Objective To develop a machine learning model integrating preoperative chest CT radiomic features with clinical data for predicting 5-year postoperative recurrence risk in stage Ⅰ non-small cell lung cancer(NSCLC)patients undergoing surgical resection.Methods A total of 217 patients with pathologically confirmed stage Ⅰ NSCLC(selected from 778 initially screened cases based on our inclusion and exclusion criteria)treated in Army Medical Center of PLA between January 2014 and December 2019 were retrospectively enrolled,including 53 recurrence cases and 164 non-recurrence cases within 5-year follow-up.They were randomly divided into a training set(n=173)and a validation set(n=44)in a ratio of 8:2.Radiomic models were established based on extracted features from tumor-dominant regions of interest(ROI)on CT images,while clinical models were developed using demographic characteristics and preoperative laboratory examinations.A combined model was further constructed by integrating both feature sets,and model performance was compared to identify the optimal predictive model.Results This study screened the features from non-contrast CT images and ultimately selected 7 radiomic features for constructing radiomic model.Among 6 machine learning algorithms,the adaptive boosting(Adaboost)model demonstrated the best overall predictive performance,with an area under the curve(AUC)of 0.866(95%CI:0.808～0.923;accuracy:0.832,specificity:0.884)in the training set and of 0.806(95%CI:0.630～0.983;accuracy:0.795,specificity:0.971)in the validation set.Univariate and multivariate logistic regression analyses identified 4 clinical features for clinical model construction.The clinical model achieved an AUC value of 0.874(95%CI:0.821～0.928;accuracy:0.827,specificity:0.891)in the training set and 0.813(95%CI:0.677～0.948;accuracy:0.636,specificity:0.600)in the validation set.By integrating the 7 radiomic features and 4 clinical features using a feature-level fusion strategy,the combined model exhibited further improved predictive performance,with an AUC value of 0.953(95%CI:0.924～0.983;accuracy:0.884,specificity:0.860)and 0.852(95%CI:0.729～0.976;accuracy:0.682,specificity:0.629),respectively in the training set and the validation set.Conclusion The combined model integrating preoperative CT radiomic features with clinical risk factors may provide an evidence-based framework for evaluating 5-year postoperative recurrence risk in stage Ⅰ NSCLC patients.

Sensorineural hearing loss is one of the most common sensory disorders. In recent years, auditory neuropathy spectrum disorders caused by mutations in the OTOF gene have garnered significant attention worldwide, marking it as the first deafness gene with breakthroughs in gene therapy. Most patients with OTOF gene mutations present with stable, congenital, or prelingual onset of hearing loss, which can range from severe to profound and even complete hearing loss. However, a minority of patients may exhibit mild to moderate progressive hearing loss or temperature-sensitive hearing loss. This review further explores the genotype-phenotype relationship of the OTOF gene based on reported cases in China and abroad. Additionally, we analyze the characteristics of the natural history of OTOF gene mutations within the Chinese population. This study aims to provide a reference for the clinical diagnosis, evaluation, and treatment of hearing loss associated with OTOF gene mutations.
Humans ; Mutation ; Phenotype ; Genotype ; Hearing Loss, Sensorineural/genetics* ; Membrane Proteins/genetics*

Traditional development of small protein scaffolds has relied on display technologies and mutation-based engineering, which limit sequence and functional diversity, thereby constraining their therapeutic and application potential. Protein design tools have significantly advanced the creation of novel protein sequences, structures, and functions. However, further improvements in design strategies are still needed to more efficiently optimize the functional performance of protein-based drugs and enhance their druggability. Here, we extended an evolution-based design protocol to create a novel minibinder, BindHer, against the human epidermal growth factor receptor 2 (HER2). It not only exhibits super stability and binding selectivity but also demonstrates remarkable properties in tissue specificity. Radiolabeling experiments with ^99mTc, ⁶⁸Ga, and ¹⁸F revealed that BindHer efficiently targets tumors in HER2-positive breast cancer mouse models, with minimal nonspecific liver absorption, outperforming scaffolds designed through traditional engineering. These findings highlight a new rational approach to automated protein design, offering significant potential for large-scale applications in therapeutic mini-protein development.

OBJECTIVE: To observe the effect of heat-sensitive moxibustion on the quality of life in the elderly patients with malignant tumor based on palliative treatment. METHODS: A total of 100 elderly patients with malignant tumor were randomly divided into an observation group (50 cases, 3 cases dropped out) and a control group (50 cases, 4 cases dropped out). The conventional palliative treatment was performed in the control group. On the basis of conventional palliative treatment, heat-sensitive moxibustion was added at Shenque (CV8) and Zhongwan (CV12) in the observation group, once a day, 5 times a week, one course of treatment was composed of 2 weeks, and 2 consecutive courses of treatment were given. In the observation group, 15 patients voluntarily continued heat-sensitive moxibustion treatment, which was collected in the sub-observation group No.1, these patients were treated 3 times a week and for 6 months consecutively. Using the propensity score matching method, 15 patients who only completed 2 courses of treatment were assigned into the sub-observation group No.2. Before and after treatment, the scores of European Organization for Research and Treatment of Cancer quality of life questionnaire (EORTC QLQ-C30), the Karnofsky performance status (KPS), and the anorexia/cachexia subscale-12 (A/CS-12), as well as the immune indexes (the contents of serum immune globulin [Ig]G, IgA, IgM and complements C3 and C4) were observed in the patients of the observation group and the control group. The monthly survivals were recorded in the two sub-observation groups after 6 months of treatment completion. The coordination was analyzed on the score of deqi scale of heat-sensitive moxibustion at the probing stage before treatment and the change in the score of EORTC QLQ-C30 before and after treatment in the patients of the observation group. RESULTS: After treatment, except the score related to the financial difficulties, the score of every items in EORTC QLQ-C30 was greater than that before treatment in the observation group (P<0.05); the scores for overall health, nausea/vomiting, pain, short breath, constipation and diarrhea of the scale were higher than those before treatment in the control group (P<0.05). The score for each item of the scale in the observation group was higher when compared with that in the control group, except the score for financial difficulties (P<0.05). After treatment, KPS score increased in the observation group when compared with that before treatment (P<0.05), and the score was higher than that of the control group (P<0.05). After treatment, A/CS-12 score was elevated in comparison with that before treatment in each group (P<0.05), and the score in the observation group was higher than that of the control group (P<0.05). After treatment, in the observation group, the contents of serum IgG, IgA and IgM, and C3 and C4 increased in comparison with those before treatment (P<0.05); and in the control group, the contents of serum IgG, C3 and C4 were declined (P<0.05). After treatment, the contents of serum IgG, IgA and IgM, and C3 and C4 in the observation group were higher than those in the control group (P<0.05). After 6 months of treatment completion, the survival rate in the sub-observation group No.1 was higher than that of the sub-observation group No.2 (P<0.05). In the observation group, the positive coordination was presented between the score of deqi scale of heat-sensitive moxibustion and the change in the score of EORTC QLQ-C30 in the observation group (r>0, P<0.001). CONCLUSION On the basis of palliative treatment, heat-sensitive moxibustion can improve the quality of life, appetite and the immunity of the elderly patients with malignant tumor. Consecutive long-term moxibustion is contributed to prolonging the life span. The stronger deqi is felt during moxibustion delivery, the more significant the therapeutic effect is obtained.
Humans ; Moxibustion ; Male ; Female ; Aged ; Quality of Life ; Neoplasms/psychology* ; Palliative Care ; Aged, 80 and over ; Middle Aged ; Acupuncture Points

Objective To explore the application value of artificial intelligence in medical research assistance, and analyze the key paths to achieve precise execution of model instructions, improvement of model interpretation completeness, and control of hallucinations. Methods Taking esophageal cancer research as the scenario, five types of literature including research articles, case reports, reviews, editorials, and guidelines were selected for model interpretation tests. The model performance was systematically evaluated from five dimensions: recognition accuracy, format accuracy, instruction execution accuracy, content reliability rate, and content completeness index. The performance differences of Ruibin Agent, GPT-4o, Claude 3.7 Sonnet, DeepSeek V3, and DouBao-pro models in medical literature interpretation tasks were compared. Results A total of 15 studies were included, with 3 studies of each type. The five models collectively conducted 1 875 tests. Due to the poor recognition accuracy of the editorial type, the overall recognition accuracy of Ruibin Agent was significantly lower than other models (92.0% vs. 100.0%, P＜0.001). In terms of format accuracy, Ruibin Agent was significantly better than Claude 3.7 Sonnet (98.7% vs. 92.0%, P=0.002) and GPT-4o (98.7% vs. 78.9%, P＜0.001). In terms of instruction execution accuracy, Ruibin Agent was better than GPT-4o (97.3% vs. 80.0%, P＜0.001). In terms of content reliability rate, Ruibin Agent was significantly lower than Claude 3.7 Sonnet (84.0% vs. 92.0%, P=0.010) and DeepSeek V3 (84.0% vs. 94.7%, P＜0.001). In terms of content completeness index, the median scores of Ruibin Agent, GPT-4o, Claude 3.7 Sonnet, DeepSeek V3, and DouBao-pro were 0.71, 0.60, 0.85, 0.74, and 0.77, respectively. Conclusion Ruibin Agent has significant advantages in terms of formatted interpretation of medical literature and instruction execution accuracy. In the future, it is necessary to focus on optimizing the recognition ability of editorial types, strengthening the coverage ability of core elements of various types of literature to improve interpretation completeness, and improving content reliability through optimizing the confidence mechanism to ensure the rigor of medical literature interpretation.

Objective To explore the value of radiomics and deep transfer learning(DTL)based on gadoxetic acid disodium-enhanced magnetic resonance imaging(MRI)for preoperative prediction of microvascular invasion(MVI)in hepatocellular carcinoma(HCC).Methods A retrospective analysis was conducted using the MRI and clinicopathological data of 369 HCC patients who underwent surgery and had pathologically confirmed MVI at the Affiliated Hospital of Qingdao University from January 2019 to September 2024.According to the negative and positive manifestations of MVI,these patients were divided into MVI-group(n=219)and MVI+group(n=150);and they were then randomly assigned into the training set(n=258)and the test set(n=111)in a ratio of 7:3.Based on the hepatobiliary phase images,the optimal features were extracted and screened from radiomics features,DTL features,and the fusion features of the two.Nine machine learning models were constructed using 3 algorithms(random forest,multi-layer perceptron,and support vector machine,separately)and trained on radiomics features,DTL features,and the fusion features of the two.The diagnostic efficacy of each model was evaluated using receiver operating characteristic curve,and the optimal model was identified as the output model.Results Among all the constructed models,those based on fused features outperformed models using individual features.The random forest classifier model in the training set had the best performance,with an AUC of 0.998(95%CI:0.996-1.000),and was therefore selected as the output model in this study.Conclusion Radiomics and DTL models based on gadoxetic acid disodium-enhanced MRI can effectively predict the MVI in HCC.Among these,the random forest classifier model utilizing fused features in the training set exhibits the best performance.

Objective To explore the value of radiomics and deep transfer learning(DTL)based on gadoxetic acid disodium-enhanced magnetic resonance imaging(MRI)for preoperative prediction of microvascular invasion(MVI)in hepatocellular carcinoma(HCC).Methods A retrospective analysis was conducted using the MRI and clinicopathological data of 369 HCC patients who underwent surgery and had pathologically confirmed MVI at the Affiliated Hospital of Qingdao University from January 2019 to September 2024.According to the negative and positive manifestations of MVI,these patients were divided into MVI-group(n=219)and MVI+group(n=150);and they were then randomly assigned into the training set(n=258)and the test set(n=111)in a ratio of 7:3.Based on the hepatobiliary phase images,the optimal features were extracted and screened from radiomics features,DTL features,and the fusion features of the two.Nine machine learning models were constructed using 3 algorithms(random forest,multi-layer perceptron,and support vector machine,separately)and trained on radiomics features,DTL features,and the fusion features of the two.The diagnostic efficacy of each model was evaluated using receiver operating characteristic curve,and the optimal model was identified as the output model.Results Among all the constructed models,those based on fused features outperformed models using individual features.The random forest classifier model in the training set had the best performance,with an AUC of 0.998(95%CI:0.996-1.000),and was therefore selected as the output model in this study.Conclusion Radiomics and DTL models based on gadoxetic acid disodium-enhanced MRI can effectively predict the MVI in HCC.Among these,the random forest classifier model utilizing fused features in the training set exhibits the best performance.

Temporomandibular joint (TMJ) diseases are common clinical conditions. The number of patients with TMJ diseases is large, and the etiology, epidemiology, disease spectrum, and treatment of the disease remain controversial and unknown. To understand and master the current situation of the occurrence, development and prevention of TMJ diseases, as well as to identify the patterns in etiology, incidence, drug sensitivity, and prognosis is crucial for alleviating patients′suffering.This will facilitate in-depth medical research, effective disease prevention measures, and the formulation of corresponding health policies. Cohort construction and research has an irreplaceable role in precise disease prevention and significant improvement in diagnosis and treatment levels. Large-scale cohort studies are needed to explore the relationship between potential risk factors and outcomes of TMJ diseases, and to observe disease prognoses through long-term follw-ups. The consensus aims to establish a standard conceptual frame work for a cohort study on patients with TMJ disease while providing ideas for cohort data standards to this condition. TMJ disease cohort data consists of both common data standards applicable to all specific disease cohorts as well as disease-specific data standards. Common data were available for each specific disease cohort. By integrating different cohort research resources, standard problems or study variables can be unified. Long-term follow-up can be performed using consistent definitions and criteria across different projects for better core data collection. It is hoped that this consensus will be facilitate the development cohort studies of TMJ diseases.

Objective:To investigate the expression of nuclear matrix protein 4 (NMP4) in hepatocellular carcinoma (HCC), and its relationship with clinicopathological features and survival prognosis of patients.Methods:The clinical data of 100 HCC patients who were treated with radical resection of liver cancer in the Department of Hepatobiliary Surgery of the Third Affiliated Hospital of Wenzhou Medical University from July 1, 2014 to July 1, 2019 were retrospectively analyzed. There were 63 males and 37 females, aged (58.5±10.4) years old. Immunohistochemical method was used to detect the expression of NMP4 protein in HCC cancer tissue and the corresponding adjacent normal tissue. According to the expression of NMP4 in HCC tissues, 100 patients were divided into two groups: the NMP4-positive expression group ( n=62) and the NMP4-negative expression group ( n=32). Univariate analysis was performed on the relationship between NMP4 expression and clinical pathological features as well as overall survival of HCC patients. Cox multivariate analysis was performed on the factors influencing postoperative prognosis of HCC patients. Results:Immunohistochemistry results showed that NMP4 was primarily expressed in the nucleus, the positive expression rate of NMP4 in HCC tissues was higher than that in adjacent non-cancerous tissues [62.0% (62/100) vs. 8.0%(8/100)], and the difference was statistically significant ( χ2=2.12, P=0.003). Univariate analysis revealed that the overall survival of HCC patients was correlated with the degree of tumor differentiation, tumor length, BCLC stage, number of tumor foci, vascular tumor thrombus and expression of NMP4 (all P<0.05). Cox multivariate analysis revealed that low differentiation, high BCLC stage (stage C), number of tumor foci (≥3), and positive expression of NMP4 were independent risk factors affecting postoperative survival and recurrence-free survival of HCC patients. The median overall survival and median recurrence-free survival of HCC patients in the NMP4-positive expression group were 22.3 months and 11.5 months, respectively. In contrast, that in the NMP4-negative expression group were 40.6 months and 19.4 months, respectively. The cumulative survival rate and recurrence-free survival rate of HCC patients in the NMP4-positive expression group were lower than those in the NMP4-negative expression group, and the differences were statistically significant (both P<0.05). Conclusion:Positive NMP4 expression was closely correlated with malignant biological progression and poor prognosis of HCC patients.

Objective To study the relationship between serum Melatonin,macrophage inflammatory pro-tein-1α(MIP-1α)and nucleotide-binding oligomerization domain-like receptor protein 3(NLRP3)inflamma-some and prognosis in children with acute respiratory distress syndrome(ARDS).Methods A total of 140 children with ARDS who were admitted to the hospital from January 2021 to January 2023 were enrolled as the ARDS group,and 100 healthy children who underwent physical examination during the same period were enrolled as the control group.According to the clinical outcome on 28 d after admission,the children with ARDS were divided into a death group(29 cases)and a survival group(111 cases).Enzyme-linked immu-nosorbent assay was used to detect the serum levels of Melatonin,MIP-1α,interleukin(IL)-1β,and IL-18.Re-al-time fluorescent quantitative PCR was used to detect the mRNA levels of NLRP3 and Caspase-1.Pearson correlation was used to analyze the correlation between serum levels of Melatonin and MIP-1α and NLRP3 in-flammasome related indicators(NLRP3 mRNA,Caspase-1 mRNA,IL-1β,IL-18)in children with ARDS.Mul-tivariate Cox regression analysis was used to analyze the factors affecting the prognosis of children with ARDS.According to the mean levels of serum Melatonin and MIP-1α,the children with ARDS were divided in-to a high/low Melatonin group and MIP-1α group.The Kaplan-Meier method was used to draw the survival curves of ARDS children with high/low levels of serum Melatonin and MIP-1α.The receiver operating charac-teristic(ROC)curve was used to analyze the predictive value of serum Melatonin and MIP-1α for death in children with ARDS.Results Compared with the control group,the ARDS group had a significantly decreased serum Melatonin level and significantly increased serum MIP-1α,IL-1β,IL-18 and NLRP3 mRNA and Caspase-1 mRNA levels in peripheral blood mononuclear cells(P＜0.05).Pearson correlation analysis showed that the serum Melatonin level of ARDS children was negatively correlated with NLRP3 mRNA,Caspase-1 mRNA,IL-1β and IL-18(P＜0.05),the level of MIP-1α was positively correlated with NLRP3 mR-NA,Caspase-1 mRNA,IL-1β and IL-18(P＜0.05).Multivariate Cox regression analysis showed that acute physiology and chronic health evaluation Ⅱ score,NLRP3 mRNA,Caspase-1 mRNA,IL-1β,IL-18 and MIP-1αwere independent risk factors affecting the prognosis of children with ARDS.Melatonin was an independent protective factor(P＜0.05).Kaplan-Meier survival curve analysis showed that the 28 d survival rate in high Melatonin group was higher than that in low Melatonin group(P＜0.05),and the 28 d survival rate in high MIP-1α group was lower than that in low MIP-1α group(P＜0.05).ROC curve analysis showed that the area under the curve of Melatonin and MIP-1α combined to predict the death of ARDS children was 0.881(95％CI 0.816-0.930).It was higher than 0.785(95％CI 0.708-0.850)and 0.778(95％CI 0.700-0.844)predic-ted by Melatonin or MIP-1α alone.Conclusion The serum Melatonin level is decreased and MIP-1α level is in-creased in children with ARDS,which is closely related to NLRP3 inflammasome and prognosis.Combined de-tection of serum Melatonin and MIP-1α levels has a high predictive value for the prognosis of children with ARDS.