AI pre-consultation services are the pioneering application in the medical process.In pre-consultation serv-ices,the core advantages of its application lie in more professional consultation knowledge,better understanding and communica-tion with patients,and more accurate diagnosis.Its typical application scenarios include remote initial consultation,pre-consulta-tion inquiries,intelligent triage and guidance,and intelligent accompanying consultation.Through the innovative application of AI pre-consultation services,the efficiency of diagnosis and treatment,diagnosis accuracy,and patient satisfaction can be signifi-cantly improved.However,issues such as data privacy security,technical accuracy and reliability,medical ethics,and personnel acceptance still need to be further addressed.

Objective Network pharmacology and molecular docking techniques were used to predict the potential mechanisms by which the active components of Piper nigrum(PN)regulate depressive-like behaviors in chronic restraint stress(CRS)mice.Methods The major chemical components and targets of PN were screened using the Traditional Chinese Medicine Systems Pharmacology database.Targets related to ferroptosis and depression were obtained from the Online Mendelian Inheritance in Man,GeneCards,and FerrDB databases.The intersecting targets were then subjected to Gene Ontology and Kyoto Encyclopedia of Genes and Gnomes(KEGG)pathway enrichment analyses,and molecular docking was performed to validate the binding capacities between the core targets and their corresponding active components.Finally,we established a CRS mouse model.Mice were treated with PN 75,150,and 300 mg/kg for 4 weeks,followed by behavioral assessments and reverse transcription-quantitative polymerase chain reaction(RT-qPCR)to verify the expression of core genes.Results Nine active components were screened from PN,corresponding to 27 targets,and 8377 targets related to depression and 547 targets associated with ferroptosis were screened from the databases.The intersection of these three sets resulted in 25 target genes.KEGG enrichment analysis revealed that these core targets were predominantly enriched in signaling pathways,including cholinergic synapses,serotonergic synapses,and neuroactive ligand-receptor interactions.Molecular docking result showed that the main active components of PN had strong binding affinities for the targets CHRM2,SLC6A4,PTGS2,and SLC6A2.Behavioral assessments demonstrated that PN significantly increased the sucrose preference index(P＜0.01,P＜0.001),reduced immobility time in the tail suspension and forced swimming tests(P＜0.01,P＜0.001),and enhanced exploratory behavior in the open field test(P＜0.05.P＜0.01,P＜0.001).PN significantly reduced the serum levels of inflammation markers(P＜0.05.P＜0.01,P＜0.001),as shown by enzyme-linked immunosorbent assay,and neurotransmitter analysis revealed that PN significantly increased the levels of serotonin and acetylcholine in the mouse hippocampus(P＜0.05).RT-qPCR showed that PN demonstrated the mRNA expression of SLC6A4(P＜0.05.P＜0.01,P＜0.001).Conclusions PN may improve depressive-like behavior in mice by modulating serotonin and acetylcholine levels,inhibiting inflammatory responses,participating in immune regulation,and exerting neuroprotective effects.

Objective Network pharmacology and molecular docking techniques were used to predict the potential mechanisms by which the active components of Piper nigrum(PN)regulate depressive-like behaviors in chronic restraint stress(CRS)mice.Methods The major chemical components and targets of PN were screened using the Traditional Chinese Medicine Systems Pharmacology database.Targets related to ferroptosis and depression were obtained from the Online Mendelian Inheritance in Man,GeneCards,and FerrDB databases.The intersecting targets were then subjected to Gene Ontology and Kyoto Encyclopedia of Genes and Gnomes(KEGG)pathway enrichment analyses,and molecular docking was performed to validate the binding capacities between the core targets and their corresponding active components.Finally,we established a CRS mouse model.Mice were treated with PN 75,150,and 300 mg/kg for 4 weeks,followed by behavioral assessments and reverse transcription-quantitative polymerase chain reaction(RT-qPCR)to verify the expression of core genes.Results Nine active components were screened from PN,corresponding to 27 targets,and 8377 targets related to depression and 547 targets associated with ferroptosis were screened from the databases.The intersection of these three sets resulted in 25 target genes.KEGG enrichment analysis revealed that these core targets were predominantly enriched in signaling pathways,including cholinergic synapses,serotonergic synapses,and neuroactive ligand-receptor interactions.Molecular docking result showed that the main active components of PN had strong binding affinities for the targets CHRM2,SLC6A4,PTGS2,and SLC6A2.Behavioral assessments demonstrated that PN significantly increased the sucrose preference index(P＜0.01,P＜0.001),reduced immobility time in the tail suspension and forced swimming tests(P＜0.01,P＜0.001),and enhanced exploratory behavior in the open field test(P＜0.05.P＜0.01,P＜0.001).PN significantly reduced the serum levels of inflammation markers(P＜0.05.P＜0.01,P＜0.001),as shown by enzyme-linked immunosorbent assay,and neurotransmitter analysis revealed that PN significantly increased the levels of serotonin and acetylcholine in the mouse hippocampus(P＜0.05).RT-qPCR showed that PN demonstrated the mRNA expression of SLC6A4(P＜0.05.P＜0.01,P＜0.001).Conclusions PN may improve depressive-like behavior in mice by modulating serotonin and acetylcholine levels,inhibiting inflammatory responses,participating in immune regulation,and exerting neuroprotective effects.

AI pre-consultation services are the pioneering application in the medical process.In pre-consultation serv-ices,the core advantages of its application lie in more professional consultation knowledge,better understanding and communica-tion with patients,and more accurate diagnosis.Its typical application scenarios include remote initial consultation,pre-consulta-tion inquiries,intelligent triage and guidance,and intelligent accompanying consultation.Through the innovative application of AI pre-consultation services,the efficiency of diagnosis and treatment,diagnosis accuracy,and patient satisfaction can be signifi-cantly improved.However,issues such as data privacy security,technical accuracy and reliability,medical ethics,and personnel acceptance still need to be further addressed.

Objective:To utilize a deep learning approach based on speech to distinguish between depressive and manic mood states in patients with bipolar disorder (BD).Methods:Sixty-one BD patients who visited the outpatient department of psychiatry at Peking University Sixth Hospital were recruited to participate in the study from June 2018 to March 2022. Quick Inventory of Depressive Symptomatology, Mood Disorder Questionnaire and Young Mania Rating Scale were used to determine patients′ mood states. The voices of the patients were recorded, including 190 samples during the patient′s remission, depressive, and manic mood period respectively. A total of 136 features were extracted from the voice samples, including Mel-frequency cepstral coefficients and zero-crossing rates using the speech analysis library in Python. A LIGHT-SERNET-based network was then used to train a model for emotion classification. Accuracy is used to evaluate the performance of the model, using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and receiver operating characteristic curve (ROC) to evaluate the predictive results of model for three mood states. Kruskal-Wallis H tests or χ 2 tests were conducted to compare the differences among the demographic information of three groups. Results:There were statistically significant differences among the three groups in age ( H=25.83, P<0.001), years of education ( H=25.25, P<0.001) and marital status (χ 2=23.81, P<0.001). There is no significant difference in gender (χ 2=4.63, P=0.099). The accuracy of the model in detecting the three emotional states was 0.84. The sensitivity and specificity in detecting remission were 0.88 and 0.93, respectively, and the positive predictive value and negative predictive value were 0.87 and 0.94, respectively. The sensitivity and specificity in detecting depressive episodes were 0.82 and 0.92, respectively, and the positive predictive value and negative predictive value were 0.84 and 0.92, respectively. The sensitivity and specificity in detecting manic episodes were 0.82 and 0.91, respectively, and the positive predictive value and negative predictive value were 0.83 and 0.91, respectively. The areas of the receiver operation characteristic curve for the three mood states were similar and all exceeded 0.90. Conclusion:The LIGHT-SERNET-based deep learning model shows good discrimination ability between depressive and manic mood states based on speech analysis.

Objective:To utilize a deep learning approach based on speech to distinguish between depressive and manic mood states in patients with bipolar disorder (BD).Methods:Sixty-one BD patients who visited the outpatient department of psychiatry at Peking University Sixth Hospital were recruited to participate in the study from June 2018 to March 2022. Quick Inventory of Depressive Symptomatology, Mood Disorder Questionnaire and Young Mania Rating Scale were used to determine patients′ mood states. The voices of the patients were recorded, including 190 samples during the patient′s remission, depressive, and manic mood period respectively. A total of 136 features were extracted from the voice samples, including Mel-frequency cepstral coefficients and zero-crossing rates using the speech analysis library in Python. A LIGHT-SERNET-based network was then used to train a model for emotion classification. Accuracy is used to evaluate the performance of the model, using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and receiver operating characteristic curve (ROC) to evaluate the predictive results of model for three mood states. Kruskal-Wallis H tests or χ 2 tests were conducted to compare the differences among the demographic information of three groups. Results:There were statistically significant differences among the three groups in age ( H=25.83, P<0.001), years of education ( H=25.25, P<0.001) and marital status (χ 2=23.81, P<0.001). There is no significant difference in gender (χ 2=4.63, P=0.099). The accuracy of the model in detecting the three emotional states was 0.84. The sensitivity and specificity in detecting remission were 0.88 and 0.93, respectively, and the positive predictive value and negative predictive value were 0.87 and 0.94, respectively. The sensitivity and specificity in detecting depressive episodes were 0.82 and 0.92, respectively, and the positive predictive value and negative predictive value were 0.84 and 0.92, respectively. The sensitivity and specificity in detecting manic episodes were 0.82 and 0.91, respectively, and the positive predictive value and negative predictive value were 0.83 and 0.91, respectively. The areas of the receiver operation characteristic curve for the three mood states were similar and all exceeded 0.90. Conclusion:The LIGHT-SERNET-based deep learning model shows good discrimination ability between depressive and manic mood states based on speech analysis.

Objective: To evaluate the effect of levonorgestrel-releasing intrauterine system (LNG-IUS) plus oral megestrol acetate (MA) as fertility-preserving treatment in patients with early-stage endometrial cancer (EEC). Methods: In this single-center, phase II study with open-label, randomized and controlled design, young patients (18–45 years) diagnosed with primary EEC were screened, who strongly required fertility-preserving treatment. Patients were randomly assigned (1:1) into MA group (160 mg oral daily) or MA (160 mg oral daily) plus LNG-IUS group. Pathologic evaluation on endometrium retrieved by hysteroscopy was performed every 3 months. The primary endpoint was complete response (CR) rate within 16 weeks of treatment. The secondary endpoints were CR rate within 32 weeks of treatment, adverse events, recurrent and pregnancy rate. Results: Between July 2017 and June 2020, 63 patients were enrolled and randomly assigned. Totally 56 patients (26 in MA group; 28 in MA + LNG-IUS group) were included into primary-endpoint analyses. The median follow-up was 31.6 months (range, 3.1–94.0). No significant difference in 16-week CR rate were found between MA and MA + LNG-IUS groups (19.2% vs. 25.0%, p=0.610; odds ratio=1.40; 95% confidence interval=0.38–5.12), while the 32-week CR rates were also similar (57.1% and 61.5%, p=0.743), accordingly. More women in MA + LNG-IUS group experienced vaginal hemorrhage (46.4% vs. 16.1%; p=0.012) compared with MA group. No intergroup difference was found regarding recurrence or pregnancy rate. Conclusion Compared with MA alone, the addition of LNG-IUS may not improve the early CR rate for EEC, and may produce more adverse events instead.

Objective:To clarify the effect and related factors of antiviral therapy on the change of esophageal varices in patients with hepatitis B virus-related cirrhosis.Methods:Fifty-two cases with hepatitis B virus-related cirrhosis who underwent endoscopy before and after antiviral therapy were selected from prospective cohorts. Patients were divided into three groups: no, mild, and moderate-severe based on the degree of esophageal varices. The changes in the severity of esophageal varices in each group were compared after antiviral therapy. Clinical characteristics (platelet, liver and kidney function, liver stiffness, and virological response) of patients with different regressions were analyzed. Measurement data were analyzed by independent sample t-test, one-way ANOVA, Mann-Whitney U test and Kruskal-Wallis H test, and Chi-Square test was used for count data.Results:All patients received entecavir-based antiviral therapy. The median treatment time was 3.1 (2.5-4.4) years. The proportion of patients without esophageal varices increased from 30.8% to 51.9%, the proportion of mild esophageal varices decreased from 40.4% to 30.8%, and the proportion of patients with moderate-to-severe esophageal varices decreased from 28.8% to 17.3% ( χ2=14.067, P=0.001). A total of 40.4% of patients had esophageal varices regression, and 13.5% had esophageal varices progression. The progression rate was significantly higher in patients with moderate-severe esophageal varices than patients with mild and no esophageal varices ( χ2=28.126, P<0.001), and 60.0% of patients with moderate-severe esophageal varices still remained in moderate-severe state after antiviral treatment. Baseline platelet count and 5-year mean change rates were significantly lower in patients with progressive moderate-to-severe esophageal varices than in those without progression (+3.3% vs. +34.1%, Z=7.00, P=0.027). Conclusion:After effective antiviral treatment, 40.4% of patients with hepatitis B virus-related cirrhosis combined with esophageal varices has obtained esophageal varices regression, but those with moderate to severe esophageal varices still have a considerable risk of progression while receiving mono antiviral treatment only. Thrombocytopenia and without significant improving are the clinical signs of progression risk after receiving antiviral treatment.

School-age children are in a specific development stage corresponding to juvenility, when the white matter of the brain experiences ongoing maturation. Diffusion-weighted magnetic resonance imaging (DWI), especially diffusion tensor imaging (DTI), is extensively used to characterize the maturation by assessing white matter properties in vivo. In the analysis of DWI data, spatial normalization is crucial for conducting inter-subject analyses or linking the individual space with the reference space. Using tensor-based registration with an appropriate diffusion tensor template presents high accuracy regarding spatial normalization. However, there is a lack of a standardized diffusion tensor template dedicated to school-age children with ongoing brain development. Here, we established the school-age children diffusion tensor (SACT) template by optimizing tensor reorientation on high-quality DTI data from a large sample of cognitively normal participants aged 6-12 years. With an age-balanced design, the SACT template represented the entire age range well by showing high similarity to the age-specific templates. Compared with the tensor template of adults, the SACT template revealed significantly higher spatial normalization accuracy and inter-subject coherence upon evaluation of subjects in two different datasets of school-age children. A practical application regarding the age associations with the normalized DTI-derived data was conducted to further compare the SACT template and the adult template. Although similar spatial patterns were found, the SACT template showed significant effects on the distributions of the statistical results, which may be related to the performance of spatial normalization. Looking forward, the SACT template could contribute to future studies of white matter development in both healthy and clinical populations. The SACT template is publicly available now ( https://figshare.com/articles/dataset/SACT_template/14071283 ).

Acidosis, regardless of hypoxia involvement, is recognized as a chronic and harsh tumor microenvironment (TME) that educates malignant cells to thrive and metastasize. Although overwhelming evidence supports an acidic environment as a driver or ubiquitous hallmark of cancer progression, the unrevealed core mechanisms underlying the direct effect of acidification on tumorigenesis have hindered the discovery of novel therapeutic targets and clinical therapy. Here, chemical-induced and transgenic mouse models for colon, liver and lung cancer were established, respectively. miR-7 and TGF-β2 expressions were examined in clinical tissues (n = 184). RNA-seq, miRNA-seq, proteomics, biosynthesis analyses and functional studies were performed to validate the mechanisms involved in the acidic TME-induced lung cancer metastasis. Our data show that lung cancer is sensitive to the increased acidification of TME, and acidic TME-induced lung cancer metastasis via inhibition of miR-7-5p. TGF-β2 is a direct target of miR-7-5p. The reduced expression of miR-7-5p subsequently increases the expression of TGF-β2 which enhances the metastatic potential of the lung cancer. Indeed, overexpression of miR-7-5p reduces the acidic pH-enhanced lung cancer metastasis. Furthermore, the human lung tumor samples also show a reduced miR-7-5p expression but an elevated level of activated TGF-β2; the expressions of both miR-7-5p and TGF-β2 are correlated with patients' survival. We are the first to identify the role of the miR-7/TGF-β2 axis in acidic pH-enhanced lung cancer metastasis. Our study not only delineates how acidification directly affects tumorigenesis, but also suggests miR-7 is a novel reliable biomarker for acidic TME and a novel therapeutic target for non-small cell lung cancer (NSCLC) treatment. Our study opens an avenue to explore the pH-sensitive subcellular components as novel therapeutic targets for cancer treatment.