Functional Networks of Reward and Punishment Processing and Their Molecular Profiles Predicting the Severity of Young Adult Drinking.

Alcohol misuse is associated with altered punishment and reward processing. Here, we investigated neural network responses to reward and punishment and the molecular profiles of the connectivity features predicting alcohol use severity in young adults. We curated the Human Connectome Project data and employed connectome-based predictive modeling (CPM) to examine how functional connectivity (FC) features during wins and losses are associated with alcohol use severity, quantified by Semi-Structured Assessment for the Genetics of Alcoholism, in 981 young adults. We combined the CPM findings and the JuSpace toolbox to characterize the molecular profiles of the network connectivity features of alcohol use severity. The connectomics predicting alcohol use severity appeared specific, comprising less than 0.12% of all features, including medial frontal, motor/sensory, and cerebellum/brainstem networks during punishment processing and medial frontal, fronto-parietal, and motor/sensory networks during reward processing. Spatial correlation analyses showed that these networks were associated predominantly with serotonergic and GABAa signaling. To conclude, a distinct pattern of network connectivity predicted alcohol use severity in young adult drinkers. These "neural fingerprints" elucidate how alcohol misuse impacts the brain and provide evidence of new targets for future intervention.

Sleep dysfunction mediates the relationship between hypothalamic-insula connectivity and anxiety-depression symptom severity bidirectionally in young adults.

BACKGROUND: The hypothalamus plays a crucial role in regulating sleep-wake cycle and motivated behavior. Sleep disturbance is associated with impairment in cognitive and affective functions. However, how hypothalamic dysfunction may contribute to inter-related sleep, cognitive, and emotional deficits remain unclear. METHODS: We curated the Human Connectome Project dataset and investigated how hypothalamic resting state functional connectivities (rsFC) were associated with sleep dysfunction, as evaluated by the Pittsburgh Sleep Quality Index (PSQI), cognitive performance, and subjective mood states in 687 young adults (342 women). Imaging data were processed with published routines and evaluated with a corrected threshold. We examined the inter-relationship amongst hypothalamic rsFC, PSQI score, and clinical measures with mediation analyses. RESULTS: In whole-brain regressions with age and drinking severity as covariates, men showed higher hypothalamic rsFC with the right insula in correlation with PSQI score. No clusters were identified in women at the same threshold. Both hypothalamic-insula rsFC and PSQI score were significantly correlated with anxiety and depression scores in men. Further, mediation analyses showed that PSQI score mediated the relationship between hypothalamic-insula rsFC and anxiety/depression symptom severity bidirectionally in men. CONCLUSIONS: Sleep dysfunction is associated with negative emotions and hypothalamic rsFC with the right insula, a core structure of the interoceptive circuits. Notably, anxiety-depression symptom severity and altered hypothalamic-insula rsFC are related bidirectionally by poor sleep quality. These findings are specific to men, suggesting potential sex differences in the neural circuits regulating sleep and emotional states that need to be further investigated.

Non-Contact Monitoring of Fetal Movement Using Abdominal Video Recording.

Fetal movement (FM) is an important indicator of fetal health. However, the current methods of FM detection are unsuitable for ambulatory or long-term observation. This paper proposes a non-contact method for monitoring FM. We recorded abdominal videos from pregnant women and then detected the maternal abdominal region within each frame. FM signals were acquired by optical flow color-coding, ensemble empirical mode decomposition, energy ratio, and correlation analysis. FM spikes, indicating the occurrence of FMs, were recognized using the differential threshold method. FM parameters including number, interval, duration, and percentage were calculated, and good agreement was found with the manual labeling performed by the professionals, achieving true detection rate, positive predictive value, sensitivity, accuracy, and F1_score of 95.75%, 95.26%, 95.75%, 91.40%, and 95.50%, respectively. The changes in FM parameters with gestational week were consistent with pregnancy progress. In general, this study provides a novel contactless FM monitoring technology for use at home.

A novel four-dimensional prediction model of soil heavy metal pollution: Geographical explanations beyond artificial intelligence "black box".

The current artificial intelligence (AI)-based prediction approaches of soil pollutants are inadequate in estimating the geospatial source-sink processes and striking a balance between the interpretability and accuracy, resulting in poor spatial extrapolation and generalization. In this study, we developed and tested a geographically interpretable four-dimensional AI prediction model for soil heavy metal (Cd) contents (4DGISHM) in Shaoguan city of China from 2016 to 2030. The 4DGISHM approach characterized spatio-temporal changes in source-sink processes of soil Cd by estimating spatio-temporal patterns and the effects of drivers and their interactions of soil Cd at local to regional scales using TreeExplainer-based SHAP and parallel ensemble AI algorithms. The results demonstrate that the prediction model achieved MSE and R2 values of 0.012 and 0.938, respectively, at a spatial resolution of 1 km. The predicted areas exceeding the risk control values for soil Cd across Shaoguan from 2022 to 2030 increased by 22.92% at the baseline scenario. By 2030, enterprise and transportation emissions (SHAP values 0.23 and 0.12 mg/kg, respectively) were the major drivers. The influence of driver interactions on soil Cd was marginal. Our approach surpasses the limitations of the AI "black box" by integrating spatio-temporal source-sink explanation and accuracy. This advancement enables geographically precise prediction and control of soil pollutants.

Sex differences in externalizing and internalizing traits and ventral striatal responses to monetary loss.

Ventral striatum (VS) processes rewarding and punishing stimuli. Women and men vary in externalizing and internalizing traits, which may influence neural responses to reward and punishment. To investigate sex differences in how individual traits influence VS responses to reward and punishment, we curated the data of the Human Connectome Project and identified 981 (473 men) subjects evaluated by the Achenbach Adult Self-Report Syndrome Scales. We processed the imaging data with published routines and extracted VS response (ß) to win and to loss vs. baseline in a gambling task for correlation with externalizing and internalizing symptom severity. Men vs. women showed more severe externalizing symptoms and higher VS response to monetary losses (VS-loss ß) but not to wins. Men but not women showed a significant, positive correlation between VS-loss ß and externalizing traits, and the sex difference was confirmed by a slope test. The correlations of VS-loss vs. externalizing and of VS-win vs. externalizing and those of VS-loss vs. externalizing and of VS-loss vs. internalizing traits both differed significantly in slope, confirming its specificity, in men. Further, the sex-specific relationship between VS-loss ß and externalizing trait did not extend to activities during exposure to negative emotion in the face matching task. To conclude, VS responses to loss but not to win and their correlation with externalizing rather than internalizing symptom severity showed sex differences in young adults. The findings highlight the relationship of externalizing traits and VS response to monetary loss and may have implications for psychological models of externalizing behaviors in men.

Dynamic risk prediction models for different subtypes of hypertensive disorders in pregnancy.

Background: Hypertensive disorders in pregnancy (HDP) are diseases that coexist with pregnancy and hypertension. The pathogenesis of this disease is complex, and different physiological and pathological states can develop different subtypes of HDP. Objective: To investigate the predictive effects of different variable selection and modeling methods on four HDP subtypes: gestational hypertension, early-onset preeclampsia, late-onset preeclampsia, and chronic hypertension complicated with preeclampsia. Methods: This research was a retrospective study of pregnant women who attended antenatal care and labored at Beijing Maternity Hospital, Beijing Haidian District Maternal and Child Health Hospital, and Peking University People's Hospital. We extracted maternal demographic data and clinical characteristics for risk factor analysis and included gestational week as a parameter in this study. Finally, we developed a dynamic prediction model for HDP subtypes by nonlinear regression, support vector machine, stepwise regression, and Lasso regression methods. Results: The AUCs of the Lasso regression dynamic prediction model for each subtype were 0.910, 0.962, 0.859, and 0.955, respectively. The AUC of the Lasso regression dynamic prediction model was higher than those of the other three prediction models. The accuracy of the Lasso regression dynamic prediction model was above 85%, and the highest was close to 92%. For the four subgroups, the Lasso regression dynamic prediction model had the best comprehensive performance in clinical application. The placental growth factor was tested significant (P < 0.05) only in the stepwise regression dynamic prediction model for early-onset preeclampsia. Conclusion: The Lasso regression dynamic prediction model could accurately predict the risk of four HDP subtypes, which provided the appropriate guidance and basis for targeted prevention of adverse outcomes and improved clinical care.

Dynamic gestational week prediction model for pre-eclampsia based on ID3 algorithm.

Pre-eclampsia (PE) is a type of hypertensive disorder during pregnancy, which is a serious threat to the life of mother and fetus. It is a placenta-derived disease that results in placental damage and necrosis due to systemic small vessel spasms that cause pathological changes such as ischemia and hypoxia and oxidative stress, which leads to fetal and maternal damage. In this study, four types of risk factors, namely, clinical epidemiology, hemodynamics, basic biochemistry, and biomarkers, were used for the initial selection of model parameters related to PE, and factors that were easily available and clinically recognized as being associated with a higher risk of PE were selected based on hospital medical record data. The model parameters were then further analyzed and screened in two subgroups: early-onset pre-eclampsia (EOPE) and late-onset pre-eclampsia (LOPE). Dynamic gestational week prediction model for PE using decision tree ID3 algorithm in machine learning. Performance of the model was: macro average (precision = 76%, recall = 73%, F1-score = 75%), weighted average (precision = 88%, recall = 89%, F1-score = 89%) and overall accuracy is 86%. In this study, the addition of the dynamic timeline parameter "gestational week" made the model more convenient for clinical application and achieved effective PE subgroup prediction.

Dynamic prediction model of fetal growth restriction based on support vector machine and logistic regression algorithm.

Background: This study analyzed the influencing factors of fetal growth restriction (FGR), and selected epidemiological and fetal parameters as risk factors for FGR. Objective: To establish a dynamic prediction model of FGR. Methods: This study used two methods, support vector machine (SVM) and multivariate logistic regression, to establish the prediction model of FGR at different gestational weeks. Results: At 20-24 weeks and 25-29 weeks of gestation, the effect of the multivariate Logistic method on model prediction was better. At 30-34 weeks of gestation, the prediction effect of FGR model using the SVM method is better. The ROC curve area was above 85%. Conclusions: The dynamic prediction model of FGR based on SVM and logistic regression is helpful to improve the sensitivity of FGR in pregnant women during prenatal screening. The establishment of prediction models at different gestational ages can effectively predict whether the fetus has FGR, and significantly improve the clinical treatment effect.

Combination of Feature Selection and Resampling Methods to Predict Preterm Birth Based on Electrohysterographic Signals from Imbalance Data.

Due to its high sensitivity, electrohysterography (EHG) has emerged as an alternative technique for predicting preterm labor. The main obstacle in designing preterm labor prediction models is the inherent preterm/term imbalance ratio, which can give rise to relatively low performance. Numerous studies obtained promising preterm labor prediction results using the synthetic minority oversampling technique. However, these studies generally overestimate mathematical models' real generalization capacity by generating synthetic data before splitting the dataset, leaking information between the training and testing partitions and thus reducing the complexity of the classification task. In this work, we analyzed the effect of combining feature selection and resampling methods to overcome the class imbalance problem for predicting preterm labor by EHG. We assessed undersampling, oversampling, and hybrid methods applied to the training and validation dataset during feature selection by genetic algorithm, and analyzed the resampling effect on training data after obtaining the optimized feature subset. The best strategy consisted of undersampling the majority class of the validation dataset to 1:1 during feature selection, without subsequent resampling of the training data, achieving an AUC of 94.5 ± 4.6%, average precision of 84.5 ± 11.7%, maximum F1-score of 79.6 ± 13.8%, and recall of 89.8 ± 12.1%. Our results outperformed the techniques currently used in clinical practice, suggesting the EHG could be used to predict preterm labor in clinics.

Regional identification of information flow termination of electrohysterographic signals: Towards understanding human uterine electrical propagation.

BACKGROUND AND OBJECTIVE: The uterine electrohysterogram (EHG) contains important information about electrical signal propagation which may be useful to monitor and predict the progress of pregnancy towards parturition. Directed information processing has the potential to be of use in studying EHG recordings. However, so far, there is no directed information-based estimation scheme that has been applied to investigating the propagation of human EHG recordings. To realize this, the approach of directed information and its reliability and adaptability should be scientifically studied. METHODS: We demonstrated an estimation scheme of directed information to identify the spatiotemporal relationship between the recording channels of EHG signal and assess the algorithm reliability initially using simulated data. Further, a regional identification of information flow termination (RIIFT) approach was developed and applied for the first time to extant multichannel EHG signals to reveal the terminal zone of propagation of the electrical activity associated with uterine contraction. RIIFT operates by estimating the pairwise directed information between neighboring EHG channels and identifying the location where there is the strongest inward flow of information. The method was then applied to publicly-available experimental data obtained from pregnant women with the use of electrodes arranged in a 4-by-4 grid. RESULTS: Our results are consistent with the suggestions from the previous studies with the added identification of preferential sites of excitation termination - within the estimated area, the direction of surface action potential propagation towards the medial axis of uterus during contraction was discovered for 72.15% of the total cases, demonstrating that our RIIFT method is a potential tool to investigate EHG propagation for advancing our understanding human uterine excitability. CONCLUSIONS: We developed a new approach and applied it to multichannel human EHG recordings to investigate the electrical signal propagation involved in uterine contraction. This provides an important platform for future studies to fill knowledge gaps in the spatiotemporal patterns of electrical excitation of the human uterus.

Assessment of Features between Multichannel Electrohysterogram for Differentiation of Labors.

Electrohysterogram (EHG) is a promising method for noninvasive monitoring of uterine electrical activity. The main purpose of this study was to characterize the multichannel EHG signals to distinguish between term delivery and preterm birth, as well as deliveries within and beyond 24 h. A total of 219 pregnant women were grouped in two ways: (1) term delivery (TD), threatened preterm labor (TPL) with the outcome of preterm birth (TPL_PB), and TPL with the outcome of term delivery (TPL_TD); (2) EHG recording time to delivery (TTD) ≤ 24 h and TTD > 24 h. Three bipolar EHG signals were analyzed for the 30 min recording. Six EHG features between multiple channels, including multivariate sample entropy, mutual information, correlation coefficient, coherence, direct partial Granger causality, and direct transfer entropy, were extracted to characterize the coupling and information flow between channels. Significant differences were found for these six features between TPL and TD, and between TTD ≤ 24 h and TTD > 24 h. No significant difference was found between TPL_PB and TPL_TD. The results indicated that EHG signals of TD were more regular and synchronized than TPL, and stronger coupling between multichannel EHG signals was exhibited as delivery approaches. In addition, EHG signals propagate downward for the majority of pregnant women regardless of different labors. In conclusion, the coupling and propagation features extracted from multichannel EHG signals could be used to differentiate term delivery and preterm birth and may predict delivery within and beyond 24 h.

Recognition of uterine contractions with electrohysterogram and exploring the best electrode combination.

BACKGROUND: As an essential indicator of labour and delivery, uterine contraction (UC) can be detected by manual palpation, external tocodynamometry and internal uterine pressure catheter. However, these methods are not applicable for long-term monitoring. OBJECTIVE: This paper aims to recognize UCs with electrohysterogram (EHG) and find the best electrode combination with fewer electrodes. METHODS: 112 EHG recordings were collected by our bespoke device in our study. Thirteen features were extracted from EHG segments of UC and non-UC. Four classifiers of the decision tree, support vector machine (SVM), artificial neural network, and convolutional neural network were established to identify UCs. The optimal classifier among them was determined by comparing their classification results. The optimal classifier was applied to evaluate all the possible electrode combinations with one to eight electrodes. RESULTS: The results showed that SVM achieved the best classification capability. With SVM, the combination of electrodes on the right part of the uterine fundus and around the uterine body's median axis achieved the overall best performance. CONCLUSIONS: The optimal electrode combination with fewer electrodes was confirmed to improve the clinical application for long-term monitoring of UCs.

Risk prevention of different forms of gestational diabetes mellitus based on energy metabolism prior to diagnosis.

BACKGROUND: Gestational diabetes mellitus (GDM) is a metabolic disease that seriously endangers the health of mothers and children. It is important to monitor GDM in real-time before diagnosis and to prevent it effectively. OBJECTIVE: GDM was divided into the second trimester diagnosed diabetes mellitus (GDM_24) and the third trimester diagnosed diabetes mellitus (GDM_30). The risk prediction of two types of GDM was performed in normal pregnant women at 11-13 and 16-19 weeks of pregnancy, respectively. METHODS: By stages, the K-W test was used to analyze the differences between basic information and energy metabolism factors, and multiple logistic regression was used to analyze the risk of energy metabolism factors and to correct the confounders with significant differences. RESULTS: For the GDM_24 group, each additional unit of oxygen consumption (VO2), carbon dioxide production, and resting energy expenditure (REE) increased the risk by 2.4%, 3.5%, 0.4%, and 2.1%, 2.6%, and 0.3%, respectively, at 11-13 and 16-19 weeks of pregnancy. For the GDM_30 group, each additional unit of VO2 and REE was associated with an increased risk of 2.3% and 0.3%, respectively, at 16-19 weeks of pregnancy. CONCLUSION: The risk of GDM_30 only appeared in pregnant women during 16-19 weeks of pregnancy, which may indicate that GDM_24 and GDM_30 have different pathogenesis.

Evaluation of VDT-Induced Visual Fatigue by Automatic Detection of Blink Features.

This study evaluates the progression of visual fatigue induced by visual display terminal (VDT) using automatically detected blink features. A total of 23 subjects were recruited to participate in a VDT task, during which they were required to watch a 120-min video on a laptop and answer a questionnaire every 30 min. Face video recordings were captured by a camera. The blinking and incomplete blinking images were recognized by automatic detection of the parameters of the eyes. Then, the blink features were extracted including blink number (BN), mean blink interval (Mean_BI), mean blink duration (Mean_BD), group blink number (GBN), mean group blink interval (Mean_GBI), incomplete blink number (IBN), and mean incomplete blink interval (Mean_IBI). The results showed that BN and GBN increased significantly, and that Mean_BI and Mean_GBI decreased significantly over time. Mean_BD and Mean_IBI increased and IBN decreased significantly only in the last 30 min. The blink features automatically detected in this study can be used to evaluate the progression of visual fatigue.

Uterus Modeling From Cell to Organ Level: Towards Better Understanding of Physiological Basis of Uterine Activity.

The relatively limited understanding of the physiology of uterine activation prevents us from achieving optimal clinical outcomes for managing serious pregnancy disorders such as preterm birth or uterine dystocia. There is increasing awareness that multi-scale computational modeling of the uterus is a promising approach for providing a qualitative and quantitative description of uterine physiology. The overarching objective of such approach is to coalesce previously fragmentary information into a predictive and testable model of uterine activity that, in turn, informs the development of new diagnostic and therapeutic approaches to these pressing clinical problems. This article assesses current progress towards this goal. We summarize the electrophysiological basis of uterine activation as presently understood and review recent research approaches to uterine modeling at different scales from single cell to tissue, whole organ and organism with particular focus on transformative data in the last decade. We describe the positives and limitations of these approaches, thereby identifying key gaps in our knowledge on which to focus, in parallel, future computational and biological research efforts.

Assessment of Dispersion and Bubble Entropy Measures for Enhancing Preterm Birth Prediction Based on Electrohysterographic Signals.

One of the remaining challenges for the scientific-technical community is predicting preterm births, for which electrohysterography (EHG) has emerged as a highly sensitive prediction technique. Sample and fuzzy entropy have been used to characterize EHG signals, although they require optimizing many internal parameters. Both bubble entropy, which only requires one internal parameter, and dispersion entropy, which can detect any changes in frequency and amplitude, have been proposed to characterize biomedical signals. In this work, we attempted to determine the clinical value of these entropy measures for predicting preterm birth by analyzing their discriminatory capacity as an individual feature and their complementarity to other EHG characteristics by developing six prediction models using obstetrical data, linear and non-linear EHG features, and linear discriminant analysis using a genetic algorithm to select the features. Both dispersion and bubble entropy better discriminated between the preterm and term groups than sample, spectral, and fuzzy entropy. Entropy metrics provided complementary information to linear features, and indeed, the improvement in model performance by including other non-linear features was negligible. The best model performance obtained an F1-score of 90.1 ± 2% for testing the dataset. This model can easily be adapted to real-time applications, thereby contributing to the transferability of the EHG technique to clinical practice.

Inherited unbalanced translocation (4p16.3p15.32 duplication/8p23.3p23.2deletion) in the four generation pedigree with intellectual disability/developmental delay.

Chromosomal copy number variants (CNVs) are an important cause of congenital malformations and mental retardation. This study reported a large Chinese pedigree (4-generation, 76 members) with mental retardation caused by chromosome microduplication/microdeletion. There were 10 affected individuals with intellectual disability (ID), developmental delay (DD), and language delay phenotypes. SNP array analysis was performed in the proband and eight patients and found all of them had a microduplication of chromosome 4p16.3p15.2 and a microdeletion of chromosome 8p23.3p23.2. The high-resolution karyotyping analysis of the proband had unbalanced karyotype [46, XY, der(8)t(4;8)(p15.2;p23.1)mat], his mother had balanced karyotype [46, XX, t(4;8) (p15.2;p23.1)], whereas his father had normal karyotype [46,XY]. Fluorescence in situ hybridization (FISH) analysis further confirmed that the proband's mother had a balanced translocation between the short arm terminal segment of chromosome 4 and the short arm end segment of chromosome 8, ish t(4;8)(8p + ,4q + ;4p + ,8q +). In conclusion, all the patients inherited chromosomes 8 with 4p16.3p15.2 duplication and 8p23.3p23.2 deletion from their parental balanced translocation, which might be the cause of the prevalence of intellectual disability. Meanwhile, 8p23.3p23.2 deletion, rather than 4p16.3p15.2 duplication might cause a more severe clinical syndrome.

Evaluation of eyestrain with vertical electrooculogram.

BACKGROUND AND OBJECTIVE: Eyestrain has been increasingly severe in our lives and works as the progress of computers and smartphones. Evaluating eyestrain helps to prevent and relieve eyestrain. Our study aimed to evaluate eyestrain by analyzing vertical electrooculogram (VEOG). METHODS: 21 young subjects were asked to watch a video on the computer for a totally 120 minutes each, during which the VEOG signal was acquired using only three electrodes, and the questionnaire was answered every 30 minutes. The VEOG signal was divided into four 30-minute phases, from which VEOG signal power probability (VEOGSPP) features and blink features were extracted. The blink features include the changes of blink number (BN), group blinks number (GBN) and ratio (GBR), mean blink amplitude (Mean_BA) and duration (Mean_BD), mean blink duration at 50% (Mean_BD50), mean closing duration (Mean_CD) and opening duration (Mean_OD), mean opening duration at early 50% (Mean_ODE50) and late 50% (Mean_ODL50), mean blink maximum rising slope (Mean_BMRS) and falling slope (Mean_BMFS). RESULTS: The results showed that the VEOGSPP in the high-frequency band (0.8-6.3Hz), BN, GBN, and GBR significantly increased while the VEOGSPP in the low-frequency band (0.1-0.4Hz), Mean_BA, Mean_OD, and Mean_ODL50 significantly decreased with eyestrain (P<0.05). CONCLUSIONS: In conclusion, eyestrain induced by watching videos for a long time could be well evaluated by analyzing the VEOG signal.

Gestational diabetes mellitus prediction model: A risk factors analysis of pregnant women with gestational diabetes mellitus but have normal oral glucose tolerance test results in the second trimester of pregnancy.

BACKGROUND: Oral glucose tolerance test (OGTT) is a standard for the diagnosis of gestational diabetes mellitus (GDM). However, clinically, some cases with normal results were diagnosed as GDM in the third trimester. OBJECTIVE: To establish a risk model based on energy metabolism, epidemiology, and biochemistry that could predict the GDM pregnant women with normal OGTT results in the second trimester. METHODS: Qualitative and quantitative data were analyzed to find out the risk factors, and the binary logistic backward LR regression was used to establish the prediction model of each factor and comprehensive factor, respectively. RESULTS: The risk factors including the rest energy expenditure per kilogram of body weight, oxygen consumption per kilogram of body weight, if more than the weight gain criteria of the Institute of Medicine, the increase of body mass index between the second trimester and pre-pregnancy, and fasting blood glucose. By comparison, the comprehensive model had the best prediction performance, indicating that 85% of high-risk individuals were correctly classified. CONCLUSION: Energy metabolism, epidemiology, and biochemistry had better recognition ability for the GDM pregnant women with normal OGTT results in the second trimester. The addition of metabolic factors in the second trimester also improved the overall prediction performance.

Prediction of hypertensive disorders in pregnancy based on placental growth factor.

BACKGROUND: The prediction of hypertensive disorders in pregnancy (HDP) mainly involves various aspects such as maternal characteristics and biomarkers. OBJECTIVE: We aimed to study the effect of the HDP prediction model with or without placental growth factor (PlGF). METHODS: This study used maternal factors and PlGF, and standardized the data uniformly. At 12-20 weeks, the comprehensive comparison of model quality with or without PlGF was conducted by logistic regression. RESULTS: The area under curve and the model accuracy of the model with PlGF were higher than those of the model without PlGF. The accuracy of the model with PlGF was above 90%. CONCLUSIONS: Adding PlGF to the model for predicting HDP improved the accuracy and effectiveness of the model. This study confirmed the predictive performance of PlGF.