Yanming Li

Yanming Li

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
13 September 2022 in JMIR Medical Informatics
Verified
Journal Article
Open access
YYYuncui Yu
Yuncui Yu
QZQiuye Zhao
Qiuye Zhao
WCWang Cao
Wang Cao
XWXiaochuan Wang
Xiaochuan Wang
YLYanming Li
Yanming Li
XWXiaoling Wang
Xiaoling Wang
Background: Severe drug hypersensitivity reactions (DHRs) refer to allergic reactions caused by drugs and usually present with severe skin rashes and internal damage as the main symptoms. Reporting of severe DHRs in hospitals now solely occurs through spontaneous reporting systems (SRSs), which clinicians in charge operate. An automatic identification system scrutinizes clinical notes and reports potential severe DHR cases. Objective: The goal of the research was to develop an automatic identification system for mining severe DHR cases and discover more DHR cases for further study. The proposed method was applied to 9 years of data in pediatrics electronic health records (EHRs) of Beijing Children’s Hospital. Methods: The phenotyping task was approached as a document classification problem. A DHR dataset containing tagged documents for training was prepared. Each document contains all the clinical notes generated during 1 inpatient visit in this data set. Document-level tags correspond to DHR types and a negative category. Strategies were evaluated for long document classification on the openly available National NLP Clinical Challenges 2016 smoking task. Four strategies were evaluated in this work: document truncation, hierarchy representation, efficient self-attention, and key sentence selection. In-domain and open-domain pretrained embeddings were evaluated on the DHR dataset. An automatic grid search was performed to tune statistical classifiers for the best performance over the transformed data. Inference efficiency and memory requirements of the best performing models were analyzed. The most efficient model for mining DHR cases from millions of documents in the EHR system was run. Results: For long document classification, key sentence selection with guideline keywords achieved the best performance and was 9 times faster than hierarchy representation models for inference. The best model discovered 1155 DHR cases in Beijing Children’s Hospital EHR system. After double-checking by clinician experts, 357 cases of severe DHRs were finally identified. For the smoking challenge, our model reached the record of state-of-the-art performance (94.1% vs 94.2%). Conclusions: The proposed method discovered 357 positive DHR cases from a large archive of EHR records, about 90% of which were missed by SRSs. SRSs reported only 36 cases during the same period. The case analysis also found more suspected drugs associated with severe DHRs in pediatrics.

21 October 2026 in Pharmaceutics
Verified
Journal Article
Open access
PDF file
YLYanming Li
Yanming Li
MLMengmeng Liu
Mengmeng Liu
QLQixian Ling
Qixian Ling
NSNing Sun
Ning Sun
HZHuyong Zheng
Huyong Zheng
LZLibo Zhao
Libo Zhao
Background: Venetoclax (VEN), a selective B-cell lymphoma 2 inhibitor, has been increasingly used off-label in pediatric patients with hematologic malignancies. However, its pharmacokinetic characteristics in pediatric patients remain insufficiently characterized. Methods: An adult VEN physiologically based pharmacokinetic (PBPK) model was developed and extrapolated to children using age-dependent physiological and CYP3A4 ontogeny data. The pediatric model was calibrated and evaluated using data from 76 children with AML (203 plasma concentrations) and subsequently applied to assess food effects, age-related pharmacokinetic differences, and VEN dose-reduction scenarios during VCZ co-administration. The clinical study was registered with the Chinese Clinical Trial Registry (ChiCTR1900027146 and ChiCTR2400080307). Results: The adult and pediatric models adequately reproduced the observed VEN concentration–time profiles. At 200 mg/m2, a normal-fat meal increased predicted AUCinf and Cmax by 2.74- and 1.77-fold, respectively, versus a low-fat meal. Children aged 2–<6 years had the highest exposure; AUCinf was 1.44- and 1.91-fold higher than in the 6–<12- and 12–<18-year groups, respectively. During VCZ co-administration, reducing VEN to 50% and 25% of the full dose decreased AUC0–168h by 36.8% and 60.5% and Cmax by 42.5% and 70.5%, respectively, with minimal changes in Tmax. Conclusions: The pediatric VEN PBPK model quantitatively characterized the effects of meal conditions, developmental age, and VCZ-mediated CYP3A inhibition on VEN pharmacokinetics. These findings support administration with a normal diet, closer safety monitoring in children aged 2–<6 years receiving 200 mg/m2, and model-informed evaluation of VEN dose reduction during concomitant VCZ therapy.