage fractures. These hold great potential drugs, combination therapies based future. Further studies cooperation scientists clinicians will help apply such novelties into practical uses sphere medicine order enhance treatment patients with osteoporosis.

Language: Английский

Citations

1