Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Sheth et al. reported that pretreatment with abaloparatide can increase bone mineral density in regions of the proximal femur that are in contact with the femoral stem of an implant in postmenopausal women with osteoporosis. An interesting finding reported is that the Gruen zones most affected by stress-shielding-induced bone loss following total hip arthroplasty were positively affected by the pretreatment, along with other proximal regions of the femur. What was not explored in this study is whether this increase in bone mineral density in the proximal femur was sufficient to affect the biomechanical properties of the bone, specifically the magnitude of stress-shielding-induced bone loss. The application of bone-adaptive modeling would be an interesting next step to address this, and it could involve the application of artificial intelligence (AI).AI has been used in medicine in various ways since the 1950s, from machine learning and chatbots that aimed to mimic human conversation to the 2020s when AI was trained to diagnose benign polyps and malignant polyps found in colonoscopies 1 . Overall, the application of AI has been slow in medicine compared with other fields, but it has been particularly slower in orthopaedics. A brief PubMed search using the key terms of "artificial intelligence in orthopaedics" yielded only 3,890 articles from 1976 to 2024. This result is much smaller than in other fields such as radiology (23,858 articles) or cancer (39,315 articles) during the same period. With the potential of AI continuously evolving, application in the field remains a moving target and can lead to confusion for researchers and clinicians.However, in a recent review 2 , 3 essential "domains" for the use of AI in personalizing orthopaedic care and improving outcomes were highlighted: (1) personalized prediction of clinical outcomes and adverse events, (2) automated diagnostic imaging analyses, and (3) forecasting resource utilization. The first 2 domains directly apply to the article by Sheth et al. and would contribute to understanding bone-adaptive modeling and the biomechanical properties associated with total hip arthroplasty. The third domain, forecasting resource utilization, is downstream of their article, but is still pertinent to the discussion of using AI in orthopaedics.The prediction of clinical outcomes and adverse events is difficult and continues to be a challenge. Machine learning has been used to predict bone mineral density from genomic data 3 or unplanned readmissions following total knee arthroplasty 4 . Another article used intraoperative load sensors and AI to improve accuracy and precision of force measurements during the balancing of total knee arthroplasty 5 . These few examples show a diverse application of predictive AI that, with improvements to the algorithms, sensors, and programs, can provide a sophisticated application to many areas of orthopaedic care.Perhaps more commonly regarded is the use of AI in analysis of diagnostic imaging, which is currently used to review 2dimensional i...
Sheth et al. reported that pretreatment with abaloparatide can increase bone mineral density in regions of the proximal femur that are in contact with the femoral stem of an implant in postmenopausal women with osteoporosis. An interesting finding reported is that the Gruen zones most affected by stress-shielding-induced bone loss following total hip arthroplasty were positively affected by the pretreatment, along with other proximal regions of the femur. What was not explored in this study is whether this increase in bone mineral density in the proximal femur was sufficient to affect the biomechanical properties of the bone, specifically the magnitude of stress-shielding-induced bone loss. The application of bone-adaptive modeling would be an interesting next step to address this, and it could involve the application of artificial intelligence (AI).AI has been used in medicine in various ways since the 1950s, from machine learning and chatbots that aimed to mimic human conversation to the 2020s when AI was trained to diagnose benign polyps and malignant polyps found in colonoscopies 1 . Overall, the application of AI has been slow in medicine compared with other fields, but it has been particularly slower in orthopaedics. A brief PubMed search using the key terms of "artificial intelligence in orthopaedics" yielded only 3,890 articles from 1976 to 2024. This result is much smaller than in other fields such as radiology (23,858 articles) or cancer (39,315 articles) during the same period. With the potential of AI continuously evolving, application in the field remains a moving target and can lead to confusion for researchers and clinicians.However, in a recent review 2 , 3 essential "domains" for the use of AI in personalizing orthopaedic care and improving outcomes were highlighted: (1) personalized prediction of clinical outcomes and adverse events, (2) automated diagnostic imaging analyses, and (3) forecasting resource utilization. The first 2 domains directly apply to the article by Sheth et al. and would contribute to understanding bone-adaptive modeling and the biomechanical properties associated with total hip arthroplasty. The third domain, forecasting resource utilization, is downstream of their article, but is still pertinent to the discussion of using AI in orthopaedics.The prediction of clinical outcomes and adverse events is difficult and continues to be a challenge. Machine learning has been used to predict bone mineral density from genomic data 3 or unplanned readmissions following total knee arthroplasty 4 . Another article used intraoperative load sensors and AI to improve accuracy and precision of force measurements during the balancing of total knee arthroplasty 5 . These few examples show a diverse application of predictive AI that, with improvements to the algorithms, sensors, and programs, can provide a sophisticated application to many areas of orthopaedic care.Perhaps more commonly regarded is the use of AI in analysis of diagnostic imaging, which is currently used to review 2dimensional i...
Medical researchers are increasingly utilizing advanced LLMs like ChatGPT-4 and Gemini to enhance diagnostic processes in the medical field. This research focuses on their ability to comprehend and apply complex medical classification systems for breast conditions, which can significantly aid plastic surgeons in making informed decisions for diagnosis and treatment, ultimately leading to improved patient outcomes. Fifty clinical scenarios were created to evaluate the classification accuracy of each LLM across five established breast-related classification systems. Scores from 0 to 2 were assigned to LLM responses to denote incorrect, partially correct, or completely correct classifications. Descriptive statistics were employed to compare the performances of ChatGPT-4 and Gemini. Gemini exhibited superior overall performance, achieving 98% accuracy compared to ChatGPT-4’s 71%. While both models performed well in the Baker classification for capsular contracture and UTSW classification for gynecomastia, Gemini consistently outperformed ChatGPT-4 in other systems, such as the Fischer Grade Classification for gender-affirming mastectomy, Kajava Classification for ectopic breast tissue, and Regnault Classification for breast ptosis. With further development, integrating LLMs into plastic surgery practice will likely enhance diagnostic support and decision making.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.