Li Li

Prof. Li Li

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 May 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
QHQing Hua
Qing Hua
FYFengchun Yang
Fengchun Yang
YZYadan Zhou
Yadan Zhou
FSFenglian Shi
Fenglian Shi
XYXiaoyan You
Xiaoyan You
LLLi Li
Li Li
Background: Fetal growth restriction (FGR) is a common complication of preeclampsia. FGR in patients with preeclampsia increases the risk of neonatal-perinatal mortality and morbidity. However, previous prediction methods for FGR are class-biased or clinically unexplainable, which makes it difficult to apply to clinical practice, leading to a relative delay in intervention and a lack of effective treatments. Objective: The study aims to develop an auxiliary diagnostic model based on machine learning (ML) to predict the occurrence of FGR in patients with preeclampsia. Methods: This study used a retrospective case-control approach to analyze 38 features, including the basic medical history and peripheral blood laboratory test results of pregnant patients with preeclampsia, either complicated or not complicated by FGR. ML models were constructed to evaluate the predictive value of maternal parameter changes on preeclampsia combined with FGR. Multiple algorithms were tested, including logistic regression, light gradient boosting, random forest (RF), extreme gradient boosting, multilayer perceptron, naive Bayes, and support vector machine. The model performance was identified by the area under the curve (AUC) and other evaluation indexes. The Shapley additive explanations (SHAP) method was adopted to rank the feature importance and explain the final model for clinical application. Results: The RF model performed best in discriminative ability among the 7 ML models. After reducing features according to importance rank, an explainable final RF model was established with 9 features, including urinary protein quantification, gestational week of delivery, umbilical artery systolic-to-diastolic ratio, amniotic fluid index, triglyceride, D-dimer, weight, height, and maximum systolic pressure. The model could accurately predict FGR for 513 patients with preeclampsia (149 with FGR and 364 without FGR) in the training and testing dataset (AUC 0.83, SD 0.03) using 5-fold cross-validation, which was closely validated for 103 patients with preeclampsia (n=45 with FGR and n=58 without FGR) in an external dataset (AUC 0.82, SD 0.048). On the whole, urinary protein quantification, umbilical artery systolic-to-diastolic ratio, and gestational week of delivery exhibited the highest contributions to the model performance (c=0.45, 0.34, and 0.33) based on SHAP analysis. For specific individual patients, SHAP results reveal the protective and risk factors to develop FGR for interpreting the model’s clinical significance. Finally, the model has been translated into a convenient web page tool to facilitate its use in clinical settings. Conclusions: The study successfully developed a model that accurately predicts FGR development in patients with preeclampsia. The SHAP method captures highly relevant risk factors for model interpretation, alleviating concerns about the “black box” problem of ML techniques.

28 December 2023 in Placenta
Verified
Journal Article
Open access
QHQing Hua
Qing Hua
ZLZhe Li
Zhe Li
YZYadan Zhou
Yadan Zhou
YWYali Wang
Yali Wang
YYYangyang Yu
Yangyang Yu
LLLi Li
Li Li
Fetal growth restriction (FGR) can lead to fetal mental development abnormalities, malformations, and even intrauterine death. Defects in the trophoblasts at the maternal-fetal interface may contribute to FGR. However, the impact of trophoblasts on FGR is still not well understood. Therefore, the objective of this study is to characterize the heterogeneity of placental cells at the single-cell level and investigate the role of trophoblast subtypes in the pathogenesis of FGR at the cellular and molecular levels. Single-cell RNA sequencing was performed on the maternal side of placentas from two normal pregnant women and two pregnant women with FGR. Lentivirus transfection was used to establish a FN1 knockout model in trophoblast HTR-8-Svneo cells. The effect of FN1 knockout on cell migration and invasion of HTR-8-Svneo cells was assessed through wound healing and transwell assays. Nine cell types were annotated in 39,161 cells derived from single-cell RNA sequencing. The FGR group exhibited a decrease in the percentage of trophoblasts, especially in subtype of extravillous trophoblasts (EVTs). The expression of FN1 was reduced in trophoblasts and EVTs. Furthermore, the protein expression levels of FN1 in the placentas of FGR patients were significantly lower than those of normal pregnant women. The cell migration and invasion ability of HTR-8-Svneo cells were inhibited after the knockdown of FN1. The dysregulation of the trophoblast subtype-EVTs is involved in placental dysplasia related to FGR. The association between aberrant placental trophoblasts and reduced FN1 expression may contribute to insufficient remodeling of spiral arteries and the formation of FGR.

6 June 2026 in Reproductive Biology
Verified
Journal Article
Closed access
QHQing Hua
Qing Hua
XYXiaoyan You
Xiaoyan You
XYXujing Yan
Xujing Yan
YXYanping Xin
Yanping Xin
DZDongmei Zhang
Dongmei Zhang
LLLi Li
Li Li

29 December 2024 in JMIR Preprints
Verified
Preprint
Open access
QHQing Hua
Qing Hua
FYFengchun Yang
Fengchun Yang
YZYadan Zhou
Yadan Zhou
FSFenglian Shi
Fenglian Shi
XYXiaoyan You
Xiaoyan You
LLLi Li
Li Li
BACKGROUND Fetal growth restriction (FGR) is a common complication of preeclampsia. FGR in patients with preeclampsia increases the risk of neonatal-perinatal mortality and morbidity. However, previous prediction methods for FGR are class-biased or clinically unexplainable, which makes it difficult to apply to clinical practice, leading to a relative delay in intervention and a lack of effective treatments. OBJECTIVE The study aims to develop an auxiliary diagnostic model based on machine learning (ML) to predict the occurrence of FGR in patients with preeclampsia. METHODS This study used a retrospective case-control approach to analyze 38 features, including the basic medical history and peripheral blood laboratory test results of pregnant patients with preeclampsia, either complicated or not complicated by FGR. ML models were constructed to evaluate the predictive value of maternal parameter changes on preeclampsia combined with FGR. Multiple algorithms were tested, including logistic regression, light gradient boosting, random forest (RF), extreme gradient boosting, multilayer perceptron, naive Bayes, and support vector machine. The model performance was identified by the area under the curve (AUC) and other evaluation indexes. The Shapley additive explanations (SHAP) method was adopted to rank the feature importance and explain the final model for clinical application. RESULTS The RF model performed best in discriminative ability among the 7 ML models. After reducing features according to importance rank, an explainable final RF model was established with 9 features, including urinary protein quantification, gestational week of delivery, umbilical artery systolic-to-diastolic ratio, amniotic fluid index, triglyceride, D-dimer, weight, height, and maximum systolic pressure. The model could accurately predict FGR for 513 patients with preeclampsia (149 with FGR and 364 without FGR) in the training and testing dataset (AUC 0.83, SD 0.03) using 5-fold cross-validation, which was closely validated for 103 patients with preeclampsia (n=45 with FGR and n=58 without FGR) in an external dataset (AUC 0.82, SD 0.048). On the whole, urinary protein quantification, umbilical artery systolic-to-diastolic ratio, and gestational week of delivery exhibited the highest contributions to the model performance (c=0.45, 0.34, and 0.33) based on SHAP analysis. For specific individual patients, SHAP results reveal the protective and risk factors to develop FGR for interpreting the model’s clinical significance. Finally, the model has been translated into a convenient web page tool to facilitate its use in clinical settings. CONCLUSIONS The study successfully developed a model that accurately predicts FGR development in patients with preeclampsia. The SHAP method captures highly relevant risk factors for model interpretation, alleviating concerns about the “black box” problem of ML techniques.