Personalized drug response prediction from molecular data is an important challenge in precision medicine for treating cancer.Computational methods have been widely explored and have become increasingly accurate in recent years.However,the clinical application of prediction methods is still in its infancy due to large discrepancies between preclinial models and patients.We present a novel disentangled synthesis transfer network(DiSyn)for drug response prediction specifically designed for transfer learning from preclinical models to clinical patients.DiSyn uses a domain separation network(DSN)to disentangle drug response related features,employs data synthesis technology to increase the sample size and iteratively trains for better feature disentanglement.DiSyn is pretrained on large-scale unlabeled cancer samples and validated by three datasets,The Cancer Genome Atlas(TCGA),Investigation of Serial Studies to Predict Your Therapeutic Response With Imaging And moLecular Analysis 2(I-SPY2)and Novartis Institutes for Biomedical Research Patient-Derived Xenograft Encyclopedia(NIBR PDXE),achieving competitive performance with the state-of-the-art methods on cancer patients and mice.Furthermore,the application of DiSyn to thousands of breast cancer patients show the heterogeneity in drug responses and demonstrate its potential value in biomarker discovery and drug combination prediction.

Personalized drug response prediction from molecular data is an important challenge in precision medicine for treating cancer. Computational methods have been widely explored and have become increasingly accurate in recent years. However, the clinical application of prediction methods is still in its infancy due to large discrepancies between preclinial models and patients. We present a novel disentangled synthesis transfer network (DiSyn) for drug response prediction specifically designed for transfer learning from preclinical models to clinical patients. DiSyn uses a domain separation network (DSN) to disentangle drug response related features, employs data synthesis technology to increase the sample size and iteratively trains for better feature disentanglement. DiSyn is pretrained on large-scale unlabeled cancer samples and validated by three datasets, The Cancer Genome Atlas (TCGA), Investigation of Serial Studies to Predict Your Therapeutic Response With Imaging And moLecular Analysis 2 (I-SPY2) and Novartis Institutes for Biomedical Research Patient-Derived Xenograft Encyclopedia (NIBR PDXE), achieving competitive performance with the state-of-the-art methods on cancer patients and mice. Furthermore, the application of DiSyn to thousands of breast cancer patients show the heterogeneity in drug responses and demonstrate its potential value in biomarker discovery and drug combination prediction.

Objective:To explore the clinical, imaging, and pathological features of glottic squamous cell carcinoma of the larynx and their relationship with prognosis. Methods:A retrospective analysis was conducted on the clinical, imaging, and pathological data of 130 patients with glottic squamous cell carcinoma of the larynx who were treated at the First People's Hospital of Yinchuan and the General Hospital of Ningxia Medical University from January 2018 to March 2023. Imaging examinations （CT and MRI） were used to evaluate the lesion boundary clarity, density, enhancement nature, and enhancement degree. Postoperative pathological examination was used to determine the pathological nature, immunohistochemistry, etc. Statistical methods such as χ² test, Spearman correlation analysis, multivariate logistic regression analysis, and Kaplan-Meier method were used to analyze the data. Results:Among the 130 patients, 127 were male and 3 were female, with an average age of （61.92±9.595） years. There was a correlation between clinical, imaging, and pathological features. Multivariate analysis showed that heterogeneous MRI density （OR=12.414;P=0.019） and squamous cell carcinoma as a subtype were correlated. The initial symptom of non-hoarseness （HR=6.045;P=0.010） and unclear MRI boundary （HR=12.559; P=0.029） were independent risk factors for poor prognosis in patients with glottic squamous cell carcinoma of the larynx. Conclusion:There is a correlation between the clinical, imaging, and pathological features of patients with glottic squamous cell carcinoma of the larynx, and they can affect prognosis. The initial symptom of non-hoarseness and unclear MRI boundary of the tumor are independent risk factors for poor prognosis.
Humans ; Laryngeal Neoplasms/diagnosis* ; Prognosis ; Male ; Female ; Retrospective Studies ; Middle Aged ; Carcinoma, Squamous Cell/diagnosis* ; Magnetic Resonance Imaging ; Glottis/pathology* ; Tomography, X-Ray Computed ; Aged

Objective:To investigate the clinical characteristics and major allergens of patients with pollen-food allergy syndrome（PFAS） and their correlation with the severity of symptoms, and to provide a basis for identifying high-risk patients, optimizing the allergen testing process and developing individualized dietary management strategies. Methods:The clinical data of 166 patients with PFAS admitted to our hospital from January 2021 to July 2023 were retrospectively analyzed. The clinical symptoms, pollen types and food allergy of the patients were analyzed by questionnaire survey and serum specific IgE detection. phi coefficient, Apriori algorithm modeling and multivariate logistic regression analysis were used to evaluate the association between allergen and symptom severity. Results:Artemisia pollen was the most common allergen in this area, with a positive rate of 96.39%. Peach and mango were the most common food allergens, which caused allergic reactions in 24.10% and 22.89% of patients, respectively. Oral mucosal symptoms were the main symptoms. Correlation analysis showed that there was a correlation between pollen allergens and allergenic food. Association rule analysis showed that when the patient was allergic to the combination of peanuts and trees, the probability of high severity of symptoms was 82.35%. Multivariate analysis showed that ragweed allergy was significantly positively correlated with the severity of PFAS symptoms. Conclusion:Artemisia pollen and related food allergens play an important role in the pathogenesis of PFAS. Association rule mining and network map analysis revealed direct associations between peanut and tree combination allergy and symptom severity, as well as potential links between other inhaled allergens and specific food allergies. Ragweed and peach allergy are independent risk factors for the aggravation of PFAS symptoms, which can be used as early warning indicators. These results help to improve the screening of high-risk patients and the construction of regional allergen databases.
Humans ; Food Hypersensitivity/immunology* ; Allergens/immunology* ; Retrospective Studies ; Pollen/immunology* ; Cross Reactions ; Immunoglobulin E/blood* ; Rhinitis, Allergic, Seasonal/immunology* ; Artemisia/immunology* ; Male ; Female ; Adult ; Prunus persica/immunology* ; Arachis/immunology* ; Middle Aged ; Surveys and Questionnaires ; Oral Allergy Syndrome

Objective:Middle ear cholesteatoma is a common otolaryngological disease, and traditional diagnostic methods have certain limitations. This study aims to construct a computer-aided diagnosis model for middle ear cholesteatoma based on integrated convolutional neural networks (CNNs) to improve diagnostic accuracy and efficiency.Methods:Firstly, Data were collected from patients who visited the Department of Otorhinolaryngology Head and Neck Surgery at the First People′s Hospital of Yinchuan between January 2020 and December 2021. 8 000 temporal bone CT images were collected, including 5 000 images diagnosed pathologically as middle ear cholesteatoma and 3 000 normal images. A five-fold cross-validation method was used to divide the dataset into training and testing sets. Next, a transfer learning approach was used to initialize model parameters, and the AlexNet, GoogleNet, and ResNet networks were pre-trained to extract deep features from the images. Then, the Softmax classification algorithm was applied to classify the features, resulting in three independent classifiers. These classifiers were combined using an ensemble learning method with a weighted voting approach to obtain the final diagnostic results. Finally, the model was evaluated by comparing the ensemble classifier with individual classifiers to assess its accuracy, precision, sensitivity, specificity, and diagnostic time, and a comparison with low-mid-and high-experience physician groups was conducted to comprehensively evaluate the model′s diagnostic performance.Results:The experimental results showed that the model achieved an accuracy of 88.8%(178/200), precision of 92.9%,(112/120) sensitivity of 89.8%(108/120), and specificity of 88.1%(70/80). The average diagnostic time for individual patient temporal bone CT images was reduced to 2-3 seconds. Compared to the diagnostic results from low-mid-and high-experience physician groups, the model demonstrated significant advantages and effectively assisted clinicians in making rapid and accurate middle ear cholesteatoma diagnoses.Conclusion:The proposed middle ear cholesteatoma diagnostic model based on integrated convolutional neural networks exhibits high recognition accuracy and rapid diagnostic speed, significantly improving clinical diagnostic efficiency, especially in early screening and auxiliary diagnosis, making it of considerable value in clinical practice.

Objective:Middle ear cholesteatoma is a common otolaryngological disease, and traditional diagnostic methods have certain limitations. This study aims to construct a computer-aided diagnosis model for middle ear cholesteatoma based on integrated convolutional neural networks (CNNs) to improve diagnostic accuracy and efficiency.Methods:Firstly, Data were collected from patients who visited the Department of Otorhinolaryngology Head and Neck Surgery at the First People′s Hospital of Yinchuan between January 2020 and December 2021. 8 000 temporal bone CT images were collected, including 5 000 images diagnosed pathologically as middle ear cholesteatoma and 3 000 normal images. A five-fold cross-validation method was used to divide the dataset into training and testing sets. Next, a transfer learning approach was used to initialize model parameters, and the AlexNet, GoogleNet, and ResNet networks were pre-trained to extract deep features from the images. Then, the Softmax classification algorithm was applied to classify the features, resulting in three independent classifiers. These classifiers were combined using an ensemble learning method with a weighted voting approach to obtain the final diagnostic results. Finally, the model was evaluated by comparing the ensemble classifier with individual classifiers to assess its accuracy, precision, sensitivity, specificity, and diagnostic time, and a comparison with low-mid-and high-experience physician groups was conducted to comprehensively evaluate the model′s diagnostic performance.Results:The experimental results showed that the model achieved an accuracy of 88.8%(178/200), precision of 92.9%,(112/120) sensitivity of 89.8%(108/120), and specificity of 88.1%(70/80). The average diagnostic time for individual patient temporal bone CT images was reduced to 2-3 seconds. Compared to the diagnostic results from low-mid-and high-experience physician groups, the model demonstrated significant advantages and effectively assisted clinicians in making rapid and accurate middle ear cholesteatoma diagnoses.Conclusion:The proposed middle ear cholesteatoma diagnostic model based on integrated convolutional neural networks exhibits high recognition accuracy and rapid diagnostic speed, significantly improving clinical diagnostic efficiency, especially in early screening and auxiliary diagnosis, making it of considerable value in clinical practice.

Objective:For tympanosclerosis patients with ossicular chain fixation, we use ossicular chain bypass technique and evaluate its long-term effects. Methods:From June 2017 to June 2019, 147 patients with tympanosclerosis who underwent middle ear surgery with otoscopy in Yinchuan First People's Hospital were reviewed. The subjects were divided into three groups according to the implemented operation plan, 51 cases in the ossicular chain mobilization group（OCM）, 56 cases in the ossicular chain bypass reconstruction group（OCB）, and 40 cases in the malleus-incus complex resection reconstruction group（MICR）. Through a three-year follow-up, the medium and long-term effects of different operation plans were compared and analyzed. Results:There was no significant difference among the three groups in the incidence of tympanic membrane perforation, delayed facial nerve palsy, and the dispatch and displacement of PORP. The incidence of tympanic membrane retraction pocket or cholesteatoma after operation in OCB group（0） was significantly lower than that in OCM group（11.76%） and MICR group（7.5%）（P<0.05）. At 12 months after operation, ΔABG of OCB group and MICR group were better than that in the OCM group（P<0.05）. At 36 months after operation, ΔABG of OCB group was better than that in the OCM group（P<0.05）, and there was no significant difference between OCB group and MICR group. The audiological performance of patients with epitympanic sclerosis（ETS） at 12, 24 and 36 months after operation was better than that of patients with posterior tympanosclerosis（PTS） and total tympanosclerosis（TTS）（P<0.05）. Conclusion:Compared with patients undergoing ossicular chain mobilization and malleus-incus complex resection for ossicular chain reconstruction, patients with tympanosclerosis undergoing bypass technique have better and stable hearing prognosis in medium and long term. This technique can effectively prevent the formation of retracted pocket and cholesteatoma in patients with tympanosclerosis after operation.
Humans ; Tympanosclerosis ; Ear Ossicles/surgery* ; Ear, Middle ; Malleus/surgery* ; Cholesteatoma ; Retrospective Studies ; Ossicular Prosthesis ; Treatment Outcome

Objective:To comprehensively search, analyze and integrate the best evidence on environmental factors for the prevention and management of myopia in children and adolescents, to provide reference for the formulation of scientific and complete myopia prevention and management programs.Methods:A comprehensive search about evidence on environmental factors prevention and management of myopia in children and adolescents was conducted in following databases: UpToDate, BMJ Best Practice, Cochrane Library, JBI Evidence-Based Health Care Center Database, Chinese Medical Ace Base, China Association of Chinese Medicine, Chinese Medical Association, American Academy of Ophthalmology, International Myopia Society, European Society of Ophthalmology, International Agency for the Prevention of Blindness, Brien Holden Vision Research Center, PubMed, Web of Science, Embase, China National Knowledge Infrastructure, Wanfang, etc. Research types included guidelines, expert consensus, systematic review/Meta-analysis, evidence summary, best clinical practice.Results:A total of 23 articles were included, including 6 guidelines, 3 expert consensus articles and 14 systematic reviews. Evidence summarized 27 items from the following 4 aspects: prevention and management purpose, risk assessment, environmental prevention and management measures and health education.Conclusions:This study summarized the best evidence on environmental factors to prevent and manage myopia in children and adolescents. When the evidence is applied, appropriate environmental prevention and management measures should be selected to prevent and control the onset and progression of myopia in children and adolescents, based on the actual situation, to promote evidence-based practice.

Objective: To investigate the effect of tripartite motif containing 59(TRIM59) on the biological function of human colorectal cancer HCT116 cells and its possible mechanism. Methods: The recombinant TRIM59 interference plasmid(si-TRIM59) was constructed and transfected into colorectal cancer cell line HCT116 by liposome transfection. The transfection efficiency was verified by RT-qPCR and Western blot. The effects of TRIM59 gene silencing on the proliferation, colony-formation ability and cell cycle of colorectal cancer cells were detected by CCK-8 method, colony formation assays and flow cytometry respectively. Western blot was used to detect the expression level of CDK4 and cyclinD1. Results: The expression levels ofTRIM59mRNA and protein in colorectal cancer cells were significantly higher than those in normal colorectal mucosa cells(P<0. 05). After knockdown of TRIM59expression, the proliferation activity and colony forming ability of HCT116 cells were significantly inhibited(P<0. 05), and the cell cycle was arrested in G0/G1 phase. At the same time, the expression levels of CDK4and CyclinD1 significantly decreased(P<0. 05). Conclusion TRIM59was highly expressed in colorectal cancer cells. Down regulation ofTRIM59expression can inhibit the proliferation and clone formation of colorectal cancer cells, suggesting thatTRIM59may become a new target for gene therapy of colorectal cancer.

Objective To evaluate the clinical value of acetic acid with narrow-band imaging ( NBI ) and magnifying endoscopy ( ME ) on diagnosis of small colorectal polyps. Methods In this prospective study, 261 small colorectal polyps from 122 patients were observed by ME, NBI-ME, and acetic acid with NBI-ME, and then received endoscopic treatment. Endoscopic images were stored electronically and randomly allocated to 3 experts and 3 non-experts for diagnosis using Kudo pit pattern. The postoperative pathologic results acted as gold standard to evaluate the diagnostic accuracy of different endoscopic modes for small colorectal polyps. The image definition and interobserver agreement were compared among different endoscopic modes. Results The diagnostic accuracy of ME, NBI-ME, and acetic acid with NBI-ME for small colorectal polyps was 65. 5％ ( 171/261) , 90. 0％ ( 235/261) , and 94. 6％ ( 247/261) , respectively, in the experts group, and 57. 1％ ( 149/261) , 83. 1％ ( 217/261) , and 89. 3％ ( 233/261) , respectively, in the non-experts group. All experts and non-experts diagnosed small colorectal polyps more accurately by acetic acid with NBI-ME than by NBI-ME ( all P<0. 05 ) and ME ( all P<0. 001 ) . The image definition scores of acetic acid with NBI-ME in the experts group and non-experts group were significantly higher than those of NBI-ME and ME ( all P<0. 001) . The results of interobserver agreement showed that Kappa values (95％CI) of ME, NBI-ME, and acetic acid with NBI-ME diagnosis were 0. 578 (0. 508-0. 648), 0. 669 (0. 599-0. 739), and 0. 940 (0. 870-1. 010), respectively, for experts and 0. 476 (0. 406-0. 546), 0. 534 ( 0. 464-0. 604) , and 0. 830 ( 0. 760-0. 900 ) , respectively, for non-experts. Acetic acid with NBI-ME showed good interobserver agreement. Conclusion Acetic acid with NBI-ME has a higher diagnostic accuracy and good reproducibility for colorectal small polyps compared with ME and NBI-ME.