Cardiotocography (CTG) is a widely used, cost-effective non-invasive fetal monitor, yet its predictive potential for adverse pregnancy outcomes is understudied. This study constructed an AI model based on CTG signals to estimate fetal biological age (CTGage), and validated CTGage-gap (CTGage minus true gestational age) as a novel digital risk biomarker. Based on 61,140 CTG signals from 11,385 pregnancies, a distribution-aligned augmented 1D residual CNN (Net1d) was trained for CTGage prediction. Subjects were split into five CTGage-gap subgroups, and severe underestimation and overestimation subgroups were pooled as a high-risk cohort for outcome incidence comparison. The average absolute error of the model was 10.86 days. The incidence of preterm birth and gestational diabetes mellitus (GDM) in the overestimation group increased, while in the underestimation group, there were increased risks of low birthweight, hypertensive disorders of pregnancy (HDP), and maternal anemia (all p < 0.05). The AI-driven CTGage can be used as a feasible non-invasive biomarker for predicting adverse pregnancy outcomes.

OBJECTIVE:Preeclampsia complicates 3-8% of pregnancies worldwide, an obstetric condition contributed to the short- and long-term morbidity and mortality of mothers and newborns. For its treatment and prevention, it is essential to comprehend the risk factors. This study aimed to investigate the potential causal influence of basal metabolic rate (BMR) on preeclampsia risk. METHODS:We utilized data from publicly available genome-wide association studies (GWAS) of European populations, focusing on BMR and preeclampsia. We selected single-nucleotide polymorphisms (SNPs) as instrumental variables for basal metabolic rate (BMR). Causal estimates were derived using multiple Mendelian Randomization (MR) methods: inverse-variance weighted (IVW), MR-Egger, weighted median, simple mode, and weighted mode. To ensure result robustness, we conducted comprehensive sensitivity analyses assessing potential pleiotropy and heterogeneity. RESULTS:We found evidence of a causal relationship between specific BMR indicators (ebi-a-GCST90029025, ukb-a-268, and ukb-a-16446) and preeclampsia risk. The IVW model indicated that genetically predicted higher BMR was associated with increased odds of preeclampsia. Cochran's Q test and I2 statistics indicated no significant heterogeneity between ukb-a-16446 and preeclampsia, however, slight heterogeneity was observed for the other indicators. According to the MR-Egger regression, our findings were barely impacted by horizontal pleiotropy. CONCLUSION:This MR study supports a causal role of BMR in preeclampsia risk. This highlights the potential of targeting metabolic pathways in preeclampsia prevention. Future research should be performed to explore the underlying mechanisms and evaluate the potential interventions modulating BMR to reduce preeclampsia incidence.

Introduction Aplastic anemia (AA), a rare disorder characterized by bone marrow failure and pancytopenia, poses exceptionally high risks when it occurs during pregnancy. This condition endangers both the mother and fetus, significantly increasing the likelihood of maternal complications such as hemorrhage and infection, as well as adverse perinatal outcomes such as preterm birth and fetal growth restriction. Consequently, pregnancy with AA demands careful management. However, tools to predict these adverse outcomes in affected pregnant women are currently lacking. Here, we applied a machine learning approach to develop and validate a prediction model for adverse pregnancy outcomes in patients with AA, with the goal of guiding early clinical decision-making and improving their overall health outcomes. Methods This study was registered at Clinicaltrials.gov: NCT07101770. We collected data from 310 pregnant women with AA admitted between January 2000 and December 2024 to 15 tertiary hospitals in China. Adverse pregnancy outcomes included at least one of placental abruption, amniotic fluid embolism, postpartum hemorrhage, postpartum infection, maternal mortality, stillbirths, preterm birth, low birthweight, fetal growth restriction, neonatal intensive care unit admission, or neonatal mortality (BJOG, 2014). Feature selection was performed through least absolute shrinkage and selection operator (LASSO) regression. The reliability of the models was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, F1 score, calibration plots, and decision curve analysis (DCA). The SHapley Additive exPlanation (SHAP) method was used to rank the feature importance and explain the final model. Results Among the 310 patients with AA (median age, 30.2 [27.6-33.9]), 201 from 7 specialized tertiary hospitals composed the derivation cohort (training set), whereas an independent cohort of 109 patients from 8 distinct academic medical centers formed the external validation set. To ensure robust model development, the training set underwent a stratified random split, yielding a model-building subset (136 patients, 67.7%) and a hold-out internal validation subset (65 patients, 32.3%), preserving the distribution of adverse outcomes, including postpartum hemorrhage, placental abruption, fetal growth restriction, and preterm delivery. In this study, anemia was present in 280 patients (90.3%). Overall, 195 patients (62.9%) experienced adverse pregnancy outcomes. Notably, among the subgroup with severe aplastic anemia (SAA, n=8), the rate of adverse pregnancy outcomes rose significantly to 75.0% (6/8). These findings underscored the high-risk nature of this cohort, particularly those with SAA, highlighting the critical need for accurate prediction tools to guide targeted antenatal interventions. The data for the variables evaluated in this study, including demographic and clinical characteristics, laboratory results, and treatment, were obtained from patient electronic medical records. Using multivariable LASSO regression, we selected the top five features for model construction: age, hemoglobin level, platelet count, neutrophil count, and the percentage of lymphocytes. Seven state-of-the-art machine learning algorithms were rigorously trained and tuned. The RF model emerged as optimal, demonstrating good discriminative ability both in internal validation (AUC: 0.765, 95% CI: 0.737–0.851) and, crucially, in external validation (AUC: 0.743, 95% CI: 0.723–0.814), confirming its generalizability across heterogeneous health care settings. Furthermore, calibration plots revealed agreement between the predicted probabilities and observed event rates, indicating reliability across risk strata. DCA indicated that the clinical implementation of the prognostic model could benefit pregnant women with AA. Conclusions To our knowledge, it's the world's largest cohort of pregnant women with AA to date. We demonstrated that the model could predict the risk of adverse pregnancy outcomes in patients with AA. The model will help clinicians identify pregnant women at high risk early and provide a basis for individualized patient treatment plans.

Given the maternal hypercoagulability during pregnancy, thrombophilia may increase the risk of adverse pregnancy outcomes (APOs). This retrospective case-control study aimed to assess whether low-molecular-weight heparin (LMWH) could improve APOs in women with protein S (PS) deficiency. We selected 35 pregnant women who were considered for potential PS deficiency, and 70 healthy pregnant women were randomly selected as the control group. Two or more consecutive miscarriages were more frequent in pregnant women with PS deficiency than in the control group (12/35 vs. 4/70, P = 0.0001). Ten pregnant women with PS deficiency conceived by in vitro fertilization-embryo transfer (IVF-ET), which was significantly higher than the number of controls who conceived by IVF-ET (4/70, P = 0.0012). All 20 women in the LMWH-treated group (P = 0.001) had live births, which were significantly higher than that in the LMWH-untreated group (8/15, 53.3

Cardiotocography (CTG) is a low-cost, non-invasive fetal health assessment technique used globally, especially in underdeveloped countries. However, it is currently mainly used to identify the fetus's current status (e.g., fetal acidosis or hypoxia), and the potential of CTG in predicting future adverse pregnancy outcomes has not been fully explored. We aim to develop an AI-based model that predicts biological age from CTG time series (named CTGage), then calculate the age gap between CTGage and actual age (named CTGage-gap), and use this gap as a new digital biomarker for future adverse pregnancy outcomes. The CTGage model is developed using 61,140 records from 11,385 pregnant women, collected at Peking University People's Hospital between 2018 and 2022. For model training, a structurally designed 1D convolutional neural network is used, incorporating distribution-aligned augmented regression technology. The CTGage-gap is categorized into five groups: < -21 days (underestimation group), -21 to -7 days, -7 to 7 days (normal group), 7 to 21 days, and > 21 days (overestimation group). We further defined the underestimation group and overestimation group together as the high-risk group. We then compare the incidence of adverse outcomes and maternal diseases across these groups. The average absolute error of the CTGage model is 10.91 days. When comparing the overestimation group with the normal group, premature infants incidence is 5.33

BACKGROUND:Preeclampsia is linked to fetal growth restriction and may have long-term implications for the offspring. Despite its significance, the fundamental mechanisms remain inadequately elucidated. The objective of this investigation was to undertake an untargeted lipidomics analysis of umbilical cord plasma, with the intention of investigating lipidomic profile alterations in newborns of mothers with preeclampsia and evaluating the associations between lipidomic patterns and neonatal physical parameters at birth. METHODS:25 newborns from mothers with preeclampsia (PE group) and 25 newborns from healthy mothers (control group) were involved in the present investigation. Untargeted lipidomics was performed using ultra-performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS) to contrast the lipid compositions present in umbilical cord plasma. Co-expression correlation analysis was performed to explore the relationships between lipidomic patterns and neonatal weight and length percentile at birth. RESULTS:Marked discrepancies in lipid metabolism profiles were detected in the comparison of the PE and control groups. In total, 364 separate lipids were noted, with AcylGlcADG (20:3-22:6-22:6) and GM3(d39:1) exhibiting the most significant decreases. Conversely, Cer-NS (d20:1-24:0) and DGTS (2:0-19:0) displayed the most significant increases. The primary lipid metabolic pathways altered in newborns from mothers with preeclampsia were enriched in choline and glycerophospholipid metabolic processes. Additionally, 20 distinct lipids exhibited significant associations with neonatal birth weight percentile between the two groups, while 21 distinct lipids showed significant associations with neonatal birth length percentile. CONCLUSIONS:Lipid profile disorders were identified in the umbilical cord plasma of infants born to mothers with preeclampsia, and the metabolic disturbances identified in this group correlated with neonatal physical parameters at birth. These findings suggest that lipidomic disorders in newborns from preeclamptic mothers may correlate with intrauterine growth outcomes.

OBJECTIVE:The study aimed to identify the risk factors of preeclampsia (PE) and establish a novel prediction model. STUDY DESIGN:A retrospective, single-center analysis was conducted using clinical data from 5099 pregnant women who gave birth at Peking University People's Hospital between June 2015 and December 2020 who had placental growth factor (PIGF) levels records at 13-20 + 6 gestation weeks. The participants were randomly divided into a training set (70%, n = 3569) and a validation set (30%, n = 1030), between which the consistency was checked, and the analysis was performed according to whether PE occurred during pregnancy. Factors with univariate logistic analysis outcome of p < 0.2 were incorporated into the multivariate logistic regression analysis model, then variable selection by stepwise regression with AIC as the criterion was executed to finally identify the variables used for modeling. The model's discriminative ability was assessed using the receiver operating characteristic (ROC) curve, and its calibration was evaluated through calibration curves and Hosmer-Lemesow test. In addition, decision curve analysis (DCA) was used for clinical net benefit appraisal. RESULTS:Logistic regression analysis identified nine risk factors for PE, including: maternal age (OR = 1.072, 95%CI = 1.025-1.120), parity(OR = 0.718,95%CI = 0.470-1.060), pre-pregnancy BMI (OR = 2.842,95%CI = 1.957-4.106), family hypertension history (OR = 3.604,95%CI = 2.433-5.264), pregestational diabetes mellitus(PGDM) (OR = 8.399, 95%CI = 4.138-15.883), pregnancy complicating nephropathy (OR = 7.931, 95% CI = 2.584-20.258),pregnancy complicating immune system disorders (OR = 3.134, 95% CI = 1.624-5.525), mean arterial pressure(MAP) at 11-13 + 6 gestational weeks (OR = 1.098, 95% CI = 1.078-1.119) and PIGF (OR = 0.647, 95% CI = 0.448-0.927) at 13-20 + 6 gestational weeks (P < 0.05). The restricted spline regression analysis (RCS) analysis results showed that PIGF and the risk of PE presented an approximately "L-shaped" relationship, with the risk of PE rising sharply with the decrease of PIGF when PIGF < 90 pg/ml, and little change with the increase of PIGF when PIGF > 90 pg/ml. A risk prediction model for PE during the first and second trimester was constructed based on the above selected 11 factors. The area under the ROC curve (AUC) for the model was 0.781(95%CI = 0.709-0.853), and the sensitivity and specificity at the optimal cut-off value (threshold probability) were 0.571 and 0.879 respectively. Chi-square of 9.616 and P value of 0.293 from Hosmer-Lemeshow test indicated that the model was well calibrated. Finally, the model showed good clinical net benefits in the threshold range of 0.03-0.3. CONCLUSION:The incidence of PE was associated with maternal age, pre-pregnancy weight and BMI, family hypertension history, PGDM, pregnancy complicating nephropathy, gestational complicating immune system disorders, blood pressure (systolic, diastolic, mean arterial pressure) at 11-13 + 6 gestational weeks, and PIGF at 13-20 + 6 gestational weeks. When PIGF < 90 pg/ml at 13-20 + 6 gestational week, the risk of PE increased significantly with the reduction of PIGF. The nomogram based on the above results was simpler and more practical in clinical application for PE predicting during the first and second trimester, and may provide an important reference for doctors and patients.

Long-term neurodevelopmental/socioemotional risks in small for gestational age (SGA) children lack robust evidence, especially maternal/neonatal predictors. The study aims to identify independent maternal and neonatal risk factors associated with atypical neurodevelopmental and socioemotional outcomes in SGA children. This longitudinal cohort study included 412 singleton SGA infants born at Peking University People’s Hospital in Beijing from January 2020 to December 2022. Participants underwent 24–36 months follow-up median 30 months, with neurodevelopmental and socioemotional outcomes evaluated using the Ages and Stages Questionnaires, Third Edition (ASQ-3) and Ages and Stages Questionnaires: Social-Emotional (ASQ: SE). These assessments categorized SGA children into normal/atypical development groups for both domains. Through assessment, there were 292 cases (70.9

Objective: This study investigated the association between paternal preconception paternal body mass index (BMI) categories and physical/neurodevelopmental outcomes in Chinese small-for-gestational-age (SGA) children. Methods: A prospective cohort study enrolled 412 singleton SGA infants born at Peking University People’s Hospital in 2020–2022. Fathers were stratified into underweight, normal-weight, overweight, and obese groups. Follow-up assessments at 24–36 months evaluated growth parameters weight, height, BMI Z-scores and neurodevelopment using the Ages and Stages Questionnaire-3 (ASQ-3) and ASQ: Social–Emotional (ASQ:SE). Multivariable regression was adjusted for paternal covariates. Results: In SGA offspring, paternal underweight correlated with lower birth weights vs. normal/obese paternal BMI and the highest severe SGA rates. Prospective monitoring identified elevated BMI Z-scores (ΔZ = +0.40) and 8.7-fold heightened obesity risk in the paternal obesity group versus normal-weight counterparts. Neurodevelopmental evaluations demonstrated gross motor impairments in both underweight (ΔZ = −0.22) and obese paternal subgroups (ΔZ = −0.25) compared with the normal-weight group, with the obesity cohort additionally exhibiting problem-solving deficiencies (ΔZ = −0.19). The paternal obesity group manifested three-fold greater likelihood of social–emotional delays than the normal-weight group. The underweight and obese paternal groups showed 3.46-fold and 2.73-fold higher probabilities of gross motor deficits, respectively, while obesity was linked to 3.27-fold elevated problem-solving impairment risk-all comparisons versus normal paternal BMI. Overweight status showed no significant links to growth or neurodevelopmental outcomes. Normal-weight fathers had lower risks of obesity and neurodevelopmental issues. Conclusions: This study revealed U-shaped paternal BMI–neurodevelopment links in SGA offspring. Paternal obesity raised offspring obesity/neurodevelopmental risks, while underweight linked to severe SGA and motor deficits, highlighting paternal weight optimization’s modifiable role.

In clinical practice, obstetricians use visual interpretation of fetal heart rate (FHR) to diagnose fetal conditions, but inconsistencies among interpretations can hinder accuracy. This study introduces MTU-Net3+, a deep learning model designed for automated, multi-task FHR analysis, aiming to improve diagnostic accuracy and efficiency. The proposed MTU-Net3 + was built upon the UNet3 + architecture, incorporating an encoder, a decoder, full-scale skip connections, and a deep supervision module, and further integrates a self-attention mechanism and bidirectional Long Short-Term Memory layers to enhance its performance. The MTU-Net3 + model accepts the preprocessed 20-minute FHR signals as input, outputting categorical probabilities and baseline values for each time point. The proposed MTU-Net3 + model was trained on a subset of a public database, and was tested on the remaining data of the public database and a private database. In the remaining public datasets, this model achieved F1 scores of 84.21

In clinical practice, obstetricians use visual interpretation of fetal heart rate (FHR) to diagnose fetal conditions, but inconsistencies among interpretations can hinder accuracy. This study introduces MTU-Net3+, a deep learning model designed for automated, multi-task FHR analysis, aiming to improve diagnostic accuracy and efficiency. The proposed MTU-Net3 + was built upon the UNet3 + architecture, incorporating an encoder, a decoder, full-scale skip connections, and a deep supervision module, and further integrates a self-attention mechanism and bidirectional Long Short-Term Memory layers to enhance its performance. The MTU-Net3 + model accepts the preprocessed 20-minute FHR signals as input, outputting categorical probabilities and baseline values for each time point. The proposed MTU-Net3 + model was trained on a subset of a public database, and was tested on the remaining data of the public database and a private database. In the remaining public datasets, this model achieved F1 scores of 84.21% for deceleration (F1.Dec) and 61.33% for acceleration (F1.Acc), with a Root Mean Square Baseline Difference (RMSD.BL) of 3.46 bpm, 0% of points with an absolute difference exceeding 15 bpm(D15bpm), a Synthetic Inconsistency Coefficient (SI) of 44.82%, and a Morphological Analysis Discordance Index (MADI) of 7.00%. On the private dataset, the model recorded an RMSD.BL of 1.37 bpm, 0% D15bpm, F1.Dec of 100%, F1.Acc of 87.50%, an SI of 12.20% and a MADI of 2.79%. The MTU-Net3 + model proposed in this study performed well in automated FHR analysis, demonstrating its potential as an effective tool in the field of fetal health assessment.

The aim was to analyze the pregnancy and neonatal outcomes of pregnant women with new- onset acute myeloid leukemia (AML) diagnosed during pregnancy. In this retrospective study 25 pregnant women who were diagnosed with new-onset AML during pregnancy from January 2010 to January 2021 were enrolled. A total of 4, 13 and 8 pregnant women with new-onset AML were diagnosed during the first, second, and third trimesters, respectively. Twelve of the 25 pregnant women underwent therapeutic abortion and 13 gave birth (9 preterm and 4 full-term newborns). The gestational age at initial clinical manifestations (13.4 ± 3.7 vs. 27.7 ± 5.6 weeks, P < 0.01) and diagnosis (16.9 ± 4.4 vs. 29.7 ± 5.5 weeks, P < 0.01) was lower in the pregnant women who underwent therapeutic abortion than in those who gave birth. Eighty-four percent (21/25) of the pregnant women with new-onset AML during pregnancy survived and were in remission and all the newborns were born alive. Three of the 13 newborns were exposed to chemotherapy, but no congenital malformations were observed. Eight newborns were admitted to the neonatal intensive care unit (NICU), and all recovered. The complete blood counts and biochemical examinations of the 8 newborns were normal. New-onset AML during an earlier stage of pregnancy may increase the risk of poor pregnancy outcomes. The neonatal outcomes of pregnant women with new-onset AML during pregnancy are good with proper treatment.

The purpose of this study is to improve the performance of existing OSA screening tools for pregnant women with machine learning algorithms. A total of 296 pregnant women who complained of snoring OSA were recruited to complete four traditional OSA screening questionnaires: Berlin, STOP, STOP-Bang questionnaires, and Epworth Sleepiness Scale. OSA status was confirmed using an overnight type III home sleep test. 76 of the participants repeated the procedure at different trimesters, generating a total of 402 records. The participants were randomly split into a training set (n = 207) and a test set (n = 89) in a 7:3 ratio. We applied a logistic regression model to build Mixture of Models for OSA screen (MoMOSA) based on demographic data and selected questions from all the questionnaires. Finally, we transformed the MoMOSA into a new questionnaire with a nomogram. MoMOSA, with 13 features, achieved the highest performance among the traditional questionnaires and built models.

Fetal heart rate (FHR) monitoring is the most widely used tool in clinics to assess fetal health. However, FHR with low-quality signals may somehow exaggerate the risk of the fetus suffering from acidemia, thus contributing to an increase in cesarean section rates. If there is an algorithm capable to identify and reject low-quality signals and then calculate heart rate parameters only on high-quality signals, inappropriate obstetric interventions may be greatly reduced. Currently, only the Signal Quality Index (SQI) is available for adults. When we applied SQI to fetal data, its performance drops dramatically. To fill the gap in the fetal signal quality index, we developed an easy-to-use Fetal heart rate Signal Quality Index (FSQI) in this paper. Firstly, we used a human-in-the-loop strategy to reduce the amount of data annotation effort. Secondly, we developed the FSQI algorithm oriented towards the fetus to identify low-quality signal segments. Further, we proposed a post-processing technique based on fine-grained recognition to identify low-quality signal segments more accurately. Finally, we applied the FSQI algorithm in combination with the existing FHR deceleration event detection algorithm to test the effectiveness of the algorithm. The results showed that the FSQI algorithm we developed achieved an overall accuracy of 99.8842% in signal quality classification, while also eliminating 94.92% of the incorrectly detected deceleration events of current state-of-the-art methods.

•This study focused on quality of discharge teaching, high-quality discharge teaching is conducive to patients continuing to complete rehabilitation and recovery at home after discharge and reducing readmission rate.•We analyzed the associated factors of discharge teaching, which would help the health care providers make specific intervention to improve quality of discharge teaching.

Background: To assess breastfeeding techniques and identify the relevant factors among postpartum women in hospital. Methods: A cross-sectional study was conducted from March, 2022 to April, 2022 at a general hospital in China. A total of 331 postpartum women were investigated using a questionnaire survey that included the LATCH (latch, audible swallowing, type of nipple, comfort, and hold) scoring system, a general information and behavior questionnaire, a breastfeeding knowledge questionnaire, and the Chinese version of the maternal breastfeeding evaluation scale. Multiple regression analysis was used to identify independent factors for in-hospital breastfeeding techniques. Results: The average score for breastfeeding techniques before discharge was 7.88. In the bivariate analysis, the factors found to be significantly associated with scores for breastfeeding technique were parity, number of births, participation in online antenatal classes during pregnancy, mastery of the hand expression technique, nipple cracking and satisfaction with breastfeeding (each p < 0.05). The result displayed parity, participation in online antenatal classes, and satisfaction with breastfeeding were included in a multiple linear regression model (p < 0.05). Conclusions: Although breastfeeding techniques prior to discharge are improving, more improvements can be made. Clinical medical staff should therefore pay particular attention to primiparas, postpartum women who did not participate in online antenatal courses during pregnancy, and postpartum women with a low satisfaction for breastfeeding. Measures that promote breastfeeding techniques, publicize online antenatal training courses, provide breastfeeding guidance shortly after delivery, and provide timely evaluation and targeted guidance should help to improve breastfeeding techniques before discharge and increase the exclusive breastfeeding rate.

•The study improves the understanding of the characteristics and management of deep vein ​thrombosis during early ​pregnancy.

Obstructive sleep apnea (OSA) is a common sleep-disordered breathing in pregnant population, which is associated with adverse perinatal outcomes, and may have long-term health consequences on both mothers and children. Currently, the vast majority of pregnant women are underdiagnosed due to the difficulties in extensively performing polysomnography, a gold standard in OSA diagnosis. So it is essential to seek other screening strategies and tools to accurately identify pregnant women with high risk of OSA to improve their perinatal outcomes. We reviewed the prevalence of OSA in pregnancy, screening status, screening timing, target population and recent advances in screening tools, to providing a theoretical basis for implementing the screening in this group.

目的 对先天性肝血管瘤的产前、产后超声特征及预后进行分析,提高先天性肝血管瘤的产前诊断率,为产前咨询提供依据.方法 对产前诊断 12 例胎儿肝血管瘤病例的超声特征及预后进行分析.结果 二维超声显示 12 例病例均为单发病灶,所有病灶和周围肝脏分界清,7 例为囊实性,5 例为实性回声.彩色及频谱多普勒显示 12 例病灶周围均可见明显的环状血流信号,病灶内部见丰富或不丰富血流信号,内探及动静脉瘘样频谱;其滋养血管来源于肝动脉并经肝静脉回流,肝动脉及受累肝静脉明显扩张,血流速度增快.随访显示 1 例在出生前病灶消退,1 例生后无消退,余 10 例在出生后病灶完全或部分消退.结论 胎儿肝血管瘤超声表现的多样性和复杂性构成其产前超声的特征性改变.大多数胎儿肝血管瘤出生后可以自愈,少数需要药物或手术治疗,预后良好.