Objective To investigate the efficacy of an interpretable integrated learning model combining clinical indicators,CT image features and radiomics features for the differential diagnosis of lung squamous cell carcinoma and adenocarcinoma,so as to provide references for clincal treatment decisions.Methods A retrospective analysis was conducted on clinical and imaging data from 220 patients(231 lesions)with primary non-small cell lung cancer at Jiangjin Central Hospital of Chongqing(Center 1)and 83 patients(84 lesions)at Chongqing General Hospital(Center 2).In Center 1,the squamous cell carcinoma group consisted of 60 patients(60 lesions),while the adenocarcinoma group included 160 patients(171 lesions).In Center 2,the squamous cell carcinoma group comprised 18 patients(18 lesions),and the adenocarcinoma group involved 65 patients(66 lesions).The patients were categorized into squamous cell carcinoma and adenocarcinoma groups based on pathological findings.Center 1 was randomly partitioned into a training set and a validation set at a 7∶3 ratio,while Center 2 served as the independent test set.Firstly,a deep learning model,VB-Net,was used to automatically segment the tumor region on the lung window image;secondly,the SMOTE(synthetic minority oversampling technique)method was used to balance the categories in the training set and standardize the extracted features with Z-scores;thirdly,the least absolute shrinkage and selection operator(LASSO)were used to select the optimal radiomics features and calculate the radiomics score(Radscore),and univariate and multivariate logistic regression was used to screen clinical indicators and independent clinical factors for differentiating lung squamous cell carcinoma and adenocarcinoma in CT image features;finally,three ensemble learning algorithms(AdaBoost,Bagging decision tree and XGBoost)were used to combine independent clinical factors and Radscore to construct the model.The receiver operating characteristic(ROC)curve was used to evaluate the diagnostic performance of the models.SHAP technique was used to analyze the feature contribution and model decision-making process.Results Among the evaluated ensemble models,AdaBoost and Bagging decision trees demonstrated overfitting tendencies.In contrast,the XGBoost model showed the best performance,achieving AUC values of 0.939,0.887 and 0.853 in the training,validation and independent test sets,respectively.SHAP indicated that Radscore was the most important feature affecting the performance of the model.The decision diagram enabled the visualization of the diagnostic process of the model.Conclusion The interpretable integrated learning model based on clinical indicators,CT image and radiomics features is expected to non-invasively diagnose lung squamous cell carcinoma and adenocarcinoma before treatment and assist clinicians make treatment decisions as early as possible.[Chinese Medical Equipment Journal,2025,46(7):12-20]

Listeria brainstem encephalitis with myelitis is extremely rare in clinical practice.Since the clinical manifestations are non-specific,MRI is helpful for diagnosis.Positive cerebrospinal fluid culture is considered the gold standard for diagnosis.This article reports a case of an immunocompetent individual with listeria brainstem encephalitis with myelitis,aiming to enhance the awareness of this condition.
Humans ; Brain Stem/pathology* ; Diagnostic Errors ; Encephalitis/complications* ; Encephalomyelitis, Acute Disseminated/diagnosis* ; Listeriosis/complications* ; Myelitis/complications*

Objective To investigate the efficacy of an interpretable integrated learning model combining clinical indicators,CT image features and radiomics features for the differential diagnosis of lung squamous cell carcinoma and adenocarcinoma,so as to provide references for clincal treatment decisions.Methods A retrospective analysis was conducted on clinical and imaging data from 220 patients(231 lesions)with primary non-small cell lung cancer at Jiangjin Central Hospital of Chongqing(Center 1)and 83 patients(84 lesions)at Chongqing General Hospital(Center 2).In Center 1,the squamous cell carcinoma group consisted of 60 patients(60 lesions),while the adenocarcinoma group included 160 patients(171 lesions).In Center 2,the squamous cell carcinoma group comprised 18 patients(18 lesions),and the adenocarcinoma group involved 65 patients(66 lesions).The patients were categorized into squamous cell carcinoma and adenocarcinoma groups based on pathological findings.Center 1 was randomly partitioned into a training set and a validation set at a 7∶3 ratio,while Center 2 served as the independent test set.Firstly,a deep learning model,VB-Net,was used to automatically segment the tumor region on the lung window image;secondly,the SMOTE(synthetic minority oversampling technique)method was used to balance the categories in the training set and standardize the extracted features with Z-scores;thirdly,the least absolute shrinkage and selection operator(LASSO)were used to select the optimal radiomics features and calculate the radiomics score(Radscore),and univariate and multivariate logistic regression was used to screen clinical indicators and independent clinical factors for differentiating lung squamous cell carcinoma and adenocarcinoma in CT image features;finally,three ensemble learning algorithms(AdaBoost,Bagging decision tree and XGBoost)were used to combine independent clinical factors and Radscore to construct the model.The receiver operating characteristic(ROC)curve was used to evaluate the diagnostic performance of the models.SHAP technique was used to analyze the feature contribution and model decision-making process.Results Among the evaluated ensemble models,AdaBoost and Bagging decision trees demonstrated overfitting tendencies.In contrast,the XGBoost model showed the best performance,achieving AUC values of 0.939,0.887 and 0.853 in the training,validation and independent test sets,respectively.SHAP indicated that Radscore was the most important feature affecting the performance of the model.The decision diagram enabled the visualization of the diagnostic process of the model.Conclusion The interpretable integrated learning model based on clinical indicators,CT image and radiomics features is expected to non-invasively diagnose lung squamous cell carcinoma and adenocarcinoma before treatment and assist clinicians make treatment decisions as early as possible.[Chinese Medical Equipment Journal,2025,46(7):12-20]

AIM: To analyze the clinical effect of 577nm subthreshold micropulse laser(SML)photocoagulation combined with intravitreal injection of Conbercept in the treatment of diabetic macular edema(DME)after vitrectomy in patients with proliferative diabetic retinopathy(PDR).METHODS:A retrospective analysis was performed on 29 cases(30 eyes)of PDR patients who had DME after vitrectomy in our hospital from January 2019 to June 2021. They were divided into two groups according to different treatment methods: 14 cases(14 eyes)in the single injection group received intravitreal injection of Conbercept, and 15 cases(16 eyes)in the combined treatment group received 577nm SML photocoagulation in the macular area combined with intravitreal injection of Conbercept. The changes in best corrected visual acuity(BCVA)and central macular thickness(CMT)before and at 6 and 12mo after treatment, as well as the changes of multifocal electroretinogram(mfERG)before and at 12mo after treatment were compared between the two groups.RESULTS: The BCVA(LogMAR)of patients in both groups improved and CMT decreased after treatment for 6 and 12mo(all P<0.001). There were no significant differences in BCVA(LogMAR)and CMT before treatment and 6mo, 12mo after treatment between single injection group and combined treatment group(all P>0.05). Compared with the combined treatment group, the amplitude was slightly lower(23.02±3.13 vs. 26.50±3.33 μV/deg2)and the latency time was prolonged(38.75±1.62 vs. 34.21±3.06ms)in single injection group at 12mo(all P≤0.001). The average injection times in single injection group was 8.14±1.46, and 5.05±1.51 in combined treatment group at 12mo after treatment(P<0.05).CONCLUSION: 577nm SML photocoagulation combined with intravitreal injection of conbercept can effectively relieve macular edema, improve BCVA and visual function of macular area and reduce the injection times of conbercept for DME patients.

This study aimed to investigate the development status of traditional Chinese medicine(TCM) intervention in psoriasis in recent ten years, analyze the research hotspots, and summarize the development trends to provide reference materials for scholars in this field. Taking the available literature related to the field of TCM intervention in psoriasis as the research object, the trends, contents, and source publications were statistically analyzed based on bibliometrics. The research cooperation and co-occurrence of keywords in this field were studied by the knowledge map analysis method based on CiteSpace. The total number of Chinese papers was 2 993 and English papers 285. In terms of publication trend, the annual publication of English papers was low but showed an obvious upward trend, while the increase in Chinese papers fluctuated and tended to be flat. In terms of the content of Chinese papers published, TCM ranked first according to the discipline(2 415). In English papers, the number of publications in pharmacology and pharmaceutical science was the highest(87). Literature source analysis showed that the Chinese and English journals with the most publications were China Journal of Traditional Chinese Medicine and Pharmacy and Evidence Based Complementary and Alternative Medicine, respectively. Beijing University of Chinese Medicine published the most dissertations in China(99). The authors with the most publications in Chinese and English were LI Bin(Yueyang Hospital of Integrated Traditional Chinese and Western Medicine Affiliated to Shanghai University of Traditional Chinese Medicine) and LU Chuan-jian(Guangdong Hospital of Traditional Chinese Medicine). As revealed by the CiteSpace analysis of the research cooperation network, there were four mature and stable core teams in this field, but the cooperation intensity between different teams was weak. According to the keywords co-occurrence knowledge graph constructed by CiteSpace, the current hot keywords in this field are as follows: psoriasis, blood-heat syndrome, blood-stasis syndrome, fire needle, blood-dryness type, imiquimod, TCM bath, etiology and pathogenesis, cytokines, cupping therapy, etc. In summary, Chinese scholars have conducted active exploration and research in the field of TCM intervention in psoriasis in recent ten years. The overall development trend is good, and the breadth and depth of the research are constantly extending. It is suggested that relevant research should be free from discipline restrictions and strive for interdisciplinary integration.
Humans ; Medicine, Chinese Traditional ; Psoriasis/drug therapy*

Objective: To investigate the histological features and clinical manifestations in different types of cardiac amyloidosis to improve diagnostic accuracy. Methods: The histopathological features and clinical manifestations of 48 patients diagnosed with cardiac amyloidosis by Congo red stain and electron microscopy through endomyocardial biopsy were collected in West China Hospital of Sichuan University from January 2018 to December 2021. Immunohistochemical stains for immunoglobulin light chains (κ and λ) and transthyretin protein were carried out, and a review of literature was made. Results: The patients age ranged from 42 to 79 years (mean 56 years) and the male to female ratio was 1.1 to 1.0. The positive rate of endomyocardial biopsy was 97.9% (47/48), which was significantly higher than that of the abdominal wall fat (7/17). Congo red staining and electron microscopy were positive in 97.9% (47/48) and 93.5% (43/46), respectively. Immunohistochemical stains showed 32 cases (68.1%) were light chain type (AL-CA), including 31 cases of AL-λ type and 1 case of AL-κ type; 9 cases (19.1%) were transthyretin protein type (ATTR-CA); and 6 cases (12.8%) were not classified. There was no significant difference in the deposition pattern of amyloid between different types (P>0.05). Clinical data showed that ATTR-CA patients had less involvement of 2 or more organs and lower N-terminal pro-B-type natriuretic peptide (NT-proBNP) than the other type patients (P<0.05). The left ventricular stroke volume and right ventricular ejection fraction of ATTR-CA patients were better than the other patients (P<0.05). Follow-up data of 45 patients was obtained, and the overall mean survival time was 15.6±2.0 months. Univariate survival analysis showed that ATTR-CA patients had a better prognosis, while cardiac amyloidosis patients with higher cardiac function grade, NT-proBNP >6 000 ng/L, and troponin T >70 ng/L had a worse prognosis (P<0.05). Multivariate survival analysis showed that NT-proBNP and cardiac function grade were independent prognostic factors for cardiac amyloidosis patients. Conclusions: AL-λ is the most common type of cardiac amyloidosis in this group. Congo red staining combined with electron microscopy can significantly improve the diagnosis of cardiac amyloidosis. The clinical manifestations and prognosis of each type are different and can be classified based on immunostaining profile. However, there are still a few cases that cannot be typed; hence mass spectrometry is recommended if feasible.
Humans ; Male ; Female ; Adult ; Middle Aged ; Aged ; Prealbumin/metabolism* ; Stroke Volume ; Cardiomyopathies/pathology* ; Congo Red ; Ventricular Function, Right ; Amyloidosis/pathology* ; Prognosis

As a recognized rare and highly fatal disease, hereditary angioedema (HAE) is difficult to diagnose and characterized by recurrent edema involving the head, limbs, genitals and larynx, etc. Diagnosis of HAE is not difficult. However, low incidence and lack of clinical characteristics lead to difficulty of doctors on timely diagnosis and correct intervention for HAE patients. Therefore, it is crucial to improve the awareness of this disease and prevent its recurrence. for HAE patients. In view of absent cognition of doctors and the general public on HAE, patients often suffer from sudden death or become disabled due to laryngeal edema which cannot be treated in time. Thus, based on the Internet mobile terminal platform, the team set up an all-day rapid emergency response system which is provided for HAE patients by setting up "one-click help". The aim is to offer optimization on overall management of HAE and designed the intelligent follow-up management to provide timely assistance and specialized suggestion for patients with acute attacks.
Humans ; Angioedemas, Hereditary/drug therapy*

Allergic diseases affect about 40% of the world's population. Environmental factors are important in the occurrence and development of allergic diseases. Dust mites are one of the most important allergens in the indoor environment. The World Health Organization proposes the "four-in-one, combination of prevention and treatment" treatment principle for allergic diseases, in which environmental control to avoid or reduce allergens is the first choice for treatment. Modern people spend much more time at home (including sleeping) than outdoors, and the control of the home environment is particularly critical. This practice introduces the hypoallergenic home visit program, which including home environment assessment, environmental and behavioral intervention guidance, and common household hypoallergenic supplies and service guidance for the patient's home environment. The real-time semi-quantitative testing of dust mite allergens, qualitative assessments of other indoor allergens, record of patients' household items and lifestyle, and precise, individualized patient prevention and control education will be conducted. The hypoallergenic home visit program improves the doctors' diagnosis and treatment data dimension, and becomes a patient management tool for doctors outside the hospital. It also helps patients continue to scientifically avoid allergens and irritants in the environment, effectively build a hypoallergenic home environment, reduce exposure to allergens in the home environment, and achieve the goal of combining the prevention and treatment of allergic diseases.
Humans ; Hospitals ; Life Style ; Sleep

As a recognized rare and highly fatal disease, hereditary angioedema (HAE) is difficult to diagnose and characterized by recurrent edema involving the head, limbs, genitals and larynx, etc. Diagnosis of HAE is not difficult. However, low incidence and lack of clinical characteristics lead to difficulty of doctors on timely diagnosis and correct intervention for HAE patients. Therefore, it is crucial to improve the awareness of this disease and prevent its recurrence. for HAE patients. In view of absent cognition of doctors and the general public on HAE, patients often suffer from sudden death or become disabled due to laryngeal edema which cannot be treated in time. Thus, based on the Internet mobile terminal platform, the team set up an all-day rapid emergency response system which is provided for HAE patients by setting up "one-click help". The aim is to offer optimization on overall management of HAE and designed the intelligent follow-up management to provide timely assistance and specialized suggestion for patients with acute attacks.
Humans ; Angioedemas, Hereditary/drug therapy*