Lan Wei

Lan Wei

Auto-generated profile, based on publicly available information

Lan Wei

Information Center, Xuanwu Hospital of Capital Medical University, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
6 January 2022 in Journal of Medical Internet Research
Verified
Journal Article
Open access
NWNi Wang
Ni Wang
MWMuyu Wang
Muyu Wang
YZYang Zhou
Yang Zhou
HLHonglei Liu
Honglei Liu
LWLan Wei
Lan Wei
HCHui Chen
Hui Chen
Background: Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. Objective: We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems. Methods: Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k–nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points—at admission, on Day 7, and at discharge—to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k–nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison. Results: With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission. Conclusions: For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance.

23 December 2022
Verified
Conference Paper
Open access
RWRong Wu
Rong Wu
HHHuifang Huang
Huifang Huang
BLBeibei Liu
Beibei Liu
JGJianhua Gao
Jianhua Gao
LWLan Wei
Lan Wei
XFXiaolu Fei
Xiaolu Fei
It is a tedious task to summarize the diagnostic impressions from the image description of vascular ultrasound, and it is more possible to make mistakes because it requires rich experience and clear logical thinking ability of ultrasound radiologists. In this paper, we explore the use of a LSTM-RNN-Attention (LRA) model to automatically generate diagnostic impressions based on the description of vascular ultrasound images, and evaluate the performance of the model by ROUGE scores. Also, the paper compares this model with pointer generation network (PGN) and basic encoder-decoder (ED) model. The LRA Model achieved a ROUGE-1 score of 26.353, a ROUGE-2 score of 11.587, a ROUGE-L score of 26.168, each score was almost 8 times higher than it of (PGN). The results showed that LRA model presented better performance than these most commonly used models in the field of chinses radiological text summarization and is useful in clinical practice.

20 July 2026 in JMIR Preprints
Verified
Preprint
Open access
YLYichen Li
Yichen Li
ZXZhongrang Xie
Zhongrang Xie
MWMuyu Wang
Muyu Wang
XXXin Xin
Xin Xin
JHJun Huang
Jun Huang
HCHui Chen
Hui Chen
BACKGROUND Heart failure (HF) is a severe and progressive clinical syndrome associated with high mortality, frequent hospitalizations, and substantial healthcare burden worldwide. Identification of critically ill HF patients and accurate assessment of cardiac function grade at discharge are essential for timely intervention, risk stratification, and optimization of post-discharge management. OBJECTIVE This study aims to develop and validate KA-STNet, an interpretable knowledge-augmented spatiotemporal framework for in-hospital mortality prediction and discharge cardiac function grade prediction in patients with HF. METHODS To address the heterogeneity of EMR data, KA-STNet adopts distinct graph representation strategies for static and time-series data. For static data, it integrates external medical knowledge with data-driven statistical associations to learn knowledge-augmented patient representations. For time-series data, it employs a spatiotemporal graph neural network to capture spatial dependencies among laboratory indicators and temporal dynamics in longitudinal laboratory sequences, while incorporating patient-level static representations to guide inter-laboratory association modeling. Interpretability analyses based on Shapley additive explanations (SHAP), GNNExplainer, and Leiden community detection are conducted to identify key predictive factors and clinically meaningful laboratory communities. RESULTS KA-STNet outperformed all baseline models across all evaluated tasks. In the in-hospital mortality risk prediction task, it attained a mean AUROC of 0.968 on the local dataset and 0.897 on the public dataset. In the discharge cardiac function grade prediction task, KA-STNet achieved a mean AUROC of 0.925. Anemia-related variables, indicators of renal function and infection-related markers were identified as important contributors to adverse outcome prediction in patients with HF. Leiden community detection further revealed meaningful multi-organ interaction patterns. Adverse outcomes were associated with network reorganization involving acid–base/electrolyte, inflammatory, and hepatic indicators. CONCLUSIONS KA-STNet provides an effective and interpretable framework for predicting HF outcomes using heterogeneous EMRs. These findings support the value of combining knowledge-augmented static representation learning with spatiotemporal dependency modeling for interpretable prediction of clinically relevant HF outcomes. CLINICALTRIAL Not applicable. This was a retrospective study based on electronic medical records and was not a clinical trial. INTERNATIONAL REGISTERED REPORT RR2-

15 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
XFXinyan Fan
Xinyan Fan
WLWei Lan
Wei Lan
TZTao Zou
Tao Zou
CTChih-Ling Tsai
Chih-Ling Tsai
In this article, we propose the mutual influence regression model (MIR) to establish the relationship between the mutual influence matrix of actors and a set of similarity matrices induced by their associated attributes. This model is able to explain the heterogeneous structure of the mutual influence matrix by extending the commonly used spatial autoregressive model while allowing it to change with time. To facilitate making inferences with MIR, we establish parameter estimation, weight matrices selection and model testing. Specifically, we employ the quasi-maximum likelihood estimation method to estimate unknown regression coefficients, and demonstrate that the resulting estimator is asymptotically normal without imposing the normality assumption and while allowing the number of similarity matrices to diverge. In addition, an extended BIC-type criterion is introduced for selecting relevant matrices from the divergent number of similarity matrices. To assess the adequacy of the proposed model, we further propose an influence matrix test and develop a novel approach in order to obtain the limiting distribution of the test. Finally, we extend the model to accommodate endogenous weight matrices, exogenous covariates, and both individual and time fixed effects, to broaden the usefulness of MIR. The simulation studies support our theoretical findings, and a real example is presented to illustrate the usefulness of the proposed MIR model.

26 May 2021 in JMIR Preprints
Verified
Preprint
Open access
NWNi Wang
Ni Wang
MWMuyu Wang
Muyu Wang
YZYang Zhou
Yang Zhou
HLHonglei Liu
Honglei Liu
LWLan Wei
Lan Wei
HCHui Chen
Hui Chen
BACKGROUND Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. OBJECTIVE We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems. METHODS Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k–nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points—at admission, on Day 7, and at discharge—to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k–nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison. RESULTS With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission. CONCLUSIONS For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance.