Objective:To develop an ultrasound multi-view fusion recognition model and evaluate its clinical value in diagnosing fetal conotruncal defects (CTD).Methods:This prospective study collected cardiac ultrasound images from fetuses at 20-32 weeks of gestation undergoing prenatal ultrasound at Dongguan Maternal and Child Health Hospital between September 2022 and May 2024. The case group comprised fetuses diagnosed with CTD, while controls with normal cardiac structures were collected at a 1∶2 ratio. Both groups were divided into modeling training and validation sets at a 3∶1 ratio. One optimal standard image each from the four-chamber view, left ventricular outflow tract view, right ventricular outflow tract view, and three vessels and trachea view was included per fetus. A deep learning-based multi-view fusion recognition model was developed to differentiate normal conotruncal anatomy from CTD. Model performance was validated against post-abortion pathology or postnatal echocardiography results. SAS software was used for statistical analysis to calculate the sensitivity and specificity of three fusion models (based on positivity in any two, three, or four views, and were designated as Fusion Model 1, Fusion Model 2, and Fusion Model 3, respectively), with the optimal model determined by the maximum Youden index. Senior, intermediate, and junior prenatal sonologists independently diagnosed cases in the validation set under blinding conditions. Their diagnostic results were compared with those of the optimal model. Paired Chi-square test (Cochran's Q test) was employed to compare the differences between the diagnostic accuracy rates of sonologists at different experience levels and the sensitivity of the optimal model, thereby analyzing the auxiliary diagnostic value of the multi-view fusion recognition model. Results:The study included 88 CTD cases, excluding six cases (non-CTD diagnosed by post-abortion pathology or postnatal echocardiography or poor image quality), divided into 60 training and 22 validation cases (12 tetralogy of Fallot, four double outlet right ventricle, three transposition of great arteries, three persistent truncus arteriosus). The control group included 176 cases, excluding 15 cases (other cardiac abnormalities confirmed postnatally or poor image quality after re-evaluation), divided into 120 training and 41 validation cases. The sensitivities of Fusion Model 1, Fusion Model 2, and Fusion Mudel 3 were 0.86, 0.64, and 0.27, while their specificities were 0.76, 0.95, and 1.00, respectively. Fusion Model 1 demonstrated the highest Youden index (0.62) and was selected as optimal. Its diagnostic sensitivity showed no significant difference from senior sonologists [86% vs. 91% (20/22), Bonferroni-corrected P>0.999], but was significantly higher than intermediate [55% (12/22), Bonferroni-corrected P=0.049] and junior sonologists [32% (7/22), Bonferroni-corrected P=0.003]. Conclusion:The deep learning multi-view fusion model achieved diagnostic performance comparable to senior sonologists, demonstrating potential value in assisting CTD diagnosis, training less experienced sonologists, and supporting research and education.

Metabolomics covers a wide range of applications in life sciences, biomedicine, and phytology. Data acquisition (to achieve high coverage and efficiency) and analysis (to pursue good classification) are two key segments involved in metabolomics workflows. Various chemometric approaches utilizing either pattern recognition or machine learning have been employed to separate different groups. However, insufficient feature extraction, inappropriate feature selection, overfitting, or underfitting lead to an insufficient capacity to discriminate plants that are often easily confused. Using two ginseng varieties, namely Panax japonicus (PJ) and Panax japonicus var. major (PJvm), containing the similar ginsenosides, we integrated pseudo-targeted metabolomics and deep neural network (DNN) modeling to achieve accurate species differentiation. A pseudo-targeted metabolomics approach was optimized through data acquisition mode, ion pairs generation, comparison between multiple reaction monitoring (MRM) and scheduled MRM (sMRM), and chromatographic elution gradient. In total, 1980 ion pairs were monitored within 23 min, allowing for the most comprehensive ginseng metabolome analysis. The established DNN model demonstrated excellent classification performance (in terms of accuracy, precision, recall, F1 score, area under the curve, and receiver operating characteristic (ROC)) using the entire metabolome data and feature-selection dataset, exhibiting superior advantages over random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and multilayer perceptron (MLP). Moreover, DNNs were advantageous for automated feature learning, nonlinear modeling, adaptability, and generalization. This study confirmed practicality of the established strategy for efficient metabolomics data analysis and reliable classification performance even when using small-volume samples. This established approach holds promise for plant metabolomics and is not limited to ginseng.

Metabolomics covers a wide range of applications in life sciences,biomedicine,and phytology.Data acquisition(to achieve high coverage and efficiency)and analysis(to pursue good classification)are two key segments involved in metabolomics workflows.Various chemometric approaches utilizing either pattern recognition or machine learning have been employed to separate different groups.However,insufficient feature extraction,inappropriate feature selection,overfitting,or underfitting lead to an insufficient capacity to discriminate plants that are often easily confused.Using two ginseng varieties,namely Panax japonicus(PJ)and Panax japonicus var.major(PJvm),containing the similar ginsenosides,we integrated pseudo-targeted metabolomics and deep neural network(DNN)modeling to achieve accurate species differentiation.A pseudo-targeted metabolomics approach was optimized through data acquisition mode,ion pairs generation,comparison between multiple reaction monitoring(MRM)and scheduled MRM(sMRM),and chromatographic elution gradient.In total,1980 ion pairs were monitored within 23 min,allowing for the most comprehensive ginseng metabolome analysis.The established DNN model demonstrated excellent classification performance(in terms of accuracy,precision,recall,F1 score,area under the curve,and receiver operating characteristic(ROC))using the entire metabolome data and feature-selection dataset,exhibiting superior advantages over random forest(RF),support vector ma-chine(SVM),extreme gradient boosting(XGBoost),and multilayer perceptron(MLP).Moreover,DNNs were advantageous for automated feature learning,nonlinear modeling,adaptability,and generalization.This study confirmed practicality of the established strategy for efficient metabolomics data analysis and reliable classification performance even when using small-volume samples.This established approach holds promise for plant metabolomics and is not limited to ginseng.

Objective:To investigate the relationship between sarcopenic obesity(SO), defined by various obesity indicators, and mortality risk in older adults based on a prospective cohort from multiple nursing homes.Methods:Sarcopenia was diagnosed according to the 2019 consensus of the Asian Working Group for Sarcopenia.Obesity was defined using six different indicators: waist circumference(WC), waist-hip ratio(WHR), waist-height ratio(WHTR), body mass index(BMI), visceral fat area(VFA), and percentage of body fat(PBF).A prospective cohort of adults aged 60 and above was established across 15 nursing homes in Zigong City, with annual follow-ups on survival status conducted over two consecutive years.Cox proportional hazards regression models were employed to analyze the association between SO, defined by different obesity indicators, and mortality risk, calculating hazard ratios( HR)and their 95% confidence intervals( CI). Results:A total of 695 older adults were included in the study, of whom 67.1% were male.During the 2-year follow-up period, 88 participants died.The prevalence of SO as defined by WC, WHR, WHTR, BMI, VFA, PBF was found to be 17.6%, 30.1%, 48.9%, 3.0%, 28.3%, and 58.7%, respectively.When SO was defined using WC, WHR, WHTR, BMI, and VFA, there was no statistically significant difference in mortality rates between the SO and non-SO groups.However, when defined by PBF, the SO group exhibited a significantly higher mortality rate compared to the non-SO group(16.9% vs.6.6%, P<0.01).Cox proportional hazards regression analysis revealed that, compared to the non-SO group, the SO group defined by PBF had a significantly increased mortality risk( HR=2.81, 95% CI: 1.67-4.73, P<0.001).After adjusting for potential confounding factors, the mortality risk for the SO group remained significantly higher than that of the non-SO group( HR=1.97, 95% CI: 1.14-3.38, P=0.015). Conclusions:The prevalence of SO varies significantly across different obesity indicators.SO defined by PBF is significantly associated with mortality risk in nursing home residents.This study provides new evidence for further optimizing the diagnostic criteria for SO in this population.

Objective:To compare the efficacy and safety of crisaborole ointment 2% versus pimecrolimus cream 1% in the treatment of mild to moderate atopic dermatitis in children aged 2 years or older.Methods:A multicenter, randomized, open-label, controlled clinical trial was conducted. A total of 120 pediatric patients aged 2 - 17 years with mild to moderate atopic dermatitis were enrolled from departments of dermatology of 8 hospitals in China between March 2022 and February 2023. The participants were randomly assigned in a 1∶1 ratio to the crisaborole group and the pimecrolimus group, and received the treatment with crisaborole ointment 2% and pimecrolimus cream 1% respectively, twice a day for 4 weeks. Visits were scheduled at baseline/on day 1, as well as on days 8, 15, and 29. The primary efficacy outcome was the percentage of patients achieving the Investigator's Static Global Assessment (ISGA) success (defined as clear [0] or almost clear [1] on the ISGA scale, combined with ≥ 2‐grade improvement from baseline) on day 29. The secondary efficacy outcomes included changes in the Eczema Area and Severity Index (EASI) total scores from baseline to day 29, percentages of patients achieving ISGA improvement (defined as clear [0] or almost clear [1] on the ISGA scale), as well as changes in the Peak Pruritus Numerical Rating Scale (NRS) scores, Dermatology Life Quality Index (DLQI) /Infants' Dermatology Life Quality Index (IDLQI) /Children's Dermatology Life Quality Index (CDLQI) scores, and in the Dermatitis Family Impact (DFI) scores. Drug safety was evaluated according to the incidence of adverse events. Categorical data were compared using the chi-square test. Since measurement data did not follow a normal distribution, the rank sum test was used for comparisons of measurement data between groups.Results:A total of 106 children with mild to moderate atopic dermatitis were included in the per-protocol analysis set, with 52 in the crisaborole group (26 males and 26 females) and 54 in the pimecrolimus group (27 males and 27 females). There were no significant differences in age, disease duration, ISGA and EASI scores at baseline between the two groups (all P > 0.05). On day 29, 22 patients (42.31%) in the crisaborole group and 25 (46.30%) in the pimecrolimus group achieved ISGA success, with no significant difference between the two groups ( χ2 = 0.17, P = 0.68) ; 35 patients (67.31%) in the crisaborole group and 45 (83.33%) in the pimecrolimus group achieved ISGA improvement, also with no significant difference between the two groups ( χ2 = 3.68, P = 0.06) ; additionally, there were no significant differences in the EASI, pruritus NRS, DLQI/IDLQI/CDLQI, or DFI scores between the two groups (all P > 0.05). Adverse reactions to the two topical agents were mainly local reactions such as mild to moderate pain, itching, or worsening of itching, and no obvious systemic adverse reactions occurred. The incidence of drug-related adverse reactions was 46.15% (24 cases) in the crisaborole group and 37.04% (20 cases) in the pimecrolimus group, with no significant difference between the two groups ( χ2 = 0.91, P = 0.34) . Conclusion:The efficacy of crisaborole ointment 2% was comparable to that of pimecrolimus cream 1% in the treatment of mild to moderate atopic dermatitis in children aged ≥ 2 years, and it yielded early and rapid improvement in the quality of life of patients and their families, with good safety and tolerability profiles.

Objective To analyze the clinical characteristics of co-infection of Talaromyces marneffei(TM)and non-tuberculous Mycobacterium(NTM)in human immunodeficiency virus(HIV)-negative patients.Methods Clinical data of 8 HIV-negative patients with co-infection of TM and NTM in a hospital from 2019 to 2022 were co-llected.Clinical manifestations,auxiliary examination,treatment and prognosis were retrospectively analyzed.Results Among the 8 patients,5 were females and 3 were males,with an average age of(52.25±12.31)years old.All patients presented TM and NTM disseminated infection.The major involved organs were lung(100％),lymph nodes(87.5％),and skin(75.0％).Clinical symptoms mainly included cough and expectoration(87.5％),fatigue(62.5％),joint and lumbosacral pains(62.5％),fever(50.0％),as well as skin and soft tissue abscess(50.0％),etc.Anti-interferon-γ(INF-γ)autoantibodies were detected in 4 patients and the results were positive.All 8 patients(100％)had pulmonary lesions,with chest CT mainly showing spots,patches,and striped shadows in both lungs.Among them,7 cases(87.5％)had increased and enlarged mediastinal lymph nodes,4 cases(50.0％)had pleural thickening and pleural effusion,2 cases each(25.0％for each)were accompanied by pulmonary mass shadows,bronchial stenosis,as well as increased and enlarged hilar lymph nodes.One case each(12.5％for each)had pulmonary cavity formation,bronchiectasis,and pericardial effusion.Conclusion The co-infection of TM and NTM in non-HIV patients presents disseminated infection,with multiple clinical symptoms.Chest imaging shows a wide variety of pulmonary lesions.It is prone to miss diagnosis in clinic,and the effect is not ideal after treatment for single pathogen infection.

Objective:To compare the efficacy and safety of crisaborole ointment 2% versus pimecrolimus cream 1% in the treatment of mild to moderate atopic dermatitis in children aged 2 years or older.Methods:A multicenter, randomized, open-label, controlled clinical trial was conducted. A total of 120 pediatric patients aged 2 - 17 years with mild to moderate atopic dermatitis were enrolled from departments of dermatology of 8 hospitals in China between March 2022 and February 2023. The participants were randomly assigned in a 1∶1 ratio to the crisaborole group and the pimecrolimus group, and received the treatment with crisaborole ointment 2% and pimecrolimus cream 1% respectively, twice a day for 4 weeks. Visits were scheduled at baseline/on day 1, as well as on days 8, 15, and 29. The primary efficacy outcome was the percentage of patients achieving the Investigator's Static Global Assessment (ISGA) success (defined as clear [0] or almost clear [1] on the ISGA scale, combined with ≥ 2‐grade improvement from baseline) on day 29. The secondary efficacy outcomes included changes in the Eczema Area and Severity Index (EASI) total scores from baseline to day 29, percentages of patients achieving ISGA improvement (defined as clear [0] or almost clear [1] on the ISGA scale), as well as changes in the Peak Pruritus Numerical Rating Scale (NRS) scores, Dermatology Life Quality Index (DLQI) /Infants' Dermatology Life Quality Index (IDLQI) /Children's Dermatology Life Quality Index (CDLQI) scores, and in the Dermatitis Family Impact (DFI) scores. Drug safety was evaluated according to the incidence of adverse events. Categorical data were compared using the chi-square test. Since measurement data did not follow a normal distribution, the rank sum test was used for comparisons of measurement data between groups.Results:A total of 106 children with mild to moderate atopic dermatitis were included in the per-protocol analysis set, with 52 in the crisaborole group (26 males and 26 females) and 54 in the pimecrolimus group (27 males and 27 females). There were no significant differences in age, disease duration, ISGA and EASI scores at baseline between the two groups (all P > 0.05). On day 29, 22 patients (42.31%) in the crisaborole group and 25 (46.30%) in the pimecrolimus group achieved ISGA success, with no significant difference between the two groups ( χ2 = 0.17, P = 0.68) ; 35 patients (67.31%) in the crisaborole group and 45 (83.33%) in the pimecrolimus group achieved ISGA improvement, also with no significant difference between the two groups ( χ2 = 3.68, P = 0.06) ; additionally, there were no significant differences in the EASI, pruritus NRS, DLQI/IDLQI/CDLQI, or DFI scores between the two groups (all P > 0.05). Adverse reactions to the two topical agents were mainly local reactions such as mild to moderate pain, itching, or worsening of itching, and no obvious systemic adverse reactions occurred. The incidence of drug-related adverse reactions was 46.15% (24 cases) in the crisaborole group and 37.04% (20 cases) in the pimecrolimus group, with no significant difference between the two groups ( χ2 = 0.91, P = 0.34) . Conclusion:The efficacy of crisaborole ointment 2% was comparable to that of pimecrolimus cream 1% in the treatment of mild to moderate atopic dermatitis in children aged ≥ 2 years, and it yielded early and rapid improvement in the quality of life of patients and their families, with good safety and tolerability profiles.

Objective To analyze the clinical characteristics of co-infection of Talaromyces marneffei(TM)and non-tuberculous Mycobacterium(NTM)in human immunodeficiency virus(HIV)-negative patients.Methods Clinical data of 8 HIV-negative patients with co-infection of TM and NTM in a hospital from 2019 to 2022 were co-llected.Clinical manifestations,auxiliary examination,treatment and prognosis were retrospectively analyzed.Results Among the 8 patients,5 were females and 3 were males,with an average age of(52.25±12.31)years old.All patients presented TM and NTM disseminated infection.The major involved organs were lung(100％),lymph nodes(87.5％),and skin(75.0％).Clinical symptoms mainly included cough and expectoration(87.5％),fatigue(62.5％),joint and lumbosacral pains(62.5％),fever(50.0％),as well as skin and soft tissue abscess(50.0％),etc.Anti-interferon-γ(INF-γ)autoantibodies were detected in 4 patients and the results were positive.All 8 patients(100％)had pulmonary lesions,with chest CT mainly showing spots,patches,and striped shadows in both lungs.Among them,7 cases(87.5％)had increased and enlarged mediastinal lymph nodes,4 cases(50.0％)had pleural thickening and pleural effusion,2 cases each(25.0％for each)were accompanied by pulmonary mass shadows,bronchial stenosis,as well as increased and enlarged hilar lymph nodes.One case each(12.5％for each)had pulmonary cavity formation,bronchiectasis,and pericardial effusion.Conclusion The co-infection of TM and NTM in non-HIV patients presents disseminated infection,with multiple clinical symptoms.Chest imaging shows a wide variety of pulmonary lesions.It is prone to miss diagnosis in clinic,and the effect is not ideal after treatment for single pathogen infection.

Objective:To investigate the relationship between sarcopenic obesity(SO), defined by various obesity indicators, and mortality risk in older adults based on a prospective cohort from multiple nursing homes.Methods:Sarcopenia was diagnosed according to the 2019 consensus of the Asian Working Group for Sarcopenia.Obesity was defined using six different indicators: waist circumference(WC), waist-hip ratio(WHR), waist-height ratio(WHTR), body mass index(BMI), visceral fat area(VFA), and percentage of body fat(PBF).A prospective cohort of adults aged 60 and above was established across 15 nursing homes in Zigong City, with annual follow-ups on survival status conducted over two consecutive years.Cox proportional hazards regression models were employed to analyze the association between SO, defined by different obesity indicators, and mortality risk, calculating hazard ratios( HR)and their 95% confidence intervals( CI). Results:A total of 695 older adults were included in the study, of whom 67.1% were male.During the 2-year follow-up period, 88 participants died.The prevalence of SO as defined by WC, WHR, WHTR, BMI, VFA, PBF was found to be 17.6%, 30.1%, 48.9%, 3.0%, 28.3%, and 58.7%, respectively.When SO was defined using WC, WHR, WHTR, BMI, and VFA, there was no statistically significant difference in mortality rates between the SO and non-SO groups.However, when defined by PBF, the SO group exhibited a significantly higher mortality rate compared to the non-SO group(16.9% vs.6.6%, P<0.01).Cox proportional hazards regression analysis revealed that, compared to the non-SO group, the SO group defined by PBF had a significantly increased mortality risk( HR=2.81, 95% CI: 1.67-4.73, P<0.001).After adjusting for potential confounding factors, the mortality risk for the SO group remained significantly higher than that of the non-SO group( HR=1.97, 95% CI: 1.14-3.38, P=0.015). Conclusions:The prevalence of SO varies significantly across different obesity indicators.SO defined by PBF is significantly associated with mortality risk in nursing home residents.This study provides new evidence for further optimizing the diagnostic criteria for SO in this population.

Objective:To develop an ultrasound multi-view fusion recognition model and evaluate its clinical value in diagnosing fetal conotruncal defects (CTD).Methods:This prospective study collected cardiac ultrasound images from fetuses at 20-32 weeks of gestation undergoing prenatal ultrasound at Dongguan Maternal and Child Health Hospital between September 2022 and May 2024. The case group comprised fetuses diagnosed with CTD, while controls with normal cardiac structures were collected at a 1∶2 ratio. Both groups were divided into modeling training and validation sets at a 3∶1 ratio. One optimal standard image each from the four-chamber view, left ventricular outflow tract view, right ventricular outflow tract view, and three vessels and trachea view was included per fetus. A deep learning-based multi-view fusion recognition model was developed to differentiate normal conotruncal anatomy from CTD. Model performance was validated against post-abortion pathology or postnatal echocardiography results. SAS software was used for statistical analysis to calculate the sensitivity and specificity of three fusion models (based on positivity in any two, three, or four views, and were designated as Fusion Model 1, Fusion Model 2, and Fusion Model 3, respectively), with the optimal model determined by the maximum Youden index. Senior, intermediate, and junior prenatal sonologists independently diagnosed cases in the validation set under blinding conditions. Their diagnostic results were compared with those of the optimal model. Paired Chi-square test (Cochran's Q test) was employed to compare the differences between the diagnostic accuracy rates of sonologists at different experience levels and the sensitivity of the optimal model, thereby analyzing the auxiliary diagnostic value of the multi-view fusion recognition model. Results:The study included 88 CTD cases, excluding six cases (non-CTD diagnosed by post-abortion pathology or postnatal echocardiography or poor image quality), divided into 60 training and 22 validation cases (12 tetralogy of Fallot, four double outlet right ventricle, three transposition of great arteries, three persistent truncus arteriosus). The control group included 176 cases, excluding 15 cases (other cardiac abnormalities confirmed postnatally or poor image quality after re-evaluation), divided into 120 training and 41 validation cases. The sensitivities of Fusion Model 1, Fusion Model 2, and Fusion Mudel 3 were 0.86, 0.64, and 0.27, while their specificities were 0.76, 0.95, and 1.00, respectively. Fusion Model 1 demonstrated the highest Youden index (0.62) and was selected as optimal. Its diagnostic sensitivity showed no significant difference from senior sonologists [86% vs. 91% (20/22), Bonferroni-corrected P>0.999], but was significantly higher than intermediate [55% (12/22), Bonferroni-corrected P=0.049] and junior sonologists [32% (7/22), Bonferroni-corrected P=0.003]. Conclusion:The deep learning multi-view fusion model achieved diagnostic performance comparable to senior sonologists, demonstrating potential value in assisting CTD diagnosis, training less experienced sonologists, and supporting research and education.