Identifying drug-drug interactions (DDIs) is essential to prevent adverse effects from polypharmacy. Although deep learning has advanced DDI identification, the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits. Here, we developed a Multi-Dimensional Feature Fusion model named MDFF, which integrates one-dimensional simplified molecular input line entry system sequence features, two-dimensional molecular graph features, and three-dimensional geometric features to enhance drug representations for predicting DDIs. MDFF was trained and validated on two DDI datasets, evaluated across three distinct scenarios, and compared with advanced DDI prediction models using accuracy, precision, recall, area under the curve, and F1 score metrics. MDFF achieved state-of-the-art performance across all metrics. Ablation experiments showed that integrating multi-dimensional drug features yielded the best results. More importantly, we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs. Among 12 real-world adverse drug reaction reports, the predictions of 9 reports were supported by relevant evidence. Additionally, MDFF demonstrated the ability to explain adverse DDI mechanisms, providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.

Identifying drug-drug interactions(DDIs)is essential to prevent adverse effects from polypharmacy.Although deep learning has advanced DDI identification,the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits.Here,we developed a Multi-Dimensional Feature Fusion model named MDFF,which integrates one-dimensional simplified molec-ular input line entry system sequence features,two-dimensional molecular graph features,and three-dimensional geometric features to enhance drug representations for predicting DDIs.MDFF was trained and validated on two DDI datasets,evaluated across three distinct scenarios,and compared with advanced DDI prediction models using accuracy,precision,recall,area under the curve,and F1 score metrics.MDFF achieved state-of-the-art performance across all metrics.Ablation experiments showed that integrating multi-dimensional drug features yielded the best results.More importantly,we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs.Among 12 real-world adverse drug reaction reports,the predictions of 9 reports were supported by relevant evidence.Additionally,MDFF demon-strated the ability to explain adverse DDI mechanisms,providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.

Objective A new type fighter pilot's helmet comfort was investigated to provide basis for generalization and popularization.Methods A quantitative questionnaire was designed to evaluate the comfort of current helmets and new helmets by pilots of series A and B fighters,and compare the new helmets with the current helmets.Thirdly,quantitative statistics of questionnaires were carried out to analyze the pilot's opinions on current helmets and new helmets.Based on the structure and quality characteristics of current helmets and new helmets,the investigation results were analyzed and discussed.Results A total of 167 pilots from series A and B fighter aircraft participated in trial wear and questionnaire investigation of new helmets.Among them,103 pilots from series A fighters and 64 pilots from series B fighters.Compared with the pilot's current helmet,the new helmet is lightweight and comfortable.Among them,92.2%of the pilots of the series A believe that the new helmet is more comfortable than the current helmet,and 90.3%of pilots think it is necessary to replace the current helmet with the new helmet.90.6%of the pilots of the Series B think the new helmet is more comfortable than the current helmet,and 92.2%of pilots think it is necessary to replace the current helmet with the new helmet.Conclusion The new fighter pilot's helmet is light and comfortable,and has been widely praised by pilots.The research results provide data support and decision-making basis for its universalization and popularization.

Clinicians need to focus on various points in the diagnosis and treatment of insomnia.This article prescribed the treatment protocol based on the unique features,such as insomnia in the elderly,women experiencing specific physiologi-cal periods,children insomnia,insomnia in sleep-breathing disorder patients,insomnia in patients with chronic liver and kidney dysfunction.It pro-vides some reference for clinicians while they make decision on diagnosis,differentiation and treat-ment methods.

Objective Non-compliance of active treatments occurred in clinical trials is usually unavoidable,and improper use of standard approaches may lead to biased results,especially for non-inferiority trials.Thus,for three-arm non-inferiority clinical trials,we established a Bayes causal model to estimate causal effects in the presence of non-compliance.Methods Based on the framework of principal stratification,population was stratified according to types of compliance,and the issue was transformed into mixed-distribution identification.Bayes causal model was constructed and data augmentation(DA)algorithm were employed to calculate the posterior distribution of parameters of interest and complete statistical inference.Through simulation,we evaluated performances of our approach,compared with traditional methods including ITT,PP and AT.Results The method of ITT,PP,and AT all had a significant bias when the type of compliance associated with outcomes.The method proposed in this study both had a good performance whether the type of compliance associated with outcomes or not.Conclusion For non-inferiority trials with a high proportion of non-compliance,the method in this article has a better control of the bias.

Background Overweight/obesity in children are a global health issue. Preschool age is an important stage of children's growth and development and dietary behaviors, so it is crucial to explore dietary behavior characteristics and childhood overweight/obesity. Objective To explore the association between dietary behavior characteristics and overweight/obesity in preschool children in Shanghai, and the consistency of children's eating behavior characteristics with their parents'. Methods The children aged 3 to 6 years in 5 kindergartens in Shanghai in 2015 were selected by convenience sampling and surveyed. Their height and weight were measured. Children's and parents' dietary behavior characteristics were self-reported by their parents. According to the weight-for-height recommended by the World Health Organization, excess weight was calculated by the following formula: excess-weight%=[(measured weight - standard weight)/standard weight×100%]; obese is determined at excess-weight% > 20%, overweight: excess-weight% at 10%-20%, normal weight: excess-weight% at −10%-<10%. Chi-squared test and t test were used to compare the differences of demographic and dietary behavior characteristics between overweight/obese and normal weight children. Multiple logistic regression models were used to evaluate the association between dietary behaviors and overweight/obesity. The consistency of dietary behavior characteristics was tested between children and their parents. Results Among the 897 preschool children, 217 (24.2%) were overweight/obese and 680 (75.8%) were of normal weight. The birth weight [(3439±472) g vs. (3361±418) g] and proportion of monthly household income < 10000 yuan (17.1% vs. 10.7%) in the overweight/obese children were significantly higher than those in the normal weight children, and there were no statistical differences in sex, age, gestational age, time of adding complementary foods, outdoor activities after school every day, and parental BMI. After adjusting for potential confounders such as sex, age, household income, outdoor activities after school every day, and parental overweight/obesity, frequently having puffed food (OR=2.46, 95%CI: 1.20-4.95), western-style fast food (OR=3.52, 95%CI: 1.41-8.79), and carbonated drinks (OR=2.92, 95%CI: 1.37-6.13), often eating a lot (OR=1.51, 95%CI: 1.09-2.08) and having a good appetite (OR=2.60, 95%CI: 1.87-3.62), having regular meals (OR=1.48, 95%CI: 1.07-2.03), and fast eating (OR=3.37, 95%CI: 2.10-5.42) were positively associated with children's overweight/obesity (P<0.05). Children's partial/picky eating was inconsistent with fathers' behavior (P<0.05), while the other dietary behaviors were similar with both mothers' and fathers'. Conclusion Eating behavior characteristics of preschool children are associated with overweight/obesity, and affected by their parents. Early identifying dietary behavior problems and improving dietary habits of children might be an effective strategy in preventing and controlling the occurrence and development of obesity in childhood.

Background: Studies have shown that intestinal microbiota is closely related to the occurrence and development of depression, however, the regulatory mechanism of the classic antidepressant fluoxetine on intestinal microbiota is still unclear. Aims: To investigate the mechanism of fluoxetine in regulating intestinal microbiota structure and metabolic diversity in rats with depression. Methods: Thirty SD rats were randomly divided into blank group, model group and fluoxetine group. Depression rat model was established by chronic unpredictable mild stress (CUMS) combined with solitary care. Fluoxetine hydrochloride dispersible tablets 3.17 mg•kg

Objective:To provide accurate eye position data for the system design of helmet mounted display by studying the eye position distribution and anthropometric items of pilots' head and face.Methods:The head and face data of 372 Chinese male fighter pilots were captured by a non-contact 3D scanning system to build cloud models. By noise cutting and mending processing each head and face model was built with same template mesh and unified anatomical coordinate system. The eye position design was defined according to monocular or binocular display. The positions (core of pupils) of left and right eyes and 12 anthropometric items were calculated from the 3D models.Results:The database of 372 fighter pilots′ head and face 3D models was established and it included 12 anthropometric items such as the coordinates of left and right eyes position, inter pupillary distance and vertex-pupil height.Conclusions:Based on 3D scanning technology, the distribution of eye locations (designed eye position and eye box) of pilots were built under the human head anatomical coordinate system and related anthropometric items of head and face are obtained, which could be used as the data foundation for designing pilot′s helmet mounted display system.

Objective:To provide accurate eye position data for the system design of helmet mounted display by studying the eye position distribution and anthropometric items of pilots' head and face.Methods:The head and face data of 372 Chinese male fighter pilots were captured by a non-contact 3D scanning system to build cloud models. By noise cutting and mending processing each head and face model was built with same template mesh and unified anatomical coordinate system. The eye position design was defined according to monocular or binocular display. The positions (core of pupils) of left and right eyes and 12 anthropometric items were calculated from the 3D models.Results:The database of 372 fighter pilots′ head and face 3D models was established and it included 12 anthropometric items such as the coordinates of left and right eyes position, inter pupillary distance and vertex-pupil height.Conclusions:Based on 3D scanning technology, the distribution of eye locations (designed eye position and eye box) of pilots were built under the human head anatomical coordinate system and related anthropometric items of head and face are obtained, which could be used as the data foundation for designing pilot′s helmet mounted display system.

Objective To study the clinical distribution and drug resistance of Acinetobacter baumannii (AB) .Methods Clinical distribution and drug resistance of 1 190 strains of AB ,isolated in 2012 and 2013 ,were retrospectively analyzed .Results Most of AB strains were isolated from sputum ,and mainly from Intensive Care Unit ,Department of Neurosurgery and Department of Re‐spiratory .Resistance rates of AB to most antimicrobial agents were 60% -80% .Resistance rate to tobramycin ,piperacillin/tazobac‐tam and imipenem was increased significantly .Resistance rate to cefoperazone/sulbactam was decreased .Conclusion Drug resist‐ance of AB might be serious ,with increasing tendency .