ABSTRACT
BACKGROUND: The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored. OBJECTIVE: This study focused on evaluating and enhancing the clinical capabilities and explainability of LLMs in specific domains, using OA management as a case study. METHODS: A domain-specific benchmark framework was developed to evaluate LLMs across a spectrum from domain-specific knowledge to clinical applications in real-world clinical scenarios. DocOA, a specialized LLM designed for OA management integrating retrieval-augmented generation and instructional prompts, was developed. It can identify the clinical evidence upon which its answers are based through retrieval-augmented generation, thereby demonstrating the explainability of those answers. The study compared the performance of GPT-3.5, GPT-4, and a specialized assistant, DocOA, using objective and human evaluations. RESULTS: Results showed that general LLMs such as GPT-3.5 and GPT-4 were less effective in the specialized domain of OA management, particularly in providing personalized treatment recommendations. However, DocOA showed significant improvements. CONCLUSIONS: This study introduces a novel benchmark framework that assesses the domain-specific abilities of LLMs in multiple aspects, highlights the limitations of generalized LLMs in clinical contexts, and demonstrates the potential of tailored approaches for developing domain-specific medical LLMs.
Subject(s)
Machine Learning , Osteoarthritis , Humans , Osteoarthritis/therapyABSTRACT
INTRODUCTION: Our study aims to assess the effectiveness of multicomponent supervised tele-rehabilitation compared to home-based self-rehabilitation management in patients following anterior cruciate ligament reconstruction (ACLR). METHODS: The current study is designed as a single-center, single-blinded, randomized controlled, two-arm trial. Participants will be randomized and allocated at a 1:1 ratio into either a multicomponent supervised tele-rehabilitation group or a home-based self-rehabilitation group. All participants receive uniform preoperative education through the HJT software. Participants in the intervention group undergo multicomponent supervised tele-rehabilitation, while those in the control group follow a home-based self-rehabilitation program. All the participants were assessed and measured for the included outcomes at the outpatient clinic before the procedure, and in 2, 4, 8, 12, and 24 weeks after ACLR by two assessors. The primary outcome was the percentage of patients who achieve a satisfactory active ROM at the 12 weeks following the ACLR. The satisfactory active ROM was also collected at 2, 4, 8, and 24 weeks after ACLR. The secondary outcomes were active and passive range of motion (ROM), pain, muscle strength, and function results. REGISTRATION DETAILS: Ethical approval has been obtained from the West China Hospital Ethics Committee (approval number 2023-1929, December 2023). The trial has been registered on ClinicalTrials.gov (registration number NCT06232824, January 2024).
Subject(s)
Anterior Cruciate Ligament Reconstruction , Range of Motion, Articular , Telerehabilitation , Humans , Anterior Cruciate Ligament Reconstruction/rehabilitation , Anterior Cruciate Ligament Reconstruction/methods , Single-Blind Method , Treatment Outcome , Adult , Male , Female , Young Adult , Home Care Services , Randomized Controlled Trials as Topic , Anterior Cruciate Ligament Injuries/surgery , Anterior Cruciate Ligament Injuries/rehabilitation , Muscle Strength , AdolescentABSTRACT
The use of large language models (LLMs) in clinical medicine is currently thriving. Effectively transferring LLMs' pertinent theoretical knowledge from computer science to their application in clinical medicine is crucial. Prompt engineering has shown potential as an effective method in this regard. To explore the application of prompt engineering in LLMs and to examine the reliability of LLMs, different styles of prompts were designed and used to ask different LLMs about their agreement with the American Academy of Orthopedic Surgeons (AAOS) osteoarthritis (OA) evidence-based guidelines. Each question was asked 5 times. We compared the consistency of the findings with guidelines across different evidence levels for different prompts and assessed the reliability of different prompts by asking the same question 5 times. gpt-4-Web with ROT prompting had the highest overall consistency (62.9%) and a significant performance for strong recommendations, with a total consistency of 77.5%. The reliability of the different LLMs for different prompts was not stable (Fleiss kappa ranged from -0.002 to 0.984). This study revealed that different prompts had variable effects across various models, and the gpt-4-Web with ROT prompt was the most consistent. An appropriate prompt could improve the accuracy of responses to professional medical questions.
ABSTRACT
PURPOSE: To investigate the accuracy and reliability of magnetic resonance imaging (MRI) in identifying and grading chondral lesions and explore the optimal imaging technique to image cartilage. METHOD: A comprehensive search was conducted on Medline, Embase, and Cochrane Library. Eligible cohort studies published before August 2022 were included. The study reports used MRI to diagnose and grade cartilage lesions, with intraoperative findings as the reference standard. Summary estimates of diagnostic performance were obtained. The reliability of MRI interpretation was summarized. Subgroup analyses were performed based on assessed imaging techniques, field strength, and joint surface. RESULTS: Forty-three trials and 3,706 patients were included in the systematic review. The overall area under curve for hierarchical summarized receiver operating characteristics was 0.91 (95% confidence interval [CI] 0.88-0.93). The pooled sensitivity for quantitative MRI, 3-dimensional MRI, and 2-dimensional MRI was 0.82 (95% CI 0.64-0.92), 0.79 (95% CI 0.74-0.83), and 0.63 (95% CI 0.51-0.73), respectively. The pooled sensitivity of 3 Tesla (3T), 1.5 Tesla (1.5T), and <1.5 Tesla MRI was 0.79 (95% CI 0.72-0.85), 0.67 (95% CI 0.60-0.74), and 0.55 (95% CI 0.39-0.71), respectively. There were differences in interobserver consistency across different studies. CONCLUSIONS: In general, MRI had high specificity in discriminating normal cartilage, but its sensitivity for identifying chondral lesions is less optimal. Further analysis showed that quantitative MRI, 3D MRI, and 3T MRI demonstrate greater sensitivity compared with 2D MRI, 1.5T MRI, and <1.5 Tesla MRI. LEVEL OF EVIDENCE: Level III, systematic review of Level II-III studies.
ABSTRACT
INTRODUCTION: Poststroke cognitive impairment (PSCI) is a common dysfunction that places a great burden on patients who had stroke and their families. Approximately 46%-92% of stroke survivors experience some degree of attention problems after a stroke. Improving attention is considered the core of successfully improving cognitive function and reintegrating patients into daily life. Eye tracking technology provides real-time feedback and accurate monitoring of cognitive processing, and using this technology to introduce attention training may improve patient treatment outcomes. The main purpose of this study was to investigate whether eye-tracking-based attention training has a positive effect on patients with PSCI. METHODS AND ANALYSIS: This study is a prospective randomised controlled trial. We will recruit 48 patients with PSCI referred to the Department of Rehabilitation Medicine at West China Hospital, Sichuan University, in Southwest China. The participants will be randomly distributed into two groups. Both groups will undergo conventional rehabilitation for 3 weeks, and the intervention group will receive 3 weeks of eye-tracking-based attention training (20-30 min/day). The primary outcome will be the patients' cognitive function, measured by the Montreal Cognitive Assessment. The secondary outcomes will be the patients' attention, independence of daily activities and event-related potential. These outcomes will be assessed at baseline, at the end of treatment (3 weeks) and at follow-up (1 month and 3 months after treatment). We will report the statistics and estimations using 95% CI. ETHICS AND DISSEMINATION: This trial received ethics approval from the Ethics Committee on Biomedical Research, West China Hospital of Sichuan University (2023 review No. 258). The results from this study will be disseminated via academic publication. TRIAL REGISTRATION NUMBER: ChiCTR2300068727.
Subject(s)
Cognitive Dysfunction , Stroke Rehabilitation , Stroke , Humans , Stroke Rehabilitation/methods , Eye-Tracking Technology , Prospective Studies , Cognitive Dysfunction/therapy , Cognitive Dysfunction/complications , Stroke/therapy , Attention , China , Randomized Controlled Trials as TopicABSTRACT
BACKGROUND: The lack of access to physical therapists in developing countries and rural areas poses a significant challenge in supervising postsurgical rehabilitation, potentially impeding desirable outcomes following surgical interventions. For this reason, this study aims to evaluate the feasibility, safety, and effectiveness of utilizing a digital rehabilitation program based on computer vision and augmented reality in comparison with traditional care for patients who will undergo isolated meniscus repair, since to date, there is no literature on this topic. METHODS: This study intends to enroll two groups of participants, each to be provided with informed consent before undergoing randomization into either the experimental or control group. The experimental group will undergo a digital rehabilitation program utilizing computer vision and augmented reality (AR) technology following their surgical procedure, while the control group will receive conventional care, involving in-clinic physical therapy sessions weekly. Both groups will adhere to a standardized rehabilitation protocol over a six-month duration. Follow-up assessments will be conducted at various intervals, including preoperatively, and at 2 weeks, 6 weeks, 12 weeks, and 24 weeks postoperatively. Imaging assessments and return-to-play evaluations will be conducted during the final follow-up. Clinical functionality will be assessed based on improvements in International Knee Documentation Committee (IKDC) and Visual Analog Scale (VAS) scores. REGISTRATION NUMBER: ChiCTR2300070582.
Subject(s)
Augmented Reality , Meniscus , Humans , Prospective Studies , Knee Joint , Physical Therapy Modalities , Treatment Outcome , Randomized Controlled Trials as TopicABSTRACT
OBJECTIVE: To evaluate the effect and influence of the "immersive contextualization-based learning" teaching mode (ICBLT) in the orthopaedic musculoskeletal disorder module of clinical medicine education. METHODS: Undergraduate students in five consecutive semesters of clinical medicine in West China Hospital, Sichuan University were enrolled in this study. During the teaching process in each semester, a cross-over design was applied, and students were randomly divided into two classes (Class A and Class B) to receive the designated experimental courses with different routes. After they took the final exams, the scores of the selected chapters (sports injury chapter and osteoarthritis chapter) were extracted to conduct Tests of Between-Subjects Effects. Q-Q plot was drawn to test whether the distribution of the scores follows normal distribution. The part of the feedback questionnaires to assess these two teaching modes were also extracted for comparison. RESULTS: A total of 441 students were enrolled in this study, among which, Class A teaching route was implemented to 222 students and Class B to the rest 219. The results of Tests of Between-Subjects Effects showed that ICBLT mode could lead to better scores compared to the Lecturing-based learning teaching (LBLT) mode (p < 0.0001). In terms of mastery of practical skills, help to deepen the memory of knowledge and satisfaction with the teaching mode, the ICBLT mode showed better results (p < 0.0001). CONCLUSION: ICBLT mode had better potential in helping mastery of practical skills and deepening the memory of knowledge.
Subject(s)
Education, Medical, Undergraduate , Musculoskeletal Diseases , Orthopedics , Humans , Education, Medical, Undergraduate/methods , Learning , Educational Status , Musculoskeletal Diseases/therapy , TeachingABSTRACT
[This corrects the article DOI: 10.3389/fbioe.2023.1185520.].
ABSTRACT
OBJECTIVE: Pelvic compensation is common in femoroacetabular impingement (FAI) patients to reduce symptoms and increase range of motion. However, little attention was given to the postoperative clinical effect of pelvic compensation. Therefore, this study aims to compare the outcomes between pelvic compensation and normal pelvic position in femoroacetabular impingement (FAI) patients after hip arthroscopy. METHODS: The retrospective study was conducted from January 2019 to June 2022, recruited consecutive patients who were diagnosed with FAI and received subsequent arthroscopic treatment. All patients completed an X-ray in the anterior-posterior standing position before and 4 weeks after surgery. Patients with pelvic compensation were compared with those who did not. Functional outcomes included hip disability and osteoarthritis outcome score (HOOS), modified Harris (mHHS) score, and lower-extremity activity scale (LEAS). Secondary outcomes included the EuroQol Five Dimensions Questionnaire (EQ-5D) and patient satisfaction. The intraclass correlation coefficient (ICC) was used to analyze interobserver and intraobserver reliability. RESULTS: Ninety patients with a mean age of 39.40 years were included in the study. No significant compensation changes were noted within groups after the elimination of impingement. The functional scores showed no significant difference between groups (p(HOOS) = 0.352, p(mHHS) = 0.183, p(LEAS) = 0.865). The EQ-5D revealed statistically better performance in usual activities in the compensatory group (p = 0.044). There are no significant between-group differences in patients' satisfaction evaluations. CONCLUSION: As assessed by Patient-Reported Outcome Measures (PROMs), patients with compensatory pelvic tilt demonstrated similar clinical outcomes without extra adverse events to patients with normal pelvic positioning in short-term follow-ups. Furthermore, compensatory pelvic tilt did not significantly enhance the range of motion or functional outcome at short-term follow-ups.
Subject(s)
Femoracetabular Impingement , Humans , Adult , Femoracetabular Impingement/surgery , Hip Joint/surgery , Retrospective Studies , Reproducibility of Results , Treatment Outcome , Patient Reported Outcome Measures , Arthroscopy/methodsABSTRACT
OBJECTIVES: Parameniscal cysts can be removed without meniscectomy, but for large or multiloculated meniscal cysts, traditional arthroscopic excision may leave the meniscus unstable. This study aimed to describe a modified fat pad approach for parameniscal cyst arthroscopic excision that retains a stable structure of the synovial margin of the meniscus and to compare the clinical outcomes between the traditional cyst excision and modified excision techniques. METHODS: Fifty-six patients with parameniscal cysts between 2014 and 2018 were retrospectively included in this study with 28 patients in each group. All patients underwent arthroscopic parameniscal cyst excisions with traditional and modified excision techniques respectively in each group. The International Knee Documentation Committee subjective (IKDC) score, Lysholm score, visual analogue scale (VAS) score, Tegner score, active range of motion (ROM) and time to recover full ROM were used to evaluate the clinical outcomes by using the t-test. RESULTS: The patient population included 21 males and 35 females, with a mean follow-up of 29 months. Of these, 28 patients underwent traditional arthroscopic cyst excisions and meniscal sutures, and 28 patients underwent arthroscopic excisions by the modified fat pad approach. There were no significant differences in the IKDC score, Lysholm score, Tegner score or VAS score between the traditional and modified excision groups at the final follow-up time point. However, the postoperative time to recover full ROM in the modified excision group was significantly lower than those in the traditional excision group (p < 0.05). CONCLUSION: Arthroscopic excision with the modified fat pad approach yielded a shorter pain phase and less time to recover full ROM during recovery compared with the traditional arthroscopic excision. The new method seemed to be effective, as evidenced by the positive clinical outcomes of patients.
Subject(s)
Cysts , Menisci, Tibial , Male , Female , Humans , Menisci, Tibial/surgery , Retrospective Studies , Follow-Up Studies , Magnetic Resonance Imaging , Cysts/surgery , Arthroscopy/methods , Treatment OutcomeABSTRACT
BACKGROUND: Bone bruise (BB) and kissing contusion are common features of acute anterior cruciate ligament (ACL) injury on magnetic resonance imaging (MRI). The correlation between the location and distance of kissing contusions and knee laxity remains unclear. PURPOSE: To determine the significance of different patterns of BB in acute noncontact ACL injury and assess the correlation between the location and distance of kissing contusions and the severity of knee laxity. STUDY DESIGN: Cross-sectional study; Level of evidence, 3. METHODS: A total of 205 patients with acute noncontact ACL injury undergoing arthroscopic treatment between January 2021 and May 2022 were included in this retrospective analysis. Patients were grouped according to the different patterns of BB. The type of ACL injury and concomitant injuries were analyzed on MRI and confirmed by arthroscopy. Anterior knee laxity was assessed by the Ligs digital arthrometer and stress radiography, and rotational knee laxity was assessed by the intraoperative pivot-shift test. The MRI parameters of the location and distance of kissing contusions were measured to assess their correlations with the severity of knee laxity. RESULTS: Of the 205 patients with acute noncontact ACL injury, 38 were in the non-BB group and 167 were in the BB group, the latter including 32 with the isolated BB on the lateral tibial plateau and 135 with kissing contusions. There was no significant difference in the mean time from initial injury to MRI scan between the non-BB group and the BB group (14.34 ± 2.92 vs 15.17 ± 2.86 days; P = .109) or between the isolated BB subgroup and the kissing contusion subgroup (14.94 ± 2.92 vs 15.23 ± 2.85 days; P = .605). The side-to-side difference (SSD) in anterior knee laxity and the incidences of complete ACL injury, concomitant injuries, and high-grade pivot-shift test were significantly higher in the BB group than in the non-BB group, and in the kissing contusion subgroup compared with the isolated BB subgroup. The kissing contusion index of the lateral femoral condyle (LFC) and the sagittal distance of kissing contusions were significantly correlated with the SSD in anterior knee laxity and the grade of pivot-shift test (P < .001). CONCLUSION: The presence of BB, in particular the appearance of kissing contusions, was related to greater knee laxity and higher incidences of complete ACL injury and concomitant injuries in acute noncontact ACL injury. For patients with kissing contusions, as the location of BB on the LFC moved forward and the distance between kissing contusions increased, anterior and rotational knee laxity became more serious.
Subject(s)
Anterior Cruciate Ligament Injuries , Contusions , Humans , Anterior Cruciate Ligament Injuries/diagnostic imaging , Anterior Cruciate Ligament Injuries/surgery , Anterior Cruciate Ligament Injuries/complications , Retrospective Studies , Cross-Sectional Studies , Knee Joint/surgery , Contusions/complications , Magnetic Resonance Imaging/methodsSubject(s)
Osteoarthritis, Hip , Osteoarthritis, Knee , Humans , Cross-Sectional Studies , Knee JointABSTRACT
PURPOSE: The purpose of this protocol was to discover the connection between patients with non-surgical pain or other discomfort and their psychosocial status. Cognitive behavior therapy will be used, which we verified will determine the effect and feasibility of postoperative rehabilitation processes. MATERIALS AND METHODS: This study will include 200 patients ranging from 18 to 60 years old who have underwent or will undergo FAI arthroscopy in the West China Hospital Sports Medicine Center from 2023 to 2026. A standardized prospective single-center parallel-group randomized controlled trial will be used for these participants. The participants will be divided into intervention (telephone versus face-to-face versus music versus floatation) and control groups. The follow-up periods will be measured pre-operatively, as well as postoperatively at 1, 3, and 6 months. The primary outcomes will include the modified Harris Hip Score (mHHS) and the Visual Analogic Score (VAS), and the secondary outcomes will include the range of motion (ROM), the Huaxi Emotional-distress Index (HEI), and the depression, anxiety, and stress scale (DASS-21 scale). Furthermore, the Patient Health Questionnaire-9 (PHQ-9) and a Short-Form 12 (SF-12) questionnaire will also be evaluated. DISCUSSION: This study will evaluate the clinical and cost-effectiveness of different types of psychosocial-therapy-based rehabilitation methods designed to improve the quality of life of FAI patients with persistent symptoms.
ABSTRACT
In recent years, graphene and its derivatives have gained wide attention in the biomedical field due to their good physicochemical properties, biocompatibility, and bioactivity. Its good antibacterial, osteoinductive and drug-carrying properties make it a promising application in the field of orthopedic biomaterials. This paper introduces the research progress of graphene and its derivatives in bone tissue engineering and cartilage tissue engineering and presents an outlook on the future development of graphene-based materials in orthopedics.
ABSTRACT
This retrospective study aimed to compare the effectiveness between concurrent meniscoplasty and conservative management on the asymptomatic side in children with unilaterally symptomatic bilateral discoid lateral meniscus operated on the symptomatic side in a tertiary level of clinical care. Patients aged under 14 with unilaterally symptomatic bilateral discoid lateral meniscus underwent arthroscopic meniscoplasty were eligible. Patients were either underwent meniscoplasty on the symptomatic side, with the asymptomatic side conservatively treated (group 1) or underwent meniscoplasty on both sides concurrently (group 2). Functional outcomes were evaluated using the Lysholm score and Ikeuchi score. Relative cost collected through the hospital data was applied by the Kruskal-Wallis test. The occurrence of symptoms was applied by the Kaplan-Meier model. A total of 50 patients (39 female and 11 male) were eligible. For the average Lysholm scores, groups 1 and 2 of the previously asymptomatic side were 90.86 ± 8.25 and 92.62 ± 8.68. For the symptomatic side, the Lysholm scores were 91.38 ± 8.90 and 95.71 ± 7.45. For the average cost of treatment, a significant difference was discovered between group 1 and 2 (P < .0001). The Kaplan-Meier survival analysis of the occurrence of symptoms showed no statistical difference between the 2 groups (P = .162), and the terminal survival rates in the 2 groups were 86.2% and 81.0%, respectively. Conservative treatment reached the same clinical outcomes as the concurrent meniscectomy, with a potential of longer mean survival time and lower demand of cost in treatment.
Subject(s)
Knee Joint , Meniscectomy , Humans , Child , Female , Male , Aged , Retrospective Studies , Knee Joint/surgery , Conservative Treatment , HospitalsABSTRACT
OBJECTIVE: To compare the mid-term clinical effect of arthroscopic surgery versus conservative treatment on the middle aged early knee osteoarthritis (EKOA) patients, with the hope to provide clinical evidence for their individual therapy. METHODS: A total of 145 middle aged EKOA patients(182 knees) who received arthroscopic surgery or conservative treatment from January 2015 to December 2016 were retrospectively enrolled, including 35 males and 110 females, aged from 47 to 79 years old with an average of (57.6±6.9) years old, and the duration of disease ranged from 6 to 48 months with an average of(14.6±8.9) months. According to treatment method, patients were divided into arthroscopic surgery group (47 patients, 58 knees) and conservative treatment group(98 patients, 124 knees). Before treatment, patients presented with symptoms of knee joint, such as pain, swelling, locking, limited flexion and extension, and weakness, as well as abnormal findings in knee X-ray (without or suspicious joint space narrow, and a few of osteophyte formation) or in knee MRI (injury or degeneration of articular cartilage or meniscus, loose body in the joint cavity and synovial hyperemia edema, etc). Related data were collected, including duration of knee symptoms, presence of meniscus injury, loose body in the joint cavity or mechanical symptoms such as locking, and visual analogue scale (VAS) and Lysholm knee function score before treatment and at the latest follow-up. Statistical analysis was performed to compare the differences in VAS or Lyshilm score before or after treatment between the low groups and within each group. RESULTS: Patients in the two groups were followed up from 60 to 76 months. In the arthroscopic surgery group, the incision healing was good and no surgical complications occurred. There were no significant differences in age, gender, BMI and follow-up time between the two groups(P>0.05). Before treatment, compared with conservative group, duration of symptoms in the arthroscopic group was longer (P<0.001), comorbidity rates of meniscus injury (P<0.001), free body (P=0.001) and mechanical symptoms (P<0.001) were higher, VAS (P<0.001) and Lysholm score (P<0.001) were worse. At the final follow-up, VAS and Lysholm score in either the conservative group or the arthroscopic group were significantly better than before treatment (P<0.05), while no significant differences between the two groups were found. The VAS was (1.5±1.2) scores in the arthroscopic group and (1.6±1.0)scores in the conservative group(P=0.549), and the Lysholm score was (84.9±12.5) scores in the arthroscopic group and (84.2±9.9) scores in the conservative group (P=0.676). CONCLUSION: Both arthroscopic surgery and conservative treatment have satisfactory intermediate clinical effect middle- aged patients with EKOA, without statistically differences. However, most of the patients before surgery in the arthroscopic treatment group had mechanical locking symptoms caused by meniscus injury or loose body. Therefore, for the middle-aged EKOA patients with mechanical locking symptoms or without obtaining satisfactory outcome after conservative treatment, arthroscopic surgery may be considered.
Subject(s)
Osteoarthritis, Knee , Male , Middle Aged , Female , Humans , Aged , Osteoarthritis, Knee/surgery , Retrospective Studies , Arthroscopy/methods , Treatment Outcome , Knee Joint/surgeryABSTRACT
INTRODUCTION: Although ultrasound can reportedly diagnose discoid lateral meniscus (DLM) in children, its widespread application is challenging because the diagnostic criteria are based on qualitative descriptions of DLM morphology rather than quantitative parameters. Additionally, no studies have applied ultrasound in classifying DLM. Therefore, this study aims to establish the quantitative ultrasound parameters that reflect DLM morphology, evaluate the feasibility and validity of these parameters for identifying DLM and their classification, and develop the quantitative ultrasound diagnostic criteria for DLM and their classification in children. METHODS AND ANALYSIS: Patients will be recruited from the outpatient clinics of the orthopaedics department at West China Hospital, Sichuan University, the Fourth Medical Center of the Chinese People's Liberation Army General Hospital, Xinhua Hospital affiliated with Shanghai Jiao Tong University School of Medicine, Yibin Hospital affiliated with West China Hospital Sichuan University, Suining Central Hospital and the Third Hospital of Mianyang from August 2022 to July 2024. Eligible patients are those aged ≤14 years, with knee symptoms such as pain, locking and limited extension, and who planned to undergo arthroscopic surgery. Exclusion criteria are patients with contraindications to ultrasound examination, such as severe skin damage or fracture around the knee. The sample size is estimated to be 576 cases with a power of 0.9 for hypothesis testing, a two-sided α of 0.05, and an expected sensitivity and specificity of 95%. Three days before surgery, ultrasound will be used to observe the morphology of the lateral meniscus and measure its width, angle α formed by the chord of upper and lower arc-shaped articular surface at the free edge, and the movement distance of the peripheral rim. Participants will be categorised according to the arthroscopy results for the DLM and its classification. The diagnostic performance of each parameter will be assessed and compared in terms of the area under the curve, sensitivity, specificity, and positive and negative predictive values. ETHICS AND DISSEMINATION: This study was approved by the Ethics Committee of West China Hospital, Sichuan University (approval no. 2022-923), and this approval covers all study hospitals. Written informed consent is required from all participants before enrolment in the study. The study's findings will be disseminated through peer-reviewed publications and conference presentations. TRIAL REGISTRATION NUMBER: Chinese Clinical Trial Registry (ChiCTR2200062000).