With the rapid development of computer science, the application of artificial intelligence (AI) in the field of medical imaging has become increasingly extensive. The temporomandibular joint (TMJ) is structurally complex, with a high incidence of related disorders and diverse clinical manifestations. This review analyzes the current state of research on AI in TMJ imaging diagnosis. Deep learning models based on U-Net and its derivatives have demonstrated outstanding performance in segmentation of condyle and articular disc. Various object detection and feature extraction algorithms have shown excellent diagnostic efficacy for common conditions, such as osteoarthrosis and disc displacement, with some models even achieving expert-level performance on test datasets. Meanwhile, explainable AI provides intuitive justification for model decisions through techniques such as heatmap visualization. Notably, current studies still face critical challenges, including coverage of disease spectra, integration of multimodal data, and model generalizability. Future studies should focus on developing integrated systems that combine diagnosis, segmentation, generation, and interpretation functions. Through multicenter data validation and algorithmic optimization, these efforts will enhance the clinical applicability and decision transparency of models, ultimately laying the foundation for precise imaging diagnosis and intelligent management of TMJ disorders.

ObjectiveTo investigate the characteristics and distribution of traditional Chinese medicine （TCM） syndromes in the patients with esophageal squamous cell carcinoma （ESCC）. MethodsAn electronic questionnaire was developed to collect the general data and four examination information of ESCC patients treated in 10 areas with high incidence of esophageal cancer in China from June 2020 to March 2021. Multiple analyses including frequency analysis， factor analysis， and hierarchical cluster analysis were performed to analyze the potential syndrome elements， disease location， and common syndromes of ESCC. ResultsA total of 2 027 patients with ESCC were included. Statistical analysis was performed on 113 symptoms， physical signs， 33 tongue manifestation variables， and 23 pulse manifestation variables of the patients’ four examination information. Factor analysis was performed on 55 variables with frequency>10%， extracting 19 common factors. According to clinical experience and expert opinions， the main lesions of patients with ESCC were in the spleen and stomach， and the main syndrome elements were Qi stagnation， blood stasis， phlegm， dampness， and Qi deficiency， with the syndrome element combination of phlegm obstruction + Qi stagnation + blood stasis being the most common. The syndromes can be classified into four categories of liver-stomach disharmony + combined phlegm and Qi obstruction， kidney-spleen dysfunction + combined phlegm and stasis， spleen-kidney Yang deficiency + obstinate phlegm and blood stasis， and liver-kidney Yin deficiency + obstinate phlegm and blood stasis. The main syndrome of ESCC was liver-stomach disharmony + combined phlegm and Qi obstruction in the early stage， liver-spleen dysfunction + combined phlegm and stasis in the middle stage， and spleen-kidney Yang deficiency + obstinate phlegm and blood stasis in the late stage. ConclusionESCC mainly has main pathological features of internal deficiency and external excess and combined deficiency and excess， with the key syndrome elements being phlegm obstruction， Qi stagnation， and blood stasis. The main disease locations are in the spleen and stomach， involving the liver， kidney， chest and diaphragm， heart， and lung. The main syndrome is liver-stomach disharmony + combined phlegm and Qi obstruction. In clinical practice， it is necessary to grasp the pathogenesis dynamics of the disease and use prescriptions according to patients’ syndromes.

Objective: To explore the independent and interactive effects of school green space exposure and outdoor activity duration on screening myopia among primary and secondary school students, so as to provide theoretical support for the prevention and control of screening myopia in children and adolescents. Methods: From September to November 2023, 117 487 primary and secondary school students from 497 schools were selected using a cluster random sampling method, covering 98 counties (cities, districts) in Jiangsu Province. Data on the students screening myopia status and associated health influencing factors were collected and analyzed. School green space exposure was quantified using the normalized difference vegetation index (NDVI), which was extracted with ArcGIS Pro software; meanwhile, information on students outdoor activity duration was gathered through self reported questionnaires. Multivariate Logistic regression was applied to assess the independent and interactive effects of green space exposure and outdoor activity duration on screening myopia among primary and secondary school students. Results: Univariate analysis showed that there were statistically significant differences in screening myopia detection rates among primary and secondary school students of different genders, NDVI groups, every outdoor activity duration, monitoring points, school stages, parents educational level, and whether they lived on campus or had parents with screening myopia ( χ 2=88.91-1 950.08, all P <0.05); as the school age and sedentary time increased, the detection rate of screening myopia in primary and secondary school students also increased ( χ 2 trend =8 410.15, 2 028.91, both P <0.05). Independent effects showed that compared to the low NDVI group, the medium and high NDVI groups had lower risks of screening myopia ( OR =0.93, 0.95, both P <0.05). Compared to those with outdoor activity duration<2 h/d, students with outdoor activity duration≥2 h/d had a lower risk of screening myopia ( OR =0.96, P <0.05). When stratified by school level, compared to the low NDVI group, the medium NDVI group had lower risks of screening myopia in primary and junior high schools (primary school: OR =0.91; junior high school: OR =0.88, both P <0.05). Compared to those with outdoor activity duration<2 h/d, junior high school students with outdoor activity duration≥2 h/d had a lower risk of screening myopia ( OR = 0.90, P <0.05). When stratified by monitoring site, urban primary and secondary school students in the medium and high NDVI groups and those with outdoor activity duration≥2 h/d had lower risks of screening myopia ( OR =0.92, 0.92, 0.93, all P <0.05). Interactive effects showed that when medium or high NDVI was combined with outdoor activity duration≥2 h/d, the risks of screening myopia among primary and secondary school students were lower (medium NDVI×≥2 h/d: OR =0.89; high NDVI×≥ 2 h/d : OR =0.89, both P <0.05), and the combined effect was superior to that of a single factor. Conclusion Green space exposure and outdoor activity duration have negative correlations with screening myopia among primary and secondary students, and the combined effect is better than that of a single factor.

Objective To mine and analyze adverse drug events(ADEs)of novel agents for multi-drug-resistant tuberculosis(MDR-TB)based on the FDA Adverse Event Reporting System(FAERS)database,to explore the signals of ADEs,and to provide reference for clinical use.Methods The FAERS database was searched and extracted from Q1 of 2015 to Q4 of 2023,and the ADE reports about bedaquiline,delamanid,and pretomanid were collected.Data mining and analysis were carried out on relevant reports of the drug using the reporting odds ratio(ROR),proportional reporting ratio(PRR),medicines and healthcare products regulatory agency(MHRA),and the Bayesian confidence progressive neural network(BCPNN).Results The number of ADE reports for the target drugs bedaquiline,delamanid,and pretomanid were 2 477,1 630,and 173,respectively.ADE of the target drugs involved multiple organ systems.Positive signals detected by the ROR,PRR,MHRA,and BCPNN methods were 246,246,215,204 for bedaquiline;251,251,224,200 for delamanid;and 25,25,24,22 for pretomanid.Clinically significant high-risk signals include prolonged QT interval on ECG,anemia,liver toxicity,peripheral neuropathy,etc.Conclusions The signal mining of ADEs based on the FAERS database indicates that close attention should be paid to risks such as prolonged QT interval on ECG,anemia,liver toxicity,and peripheral neuropathy during the clinical use of bedaquiline,delamanid,and pretomanid.In addition,monitoring of new potential ADE signals(such as acute heart failure,respiratory failure,acute kidney injury,etc.)should be strengthened,and timely intervention measures should be taken to ensure medication safety.

Colorectal cancer(CRC)ranks among the leading causes of cancer incidence and mortality worldwide.Microsatellite instability(MSI)is a key molecular biomarker with important implications for prognosis and immunotherapy selection.Although conventional detection methods such as immunohistochemistry,PCR,and next-generation sequencing have been standardized,they remain limited by high costs,technical complexity,and inconsistent results.In recent years,artificial intelligence(AI)has shown great potential in MSI detection by integrating multimodal data that includes histopathological images,genomic information,and medical imaging to achieve accurate prediction and enable a data-driven paradigm in oncology.This review summarizes the latest advances in AI-based multimodal modeling for MSI detection in CRC,compares different methodological approaches and their translational challenges,and discusses future directions such as multimodal integration,model generalizability,and interpretability enhancement,providing new insights for precision medicine.

Objective To investigate the clinical application value of detection of interleukin-6(IL-6),C reactive protein(CRP),and neutrophic-to-lymphocyte ratio(NLR)alone and in combination in the prognosis assessment of severe pneumonia(SP).Methods A total of 81 patients with SP admitted from December 2022 to December 2023 were selected as the research subjects.According to the discharge outcomes of the patients,they were divided into the survival group(n=62)and the death group(n=19).The general clinical data at admission and laboratory parameters of the two groups were collected and compared.The receiver operating characteristic(ROC)curve was used to analyze the value of serum IL-6,CRP and NLR detection in the prognosis assessment of SP.Results At admission,the pulse of the death group was higher than that of the survival group,while the systolic blood pressure(SBP)was lower than that of the survival group(P<0.05,P<0.01).The incidence of chest tightness in the death group at admission was significant higher than that in the survival group(P<0.05).Compared with the survival group,the number of lymphocyte counts and albumin levels in the death group were lower,while the percentage of neutrophils,NLR and procalcitonin were higher than those in the survival group(P<0.05,P<0.01).ROC curve analysis showed that the area under the curve(AUC)for predicting poor prognosis of SP by the combined detection of IL-6,CRP and NLR was 0.75,which was higher than that predicted by each indicator alone.Conclusion Compared with the detection of IL-6,CRP and NLR alone,the combined detection of the three has a more significant value in predicting the risk of death in patients with SP.It suggests that clinicians should promptly,comprehensively and dynamically monitor the above infection indicators during diagnosis and treatment,and take prompt and effective intervention measures to reduce the mortality rate of patients.

Objective To mine and analyze adverse drug events(ADEs)of novel agents for multi-drug-resistant tuberculosis(MDR-TB)based on the FDA Adverse Event Reporting System(FAERS)database,to explore the signals of ADEs,and to provide reference for clinical use.Methods The FAERS database was searched and extracted from Q1 of 2015 to Q4 of 2023,and the ADE reports about bedaquiline,delamanid,and pretomanid were collected.Data mining and analysis were carried out on relevant reports of the drug using the reporting odds ratio(ROR),proportional reporting ratio(PRR),medicines and healthcare products regulatory agency(MHRA),and the Bayesian confidence progressive neural network(BCPNN).Results The number of ADE reports for the target drugs bedaquiline,delamanid,and pretomanid were 2 477,1 630,and 173,respectively.ADE of the target drugs involved multiple organ systems.Positive signals detected by the ROR,PRR,MHRA,and BCPNN methods were 246,246,215,204 for bedaquiline;251,251,224,200 for delamanid;and 25,25,24,22 for pretomanid.Clinically significant high-risk signals include prolonged QT interval on ECG,anemia,liver toxicity,peripheral neuropathy,etc.Conclusions The signal mining of ADEs based on the FAERS database indicates that close attention should be paid to risks such as prolonged QT interval on ECG,anemia,liver toxicity,and peripheral neuropathy during the clinical use of bedaquiline,delamanid,and pretomanid.In addition,monitoring of new potential ADE signals(such as acute heart failure,respiratory failure,acute kidney injury,etc.)should be strengthened,and timely intervention measures should be taken to ensure medication safety.

Colorectal cancer(CRC)ranks among the leading causes of cancer incidence and mortality worldwide.Microsatellite instability(MSI)is a key molecular biomarker with important implications for prognosis and immunotherapy selection.Although conventional detection methods such as immunohistochemistry,PCR,and next-generation sequencing have been standardized,they remain limited by high costs,technical complexity,and inconsistent results.In recent years,artificial intelligence(AI)has shown great potential in MSI detection by integrating multimodal data that includes histopathological images,genomic information,and medical imaging to achieve accurate prediction and enable a data-driven paradigm in oncology.This review summarizes the latest advances in AI-based multimodal modeling for MSI detection in CRC,compares different methodological approaches and their translational challenges,and discusses future directions such as multimodal integration,model generalizability,and interpretability enhancement,providing new insights for precision medicine.

Objective To investigate the clinical application value of detection of interleukin-6(IL-6),C reactive protein(CRP),and neutrophic-to-lymphocyte ratio(NLR)alone and in combination in the prognosis assessment of severe pneumonia(SP).Methods A total of 81 patients with SP admitted from December 2022 to December 2023 were selected as the research subjects.According to the discharge outcomes of the patients,they were divided into the survival group(n=62)and the death group(n=19).The general clinical data at admission and laboratory parameters of the two groups were collected and compared.The receiver operating characteristic(ROC)curve was used to analyze the value of serum IL-6,CRP and NLR detection in the prognosis assessment of SP.Results At admission,the pulse of the death group was higher than that of the survival group,while the systolic blood pressure(SBP)was lower than that of the survival group(P<0.05,P<0.01).The incidence of chest tightness in the death group at admission was significant higher than that in the survival group(P<0.05).Compared with the survival group,the number of lymphocyte counts and albumin levels in the death group were lower,while the percentage of neutrophils,NLR and procalcitonin were higher than those in the survival group(P<0.05,P<0.01).ROC curve analysis showed that the area under the curve(AUC)for predicting poor prognosis of SP by the combined detection of IL-6,CRP and NLR was 0.75,which was higher than that predicted by each indicator alone.Conclusion Compared with the detection of IL-6,CRP and NLR alone,the combined detection of the three has a more significant value in predicting the risk of death in patients with SP.It suggests that clinicians should promptly,comprehensively and dynamically monitor the above infection indicators during diagnosis and treatment,and take prompt and effective intervention measures to reduce the mortality rate of patients.