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:To study the characteristics of laryngopharyngeal reflux (LPR) events in patients with obstructive sleep apnea (OSA).Methods:This cross-sectional study analyzed OSA patients who were admitted in the Department of Otolaryngology-Head and Neck Surgery, the Sixth Medical Center of the Chinese PLA General Hospital between November 2020 to July 2023[OSA group, 52 males, 6 females, aged 23-69 (41.22±11.42) years], and non-OSA patients admitted during the same period serve as the control group[non-OSA group, 40 males, 1 female, aged 21-68 (45.12±11.30) years]. All participants completed the Reflux Symptom Index (RSI), Reflux Finding Score (RFS) scale, and 24-hour Hypopharyngeal Esophageal Multichannel Intraluminal Impedance-pH (HEMII-pH) monitoring. LPR events were categorized based on their physical composition-liquid, gas, or gas-liquid mixed, according to the change of impedance values; and further classified by pH levels as acidic, weakly acidic, or alkaline. Differences in LPR events physical properties and the time trends of LPR events between the two groups were compared. Group comparisons were performed using t-test or Mann-Whitney U-test. Analyses were conducted using Pearson, Spearman, or Kendall′s tau-b correlation analysis. Categorical data were analyzed using chi-square test. Results:A total of 99 patients were enrolled, including 58 with OSA and 41 without OSA. Of these, 88.89% (88/99) met the diagnostic criteria for laryngopharyngeal reflux disease (LPRD). In LPRD patients, the median proportion of non gas reflux events and the number of alkaline reflux were significantly higher in the OSA with LPRD group than in the non OSA with LPRD group (70.00% vs 36.36%, 0 vs 0, Z-values respectively -3.373, -3.134, P<0.01). Liquid reflux proportion and the number of both liquid and mixed reflux events showed a positive correlation with the apnea-hypopnea index (AHI) ( r-values respectively 0.304, 0.326, 0.268, P<0.05), while the gas reflux constituent ratio was inversely correlated with AHI ( r=-0.358, P<0.01). The frequency and proportion of nocturnal reflux events showed a positive correlation with AHI ( r-values respectively 0.250, 0.211, P<0.05). A significantly higher proportion of OSA with LPRD group experienced both daytime and nighttime reflux compared to non OSA with LPRD group (66.67% vs 38.71%, P<0.05). In LPRD patients, over 50% of all LPR events occurred within 3 hours after each of the three main meals. Conclusions:In OSA with LPRD patients, LPR events are predominantly non gas in nature. OSA with LPRD patients exhibits a higher proportion and frequency of nocturnal reflux events and a greater number of alkaline reflux episodes compared to non OSA with LPRD patients.

Objective:To study the characteristics of laryngopharyngeal reflux (LPR) events in patients with obstructive sleep apnea (OSA).Methods:This cross-sectional study analyzed OSA patients who were admitted in the Department of Otolaryngology-Head and Neck Surgery, the Sixth Medical Center of the Chinese PLA General Hospital between November 2020 to July 2023[OSA group, 52 males, 6 females, aged 23-69 (41.22±11.42) years], and non-OSA patients admitted during the same period serve as the control group[non-OSA group, 40 males, 1 female, aged 21-68 (45.12±11.30) years]. All participants completed the Reflux Symptom Index (RSI), Reflux Finding Score (RFS) scale, and 24-hour Hypopharyngeal Esophageal Multichannel Intraluminal Impedance-pH (HEMII-pH) monitoring. LPR events were categorized based on their physical composition-liquid, gas, or gas-liquid mixed, according to the change of impedance values; and further classified by pH levels as acidic, weakly acidic, or alkaline. Differences in LPR events physical properties and the time trends of LPR events between the two groups were compared. Group comparisons were performed using t-test or Mann-Whitney U-test. Analyses were conducted using Pearson, Spearman, or Kendall′s tau-b correlation analysis. Categorical data were analyzed using chi-square test. Results:A total of 99 patients were enrolled, including 58 with OSA and 41 without OSA. Of these, 88.89% (88/99) met the diagnostic criteria for laryngopharyngeal reflux disease (LPRD). In LPRD patients, the median proportion of non gas reflux events and the number of alkaline reflux were significantly higher in the OSA with LPRD group than in the non OSA with LPRD group (70.00% vs 36.36%, 0 vs 0, Z-values respectively -3.373, -3.134, P<0.01). Liquid reflux proportion and the number of both liquid and mixed reflux events showed a positive correlation with the apnea-hypopnea index (AHI) ( r-values respectively 0.304, 0.326, 0.268, P<0.05), while the gas reflux constituent ratio was inversely correlated with AHI ( r=-0.358, P<0.01). The frequency and proportion of nocturnal reflux events showed a positive correlation with AHI ( r-values respectively 0.250, 0.211, P<0.05). A significantly higher proportion of OSA with LPRD group experienced both daytime and nighttime reflux compared to non OSA with LPRD group (66.67% vs 38.71%, P<0.05). In LPRD patients, over 50% of all LPR events occurred within 3 hours after each of the three main meals. Conclusions:In OSA with LPRD patients, LPR events are predominantly non gas in nature. OSA with LPRD patients exhibits a higher proportion and frequency of nocturnal reflux events and a greater number of alkaline reflux episodes compared to non OSA with LPRD patients.

Objective:To investigate the feasibility of predicting the risk of spontaneous preterm birth in singleton pregnancy women with low risk of preterm birth by transabdominal-transvaginal ultrasound cervical length sequential screening in the second trimester.Methods:This prospective longitudinal cohort study included singleton pregnant women at 11-13 +6 gestational weeks who were admitted to Nanjing Drum Tower Hospital from January 2023 to September 2023. Transabdominal and transvaginal cervical lengths were measured during the mid-trimester fetal ultrasound scan at 18-24 weeks, and pregnancy outcomes were obtained after delivery. A short cervix was defined as a transvaginal cervical length of ≤25 mm, and the outcomes were defined as spontaneous preterm birth occurs between 20 and 36 +6 weeks and extremely preterm birth before 32 weeks. The area under the receiver operating characteristic (ROC) curve was used to evaluate the effectiveness of predicting spontaneous preterm birth by transabdominal and transvaginal cervix length, as well as the effectiveness of predicting short cervix by transabdominal cervical length. The relationship between transabdominal and transvaginal cervical length was evaluated using a scatter plot. Results:A total of 562 cases were included in this study, comprising 33 cases of spontaneous preterm birth (7 cases occurring before 32 weeks) and 529 cases of term birth. (1) Compared to the term birth group, transabdominal cervical length (median: 37.6 vs 33.2 mm; Z=-3.838, P<0.001) and transvaginal cervical length (median: 34.0 vs 29.9 mm, Z=-3.030, P=0.002) in the spontaneous preterm birth group were significantly shorter. (2) The areas under the ROC curve for predicting spontaneous preterm birth by transabdominal and transvaginal cervical length were 0.699 (95% CI: 0.588-0.809) and 0.657 (95% CI: 0.540-0.774), respectively. The sensitivity, specificity and positive predictive value of transvaginal cervical length Conclusions:In singleton pregnancy women with low risk of preterm birth, transabdominal-transvaginal cervical length sequential screening can reduce unnecessary transvaginal ultrasounds by approximately 41% without missing the diagnosis of pregnant women with a short cervix. This method also enhances the effectiveness of transvaginal cervical length to spontaneous preterm birth.

Objective:To explore the prevalence of malnutrition among stroke survivors with bulbar palsy and the risk factors involved, and to construct a prediction model.Methods:This was a retrospective study of 325 stroke survivors. The nutritional status of those with and without bulbar palsy was compared. Univariate and multivariate logistic regressions were evaluated to highlight risk factors. A risk prediction model was constructed and a receiver operating characteristics (ROC) curve was drawn.Results:The prevalence of malnutrition among the stroke survivors with bulbar palsy was 66%, significantly greater than among all patients (52%). Among the stroke survivors with bulbar palsy there were significant differences between the normal nutrition group and the malnutrition group in terms of age, National Institutes of Health Stroke Scale (NIHSS) scores, hemoglobin, daily activities and pulmonary infection. The multivariate logistic regressions showed that pulmonary infection, a higher NIHSS score and lower hemoglobin were independent risk factors predicting malnutrition among stroke survivors with bulbar palsy. A risk prediction model for malnutrition was constructed based on the 3 major indicators and the area under the ROC curve was 0.86, with sensitivity of 0.79 and specificity of 0.83. A Hosmer-Lemeshow test indicated that the model was well calibrated, indicating that it would have good predictive value.Conclusions:Malnutrition is prevalent among stroke survivors with bulbar palsy. Pulmonary infection, a high NIHSS score and low hemoglobin are independent risk factors. They should be treated as important by medical staff.

Objective:To construct an artificial intelligence-assisted diagnosis system to recognize the characteristics of Helicobacter pylori ( HP) infection under endoscopy, and evaluate its performance in real clinical cases. Methods:A total of 1 033 cases who underwent 13C-urea breath test and gastroscopy in the Digestive Endoscopy Center of Renmin Hospital of Wuhan University from January 2020 to March 2021 were collected retrospectively. Patients with positive results of 13C-urea breath test (which were defined as HP infertion) were assigned to the case group ( n=485), and those with negative results to the control group ( n=548). Gastroscopic images of various mucosal features indicating HP positive and negative, as well as the gastroscopic images of HP positive and negative cases were randomly assigned to the training set, validation set and test set with at 8∶1∶1. An artificial intelligence-assisted diagnosis system for identifying HP infection was developed based on convolutional neural network (CNN) and long short-term memory network (LSTM). In the system, CNN can identify and extract mucosal features of endoscopic images of each patient, generate feature vectors, and then LSTM receives feature vectors to comprehensively judge HP infection status. The diagnostic performance of the system was evaluated by sensitivity, specificity, accuracy and area under receiver operating characteristic curve (AUC). Results:The diagnostic accuracy of this system for nodularity, atrophy, intestinal metaplasia, xanthoma, diffuse redness + spotty redness, mucosal swelling + enlarged fold + sticky mucus and HP negative features was 87.5% (14/16), 74.1% (83/112), 90.0% (45/50), 88.0% (22/25), 63.3% (38/60), 80.1% (238/297) and 85.7% (36 /42), respectively. The sensitivity, specificity, accuracy and AUC of the system for predicting HP infection was 89.6% (43/48), 61.8% (34/55), 74.8% (77/103), and 0.757, respectively. The diagnostic accuracy of the system was equivalent to that of endoscopist in diagnosing HP infection under white light (74.8% VS 72.1%, χ2=0.246, P=0.620). Conclusion:The system developed in this study shows noteworthy ability in evaluating HP status, and can be used to assist endoscopists to diagnose HP infection.

Objective:To assess the diagnostic efficacy of upper gastrointestinal endoscopic image assisted diagnosis system (ENDOANGEL-LD) based on artificial intelligence (AI) for detecting gastric lesions and neoplastic lesions under white light endoscopy.Methods:The diagnostic efficacy of ENDOANGEL-LD was tested using image testing dataset and video testing dataset, respectively. The image testing dataset included 300 images of gastric neoplastic lesions, 505 images of non-neoplastic lesions and 990 images of normal stomach of 191 patients in Renmin Hospital of Wuhan University from June 2019 to September 2019. Video testing dataset was from 83 videos (38 gastric neoplastic lesions and 45 non-neoplastic lesions) of 78 patients in Renmin Hospital of Wuhan University from November 2020 to April 2021. The accuracy, the sensitivity and the specificity of ENDOANGEL-LD for image testing dataset were calculated. The accuracy, the sensitivity and the specificity of ENDOANGEL-LD in video testing dataset for gastric neoplastic lesions were compared with those of four senior endoscopists.Results:In the image testing dataset, the accuracy, the sensitivity, the specificity of ENDOANGEL-LD for gastric lesions were 93.9% (1 685/1 795), 98.0% (789/805) and 90.5% (896/990) respectively; while the accuracy, the sensitivity and the specificity of ENDOANGEL-LD for gastric neoplastic lesions were 88.7% (714/805), 91.0% (273/300) and 87.3% (441/505) respectively. In the video testing dataset, the sensitivity [100.0% (38/38) VS 85.5% (130/152), χ2=6.220, P=0.013] of ENDOANGEL-LD was higher than that of four senior endoscopists. The accuracy [81.9% (68/83) VS 72.0% (239/332), χ2=3.408, P=0.065] and the specificity [ 66.7% (30/45) VS 60.6% (109/180), χ2=0.569, P=0.451] of ENDOANGEL-LD were comparable with those of four senior endoscopists. Conclusion:The ENDOANGEL-LD can accurately detect gastric lesions and further diagnose neoplastic lesions to help endoscopists in clinical work.

Objective:To construct a real-time artificial intelligence (AI)-assisted endoscepic diagnosis system based on YOLO v3 algorithm, and to evaluate its ability of detecting focal gastric lesions in gastroscopy.Methods:A total of 5 488 white light gastroscopic images (2 733 images with gastric focal lesions and 2 755 images without gastric focal lesions) from June to November 2019 and videos of 92 cases (288 168 clear stomach frames) from May to June 2020 at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University were retrospectively collected for AI System test. A total of 3 997 prospective consecutive patients undergoing gastroscopy at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University from July 6, 2020 to November 27, 2020 and May 6, 2021 to August 2, 2021 were enrolled to assess the clinical applicability of AI System. When AI System recognized an abnormal lesion, it marked the lesion with a blue box as a warning. The ability to identify focal gastric lesions and the frequency and causes of false positives and false negatives of AI System were statistically analyzed.Results:In the image test set, the accuracy, the sensitivity, the specificity, the positive predictive value and the negative predictive value of AI System were 92.3% (5 064/5 488), 95.0% (2 597/2 733), 89.5% (2 467/ 2 755), 90.0% (2 597/2 885) and 94.8% (2 467/2 603), respectively. In the video test set, the accuracy, the sensitivity, the specificity, the positive predictive value and the negative predictive value of AI System were 95.4% (274 792/288 168), 95.2% (109 727/115 287), 95.5% (165 065/172 881), 93.4% (109 727/117 543) and 96.7% (165 065/170 625), respectively. In clinical application, the detection rate of local gastric lesions by AI System was 93.0% (6 830/7 344). A total of 514 focal gastric lesions were missed by AI System. The main reasons were punctate erosions (48.8%, 251/514), diminutive xanthomas (22.8%, 117/514) and diminutive polyps (21.4%, 110/514). The mean number of false positives per gastroscopy was 2 (1, 4), most of which were due to normal mucosa folds (50.2%, 5 635/11 225), bubbles and mucus (35.0%, 3 928/11 225), and liquid deposited in the fundus (9.1%, 1 021/11 225).Conclusion:The application of AI System can increase the detection rate of focal gastric lesions.

OBJECTIVE To analyze the status quo ，influential factors of medication compliance and adverse drug reactions of home-based patients with severe mental disorders . METHODS Patients with severe mental disorders at home who were enrolled in the Shanghai mental health information management system in Jinshan district of Shanghai in Jan . 2022 were selected as the research objects . In combination with the relevant basic data registered in the information system and through face -to-face or telephone surveys by mental health doctors ，basic information ，medication compliance ，mental symptoms ，social function defects ， drug use information and adverse drug reactions of patients were understood . Univariate and multivariate Logistic regression analysis of medication compliance were performed . RESULTS Totally 2 684 questionnaires were distributed and 2 606 valid questionnaires were recovered ，with an effective recovery rate of 97.10%. The overall medication compliance of patients with severe mental disorders at home was 68.11%. The results of multivariate Logistic regression analysis showed that 51-60 years old ，unmarried， divorced or widowed ，partial social function defects ，no social function defects ， and use of third -generation antipsychotic drugs were the promotion factors of medication compliance ， （P＜0.05）；medical insurance ，non participation in work ，total number of hospitalizations of 1-4 times，total number of hospitalizations ≥ 5 times，general mental symptoms ，and use of second -generation antipsychotic drugs were the obstacles to medication compliance （P＜0.05）. The incidence of adverse drug reactions in patients with severe mental disorders a t home was 10.59%，mainly caused by second -generation antipsychotic drugs，and no new and serious adverse reactions were reported . CONCLUSIONS The medication compliance of patients with severe mental disorders at home is affected by many factors . It is urgent to need pharmacists ’participation to promote the standardization and rationality of patients ’medication.