The Potential of ChatGPT as a Self-Diagnostic Tool in Common Orthopedic Diseases: Exploratory Study

BACKGROUND

Artificial intelligence (AI) has gained tremendous popularity recently, especially the use of natural language processing (NLP). ChatGPT is a state-of-the-art chatbot capable of creating natural conversations using NLP. The use of AI in medicine can have a tremendous impact on health care delivery. Although some studies have evaluated ChatGPT's accuracy in self-diagnosis, there is no research regarding its precision and the degree to which it recommends medical consultations.

OBJECTIVE

The aim of this study was to evaluate ChatGPT's ability to accurately and precisely self-diagnose common orthopedic diseases, as well as the degree of recommendation it provides for medical consultations.

METHODS

Over a 5-day course, each of the study authors submitted the same questions to ChatGPT. The conditions evaluated were carpal tunnel syndrome (CTS), cervical myelopathy (CM), lumbar spinal stenosis (LSS), knee osteoarthritis (KOA), and hip osteoarthritis (HOA). Answers were categorized as either correct, partially correct, incorrect, or a differential diagnosis. The percentage of correct answers and reproducibility were calculated. The reproducibility between days and raters were calculated using the Fleiss κ coefficient. Answers that recommended that the patient seek medical attention were recategorized according to the strength of the recommendation as defined by the study.

RESULTS

The ratios of correct answers were 25/25, 1/25, 24/25, 16/25, and 17/25 for CTS, CM, LSS, KOA, and HOA, respectively. The ratios of incorrect answers were 23/25 for CM and 0/25 for all other conditions. The reproducibility between days was 1.0, 0.15, 0.7, 0.6, and 0.6 for CTS, CM, LSS, KOA, and HOA, respectively. The reproducibility between raters was 1.0, 0.1, 0.64, -0.12, and 0.04 for CTS, CM, LSS, KOA, and HOA, respectively. Among the answers recommending medical attention, the phrases "essential," "recommended," "best," and "important" were used. Specifically, "essential" occurred in 4 out of 125, "recommended" in 12 out of 125, "best" in 6 out of 125, and "important" in 94 out of 125 answers. Additionally, 7 out of the 125 answers did not include a recommendation to seek medical attention.

CONCLUSIONS

The accuracy and reproducibility of ChatGPT to self-diagnose five common orthopedic conditions were inconsistent. The accuracy could potentially be improved by adding symptoms that could easily identify a specific location. Only a few answers were accompanied by a strong recommendation to seek medical attention according to our study standards. Although ChatGPT could serve as a potential first step in accessing care, we found variability in accurate self-diagnosis. Given the risk of harm with self-diagnosis without medical follow-up, it would be prudent for an NLP to include clear language alerting patients to seek expert medical opinions. We hope to shed further light on the use of AI in a future clinical study.

Molecular Mechanism of Ferroptosis in Orthopedic Diseases

Ferroptosis is a new iron-dependent programmed cell death process that is directly mediated by the accumulation of lipid peroxides and reactive oxygen species. Numerous studies have shown that ferroptosis is important in regulating the occurrence and development of bone-related diseases, but the underlying mechanisms are not completely clear. Herein, we review the progress of the mechanism of ferroptosis in bone marrow injury, osteoporosis, osteoarthritis, and osteosarcoma and attempt to deeply understand the regulatory targets of ferroptosis, which will open up a new way for the prevention and treatment of orthopedic diseases.

The Role of Mesenchymal Stem Cells (MSCs) in Veterinary Medicine and Their Use in Musculoskeletal Disorders

Regenerative medicine is a dynamically developing field of human and veterinary medicine. The animal model was most commonly used for mesenchymal stem cells (MSCs) treatment in experimental and preclinical studies with a satisfactory therapeutic effect. Year by year, the need for alternative treatments in veterinary medicine is increasing, and other applications for promising MSCs and their biological derivatives are constantly being sought. There is also an increase in demand for other methods of treating disease states, of which the classical treatment methods did not bring the desired results. Cell therapy can be a realistic option for treating human and animal diseases in the near future and therefore additional research is needed to optimize cell origins, numbers, or application methods in order to standardize the treatment process and assess its effects. The aim of the following work was to summarize available knowledge about stem cells in veterinary medicine and their possible application in the treatment of chosen musculoskeletal disorders in dogs and horses.

Family Caregiver Strain and Challenges When Caring for Orthopedic Patients: A Systematic Review

Background: Caregivers represent the core of patients’ care in hospital structures, in the process of care and self-care after discharge. We aim to identify the factors that affect the strain of caring for orthopedic patients and how these factors are related to the quality of life of caregivers. We also want to evaluate the role of caregivers in orthopedic disease, focusing attention on the patient–caregiver dyad. Methods: A comprehensive search on PubMed, Cochrane, CINAHL and Embase databases was conducted. This review was reported following PRISMA statement guidance. Studies were selected, according to inclusion and exclusion criteria, about patient–caregiver dyads. For quality assessment, we used the MINORS and the Cochrane Risk of BIAS assessment tool. Results: 28 studies were included in the systematic review; in these studies, 3034 dyads were analyzed. Caregivers were not always able to bear the difficulties of care. An improvement in strain was observed after behavioral interventions from health-care team members; Conclusions: The role of the caregiver can lead to a deterioration of physical, cognitive and mental conditions. The use of behavioral interventions increased quality of life, reducing the strain in caregivers of orthopedic patients. For this reason, it is important to consider the impact that orthopedic disease has on the strain of the caregiver and to address this topic.

Calibration of an item bank in 474 orthopedic patients using Rasch analysis for computer-adaptive assessment of anxiety

OBJECTIVE

To calibrate an item bank of anxiety-related questions for use in orthopedic patients within a computer-adaptive test.

DESIGN

This is a psychometric study.

SETTING

The sample of orthopedic patients was recruited in two orthopedic rehabilitation clinics in Germany.

SUBJECTS

A total of 474 orthopedic rehabilitation patients were recruited for this study.

INTERVENTIONS

Not applicable.

MAIN MEASURES

The main measure is an adapted version of an existing anxiety item pool for cardiovascular rehabilitation patients.

RESULTS

The results of the confirmatory factor analysis and Mokken analysis confirmed a one-factor structure and double monotonicity. An anxiety item bank (48 items) could be developed and calibrated using Rasch analysis. It fitted to the Rasch model with a non-significant item-trait interaction (χ²(203) = 172.59; P = .94) and was free of differential item functioning. Unidimensionality could be verified and the person separation reliability was .96. The category threshold parameters varied between 4.72 and 3.16 (7.88 logits).

CONCLUSION

The unidimensional anxiety item bank provides the basis for a computer-adaptive test to assess a wide range of anxiety in rehabilitation patients with orthopedic diseases with very good psychometric characteristics.

Surgical treatment of cranial cruciate ligament disease in dogs using Tibial Plateau Leveling Osteotomy or Tibial Tuberosity Advancement-A systematic review with a meta-analytic approach

Tibial Plateau Leveling Osteotomy (TPLO) or Tibial Tuberosity Advancement (TTA) are commonly used surgical techniques for correction of cranial cruciate ligament (CCL) rupture in dogs. This systematic review aims to investigate whether one technique is superior to the other. Seventy-two studies on surgical management of CCL rupture have been identified and evaluated in regard of subjective and objective gait analysis criteria, development of osteoarthritis (OA), thigh circumference measurements, goniometry, joint stability, pain and complication rates. Almost half (47.2 %) of the studies were considered of low quality of evidence, leading to high heterogeneity in quality among studies; this posed a major limitation for an evidence-based systematic review of both surgical techniques. Out of 72 studies, there were only eleven blinded randomized clinical trials, of which five were rated with a low overall risk of bias. However, both techniques were considered to be successful management options. Subjective and objective gait analysis revealed no lameness at long-term evaluation for the majority of the patients. However, it appeared that TTA lead to better OA scores up to 6 months postoperatively, while TPLO had a lower rate of surgical site infections. In summary, no method can be clearly preferred, as most of the study evaluated were subpar. Studies with a high level of evidence are therefore urgently needed for such a common surgical procedure.

Identifying determinants of physical activity in older patients with musculoskeletal disorders undergoing rehabilitation: Comparison of two distinct models using structural equation modeling

AIM

Mobility restrictions cause older adults with musculoskeletal disorders to have lower levels of physical activity. However, the determinants of their physical activity during hospitalization are unclear. We aimed to compare two conceptual frameworks using structural equation modeling to identify factors influencing physical activity in older patients with musculoskeletal disorders.

METHODS

This cross-sectional study included older patients with musculoskeletal disorders at a single convalescent rehabilitation hospital. Physical activity was objectively measured using a triaxial accelerometer. We utilized structural equation modeling to contrast two conceptual frameworks: (i) the sarcopenia/nutrition/activities of daily living model, and (ii) the age-related deconditioning/activities of daily living model. The models' goodness-of-fit was evaluated, including root mean square approximation error, goodness-of-fit index (GFI), adjusted GFI and Akaike information criterion.

RESULTS

We enrolled 274 older patients (age 78.0 years; 42 men, 232 women) with musculoskeletal disorders. Among them, 123 (44.9%) were diagnosed with sarcopenia and 69 (25.2%) with malnutrition. The goodness-of-fit of the (ii) model (root mean square approximation error = 0.068, GFI = 0.958, adjusted GFI = 0.909, Akaike information criterion = 5780.875) was superior to the (i) model (root mean square approximation error = 0.080, GFI = 0.953, adjusted GFI = 0.887, Akaike information criterion = 5791.429).

CONCLUSIONS

We discovered that the age-related deconditioning/activities of daily living model effectively explained physical activity in hospitalized older patients with musculoskeletal disorders. A comprehensive approach considering age-related changes, such as sarcopenia and malnutrition, might offer a simpler and more effective framework for understanding and promoting physical activity in this demographic. Geriatr Gerontol Int 2025; 25: 160-166.

Prevalence of Low Back Pain and Its Associated Factors Among Medical Students at Nineveh University in Iraq: A Cross-Sectional Study

Background Low back pain (LBP) is a common problem encountered in medical practice, leading to limitations in daily activities and causing social and economic hardships. Objectives This study aimed to assess the prevalence of LBP and its associated factors among medical students at Nineveh University in Iraq. Methods Between December 2022 and January 2023, a cross-sectional study was conducted among medical students at Nineveh University. A modified version of the Standard Nordic Questionnaire was used for data collection. Results Out of 308 students, 229 (74.4%) experienced LBP at some point in their lives. In addition, 209 (67.9%) reported having LBP during the last 12 months, 148 (48.1%) during the previous seven days, and 126 (40.9%) at the time of answering the survey. Factors significantly associated with LBP during the last 12 months were being in the fifth-stage academic year (p=0.047), family history of LBP (p=0.003), and history of trauma (p=0.006). On the multivariable logistic regression analysis, factors significantly associated with LBP during the last 12 months were family history of LBP (p=0.02) and history of trauma (p=0.01). Conclusions The prevalence of LBP among medical students at Nineveh University was comparatively high. A family history of LBP and a history of trauma were factors significantly associated with LBP during the last 12 months. Managing this health concern should be a priority for the administration of medical schools.

Bidirectional Patellar Luxation in Small- or Miniature-Breed Dogs in Japan; Patient Characteristics and Radiographic Measures Compared with Medial Patellar Luxation

Bidirectional patellar luxation (BPL) is a relatively rare form of patellar luxation, with limited information reported regarding breed predisposition and etiology. The purpose of this study was to describe the patient characteristics and radiographic measures of proximodistal patellar position associated with BPL in dogs in Japan, compared with dogs with medial patellar luxation (MPL). A retrospective medical record search of surgically corrected MPL and BPL dogs was performed, and breed, age, sex, body weight, and presence of the patella alta in the extended-stifle position were recorded. The ratio of the patellar ligament length to patella length (PLL/PL) and the ratio of the distance between the proximal pole of the patella and the femoral condyle to patella length (A/PL) were measured on stifle radiographs. A total of 35 dogs with BPL and 95 dogs with MPL were included. The BPL was most commonly present in Toy Poodles (odds ratio compared to MPL dogs: 7.05) in the present study. There were no significant differences in age, sex, or body weight between the BPL and MPL groups. Patella alta in the extended-stifle position was more common in the BPL group (23.4%) than in the MPL group (0.8%). However, there were no significant differences in PLL/PL or A/PL between the BPL and MPL groups. The study highlights BPL in different dog breeds in Japan, and suggests that the occurrence of BPL may be related to stifle extension. However, more research is needed to fully understand the etiology of BPL.

Economic Considerations on Costs and Pricing of Two Surgical Techniques for Treating Cranial Cruciate Disease in Dogs

In surgical treatment of cranial cruciate ligament disease in dogs, Tibial Plateau Levelling Osteotomy (TPLO) and Tibial Tuberosity Advancement (TTA) are commonly established procedures and have proven effective in restoring limb function. Unlike clinical outcome, economic aspects have not been studied as extensively. However, the surgical intervention poses an enormous financial burden on patients' owners. In a veterinary practice setting, this study compares prices for TPLO and TTA and examines prices differences as well as potential cost drivers. Charges for veterinary treatments are based on the Gebührenordnung für Tierärztinnen und Tierärzte (GOT), which is mandatory for veterinarians in Germany but allows a certain range in billing. This study found that TPLO is charged at a higher price than TTA; however, this might not cover the additional costs of this procedure. The price is also associated with weight, heavier dogs being more expensive. The underlying strategies for pricing decisions may be based on costs, as efforts for TPLO and heavier dogs are higher in terms of a prolonged surgical time, the number of staff involved and in surgeons' training. Price setting may also be based on a quality promise, suggesting better clinical outcome in a more expensive procedure. Future investigations should involve economic considerations and consider cost-effectiveness analysis when evaluating surgical treatment options.

Enhanced deep residual network for bone classification and abnormality detection

PURPOSE

A two-stage deep learning framework for bone classification and abnormality detection is proposed based on X-rays. The primary focus is on improving the speed of orthopedic disease diagnosis and helping physicians reduce the probability of false diagnoses.

METHODS

The method is based on two stages. In the first stage, one classifier with ResNeXt50 as the backbone is used to classify bones to eliminate the effect of bone type differences on abnormality detection. In the second stage, seven anomaly detectors are trained based on each type of training data. The seven detectors tested the seven results of the first stage, respectively. Pretrained models, data augmentation, focal loss, label smoothing loss, LR-attenuation and early stopping are used to improve performance and reduce the risk of overfitting.

RESULTS

Experiments are based on the largest dataset for bone abnormality detection, MURA. In the first stage for bone classification, we got an accuracy of 96.69%, a sensitivity of 96.69%, a specificity of 99.46%, and an F1 score of 96.42%. In the second stage for abnormality detection, we got an accuracy of 84.15%, a sensitivity of 84.15%, a specificity of 87.50%, an F1 score of 84.10%, a Cohen's Kappa of 0.72, and an area under the ROC curve (AUC) score of 0.90.

CONCLUSIONS

Compared with other excellent convolutional neural network models, the framework's effectiveness was verified with better accuracy, sensitivity, specificity, F1 score, Cohen's Kappa score, and AUC score for bone classification and abnormality detection.