Search for Medical Information and Treatment Options for Musculoskeletal Disorders through an Artificial Intelligence Chatbot: Focusing on Shoulder Impingement Syndrome
Kim, J.
10.1101/2022.12.16.22283512 medRxivShow abstract
BackgroundThe ChatGPT is an artificial intelligence chatbot that processes natural language text learned through reinforcement learning based on the GPT-3.5 architecture, a large-scale language model. Natural language processing models are being used in various fields and are gradually expanding their use in the medical field. PurposeThis study aimed to investigate the medical information and treatment options that ChatGPT can provide for SIS. MethodUsing ChatGPT, which is provided as a free beta test, messages related to SIS were entered, and responses to medical information and treatment options were received and analyzed. ResultChatGPT not only provided answers to the definition, prevalence, and risk factors of SIS, but also symptoms, diseases with similar symptoms, and orthopedic tests according to the messages input. Additionally, a list of treatment options and exercises were provided. ConclusionChatGPT will be able to provide overall useful medical information and treatment options to patients unfamiliar with SIS. However, caution is required as it contains content that may be biased or inappropriate information for patients with SIS. Nevertheless, if natural language processing technology develops further, it is expected to be able to express more detailed medical information and treatment options.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Action observation intervention using three - dimensional movies improves the usability of hands with distal radius fractures in daily life: a nonrandomized controlled trial in women 96%
- Investigation of locomotive syndrome improvement by total hip arthroplasty in patients with hip osteoarthritis: a before-after comparative study focusing on 25-question geriatric locomotive function scale 95%
- A case-control study evaluating CT signs of xiphoid process associated with xiphodynia 95%
Similar papers in this journal
- Predicting pain and function outcomes in people consulting with shoulder pain: The PANDA-S clinical cohort and qualitative study protocol (ISRCTN 46948079) 94%
- Comparative Computed Tomography with Stress Manoeuvres for Diagnosing Distal Isolated Tibiofibular Syndesmotic Injury in Acute Ankle Sprain: a Protocol for an Accuracy-Test Prospective Study. 94%
- The Effects of Pericapsular nerve group (PENG) block on Postoperative Recovery in Elderly Patients with Hip fracture: a study protocol for randomized, parallel controlled, double-blind trial 94%
Similar papers in this journal
- Development and content validation of a questionnaire identifying patients’ functional priorities and abilities after hip or knee arthroplasty 95%
- Kinematics associated with treadmill walking in Rett Syndrome 93%
- Physiotherapists’ use of aerobic exercise during stroke rehabilitation: a qualitative study using chart-stimulated recall 93%
Similar papers in this journal
- The COVID-19 Yorkshire Rehabilitation Scale (C19-YRS): application and psychometric analysis in a post-COVID-19 syndrome cohort 92%
- The modified COVID-19 Yorkshire Rehabilitation Scale (C19-YRSm) patient-reported outcome measure for Long Covid or Post-COVID syndrome 91%
- Large-scale psychometric assessment and validation of the Modified COVID-19 Yorkshire Rehabilitation Scale (C19-YRSm) patient-reported outcome measure for Long COVID or Post-COVID syndrome 90%
Similar papers in this journal
- Characteristics of patients with myofascial pain syndrome of the low back 95%
- Perception of yips among professional Japanese golfers: perspectives and challenges 94%
- Immediate effect of osteopathic techniques on human resting muscle tone in healthy subjects using myotonometry: A factorial randomized trial 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.