Objective To construct machine learning models that can be used to predict AUC fold change(FC)using a database of existing pharmacokinetic(PK)and drug-drug interaction(DDI)information,which can be used to explore the possibility of predicting existing drug interactions and to provide certain rational recommendations for clinical drug use.Methods PK data of DDIs and AUC fold change data were extracted from FDA-approved drug labels.Peptide and pharmacodynamic(PD)information related to drug interactions were retrieved through DrugBank,and PPDT identification of relevant peptide IDs was performed using Protein Resource(UniProt),and a matrix normalization code was used to generate multidimensional vector data that were easy to analysis.The effect of PPDT on the AUC,and the resulting multiplicity change was used as the dependent variable for machine learning model construction.The model with the smallest root mean square error(RMES)value was used for model construction to train a bagged decision tree(Bagged)prediction model.The models were tested using the trained models for some of the drug tests.The models were evaluated by reviewing the available literature findings on detection of drug interaction pairs and analyzing and comparing the predicted values.Results A total of 16 pairs of model drug pairs were tested for the effects of 16 drugs on tacrolimus,and it was found that the accuracy of the prediction of the presence or absence of drug interactions was 81.25％;the prediction results were classified according to the FDA standard classification of the strong and weak for the strength of drug interactions,and the results showed that the prediction of the strength of drug interactions,with a large deviation from the larger prediction was less.Conclusion The evaluation of the model to predict the presence or absence of drug interactions was general;however,after classifying the strengths and weaknesses of drug interactions,the prediction of drug interactions was better,and the prediction results indicated that the model prediction performance has a certain reference value for potential DDI assessment before clinical trials.

Objective To investigate the attributable risk(AR)of Acinetobacter baumannii(AB)infection in criti-cally ill patients.Methods A multicenter retrospective cohort study was conducted among adult patients in inten-sive care unit(ICU).Patients with AB isolated from sterile body fluid and confirmed with AB infection in each cen-ter were selected as the infected group.According to the matching criteria that patients should be from the same pe-riod,in the same ICU,as well as with similar APACHE Ⅱ score(±5 points)and primary diagnosis,patients who did not infect with AB were selected as the non-infected group in a 1:2 ratio.The AR was calculated.Results The in-hospital mortality of patients with AB infection in sterile body fluid was 33.3％,and that of non-infected group was 23.1％,with no statistically significant difference between the two groups(P=0.069).The AR was 10.2％(95％CI:-2.3％-22.8％).There is no statistically significant difference in mortality between non-infected pa-tients and infected patients from whose blood,cerebrospinal fluid and other specimen sources AB were isolated(P＞0.05).After infected with AB,critically ill patients with the major diagnosis of pulmonary infection had the high-est AR.There was no statistically significant difference in mortality between patients in the infected and non-infec-ted groups(P＞0.05),or between other diagnostic classifications.Conclusion The prognosis of AB infection in critically ill patients is highly overestimated,but active healthcare-associated infection control for AB in the ICU should still be carried out.

Objective:To automatically classify hypertensive heart disease (HHD) and hypertrophic cardiomyopathy (HCM) based on mul-titask learning algorithm using native T1 mapping images.Methods:A total of 203 patients admitted to Ren Ji Hospital, School of Medicine, Shanghai Jiao Tong University from January 2017 to December 2021 were enrolled, including 53 patients with HHD, 121 patients with HCM, and 29 patients with normal control (NC). Native T1 mapping images of all enrolled patients were acquired using MRI and processed by a multi-task learning algorithm. The classification performance of each model was validated using ten-fold crossover, confusion matrix, and receiver operator characteristic (ROC) curves. The Resnet 50 model based on the original images was established as a control.Results:The ten-fold crossover validation results showed that the MTL-1 024, MTL-64, and MTL-all models showed better performance in terms of area under the curve (AUC), accuracy, sensitivity, and specificity compared to the Resnet 50 model. In the classification task, the MTL-64 model showed the best performance in terms of AUC (0.942 1), while the MTL-all model reached the highest value in terms of accuracy (0.852 2). In the segmentation task, the MTL-64 model achieved the best results with the Dice coefficient (0.879 7). The confusion matrix plot showed that the MTL model outperforms the Resnet 50 model based on the original image in terms of overall performance. The ROC graphs of all MTL models were significantly higher than the original image input Resnet 50 model.Conclusions:Multi-task learning-based native T1 mapping images are effective for automatic classification of HHD and HCM.

Objective:To observe the genetic variation of SH2B3 in patients with myeloid neoplasms.Methods:The results of targeted DNA sequencing associated with myeloid neoplasms in the Department of Hematology,Xuanwu Hospital,Capital Medical University from November 2017 to November 2022 were retrospectively analyzed,and the patients with SH2B3 gene mutations were identified.The demographic and clinical data of these patients were collected,and characteristics of SH2B3 gene mutation,co-mutated genes and their correlations with diseases were analyzed.Results:The sequencing results were obtained from 1 005 patients,in which 19 patients were detected with SH2B3 gene mutation,including 18 missense mutations(94.74％),1 nonsense mutation(5.26％),and 10 patients with co-mutated genes(52.63％).Variant allele frequency(VAF)ranged from 0.03 to 0.66.The highest frequency mutation was p.Ile568Thr(5/19,26.32％),with an average VAF of 0.49,involving 1 case of MDS/MPN-RS(with SF3B1 mutation),1 case of MDS-U(with SF3B1 mutation),1 case of aplastic anemia with PNH clone(with PIGA and KMT2A mutations),2 cases of MDS-MLD(1 case with SETBP1 mutation).The other mutations included p.Ala567Thr in 2 cases(10.53％),p.Arg566Trp,p.Glu533Lys,p.Met437Arg,p.Arg425Cys,p.Glu314Lys,p.Arg308*,p.Gln294Glu,p.Arg282Gln,p.Arg175Gln,p.Gly86Cys,p.His55Asn and p.Gln54Pro in 1 case each.Conclusion:A wide distribution of genetic mutation sites and low recurrence of SH2B3 is observed in myeloid neoplasms,among of them,p.Ile568Thr mutation is detected with a higher incidence and often coexists with characteristic mutations of other diseases.

Objective:To investigate the value of nomogram based on radiomics features of CT enterography (CTE) combined with clinical characteristics to predict secondary loss of response (SLOR) after infliximab (IFX) treatment in patients with Crohn′s disease (CD).Methods:This study was a case-control study. Clinical and imaging data of 155 patients with CD diagnosed at the First Affiliated Hospital of Anhui Medical University from March 2015 to July 2022 were retrospectively collected. The patients were divided into a training set ( n=108) and a testing set ( n=47) in the ratio of 7∶3 by stratified sampling method. All patients were treated according to the standardized protocol and were classified as SLOR (43 in the training set and 18 in the testing set) and non-SLOR (65 in the training set and 29 in the testing set) according to treatment outcome. Based on the data from the training group, independent clinical predictors of SLOR after IFX treatment were screened in the clinical data using univariate and multivariate logistic regression analysis to establish a clinical model. Intestinal phase images were selected to be outlined layer by layer along the margin of the lesion to obtain the volume of the region of interest to extract the radiomics features. The radiomics features were screened using univariate analysis and the minimum absolute shrinkage and selection operator to establish the radiomics model. Multivariate logistic regression analysis was used to build a combined clinical-radiomics model based on the screened clinical independent predictors and radiomics characters, then a nomogram was drawn. The predictive efficacy of the 3 models for SLOR after IFX treatment was assessed by receiver operating characteristic curves, and the area under the curve (AUC) was calculated. The decision curve analysis was applied to evaluate the clinical utility of the models. Results:Disease duration ( OR=1.983, 95% CI 1.966-2.000, P=0.046) and intestinal stenosis ( OR=1.246, 95% CI 1.079-1.764, P=0.015) were identified as the independent predictors of SLOR in the clinical data, and a clinical model was established. Totally 9 radiomics features were included in the radiomics model. The AUCs of clinical, radiomics, and combined models for predicting SLOR after IFX treatment in CD patients were 0.691 (95% CI 0.591-0.792), 0.896 (95% CI 0.836-0.955), and 0.910 (95% CI 0.855-0.965) in the training set, and 0.722 (95% CI 0.574-0.871), 0.866 (95% CI 0.764-0.968), and 0.889 (95% CI 0.796-0.982) in the testing set. Decision curve analysis in the testing set showed higher net clinical benefits for both the radiomics model and combined model than the clinical model, and combined model had higher net clinical benefits than the radiomics model over most threshold probability intervals. Conclusions:CTE-based radiomics model can effectively predict SLOR after IFX treatment in patients with CD, and a combined model by incorporating clinical characteristics of disease duration and intestinal stenosis can further improve the predictive efficacy.

Objectives: This study aimed to present the Asia-Pacific consensus on long-term and sequential therapy for osteoporosis, offering evidence-based recommendations for the effective management of this chronic condition.The primary focus is on achieving optimal fracture prevention through a comprehensive, individualized approach. Methods: A panel of experts convened to develop consensus statements by synthesizing the current literature and leveraging clinical expertise. The review encompassed long-term anti-osteoporosis medication goals, first-line treatments for individuals at very high fracture risk, and the strategic integration of anabolic and anti resorptive agents in sequential therapy approaches. Results: The panelists reached a consensus on 12 statements. Key recommendations included advocating for anabolic agents as the first-line treatment for individuals at very high fracture risk and transitioning to anti resorptive agents following the completion of anabolic therapy. Anabolic therapy remains an option for in dividuals experiencing new fractures or persistent high fracture risk despite antiresorptive treatment. In cases of inadequate response, the consensus recommended considering a switch to more potent medications. The consensus also addressed the management of medication-related complications, proposing alternatives instead of discontinuation of treatment. Conclusions This consensus provides a comprehensive, cost-effective strategy for fracture prevention with an emphasis on shared decision-making and the incorporation of country-specific case management systems, such as fracture liaison services. It serves as a valuable guide for healthcare professionals in the Asia-Pacific region, contributing to the ongoing evolution of osteoporosis management.

OBJECTIVE: To retrospectively analyze the clinical efficacy of anterior cruciate ligament (ACL) reconstruction combined with anterolateral complex repair and ACL reconstruction combined with ALL reconstruction in the treatment of anterior cruciate ligament injuries with high-grade pivot shift. METHODS: From January 2018 to June 2022, 49 patients combined ACL and ALL injuries with high-grade pivot shift were retrospectively studied from three hospitals, 29 of them underwent ACL reconstruction with anterolateral complex repair (repair group), including 23 males and 6 females with an average age of (27.5±4.8) years old, ranged from 20 to 37 years old;the injured sides were 13 on the left and 16 on the right, and 11 patients were suffered with meniscus injury. The other 20 patients underwent ACL and ALL reconstruction (reconstruction group) including 17 males and 3 females with the mean age of (27.1±4.5) years old, ranged from 20 to 38 years old;the injured sides were 8 on the left and 12 on the right, and 6 patients were suffered with meniscus injury. Knee stability (pivot shift test, KT-2000), range of motion, knee function (Lysholm scoring scale, Cincinnati sports activity scale (CSAS) scoring scale, and Tegner activity level score between two groups were compared. RESULTS: A total of 49 patients were followed up, the repair group receiving 13 to 20(15.3±1.8) months and the reconstruction group receiving 12 to 21(16.0±2.2) months. There was no statistically significant difference in the preoperative pivot shift test grading distribution between two groups (P>0.05). At the last postoperative follow-up, there were 24 patients with grade 0 and 5 patients with grade 1 in the repair group, and there were 18 patients with grade 0 and 2 patients with grade 1 in the reconstruction group, there is no significant difference in the distribution of axial shift test grading between two groups(P>0.05). The preoperative KT-2000 tibial displacement of two groups were (9.39±0.77) mm (repair group) and (9.14±0.78) mm (reconstruction group) respectively, with no statistically significant difference (P>0.05). At the final postoperative follow-up, there were 24 patients with KT-2000 tibial displacement <3 mm and 5 patients with 3 to 5 mm in the repair group, while 18 patients with <3 mm and 2 patients with 3 to 5 mm in the reconstruction group, KT-2000 tibial displacement distribution of two groups was no significant difference (P>0.05), but the KT-2000 tibial displacement in the reconstruction group (1.30±0.86) mm was significantly smaller than that in the repair group (1.99±1.11) mm (P<0.05). The final postoperative follow-up range of motion of the contralateral side knee between two groups was no significant difference (P>0.05). The range of motion of the suffering knee in the repair group was less than that in the reconstruction group (P<0.05). There was no significant difference in preoperative Lysholm and CSAS scores between two groups (P>0.05). At the final postoperative follow-up, both groups showed significant improvement in Lysholm and CSAS scores, while the Lysholm and CSAS scores of the reconstruction group were better than those of the repair group, and the difference was statistically significant (P<0.05). Significant differences was found in Tegner scores between two groups, which 16 patients in the repair group returned to their pre-injury activity level, and 17 patients in the reconstruction group returned to their pre-injury level (P<0.05). CONCLUSION Compared to anterolateral complex repair, combined ACL and ALL reconstruction in the treatment of ACL injuries with high-grade pivot shift results in better knee joint function and stability. This is advantageous in reducing the risk of ACL reconstruction failure.
Humans ; Male ; Female ; Adult ; Anterior Cruciate Ligament Reconstruction/methods* ; Anterior Cruciate Ligament Injuries/surgery* ; Young Adult ; Retrospective Studies ; Anterior Cruciate Ligament/surgery* ; Range of Motion, Articular

The structures and activities of enzymes are influenced by pH of the environment. Understanding and distinguishing the adaptation mechanisms of enzymes to extreme pH values is of great significance for elucidating the molecular mechanisms and promoting the industrial applications of enzymes. In this study, the ESM-2 protein language model was used to encode the secreted microbial proteins with the optimal performance above pH 9 and below pH 5, which yielded 47 725 high-pH protein sequences and 66 079 low-pH protein sequences, respectively. A deep learning model was constructed to identify protein acid-base tolerance based on amino acid sequences. The model showcased significantly higher accuracy than other methods, with the overall accuracy of 94.8%, precision of 91.8%, and a recall rate of 93.4% on the test set. Furthermore, we built a website (https://enzymepred.biodesign.ac.cn), which enabled users to predict the acid-base tolerance by submitting the protein sequences of enzymes. This study has accelerated the application of enzymes in various fields, including biotechnology, pharmaceuticals, and chemicals. It provides a powerful tool for the rapid screening and optimization of industrial enzymes.
Deep Learning ; Hydrogen-Ion Concentration ; Amino Acid Sequence ; Enzymes/metabolism* ; Sequence Analysis, Protein ; Proteins/metabolism* ; Bacterial Proteins/metabolism*

Objective: To investigate the species, concentration and seasonal trends of main airborne allergenic pollen in 4 districts and 5 counties of Hohhot City. Methods: The Department of allergy, Beijing Shijitan Hospital Affiliated to Capital Medical University conducted a cross-sectional study about monitoring the airborne allergenic pollen from August 1, 2021 to July 31, 2022 by the gravitational method in 4 districts and 5 counties of Hohhot City, which include Yuquan District, Xincheng District, Huimin District, Saihan District, Tuoketuo County, Helingeer County, Tumotezuoqi County, Wuchuan County and Qingshuihe County. Daily pollens were counted and identified by optical microscopy, and the data were analyzed. Results: The airborne allergenic pollen was collected every month all year round in 4 districts and 5 counties of Hohhot city. Through the whole year of the total quantity of pollens ranged from 24 850 to 50 154 grains per 1 000 mm² and two peaks of pollen concentration in air were observed,which happened in spring (from March to May) and in summer and autumn (from July to September). In spring, the main pollens were tree pollens, which principally distributed in Populus pollen (18.29%), Ulmus pollen (8.36%), Pinus pollen (6.20%), Cupressaceae pollen (5.23%), Betulaceae pollen (2.73%), Salix pollen (1.80%) and Quercus pollen (1.16%). In summer and autumn, the main pollens were weed pollens, which mainly included Artemisia pollen (42.73%), Chenopodiaceae pollen or Amaranthaceae pollen (7.46%), Poaceae pollen (2.26%), Humulus pollen or Cannabis pollen (0.60%). Conclusion: There were two peaks of main airborne allergenic pollen in 4 districts and 5 counties of Hohhot City. In the spring peak of pollen, the main airborne pollens were tree pollens. In the summer and autumn peak of pollen, the main airborne pollens were weed pollens. The Artemisia pollen was the most major airborne pollen in this area.
Humans ; Cross-Sectional Studies ; Pollen ; Hospitals

Objective: To investigate the species, concentration and seasonal trends of main airborne allergenic pollen in 4 districts and 5 counties of Hohhot City. Methods: The Department of allergy, Beijing Shijitan Hospital Affiliated to Capital Medical University conducted a cross-sectional study about monitoring the airborne allergenic pollen from August 1, 2021 to July 31, 2022 by the gravitational method in 4 districts and 5 counties of Hohhot City, which include Yuquan District, Xincheng District, Huimin District, Saihan District, Tuoketuo County, Helingeer County, Tumotezuoqi County, Wuchuan County and Qingshuihe County. Daily pollens were counted and identified by optical microscopy, and the data were analyzed. Results: The airborne allergenic pollen was collected every month all year round in 4 districts and 5 counties of Hohhot city. Through the whole year of the total quantity of pollens ranged from 24 850 to 50 154 grains per 1 000 mm² and two peaks of pollen concentration in air were observed,which happened in spring (from March to May) and in summer and autumn (from July to September). In spring, the main pollens were tree pollens, which principally distributed in Populus pollen (18.29%), Ulmus pollen (8.36%), Pinus pollen (6.20%), Cupressaceae pollen (5.23%), Betulaceae pollen (2.73%), Salix pollen (1.80%) and Quercus pollen (1.16%). In summer and autumn, the main pollens were weed pollens, which mainly included Artemisia pollen (42.73%), Chenopodiaceae pollen or Amaranthaceae pollen (7.46%), Poaceae pollen (2.26%), Humulus pollen or Cannabis pollen (0.60%). Conclusion: There were two peaks of main airborne allergenic pollen in 4 districts and 5 counties of Hohhot City. In the spring peak of pollen, the main airborne pollens were tree pollens. In the summer and autumn peak of pollen, the main airborne pollens were weed pollens. The Artemisia pollen was the most major airborne pollen in this area.
Humans ; Cross-Sectional Studies ; Pollen ; Hospitals