[Constructing a cataplexy face prediction model for narcolepsy type 1 based on ResNet-18].

Objective: To establish a prediction model for the identifying of cataplexy facial features based on clinical shooting videos by using a deep learning image recognition network ResNet-18. Methods: A cross-sectional study. Twenty-five narcolepsy type 1 patients who were first diagnosed and never received treatment and 25 healthy controls recruited by advertisement in the Second Affiliated Hospital of Nanchang University from 2020 to 2023.After image preprocessing, a total of 1 180 images were obtained, including 583 cataplexy faces and 597 normal faces.90% were selected as the training set and validation set, and then expanded the data by 5 times.80% of the expanded data set was extracted as the training set and 20% as the validation set, that is, the number of the training set was (583+597)×0.9×0.8×5=4 248, the number of the validation set was (583+597)×0.9×0.2×5=1 062. The data sets for training and validation were used train parameters to establish the model and were trained through the five-fold cross-validation method, to establish the ResNet-18 cataplexy face recognition model via transfer learning.10% (118 images) of the original non-amplified images were extracted as the test set. The test set data did not participate in data enhancement and model training, and was only used to evaluate the final performance of the model. Finally, ResNet-18 was compared with VGG-16, ResNet-34 and Inception V3 deep learning models, and the receiver operating characteristic curve was used to evaluate the value of ResNet-18 image recognition network in cataplexy face recognition. Results: Among 25 patients with narcolepsy type 1, 15 were males and 10 were females, aged [M (Q1, Q3)] of 14.0(11.0, 20.5) years.Among 25 healthy controls, 14 were males and 11 were females, with a median age of 16.0(14.4, 23.0) years.The overall accuracy of ResNet-18 image recognition network in the test set was 90.9%, the sensitivity was 96.4% and the specificity was 85.2%. The area under the ROC curve was 0.99(95%CI:0.96-1.00). The ResNet-18 model parameter amount was 11.69 M, the floating point operation amount was 1 824.03 M, and the single image recognition time was 5.9 ms. Conclusions: The cataplexy face prediction model built based on the deep learning image recognition network ResNet-18 has a high accuracy in identifying cataplexy faces.

[Analysis of the maternal and fetal adverse outcomes of 154 pregnant women with cesarean section in the second stage of labor].

Objective: To investigate the perinatal maternal and fetal adverse outcomes of cesarean section in the different duration of the second stage of labor. Methods: A retrospective cohort study was conducted on the clinical data of 154 pregnant women with singleton head pregnancy who underwent cesarean section at different times of the second stage of labor due to maternal and fetal factors in the First Affiliated Hospital of Nanjing Medical University from January 1, 2019 to December 31, 2021. According to the duration of the second stage of labor, they were divided into <2 h group (54 cases), 2-<3 h group (61 cases), and ≥3 h group (39 cases). The general data of pregnant women and neonates, preoperative maternal and neonatal conditions related to labor stages, surgical indications, surgical procedures, and perioperative maternal and neonatal adverse outcomes were compared among the three groups. Results: (1) General Information: there were no significant differences in maternal age, gravidity and parity, proportion of primipara, gestational age at delivery, body mass index before delivery, pregnancy complications, labor analgesia rate and the duration of the first stage of labor among the three groups (all P>0.05). The differences of the gender composition, birth weight and incidence of macrosomia of the three groups were also not statistically significant (all P>0.05). (2) Maternal and fetal status and surgical indications: the incidence of intrapartum fever and type Ⅱ and Ⅲ fetal heart rate monitoring in the <2 h group were higher than those in the 2-<3 h group and the ≥3 h group, and the preoperative fetal head position in the ≥3 h group was lower than that in the 2-<3 h group, with statistically significant differences (all P<0.05). The proportion of cesarean section due to "fetal distress" was 40.7% (22/54) in the <2 h group, which was higher than that in the 2-<3 h group (4.9%, 3/61) and the ≥3 h group (2.6%, 1/39). The proportions of surgical indication of "relative cephalo-pelvic disproportion" were 98.4% (60/61) and 94.9% (37/39) in the 2-<3 h group and ≥3 h group, respectively, and the surgical indication of "fetal head descent arrest" were 41.0% (25/61) and 59.0% (23/39), respectively. Compared with <2 h group [63.0% (34/54), 13.0% (7/54)], the differences were statistically significant (all P<0.05). There were no significant difference in surgical indications between 2-<3 h group and ≥3 h group (all P>0.05). (3) Intraoperative conditions and perioperative complications of cesarean section: the puerperal morbidity rate of <2 h group was 37.0% (20/54), which was higher than those of 2-<3 h group (18.0%, 11/61) and ≥3 h group (7.7%, 3/39), the difference was statistically significant (P<0.05). There were no significant differences in operation time, intraoperative blood loss, incidence of fetal head inlay, uterine incision tear, modified B-Lynch suture for uterine atony, postpartum hemorrhage, perioperative blood transfusion, preoperative hemoglobin (Hb) level, perioperative Hb change, and postoperative hospital stay among the three groups (all P>0.05). (4) Adverse neonatal outcomes: non-hemolytic neonatal hyperbilirubinemia in ≥3 h group was 35.9% (14/39), which was significantly higher than that in <2 h group (13.0%, 7/54; P<0.05). Among the neonates admitted to neonatal intensive care unit (NICU) within 1 week after birth, the proportion of neonates admitted to NICU due to neonatal hyperbilirubinemia in ≥3 h group (15/19) was significantly higher than that in <2 h group (9/17) and 2-<3 h group (10/19), and the differences were statistically significant (all P<0.05). However, there was no significant difference between the <2 h group and the 2-<3 h group (P>0.05). There was no perinatal death in the three groups. Conclusions: The rate of puerperal morbidity is higher in patients who were transferred to cesarean section within 2 hours of the second stage of labor. In the early stage of the second stage of labor, the monitoring of fetal heart rate and amniotic fluid characteristics should be strengthened, especially the presence or absence of prenatal fever. In good maternal and neonatal conditions, conversion to cesarean section after 2 hours of the second stage of labor does not significantly increase the incidence of serious adverse maternal and neonatal outcomes. For the second stage of labor more than 3 hours before cesarean section, it is necessary to strengthen the monitoring of neonatal bilirubin.

Hypertension, fetal growth restriction and obstructive sleep apnoea in pregnancy.

OBJECTIVE: To test the hypothesis that obstructive sleep apnoea (OSA) is more common in pregnancies complicated by hypertensive disease and fetal growth restriction. STUDY DESIGN: An observational study comparing pregnant women with these two complications with normal pregnant women and non-pregnant women in two UK maternity hospitals. Each participant completed a sleep apnoea questionnaire and underwent nocturnal oxygen saturation monitoring. RESULTS: Using a strict definition of obstructive sleep apnoea confirmed by oxygen saturation monitoring only two mild cases were seen, 0/50 non-pregnant women, 1/69 of normal pregnant women, 0/48 women with various types of hypertensive disease, and 1/33 women carrying fetuses affected with fetal growth restriction. Even using less strict definitions and self-reported sleepiness scores there was no relation between sleep apnoea and either fetal growth restriction or hypertensive diseases. CONCLUSION: Obstructive sleep apnoea is at most a rare cause of either growth restriction or hypertensive disease in pregnancy.

[Epidemiological features of hepatitis C and its related influencing factors in Shandong province, 2007-2016].

Objective: To analyze the epidemiological characteristics, dynamic trend of development and related influencing factors of hepatitis C in Shandong, China, 2007-2016, also to provide epidemiological evidence for prevention and control of HCV. Methods: National surveillance data of hepatitis C from 2007 to 2016 in Shandong was used, with distribution and clustering map of hepatitis C drawn at the county level. Panel Poisson regression was used to explore the influencing factors of hepatitis C at the city level. Results: The incidence of hepatitis C in Shandong increased from 1.49/100 000 in 2007 to 4.72/100 000 in 2016, with the high incidence mainly clustered in the urban regions in Jinan, Zibo, Weihai et al. and surrounding vicinities. Majority of the cases were young adults, with 53.16% (14 711/27 671) of them being farmers. Results from the Multiple panel Poisson regression analysis indicated that factors as: population density (aIRR=1.07, 95%CI: 1.05-1.10), number of hospital per hundred thousand people shared (aIRR=1.16, 95%CI: 1.08-1.24), expenditure of medical fee in rural (aIRR=1.21, 95%CI: 1.08-1.37) and the proportion of the tertiary industry (aIRR=1.08, 95%CI: 1.07-1.09) were all correlated to the incidence of hepatitis C. Conclusions: The incidence of hepatitis C had been increasing rapidly in recent years, in Shandong. Prevention and control of HCV should focus on high risk population. In addition, rural, especially in areas with lower economics provision should be under more attentions, so as to find more concealed cases for early treatment.

No correlation between ultrasound placental grading at 31-34 weeks of gestation and a surrogate estimate of organ function at term obtained by stereological analysis.

We test the experimental hypothesis that early changes in the ultrasound appearance of the placenta reflect poor or reduced placental function. The sonographic (Grannum) grade of placental maturity was compared to placental function as expressed by the morphometric oxygen diffusive conductance of the villous membrane. Ultrasonography was used to assess the Grannum grade of 32 placentas at 31-34 weeks of gestation. Indications for the scans included a history of previous fetal abnormalities, previous fetal growth problems or suspicion of IUGR. Placentas were classified from grade 0 (most immature) to grade III (most mature). We did not exclude smokers or complicated pregnancies as we aimed to correlate the early appearance of mature placentas with placental function. After delivery, microscopical fields on formalin-fixed, trichrome-stained histological sections of each placenta were obtained by multistage systematic uniform random sampling. Using design-based stereological methods, the exchange surface areas of peripheral (terminal and intermediate) villi and their fetal capillaries and the arithmetic and harmonic mean thicknesses of the villous membrane (maternal surface of villous trophoblast to adluminal surface of vascular endothelium) were estimated. An index of the variability in thickness of this membrane, and an estimate of its oxygen diffusive conductance, were derived secondarily as were estimates of the mean diameters and total lengths of villi and fetal capillaries. Group comparisons were drawn using analysis of variance. We found no significant differences in placental volume or composition or in the dimensions or diffusive conductances of the villous membrane. Subsequent exclusion of smokers did not alter these main findings. Grannum grades at 31-34 weeks of gestation appear not to provide reliable predictors of the functional capacity of the term placenta as expressed by the surrogate measure, morphometric diffusive conductance.