Honglei Liu

Honglei Liu

Auto-generated profile, based on publicly available information

Honglei Liu

School of Biomedical Engineering, Capital Medical University, Beijing, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
12 January 2021 in Journal of Medical Internet Research
Verified
Journal Article
Open access
HLHonglei Liu
Honglei Liu
ZZZhiqiang Zhang
Zhiqiang Zhang
YXYan Xu
Yan Xu
NWNi Wang
Ni Wang
YHYanqun Huang
Yanqun Huang
HCHui Chen
Hui Chen
Background: Liver cancer is a substantial disease burden in China. As one of the primary diagnostic tools for detecting liver cancer, dynamic contrast-enhanced computed tomography provides detailed evidences for diagnosis that are recorded in free-text radiology reports. Objective: The aim of our study was to apply a deep learning model and rule-based natural language processing (NLP) method to identify evidences for liver cancer diagnosis automatically. Methods: We proposed a pretrained, fine-tuned BERT (Bidirectional Encoder Representations from Transformers)-based BiLSTM-CRF (Bidirectional Long Short-Term Memory-Conditional Random Field) model to recognize the phrases of APHE (hyperintense enhancement in the arterial phase) and PDPH (hypointense in the portal and delayed phases). To identify more essential diagnostic evidences, we used the traditional rule-based NLP methods for the extraction of radiological features. APHE, PDPH, and other extracted radiological features were used to design a computer-aided liver cancer diagnosis framework by random forest. Results: The BERT-BiLSTM-CRF predicted the phrases of APHE and PDPH with an F1 score of 98.40% and 90.67%, respectively. The prediction model using combined features had a higher performance (F1 score, 88.55%) than those using APHE and PDPH (84.88%) or other extracted radiological features (83.52%). APHE and PDPH were the top 2 essential features for liver cancer diagnosis. Conclusions: This work was a comprehensive NLP study, wherein we identified evidences for the diagnosis of liver cancer from Chinese radiology reports, considering both clinical knowledge and radiology findings. The BERT-based deep learning method for the extraction of diagnostic evidence achieved state-of-the-art performance. The high performance proves the feasibility of the BERT-BiLSTM-CRF model in information extraction from Chinese radiology reports. The findings of our study suggest that the deep learning–based method for automatically identifying evidences for diagnosis can be extended to other types of Chinese clinical texts.

28 August 2020 in IEEE Access
Verified
Journal Article
Open access
HLHonglei Liu
Honglei Liu
YXYan Xu
Yan Xu
ZZZhiqiang Zhang
Zhiqiang Zhang
NWNi Wang
Ni Wang
YHYanqun Huang
Yanqun Huang
HCHui Chen
Hui Chen
Despite the rapid development of natural language processing (NLP) implementation in electronic medical records (EMRs), Chinese EMRs processing remains challenging due to the limited corpus and specific grammatical characteristics, especially for radiology reports. In this study, we designed an NLP pipeline for the direct extraction of clinically relevant features from Chinese radiology reports, which is the first key step in computer-aided radiologic diagnosis. The pipeline was comprised of named entity recognition, synonyms normalization, and relationship extraction to finally derive the radiological features composed of one or more terms. In named entity recognition, we incorporated lexicon into deep learning model bidirectional long short-term memory-conditional random field (BiLSTM-CRF), and the model finally achieved an F1 score of 93.00%. With the extracted radiological features, least absolute shrinkage and selection operator and machine learning methods (support vector machine, random forest, decision tree, and logistic regression) were used to build the classifiers for liver cancer prediction. For liver cancer diagnosis, random forest had the highest predictive performance in liver cancer diagnosis (F1 score 86.97%, precision 87.71%, and recall 86.25%). This work was a comprehensive NLP study focusing on Chinese radiology reports and the application of NLP in cancer risk prediction. The proposed NLP pipeline for the radiological feature extraction could be easily implemented in other kinds of Chinese clinical texts and other disease predictive tasks.

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.

22 October 2021 in Frontiers in Psychiatry
Verified
Journal Article
Open access
NWNi Wang
Ni Wang
MWMuyu Wang
Muyu Wang
XXXin Xin
Xin Xin
TZTong Zhang
Tong Zhang
HWHao Wu
Hao Wu
HLHonglei Liu
Honglei Liu
Background: Mental disorder of people living with HIV (PLWH) has become a common and increasing worldwide public health concern. We aimed to explore the relationship between anxiety, depression, and sleep disturbance for PLWH from a network perspective.Methods: The network model featured 28 symptoms on the Hospital Anxiety and Depression scale questionnaire and Pittsburgh Sleep Quality Index questionnaire in a sample of 4,091 HIV-infected persons. Node predictability and strength were computed to assess the importance of items. We estimated and compared 20 different networks based on subpopulations such as males and females to analyze similarities and differences in network structure, connections, and symptoms.Results: Several consistent patterns and interesting differences emerged across subgroups. Pertaining to the connections, some symptoms such as S12–S13 (“sleepy”—“without enthusiasm”) shown a strong positive relationship, indicating that feeling sleepy was a good predictor of lacking enthusiasm, and vice versa. While other symptoms, such as A3–D3 (“worried”—“cheerful”), were negatively related in all networks, revealing that nodes A3 and D3 were bridge symptoms between anxiety and depression. Across all subgroups, the most central symptom was A7 “panic” and S2 “awake”, which had the greatest potential to affect an individual's mental state. While S3 “bathroom” and S5 “cough or snore” shown consistent lower node importance, which would be of limited therapeutic use.Conclusions: Mental conditions of PLWH varied considerably among subgroups, inspiring psychiatrists and clinicians that personalized invention to a particular subgroup was essential and might be more effective during treatment than adopting the same therapeutic schedule.

8 February 2018 in BioMed Research International
Verified
Journal Article
Open access
PDF file
HLHonglei Liu
Honglei Liu
NWNi Wang
Ni Wang
WCWei Chen
Wei Chen
WLWenyan Liu
Wenyan Liu
SWShiping Wang
Shiping Wang
HCHui Chen
Hui Chen
Chronic obstructive pulmonary disease (COPD), pneumonia, asthma, and lung cancer are four common respiratory diseases that impose a substantial economic burden on both patients and government in China. The objective of our study is to analyze the temporal trends of several clinical tracking metrics for hospitalization regarding these diseases. Hospital discharge data of 54 hospitals for the period 2005–2015 were derived from the Health and Family Planning Commission in Northeast China. The age-adjusted rate of discharge for the four respiratory diseases increased significantly (COPD, pneumonia, asthma: P trend < .001; lung cancer: P trend = .046). The mean LOS for the four diseases all showed a significant decline (P trend < .001), whereas the mean charge per stay and aggregate charge followed an upward trend over time (P trend < .001). There was a clear upward trend for the readmission rate for asthma patients (P trend = .001), while the trend for COPD patients was unclear (P trend = .224). Age-adjusted discharge rates, LOS, and charges for hospitalization regarding several common respiratory diseases in China showed different patterns of change over the past decade. Our results should aid government and administrators in making informed decisions about the management and treatment of respiratory diseases.

23 July 2021 in JMIR Medical Informatics
Verified
Journal Article
Open access
YHYanqun Huang
Yanqun Huang
NWNi Wang
Ni Wang
ZZZhiqiang Zhang
Zhiqiang Zhang
HLHonglei Liu
Honglei Liu
XFXiaolu Fei
Xiaolu Fei
HCHui Chen
Hui Chen
Background: The secondary use of structured electronic medical record (sEMR) data has become a challenge due to the diversity, sparsity, and high dimensionality of the data representation. Constructing an effective representation for sEMR data is becoming more and more crucial for subsequent data applications. Objective: We aimed to apply the embedding technique used in the natural language processing domain for the sEMR data representation and to explore the feasibility and superiority of the embedding-based feature and patient representations in clinical application. Methods: The entire training corpus consisted of records of 104,752 hospitalized patients with 13,757 medical concepts of disease diagnoses, physical examinations and procedures, laboratory tests, medications, etc. Each medical concept was embedded into a 200-dimensional real number vector using the Skip-gram algorithm with some adaptive changes from shuffling the medical concepts in a record 20 times. The average of vectors for all medical concepts in a patient record represented the patient. For embedding-based feature representation evaluation, we used the cosine similarities among the medical concept vectors to capture the latent clinical associations among the medical concepts. We further conducted a clustering analysis on stroke patients to evaluate and compare the embedding-based patient representations. The Hopkins statistic, Silhouette index (SI), and Davies-Bouldin index were used for the unsupervised evaluation, and the precision, recall, and F1 score were used for the supervised evaluation. Results: The dimension of patient representation was reduced from 13,757 to 200 using the embedding-based representation. The average cosine similarity of the selected disease (subarachnoid hemorrhage) and its 15 clinically relevant medical concepts was 0.973. Stroke patients were clustered into two clusters with the highest SI (0.852). Clustering analyses conducted on patients with the embedding representations showed higher applicability (Hopkins statistic 0.931), higher aggregation (SI 0.862), and lower dispersion (Davies-Bouldin index 0.551) than those conducted on patients with reference representation methods. The clustering solutions for patients with the embedding-based representation achieved the highest F1 scores of 0.944 and 0.717 for two clusters. Conclusions: The feature-level embedding-based representations can reflect the potential clinical associations among medical concepts effectively. The patient-level embedding-based representation is easy to use as continuous input to standard machine learning algorithms and can bring performance improvements. It is expected that the embedding-based representation will be helpful in a wide range of secondary uses of sEMR data.