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.

Objective:To investigate the clinical manifestations of medically refractory hereditary movement disorders in children and the efficacy of deep brain stimulation (DBS).Methods:A case series study.The clinical and follow-up data of 20 children with medically refractory hereditary movement disorders who underwent DBS treatment at the Neurology and Functional Neurosurgery Departments of Beijing Children′s Hospital, Capital Medical University, from July 2018 to April 2024, were retrospectively analyzed.The severity of movement disorder symptoms and surgical effects were evaluated using the Burke-Fahn-Marsden Dystonia Rating Scale Movement(BFMDRS-M) or the Unified Parkinson′s Disease Rating Scale Ⅲ(UPDRS Ⅲ).Results:There were 12 males and 8 females among the 20 children, with an onset age ranging from 4 months to 12 years and 5 months.Fourteen patients had hereditary dystonia, which is related to KMT2B in 11 patients, TOR1A in 2 patients and SGCE in 1 patient.Two patients had choreoathetosis, which is related to ADCY5-related familial movement disorders.Two patients had early-onset Parkinson′s disease, which is related to ATP6AP2 in 1 patient and VPS13C in 1 patient.Two patients had neurodevelopmental disorders with involuntary movements, which is related to GNAO1 in 1 patient, and the other patient was idiopathic.All the children were given oral Levodopa, Benzhexol, Baclofen, Tiapride Hydrochloride, Clonazepam alone or in combination.Three children showed obvious dyskinesia after Levodopa treatment.The symptoms of movement disorders in all children exhibited little to no improvement.Levetiracetam and Zonisamide had unstable effects in the treatment of myoclonia.DBS surgery was performed on all the patients aged from 3 to 16 years.Electrodes were successfully inserted into bilateral globus pallidus internus in 14 cases and bilateral subthalamic nuclei in 4 cases.The target was unknown in 2 cases.No surgery-related complications were observed.The patients were followed up for 3 months to 6 years, and the last follow-up age of the patients ranged from 5 years and 7 months to 22 years and 1 month.The rate of improvement in BFMDRS-M score was 37%-100% in 16 patients and >70% in 7 patients with hereditary dystonia.The rate of improvement in UPDRS Ⅲ score was 23% in 1 patient with VPS13C-related early-onset Parkinson′s disease. Conclusions:Childhood medically refractory hereditary movement disorders are a case series that exhibits significant phenotypic and genotypic heterogeneity.DBS surgery demonstrates significant efficacy for KMT2B-, TOR1A-, and SGCE-related hereditary movement disorders.

Objective:To investigate the clinical manifestations of medically refractory hereditary movement disorders in children and the efficacy of deep brain stimulation (DBS).Methods:A case series study.The clinical and follow-up data of 20 children with medically refractory hereditary movement disorders who underwent DBS treatment at the Neurology and Functional Neurosurgery Departments of Beijing Children′s Hospital, Capital Medical University, from July 2018 to April 2024, were retrospectively analyzed.The severity of movement disorder symptoms and surgical effects were evaluated using the Burke-Fahn-Marsden Dystonia Rating Scale Movement(BFMDRS-M) or the Unified Parkinson′s Disease Rating Scale Ⅲ(UPDRS Ⅲ).Results:There were 12 males and 8 females among the 20 children, with an onset age ranging from 4 months to 12 years and 5 months.Fourteen patients had hereditary dystonia, which is related to KMT2B in 11 patients, TOR1A in 2 patients and SGCE in 1 patient.Two patients had choreoathetosis, which is related to ADCY5-related familial movement disorders.Two patients had early-onset Parkinson′s disease, which is related to ATP6AP2 in 1 patient and VPS13C in 1 patient.Two patients had neurodevelopmental disorders with involuntary movements, which is related to GNAO1 in 1 patient, and the other patient was idiopathic.All the children were given oral Levodopa, Benzhexol, Baclofen, Tiapride Hydrochloride, Clonazepam alone or in combination.Three children showed obvious dyskinesia after Levodopa treatment.The symptoms of movement disorders in all children exhibited little to no improvement.Levetiracetam and Zonisamide had unstable effects in the treatment of myoclonia.DBS surgery was performed on all the patients aged from 3 to 16 years.Electrodes were successfully inserted into bilateral globus pallidus internus in 14 cases and bilateral subthalamic nuclei in 4 cases.The target was unknown in 2 cases.No surgery-related complications were observed.The patients were followed up for 3 months to 6 years, and the last follow-up age of the patients ranged from 5 years and 7 months to 22 years and 1 month.The rate of improvement in BFMDRS-M score was 37%-100% in 16 patients and >70% in 7 patients with hereditary dystonia.The rate of improvement in UPDRS Ⅲ score was 23% in 1 patient with VPS13C-related early-onset Parkinson′s disease. Conclusions:Childhood medically refractory hereditary movement disorders are a case series that exhibits significant phenotypic and genotypic heterogeneity.DBS surgery demonstrates significant efficacy for KMT2B-, TOR1A-, and SGCE-related hereditary movement disorders.

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.

Background::Adamantinomatous craniopharyngioma (ACP) is the commonest pediatric sellar tumor. No effective drug is available and interpatient heterogeneity is prominent. This study aimed to identify distinct molecular subgroups of ACP based on the multi-omics profiles, imaging findings, and histological features, in order to predict the response to anti-inflammatory treatment and immunotherapies.Methods::Totally 142 Chinese cases diagnosed with craniopharyngiomas were profiled, including 119 ACPs and 23 papillary craniopharyngiomas. Whole-exome sequencing (151 tumors, including recurrent ones), RNA sequencing (84 tumors), and DNA methylome profiling (95 tumors) were performed. Consensus clustering and non-negative matrix factorization were used for subgrouping, and Cox regression were utilized for prognostic evaluation, respectively.Results::Three distinct molecular subgroups were identified: WNT, ImA, and ImB. The WNT subgroup showed higher Wnt/β-catenin pathway activity, with a greater number of epithelial cells and more predominantly solid tumors. The ImA and ImB subgroups had activated inflammatory and interferon response pathways, with enhanced immune cell infiltration and more predominantly cystic tumors. Mitogen-activated protein kinases (MEK/MAPK) signaling was activated only in ImA samples, while IL-6 and epithelial-mesenchymal transition biomarkers were highly expressed in the ImB group, mostly consisting of children. The degree of astrogliosis was significantly elevated in the ImA group, with severe finger-like protrusions at the invasive front of the tumor. The molecular subgrouping was an independent prognostic factor, with the WNT group having longer event-free survival than ImB (Cox, P = 0.04). ImA/ImB cases were more likely to respond to immune checkpoint blockade (ICB) therapy than the WNT group ( P <0.01). In the preliminary screening of subtyping markers, CD38 was significantly downregulated in WNT compared with ImA and ImB ( P = 0.01). Conclusions::ACP comprises three molecular subtypes with distinct imaging and histological features. The prognosis of the WNT type is better than that of the ImB group, which is more likely to benefit from the ICB treatment.

Objective:To summarize the clinical manifestations and gene mutation features of patients with nucleotide excision repair (NER) disorders.Methods:A retrospective analysis was made on clinical data of patients with NER disorders who were admitted to the Chinese People′s Liberation Army General Hospital from October 2008 to February 2022 and diagnosed in the Outpatient Department of Beijing Children′s Hospital, Capital Medical University from October 2015 to February 2022.Literature on previously reported Chinese patients with NER disorders was reviewed.Results:(1)A total of 16 patients with NER disorders were enrolled, including 6 males and 10 females.The onset age was 7.5 (4.0, 12.0) months and the age at diagnosis was 42.0 (21.5, 77.0) months.There were 3 types of NER disorders: Cockayne syndrome (CS) in 13 cases, Xeroderma Pigmentosum (XP) in 2 cases and Cerebro-Oculo-Facio-Skeletal syndrome (COFS) in 1 case.Four disease-causing genes were detected: CSA gene in 11 cases, CSB gene in 3 cases, XPG gene in 1 case, and XPD gene in 1 case.The first symptoms of the 16 patients were photosensitivity and developmental delay, and neurological symptoms were observed in all the 3 NER disorder types.XP and CS patients had skin symptoms.CS patients presented typical facial features, visual and auditory impairment, microcephaly and changes in neuroimaging features.COFS patients showed intrauterine growth retardation.(2)Results of literature review: a total of 96 Chinese patients reported were retrieved, involving 6 disease types, including CS in 45 cases, XP in 44 cases, trichothiodystrophy in 4 cases, COFS in 1 case, XP-CS in 1 case, and ultraviolet sensitive syndrome in 1 case.Nine mutated genes were identified: CSA in 33 cases, XPA in 15 cases, CSB in 13 cases, XPV in 10 cases, XPC in 9 cases, XPG in 7 cases, XPD in 7 cases, XPF in 1 case, and MPLKIP in 1 case.The common symptoms were growth failure (62 cases), skin photosensitivity (61 cases), typical facial features (52 cases), mental retardation (49 cases) and microcephaly (48 cases). Among 36 cases had imaging data 33 cases(91.7%)had calcification of basal nucleus or globus pallidus.Three cases had intrauterine growth retardation and microcephaly during pregnancy. Conclusions:Patients with such prenatal manifestations as intrauterine growth retardation and microcephaly or with typical symptoms like skin photosensitivity, typical facial features, growth failure, mental retardation, hypertonia, and calcifications of basal ganglia should be suspected of NER disorders.Early genetic testing is recommended to confirm the diagnosis.

Objective:To explore the associations of platelet parameters platelet count (PLT), mean platelet volume (MPV), platelet distribution width (PDW) and plateletcrit (PCT) with the risk for stroke in people with different blood pressure levels.Methods:All the participants were from Dongfeng-Tongji cohort, including 38 295 retired employees from Dongfeng Motor Corporation at the first follow-up survey. After excluding participants with coronary heart disease, stroke, cancer, history of platelet influential drug use and those with missed data of platelet parameters or blood pressure or lost to follow-up, finally a total of 21 294 participants were included in this study. All the participants completed baseline questionnaires, physical examinations, clinical biochemical tests, and blood sample collection. Cox proportional hazard models were used to estimate the hazard ratios ( HRs) and the corresponding 95% confident intervals ( CIs) for the associations between platelet parameters and risk for stroke in people with different blood pressure levels. Results:After a mean follow-up of 8.0 years, 1 578 participants developed incident stroke [1 266 ischemic stroke (IS) cases and 312 hemorrhagic stroke (HS) cases]. Compared with the participants with PLT<188×10 9/L, those with PLT≥188×10 9/L among hypertension cases were significantly associated with higher risks for stroke and IS (stroke: HR=1.27, 95% CI: 1.12-1.44; IS: HR=1.39, 95% CI: 1.21-1.60). Among hypertension group, compared with participants with PCT<0.165%, PCT≥0.165% were significantly associated with higher risk for stroke ( HR=1.15, 95% CI: 1.01-1.30) and lower risk for HS ( HR=0.70, 95% CI: 0.53-0.93); Among non-hypertension and hypertension group, PCT ≥0.165% were significantly associated with higher risks of IS ( HR=1.27, 95% CI: 1.05-1.54; HR=1.31, 95% CI: 1.14-1.50). MPV and PDW were not significantly associated with risk for stroke. Risk for stroke increased significantly in hypertension cases with different platelet parameters levels compared with non-hypertension cases with lower levels of each platelet parameters. Conclusion:Higher levels of PLT and PCT could increase the risks for stroke and IS in middle-aged and elderly hypertension patients, and lower levels of PCT could decrease the risk for HS in hypertension patients.

Objective:To explore the effects of interpregnancy interval (IPI) on pregnancy outcomes of subsequent pregnancy.Methods:A multicenter retrospective study was conducted in 21 hospitals in China. Information of age, height, pre-pregnancy weight, IPI, history of diseases, complications of pregnancy, gestational age of delivery, delivery mode, and pregnancy outcomes of the participants were collected by consulting medical records of pregnant women who had two consecutive deliveries in the same hospital during 2011 to 2018. The participants were divided into 4 groups according to IPI:<18 months, 18-23 months, 24-59 months and ≥60 months. According to the WHO′s recommendation, with the IPI of 24-59 months group as a reference, to the effects of IPI on pregnancy outcomes of subsequent pregnancy were analyzed. Stratified analysis was further carried out based on age, history of gestational diabetes mellitus (GDM), macrosomia, and premature delivery, to explore the differences in the effects of IPI on pregnancy outcomes among women with different characteristics.Results:A total of 8 026 women were included in this study. There were 423, 623, 5 512 and 1 468 participants in <18 months group, 18-23 months group, 24-59 months group and ≥60 months group, respectively. (1) The age, pre-pregnancy body mass index (BMI), history of cesarean section, GDM, gestational hypertension and cesarean section delivery rate of <18 months group, 18-23 months group, 24-59 months group and ≥60 months group were gradually increased, and the differences were statistically significant ( P<0.05). (2) After adjusting for potential confounding factors, compared with women in the IPI of 24-59 months group, the risk of premature delivery, premature rupture of membranes, and oligohydramnios were increased by 42% ( OR=1.42, 95% CI: 1.07-1.88, P=0.015), 46% ( OR=1.46, 95% CI: 1.13-1.88, P=0.004), and 64% ( OR=1.64, 95% CI: 1.13-2.38, P=0.009) respectively for women in the IPI≥60 months group. No effects of IPI on other pregnancy outcomes were found in this study ( P>0.05). (3) After stratified by age and adjusted for confounding factors, compared with women in the IPI of 24-59 months group, IPI≥60 months would significantly increase the risk of oligohydramnios for women with advanced age ( OR=2.87, 95% CI: 1.41-5.83, P=0.004); and <18 months could increase the risk of premature rupture of membranes for women under the age of 35 ( OR=1.59, 95% CI: 1.04-2.43, P=0.032). Both the risk of premature rupture of membranes ( OR=1.58, 95% CI: 1.18-2.13, P=0.002) and premature delivery ( OR=1.52, 95% CI: 1.07-2.17, P=0.020) were significantly increased in the IPI≥60 months group. After stratified by history of GDM and adjusted for confounding factors, compared with women in the IPI of 24-59 months group, IPI≥60 months would lead to an increased risk of postpartum hemorrhage for women with a history of GDM ( OR=5.34, 95% CI: 1.45-19.70, P=0.012) and an increased risk of premature rupture of membranes for women without a history of GDM ( OR=1.44, 95% CI: 1.10-1.90, P=0.009). After stratified by history of macrosomia and adjusted for confounding factors, compared with women in the IPI of 24-59 months group, IPI≥60 months could increase the proportion of cesarean section for women with a history of macrosomia ( OR=4.11, 95% CI: 1.18-14.27, P=0.026) and the risk of premature rupture of membranes for women without a history of macrosomia ( OR=1.46, 95% CI: 1.12-1.89, P=0.005). After stratified by history of premature delivery and adjusted for confounding factors, compared with women in the IPI of 24-59 months group, IPI≥60 months would significantly increase the risk of premature rupture of membranes for women without a history of premature delivery ( OR=1.47, 95% CI: 1.13-1.92, P=0.004). Conclusions:Both IPI≥60 months and <18 months would increase the risk of adverse pregnancy outcomes in the subsequent pregnancy. Healthcare education and consultation should be conducted for women of reproductive age to maintain an appropriate IPI when they plan to pregnant again, to reduce the risk of adverse pregnancy outcomes in the subsequent pregnancy.

OBJECTIVES: The measurement of diabetic foot ulcers is important for the success in diabetic foot ulcer management. At present, it lacks the accurate and convenient measurement tools in clinical. In recent years, artificial intelligence technology has demonstrated the potential application value in the field of image segmentation and recognition. This study aims to construct an intelligent measurement model of diabetic foot ulcers based on the deep learning method, and to conduct preliminary verification. METHODS: The data of 1 042 diabetic foot ulcers clinical samples were collected. The ulcers and color areas were manually labeled, of which 782 were used as the training data set and 260 as the test data set. The Mask RCNN ulcer tissue color semantic segmentation and RetinaNet scale digital scale target detection were used to build a model. The training data set was input into the model and iterated. The test data set was used to verify the intelligent measurement model. RESULTS: This study established an intelligent measurement model of diabetic foot ulcers based on deep learning. The mean average precision@.5 intersection over union (mAP@.5IOU) of the color region segmentation in the training set and the test set were 87.9% and 63.9%, respectively; the mAP@.5IOU of the ruler scale digital detection in the training set and the test set were 96.5% and 83.4%, respectively. Compared with the manual measurement result of the test sample, the average error of the intelligent measurement result was about 3 mm. CONCLUSIONS The intelligent measurement model has good accuracy and robustness in measuring the diabetic foot ulcers. Future research can further optimize the model with larger-scale data samples.
Artificial Intelligence ; Diabetes Mellitus ; Diabetic Foot ; Humans

Objective:To investigate the physical indices and growth status of preterm children aged 0 to 4 years with different birth weight.Methods:Following the real world research approach, the current study retrospectively collected e-chart information of 8 496 preterm children from the child health care system of the Children′s Hospital of Chongqing Medical University from December 2010 to December 2017, with 203 123 full-term children followed up during the same period as controls. Premature children were divided into normal birth weight (NBW) group, low birth weight (LBW) group, and very low birth weight (VLBW) group based on their birth weights. The weight and length development within 48 months of age of preterm boys and girls in each group were measured and recorded to establish a numerical table and analyze the growth levels, growth rate, and proportionality. The t-test or chi-square test was used for between-group comparison. Results:Of the 8 496 preterm children, 4 839 were girls and 3 657 boys, including 525 in the VLBW group, with an average birth weight of (1.28±0.14) kg, 3 862 in the LBW group, with an average birth weight of (2.07±0.28) kg, and 4 109 in the NBW group, with an average birth weight of (2.86±0.35) kg. The weight at the actual age of 2-<3 months ((5.61±0.96) vs. (5.64±0.78) kg in boys, (5.11±0.67) vs. (5.18±0.71) kg in girls) and the length at the actual age of 8-<10 months ((70.3±2.4) vs. (70.6±2.4) cm in boys, (68.9±2.2) vs. (68.9±2.4) cm in girls) in the NBW group reached the average weight and length of full-term children. The difference of physical growth before 24 months of age between LBW and control group decreased as children age, with that of LBW group approaches the average of full-term children after 24 months of age, with a weight difference of 0.64-0.95 kg and height difference of 1.3-1.7 cm. The weight and height of the VLBW group were lower than those of full-term infants (2.80-2.86 kg and 3.3-4.3 cm, respectively) at 48 months of age. During 2-12 months of age, the corresponding values of the VLBW group were higher than that of the LBW and NBW groups by 0.35 kg and 0.71 kg, respectively. However, the corresponding values of the VLBW group were lower than that of the LBW and NBW groups(0.64 kg and 0.76 kg at 0-2 months of age, 1.04 kg and 1.49 kg at 12-48 months of age, respectively). The rates of delayed development, underweight, and emaciation were the highest in the VLBW group (all P<0.01), while the rates of overweight and obesity were the highest in the NBW group, with that of the VLBW group being lower than LBW group ( P<0.01) at the age of 24-<36 months. Conclusions:Prior to 4 years of age, the time for preterm children to reach the average physical indices of full-term children differ by birth weights, hence warranting further examination of the corrected gestational age for preterm children. Normal birth weight preterm children present with the highest incidence of overweight and obesity and very low birth weight preterm children present with the highest incidence of growth disorders, marking both groups at high risks of malnutrition.