BACKGROUND:The sports medicine community has widely called for the use of machine learning technology to efficiently process the huge and complicated sports data resources,and construct intelligent sports injury prediction models,enabling accurate early warning of sports injuries.It is of great significance to comprehensively summarize and review such research results so as to grasp the direction of early warning model improvement and to guide the construction of sports injury prediction models in China. OBJECTIVE:To systematically review and analyze relevant research on sports injury prediction models based on machine learning technology,thereby providing references for the development of sports injury prediction models in China. METHODS:Literature search was conducted on CNKI,Web of Science and EBSCO databases,which mainly searched for literature related to machine learning techniques and sports injuries.Finally,61 articles related to sports injury prediction models were included for analysis. RESULTS AND CONCLUSION:(1)In terms of external risk feature indicators,there is a lack of competition scenario indicators,and the inclusion of related feature indicators needs to be further improved to further enrich the dimensions of the dataset for model training.In addition,the inclusion feature weighting methods of the sports injury prediction model are mainly based on filtering methods and the use of embedding and wrapping weighting methods needs to be strengthened in order to enhance the analysis of the interaction effects of multiple risk factors.(2)In terms of model body training,supervised learning algorithms become the mainstream choice.Such algorithms have higher requirements for the completeness of sample labeling information,and the application scenarios are easily limited.Therefore,the application of unsupervised and semi-supervised algorithms can be increased in the later stage.(3)In terms of model performance evaluation and optimization,the current studies mainly adopt two verification methods:HoldOut crossover and k-crossover.The range of AUC values is(0.76±0.12),the range of sensitivity is(75.92±11.03)%,the range of specificity is(0.03±4.54)%,the range of F1 score is(80.60±10.63)%,the range of accuracy is(69.96±13.10)%,and the range of precision is(70±14.71)%.Data augmentation and feature optimization are the most common model optimization operations.The accuracy and precision of the current sports injury prediction model are about 70%,and the early warning effect is good.However,the model optimization operation is relatively single,and data augmentation methods are often used to improve model performance.Further adjustments to the model algorithm and hyperparameters are needed to further improve model performance.(4)In terms of model feature extraction,most of the internal risk profile indicators included are mainly based on anthropometrics,training load,years of training,and injury history,but there is a lack of sports recovery and physical function indicators.

ObjectiveTo compare the clinical features of patients with hepatitis B virus （HBV）-related early-onset liver cancer and those with late-onset liver cancer， to assess the severity of the disease， and to provide a theoretical basis for the early diagnosis and treatment of liver cancer. MethodsA retrospective analysis was performed for 695 patients who were diagnosed with HBV-related liver cancer for the first time in Guangzhou Eighth People’s Hospital， Guangzhou Medical University， from January 2019 to August 2023， among whom 93 had early-onset liver cancer （defined as an age of50 years for female patients and40 years for male patients） and 602 had late-onset liver cancer （defined as an age of ≥50 years for female patients and ≥40 years for male patients）. Related clinical data were collected， including demographic data， clinical symptoms at initial diagnosis， comorbidities， smoking history， drinking history， family history， routine blood test results， biochemical parameters of liver function， serum alpha-fetoprotein（AFP）， virological indicators， coagulation function， and imaging findings. The pan-inflammatory indices neutrophil-to-lymphocyte ratio （NLR）， platelet-to-lymphocyte ratio （PLR）， and lymphocyte-to-monocyte ratio （LMR） were calculated， as well as FIB-4 index， aspartate aminotransferase-to-platelet ratio index （APRI）， S index， Model for End-Stage Liver Disease （MELD） score， Child-Turcotte-Pugh （CTP） score， albumin-bilirubin （AIBL） grade， and Barcelona Clinic Liver Cancer （BCLC） stage. The independent-samples t test was used for comparison of normally distributed continuous data between two groups， and the Wilcoxon rank-sum test was used for comparison of non-normally distributed continuous data between two groups； the chi-square test or Fisher’s exact test were used for comparison of categorical data between two groups. ResultsThere were significant differences between the two groups in the proportion of male patients and the incidence rates of diabetes， hypertension， and fatty liver disease （χ²=6.357， 15.230， 11.467， and 14.204， all P0.05）， and compared with the late-onset liver cancer group， the early-onset liver cancer group had a significantly higher proportion of patients progressing to liver cancer without underlying cirrhosis （χ²=24.657， P0.001） and a significantly higher proportion of patients with advanced BCLC stage （χ²=6.172， P=0.046）. For the overall population， the most common clinical symptoms included abdominal distension， abdominal pain， poor appetite， weakness， a reduction in body weight， edema of both lower limbs， jaundice， yellow urine， and nausea， and 55 patients （7.9%） had no obvious symptoms at the time of diagnosis and were found to have liver cancer by routine reexamination， physical examination suggesting an increase in AFP， or radiological examination indicating hepatic space-occupying lesion； compared with the late-onset liver cancer group， the patients in the early-onset liver cancer group were more likely to have the symptoms of abdominal distension， abdominal pain， and jaundice （all P0.05）. Compared with the late-onset liver cancer group， the early-onset liver cancer group had a significantly larger tumor diameter （Z=2.845， P=0.034）， with higher prevalence rates of multiple tumors and intrahepatic， perihepatic， or distant metastasis （χ²=5.889 and 4.079， both P0.05）， and there were significant differences between the two groups in tumor location and size （χ²=3.948 and 11.317， both P0.05）. Compared with the late-onset liver cancer group， the early-onset liver cancer group had significantly lower FIB-4 index， proportion of patients with HBsAg ≤1 500 IU/mL， and levels of LMR and Cr （all P0.05）， as well as significantly higher positive rate of HBeAg and levels of log₁₀ HBV DNA， AFP， WBC， Hb， PLT， NLR， PLR， TBil， ALT， Alb， and TC （all P0.05）. ConclusionCompared with late-onset liver cancer， patients with early-onset liver cancer tend to develop liver cancer without liver cirrhosis and have multiple tumors， obvious clinical symptoms， and advanced BCLC stage， which indicates a poor prognosis.

Patients with periodontal disease often require combined periodontal-orthodontic interventions to restore periodontal health, function, and aesthetics, ensuring both patient satisfaction and long-term stability. Managing these patients involving orthodontic tooth movement can be particularly challenging due to compromised periodontal soft and hard tissues, especially in severe cases. Therefore, close collaboration between orthodontists and periodontists for comprehensive diagnosis and sequential treatment, along with diligent patient compliance throughout the entire process, is crucial for achieving favorable treatment outcomes. Moreover, long-term orthodontic retention and periodontal follow-up are essential to sustain treatment success. This expert consensus, informed by the latest clinical research and practical experience, addresses clinical considerations for orthodontic treatment of periodontal patients, delineating indications, objectives, procedures, and principles with the aim of providing clear and practical guidance for clinical practitioners.
Humans ; Consensus ; Orthodontics, Corrective/standards* ; Periodontal Diseases/complications* ; Tooth Movement Techniques/methods* ; Practice Guidelines as Topic

Cemental tear is a rare and indetectable condition unless obvious clinical signs present with the involvement of surrounding periodontal and periapical tissues. Due to its clinical manifestations similar to common dental issues, such as vertical root fracture, primary endodontic diseases, and periodontal diseases, as well as the low awareness of cemental tear for clinicians, misdiagnosis often occurs. The critical principle for cemental tear treatment is to remove torn fragments, and overlooking fragments leads to futile therapy, which could deteriorate the conditions of the affected teeth. Therefore, accurate diagnosis and subsequent appropriate interventions are vital for managing cemental tear. Novel diagnostic tools, including cone-beam computed tomography (CBCT), microscopes, and enamel matrix derivatives, have improved early detection and management, enhancing tooth retention. The implementation of standardized diagnostic criteria and treatment protocols, combined with improved clinical awareness among dental professionals, serves to mitigate risks of diagnostic errors and suboptimal therapeutic interventions. This expert consensus reviewed the epidemiology, pathogenesis, potential predisposing factors, clinical manifestations, diagnosis, differential diagnosis, treatment, and prognosis of cemental tear, aiming to provide a clinical guideline and facilitate clinicians to have a better understanding of cemental tear.
Humans ; Dental Cementum/injuries* ; Consensus ; Diagnosis, Differential ; Cone-Beam Computed Tomography ; Tooth Fractures/therapy*

Objective To investigate the relationship between the expression of serum long non coding RNA nuclear-enriched abundant transcript 1(lncRNA NEAT1)and microRNA-106a-5p(miR-106a-5p)and the severity and prognosis of sepsis patients.Methods A total of 185 patients with sepsis who were diagnosed and treated in this hospital from August 2021 to July 2024 were selected as the study group,and another 215 healthy volunteers who underwent physical examinations in this hospital during the same period were selected as the control group.The research group was divided into the mild group(n=92),the severe group(n=58)and the shock group(n=35)according to the severity of the disease.The research group was divided into the good prognosis group(n=121)and the poor prognosis group(n=64)according to the prognosis.The expres-sions of lncRNA NEAT1 and miR-106a-5p were detected by real-time fluorescence quantitative polymerase chain reaction,and the correlation of the expressions of lncRNA NEAT1 and miR-106a-5p in the study group was analyzed by Pearson correlation analysis.The binding sites of lncRNA NEAT1 and miR-106a-5p were an-alyzed by StarBase,and the influencing factors of poor prognosis in patients were analyzed by multivariate Lo-gistic regression.The receiver operating characteristic curve was used to analyze the diagnostic value of the combination of lncRNA NEAT1 and miR-106a-5p for poor prognosis in patients.Results The expression of lncRNA NEAT1 in the study group was higher than that in the control group,and the expression of miR-106a-5p was lower than that in the control group,the difference was statistically significant(P＜0.05).The expressions of lncRNA NEAT1 and miR-106a-5p in the study group were negatively correlated(r=-0.413,P＜0.001),and there were binding sites between the two.With the increase of the severity of sepsis,the ex-pression of lncRNA NEAT1 increased and the expression of miR-106a-5p decreased,and the difference was statistically significant(P＜0.05).The acute physiology and chronic health evaluation Ⅱ(APACHE Ⅱ)score,sequential organ failure assessment(SOFA)score,tumor necrosis factor-α,C-reactive protein,and ln-cRNA NEAT1 in the poor prognosis group were higher than those in the good prognosis group,while the ex-pression of miR-106a-5p was lower than that in the good prognosis group,the difference was statistically sig-nificant(P＜0.05).Elevated APACHE Ⅱ score,SOFA score and lncRNA NEAT1 were independent risk fac-tors for poor prognosis in patients,and miR-106a-5p was an independent protective factor(P＜0.05).The ar-ea under the curve of the combined diagnosis of the two was 0.918(95％CI:0.868-0.953),which was supe-rior to the separate diagnosis of each(Zcombined with lncRNA NEAT1=4.112,Zcombined with miR-106a-5p=4.023,P＜0.05).Con-clusion With the increase of disease severity in patients with sepsis,the expression of lncRNA NEAT1 in-creases and the expression of miR-106a-5p decreases.The combined diagnosis of the two for poor prognosis in patients has a high clinical value.

Objective To discuss the application value of CT and DSA multimodal image fusion technology in endovascular interventional therapy for arterial occlusive lesions of lower extremities and to evaluate its efficacy and safety so as to provide a scientific basis for clinical decision-making.Methods A total of 283 lower limbs with arterial complete occlusive lesions,who received treatment at Affiliated Baiyun Hospital of Guizhou Medical University hospital from January 2020 to December 2023,were selected for this study.The 283 diseased lower limbs were randomly divided into study group(n=142)and control group(n=141).In the study group the endovascular interventional therapy assisted by CT and DSA multimodal image fusion technology was adopted,while in the control group the traditional DSA-guided endovascular interventional therapy was employed.The imaging parameters,surgical success rates,X-ray exposure doses,time spent for operation,incidence of postoperative complications,changes of ankle-brachial index(ABI),primary patency rate,assisted primary patency rate,and secondary patency rate were compared between the two groups.Results The surgical success rate in the study group was 96.47％,which was significantly higher than 87.94％in the control group(P＜0.05).The mean time spent for operation in the study group was(125.42±23.74)minutes,which was shorter than(147.81±29.33)minutes in the control group.The mean X-ray exposure dose in the study group was(2 856.34±427.82)mGy·cm2,which was lower than(3 674.53±512.60)mGy·cm2 in the control group.The incidence of postoperative complications in the study group was 4.23％,which was significantly lower than 12.57％in the control group(P＜0.05).The ABI values of the affected limbs in the study group and control group increased from preoperative(0.65±0.15)and(0.60±0.18)respectively to postoperative(1.09±0.32)and(0.90±0.28)respectively.The postoperative ABI value in the study group was higher than that in the control group(P＜0.05).The postoperative 12-month primary patency rate,assisted primary patency rate and secondary patency rate in the study group were 78.17％,85.92％and 90.14％respectively,which were better than 67.38％,75.89％and 80.85％respectively in the control group.Conclusion For arterial occlusive lesions of lower extremities,endovascular interventional therapy with the help of CT and DSA multimodal image fusion technology has high surgical success rates,low incidence of complications,and satisfactory revascularization rate.This technology provides new idea and method for the treatment of arterial occlusive lesions of lower extremities with high clinical safety.Therefore,this technology is worthy of clinical promotion and application.

A novel technology is proposed for non-contact and real-time detection of atrial fibrillation using millimeter-wave radar.A 60 GHz PCR millimeter wave radar is used to continuously detect the chest echo signal of the subject.After signal acquisition,I-Q signal is generated through I-Q demodulation,and the signal phase information is extracted using effective points phase trend evaluation for obtaining the signals from oscillations in the chest wall,from which the respiratory signals and cardiac signals are extracted through digital filtering for the analysis of cardiac movement.Whether the atrial fibrillation occurs or not is determined by the characteristics of atrial fibrillation wave in the time domain.The effective points phase trend evaluation for extracting more accurate signal phase information and the time-domain method for real-time atrial fibrillation detection are the innovations of the study.The experimental results show that the proposed method achieves a detection accuracy of 99.2%in clinic.

Objective:To observe the effects of warm acupuncture on post-stroke cognitive impairment (PSCI) based on the theory of intestinal flora.Methods:A randomized controlled trial was conducted. 60 patients with PSCI in the Department of Acupuncture and Neurology of the First Affiliated Hospital of Xinjiang Medical University from October 2020 to June 2022 were selected as the observation objects, and were divided into 2 groups by random number table, with 30 cases in each group. On the basis of cognitive rehabilitation training, the treatment group was given warm acupuncture treatment, and the control group was given routine acupuncture treatment. 2 groups were treated for 4 weeks as 1 course, and a total of 4 courses were treated. Montreal cognitive assessment (MoCA) was used to assess patients' cognitive function before and after treatment, and mini-mental state examination (MMSE) was used to assess patients' intelligence level. The numbers of bifidobacteria and lactic acid bacteria in fecal samples were calculated, and plasma gamma-aminobutyric acid (GABA) levels were detected by ELISA to evaluate the clinical efficacy.Results:During the study, 1 case was lost in each of the two groups, and finally 29 cases were included in the curative effect statistics. The total effective rate was 79.3% (23/29) in the treatment group and 65.5% (19/29) in the control group, with statistical significance ( χ2=43.39， P<0.05). After treatment, MoCA score [(24.23±1.36) vs. (21.26±1.30), t=3.12] and MMSE score [(25.35±1.24) vs. (21.52±1.22), t=3.25] in the treatment group were higher than those in the control group ( P<0.05); Bifidobacterium [(9.20±1.25) LgCFU/g vs. (7.23±1.21) LgCFU/g, t=2.98], Lactic acid bacteria [(8.24±1.12) LgCFU/g vs. (6.25±1.22) LgCFU/g, t=2.92], and the level of GABA [(283.80±83.54) mmol/L vs. (264.76±61.38) mmol/L, t=10.54] were higher than those in the control group ( P<0.05 or P<0.01). Conclusion:Warm acupuncture and moxibustion can effectively regulate the number of intestinal beneficial bacteria in PSCI patients, increase the level of GABA, promote brain tissue repair and improve cognitive function.

Objective:The distribution characteristics of intrathecal drugs and the limitation of current catheterization techniques make traditional intrathecal analgesic treatment nearly useless for refractory craniofacial pain,such as trigemina neuralgia.This technical guideline aims to promote the widespread and standardize the application of intra-prepontine cisternal drug delivery via spinal puncture and catheterization. Methods:A modified Delphi approach was used to work for this guideline.On the issues related to the intra-prepontine cisternal targeted drug delivery technique,the working group consulted 10 experts from the field with 3 rounds of email feedback and 3 rounds of conference discussion. Results:For the efficacy and safety of the intra-prepontine cisternal targeted drug delivery technique,a consensus was formed on 7 topics(with an agreement rate of more than 80%),including the principles of the technique,indications and contraindications,patient preparation,surgical specifications for intra-prepontine cisternal catheter placement,analgesic dosage coordination,analgesic management,and prevention and treatment of complications. Conclusion:Utilizing the intra-prepontine cisternal drug infusion system to manage refractory craniofacial pain could provide advantages in terms of minimally invasive,secure,and effective treatment.This application can not only alleviate the suffering of individuals experiencing the prolonged pain but also support the maintenance of quality of life and dignity in their final moments,justifiing its widespread dissemination and standardized adoption in domestic and international professional fields.

ObjectiveTo investigate the difference in bilateral lower limb muscle synergy mode during gait in patients after unilateral anterior cruciate ligament reconstruction. MethodsElectromyography from bilateral lower limb muscles during gait were collected from twelve male and eight female patients after unilateral anterior cruciate ligament reconstruction in Affiliated Hospital of Wuhan Sports University, from April to June, 2023. The data were analyzed using non-negative matrix decomposition algorithm to extract the number of muscle synergies in the affected and unaffected legs, the time to peak activation of muscle synergies and the relative weights of the muscles. ResultsSix types of muscle synergy were identified in the unaffected leg of males during gait, while five types were identified in the affected leg, lacking synergy 2 that mainly from the tibialis anterior muscle. Six types of muscle synergy were identified in both legs in females during gait. There was no significant difference in the time to peak activation of muscle synergies between both legs in males (P > 0.05). However, the time to peak activation of muscle synergies increased in females in the affected leg for synergy 3 and synergy 5 (P < 0.05). The relative weight of the rectus femoris was lower in synergy 1 in the affected leg in males (P < 0.05). For female, the relative weight of the vastus lateralis was higher and the relative weight of the biceps femoris was lower in synergy 2 in the affected leg in females (P < 0.05); while the relative weight of the rectus femoris was lower in synergy 3 (P < 0.05), and the relative weight of the biceps femoris was lower in synergy 6 (P < 0.05). ConclusionMales would freeze the muscle synergy dominating ankle dorsiflexion in affected leg to enhance ankle stability, and reduce the relative weight of rectus femoris during the loading response phase to weaken the knee landing cushioning. However, females would delay the activation of synergies dominating in loading response phase and the mid-stance phase, enhance the relative weight of vastus lateralis during the loading response phase, and reduce the relative weights of rectus femoris in the loading response phase and the relative weight of biceps femoris in the mid-stance phase, to limit knee flexion.