ChatGPT is designed to provide accurate and reliable information to the best of its abilities based on the data input and knowledge available. Thus, ChatGPT is being studied as a patient information ...tool. This artificial intelligence (AI) tool has been shown to frequently provide technically correct information but with limitations. ChatGPT provides different answers to similar questions based on the prompts, and patients may not have expertise in prompting ChatGPT to elicit a best answer. (Prompting large language models has been shown to be a skill that can improve.) Of greater concern, ChatGPT fails to provide sources or references for its answers. At present, ChatGPT cannot be relied upon to address patient questions; in the future, ChatGPT will improve. Today, AI requires physician expertise to interpret AI answers for patients.
PURPOSEThe purpose of this study was to analyze the quality and readability of the information generated by an online artificial intelligence (AI) platform regarding 4 common hand surgeries and to ...compare AI-generated responses to those provided in the informational articles published by the American Society for Surgery of the Hand (ASSH) HandCare website.METHODSAn open AI model (ChatGPT) was used to answer questions commonly asked by patients on 4 common hand surgeries (carpal tunnel release, cubital tunnel release, trigger finger release, and distal radius fracture fixation). These answers were evaluated for medical accuracy, quality and readability and compared to answers derived from the ASSH HandCare materials.RESULTSFor the AI model, the Journal of the American Medical Association benchmark criteria score was 0/4, and the DISCERN score was 58 (considered good). The areas in which the AI model lost points were primarily related to the lack of attribution, reliability and currency of the source material. For AI responses, the mean Flesch Kinkaid Reading Ease score was 15, and the Flesch Kinkaid Grade Level was 34, which is considered to be college level. For comparison, ASSH HandCare materials scored 3/4 on the Journal of the American Medical Association Benchmark, 71 on DISCERN (excellent), 9 on Flesch Kinkaid Grade Level, and 60 on Flesch Kinkaid Reading Ease score (eighth/ninth grade level).CONCLUSIONAn AI language model (ChatGPT) provided generally high-quality answers to frequently asked questions relating to the common hand procedures queried, but it is unclear when or where these answers came from without citations to source material. Furthermore, a high reading level was required to comprehend the information presented. The AI software repeatedly referenced the need to discuss these questions with a surgeon, the importance of shared decision-making and individualized care, and compliance with surgeon treatment recommendations.CLINICAL RELEVANCEAs novel AI applications become increasingly mainstream, hand surgeons must understand the limitations and ramifications these technologies have for patient care.
To analyze the quality and readability of information regarding shoulder stabilization surgery available using an online AI software (ChatGPT), using standardized scoring systems, as well as to ...report on the given answers by the AI.
An open AI model (ChatGPT) was used to answer 23 commonly asked questions from patients on shoulder stabilization surgery. These answers were evaluated for medical accuracy, quality, and readability using The JAMA Benchmark criteria, DISCERN score, Flesch-Kincaid Reading Ease Score (FRES) & Grade Level (FKGL).
The JAMA Benchmark criteria score was 0, which is the lowest score, indicating no reliable resources cited. The DISCERN score was 60, which is considered a good score. The areas that open AI model did not achieve full marks were also related to the lack of available source material used to compile the answers, and finally some shortcomings with information not fully supported by the literature. The FRES was 26.2, and the FKGL was considered to be that of a college graduate.
There was generally high quality in the answers given on questions relating to shoulder stabilization surgery, but there was a high reading level required to comprehend the information presented. However, it is unclear where the answers came from with no source material cited. It is important to note that the ChatGPT software repeatedly references the need to discuss these questions with an orthopaedic surgeon and the importance of shared discussion making, as well as compliance with surgeon treatment recommendations.
As shoulder instability is an injury that predominantly affects younger individuals who may use the Internet for information, this study shows what information patients may be getting online.
Background:
Arthroscopic rotator cuff repair (ARCR) is one of the most commonly performed orthopaedic procedures; however, it is unclear how to manage patients with symptomatic retears.
Purpose:
To ...perform a systematic review to evaluate the outcomes of revision ARCR in the literature.
Study Design:
Systematic review; Level of evidence, 4.
Methods:
A systematic literature search based on PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines was performed utilizing the Embase, MEDLINE, and Cochrane Library databases. Eligible for inclusion were clinical studies reporting on revision rotator cuff repair. Clinical outcomes were recorded.
Results:
The 17 included studies were composed of 888 shoulders in 885 patients. The mean age of the 885 patients was 58.6 ± 9.1 years, with a mean follow-up of 28.1 ± 22.1 months. The mean visual analog scale score was 2.1 ± 1.8, the mean American Shoulder and Elbow Surgeons score was 75.0 ± 18.3, and the mean Constant score was 67.4 ± 16.6. The overall rate of retears after revision was 25.3%, with an 8.0% reoperation rate including 2.7% undergoing reverse shoulder arthroplasty and 2.0% undergoing subsequent rotator cuff repair. Finally, the complication rate was 8.6%.
Conclusion:
Revision ARCR improved patient-reported outcomes, with 92% of patients free from reoperations at a mean follow-up of 2 years. Overall, 78.4% of patients were satisfied at final follow-up; however, the rate of retears was found to be higher than after primary ARCR.
Bone marrow stimulation (BMS) has been proposed to augment healing at the time of arthroscopic rotator cuff repair (ARCR) by creating several bone marrow vents in the footprint of the rotator cuff, ...allowing mesenchymal stem cells, platelets, and growth factors to cover the area as a "crimson duvet."
To perform a meta-analysis of randomized controlled trials (RCTs) to compare the outcomes after BMS and a control for those undergoing ARCR.
Meta-analysis; Level of evidence, 1.
A literature search of 3 databases was performed based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. RCTs comparing BMS and a control for ARCR were included. Clinical outcomes were compared, and a
value <.05 was considered to be statistically significant.
A total of 7 RCTs with 576 patients were included. Overall, 18.8% of patients treated with BMS and 21.0% of patients treated with a control had a retear (
= 43%;
= .61). With BMS, the mean Constant score was 88.2, and with the control, the mean Constant score was 86.7 (
= .12). Additionally, there was no significant difference in the American Shoulder and Elbow Surgeons score (94.3 vs 93.2, respectively;
= .31) or visual analog scale score (0.9 vs 0.9, respectively;
= .89).
The level 1 evidence in the literature did not support BMS as a modality to improve retear rates or clinical outcomes after ARCR.
To perform a meta-analysis of randomized controlled trials (RCTs) to compare the outcomes of arthroscopic rotator cuff repair (ARCR) with and without acellular collagen matrix patch (ACMP) ...augmentation.
A literature search of 3 databases was performed based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. RCTs comparing ACMP augmentation and a control for ARCR were included. Clinical outcomes were compared using Revman, and a P value < .05 was considered to be statistically significant.
Five RCTs with 307 patients were included. Overall, 11% of patients treated with ACMP augmentation and 34% of patients in the control group had a re-tear (P = .0006). The mean Constant score was 90.1 with ACMP augmentation, and 87.3 in controls (P = .02). Additionally, there was a significant higher American Shoulder and Elbow Surgeons score with ACMP augmentation (87.7 vs 82.1, P = .01).
The RCTs in the literature support the use of ACMP augment as a modality to reduce re-tear rates and improve outcomes after ARCR.
Level II, Meta-Analysis of Level II Studies meta-analysis of Level II studies
BACKGROUNDThe purpose of this study was to perform a meta-analysis of randomized controlled trials (RCTs) to compare outcomes following intramedullary nailing (IMN) vs. open reduction-internal ...fixation (ORIF) for humeral shaft fractures.METHODSA literature search of 3 databases was performed based on the Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines. RCTs comparing IMN and ORIF for humeral shaft fractures were included. Clinical outcomes were compared using RevMan. P < .05 was considered statistically significant.RESULTSTen RCTs with 512 patients were included. Overall, 8.4% of patients treated with IMN and 6.4% of patients treated with ORIF had nonunion (P = .57, I2 = 0%), with a significantly faster time to union with IMN (10 weeks vs. 11.9 weeks, P < .05). There was no significant difference in the rate of reoperation (11.6% in IMN group vs. 7.6% in ORIF group, P = .26) or radial nerve palsy (2.8% in IMN group vs. 4.2% in ORIF group, P = .58). A lower rate of infection was noted with IMN (1.2% vs. 5.3%, P < .05). Additionally, there was a lower operative time with IMN (61 minutes vs. 88 minutes, P < .05).CONCLUSIONSThe Level I evidence in the literature does not show a significant difference in rates of union, reoperation, or radial nerve palsy between IMN and ORIF for humeral shaft fractures. Overall, treatment with IMN results in a lower infection rate, less operative time, and a modestly quicker time to union. The optimal treatment strategy for humeral shaft fractures may be best informed by fracture pattern and surgeon preference.
Anterior cruciate ligament (ACL) rupture alters knee kinematics and contributes to premature development of osteoarthritis. However, there is limited data regarding the in vivo biomechanical response ...of tibiofemoral cartilage to activities of daily living (ADLs) in ACL-deficient knees. In this study, eight otherwise healthy participants with chronic unilateral ACL deficiency completed a stress test to assess the effect of 20 min of level treadmill walking at a speed of 2.5 mph on tibiofemoral cartilage in their ACL-deficient and contralateral ACL-intact knees. Three-dimensional surface models developed from pre- and post-activity magnetic resonance (MR) images of the injured and uninjured knees were used to determine compressive strain across multiple regions of tibiofemoral cartilage (medial and lateral tibial plateaus, medial and lateral femoral condyles, medial aspect of femoral condyle adjacent to intercondylar notch of the femur). In the ACL-deficient knees, we observed significantly increased cartilage strain in the region of the medial femoral condyle adjacent to the intercondylar notch (6% in deficient vs. 2% in contralateral, p = 0.01) as well as across the medial and lateral tibial plateaus (4% vs. 3%, p = 0.01) relative to the contralateral ACL-intact knees. Increased compressive strain at the medial intercondylar notch and tibial plateau suggests alterations in mechanical loading or the response to load in these regions, presumably related to altered knee kinematics. These changes may disrupt cartilage homeostasis and contribute to subsequent development of osteoarthritis.
The ability to efficiently and reproducibly generate subject-specific 3D models of bone and soft tissue is important to many areas of musculoskeletal research. However, methodologies requiring such ...models have largely been limited by lengthy manual segmentation times. Recently, machine learning, and more specifically, convolutional neural networks, have shown potential to alleviate this bottleneck in research throughput. Thus, the purpose of this work was to develop a modified version of the convolutional neural network architecture U-Net to automate segmentation of the tibia and femur from double echo steady state knee magnetic resonance (MR) images. Our model was trained on a dataset of over 4,000 MR images from 34 subjects, segmented by three experienced researchers, and reviewed by a musculoskeletal radiologist. For our validation and testing sets, we achieved dice coefficients of 0.985 and 0.984, respectively. As further testing, we applied our trained model to a prior study of tibial cartilage strain and recovery. In this analysis, across all subjects, there were no statistically significant differences in cartilage strain between the machine learning and ground truth bone models, with a mean difference of 0.2 ± 0.7 % (mean ± 95 % confidence interval). This difference is within the measurement resolution of previous cartilage strain studies from our lab using manual segmentation. In summary, we successfully trained, validated, and tested a machine learning model capable of segmenting MR images of the knee, achieving results that are comparable to trained human segmenters.