Ying Li

Ying Li

Auto-generated profile, based on publicly available information

Ying Li

Regeneron, Tarrytown, NY, USA

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
8 May 2020 in Drug Safety
Verified
Journal Article
Open access
PDF file
YLYing Li
Ying Li
AYAntonio Jimeno Yepes
Antonio Jimeno Yepes
CXCao Xiao
Cao Xiao
Introduction Adverse drug reactions (ADRs) are unintended reactions caused by a drug or combination of drugs taken by a patient. The current safety surveillance system relies on spontaneous reporting systems (SRSs) and more recently on observational health data; however, ADR detection may be delayed and lack geographic diversity. The broad scope of social media conversations, such as those on Twitter, can include health-related topics. Consequently, these data could be used to detect potentially novel ADRs with less latency. Although research regarding ADR detection using social media has made progress, findings are based on single information sources, and no study has yet integrated drug safety evidence from both an SRS and Twitter. Objective The aim of this study was to combine signals from an SRS and Twitter to facilitate the detection of safety signals and compare the performance of the combined system with signals generated by individual data sources. Methods We extracted potential drug–ADR posts from Twitter, used Monte Carlo expectation maximization to generate drug safety signals from both the US FDA Adverse Event Reporting System and posts from Twitter, and then integrated these signals using a Bayesian hierarchical model. The results from the integrated system and two individual sources were evaluated using a reference standard derived from drug labels. Area under the receiver operating characteristics curve (AUC) was computed to measure performance. Results We observed a significant improvement in the AUC of the combined system when comparing it with Twitter alone, and no improvement when comparing with the SRS alone. The AUCs ranged from 0.587 to 0.637 for the combined SRS and Twitter, from 0.525 to 0.534 for Twitter alone, and from 0.612 to 0.642 for the SRS alone. The results varied because different preprocessing procedures were applied to Twitter. Conclusion The accuracy of signal detection using social media can be improved by combining signals with those from SRSs. However, the combined system cannot achieve better AUC performance than data from FAERS alone, which may indicate that Twitter data are not ready to be integrated into a purely data-driven combination system.

25 April 2023 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
ZYZijun Yao
Zijun Yao
BLBin Liu
Bin Liu
FWFei Wang
Fei Wang
DSDaby Sow
Daby Sow
YLYing Li
Ying Li
For care of chronic diseases (e.g., depression, diabetes, hypertension), it is critical to identify effective treatment pathways that aim to promptly update the medication following the change of patient state and disease progression. This task is challenging because the optimal treatment pathway for each patient needs to be personalized due to the significant heterogeneity among individuals. Therefore, it is naturally promising to investigate how to use the abundant electronic health records to recommend effective and safe prescriptions. However, prescription recommendation needs to consider multiple aspects of life-critical evidence, such as the information relevance in terms of medical concepts, the health condition in terms of diagnosis history, and the further constraint in terms of side information (e.g., patient demographics and drug side effects). To this end, in this article, we propose a novel prescription recommendation framework named OntoPath to predict the next drug in disease treatment pathways, by building an ontology-aware hierarchical-attention model that integrates multiple medical evidence from domain knowledge guidance, medical history profiling, and side information utilization. Specifically, our method can be characterized from three aspects: (1) by incorporating the longitudinal diagnosis history, we enrich the profiling of patients in terms of comprehensive health conditions, which can largely influence a drug’s outcome on individual patients; (2) using the hierarchical disease and drug ontology structures, we are able to model the domain-specific relevance between patients and drugs at multiple levels of granularity and achieve in-depth collaborative filtering; (3) we introduce a pre-training stage to enhance the discriminativeness of network representations, which helps us obtain a premium model initialization to further boost the final recommendation training. We perform extensive experiments on a large-scale depression cohort with over 37,000 patients from a real-world medical claims database. The quantitative and qualitative results demonstrate the effectiveness of OntoPath through the consistent outperformance over state-of-the-art prescription recommendation baselines and the interpretation of model mechanism in case studies.

8 March 2019 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
BLBin Liu
Bin Liu
YLYing Li
Ying Li
SGSoumya Ghosh
Soumya Ghosh
ZSZhaonan Sun
Zhaonan Sun
KNKenney Ng
Kenney Ng
JHJianying Hu
Jianying Hu
Diabetes is a chronic disease that often results in multiple complications. Risk prediction and profiling of diabetes complications is critical for improved outcomes. In this paper, focusing on Type 2 diabetes mellitus (T2DM), we study the risk of developing complications after the initial T2DM diagnosis from longitudinal patient records. We propose a novel multi-task learning approach to simultaneously model multiple complications where each task corresponds to the risk modeling of one complication. Specifically, the proposed method strategically captures the relationships (1) between the risks of multiple T2DM complications, (2) between the different risk factors, and (3) between the risk factor selection patterns, which assumes similar complications have similar contributing risk factors. The method uses coefficient shrinkage to identify an informative subset of risk factors from high-dimensional data, and uses a hierarchical Bayesian framework to allow domain knowledge to be incorporated as priors. The proposed method is favorable for healthcare applications because in additional to improved prediction performance, relationships among the different risks and risk factors are also identified. Extensive experimental results on a large electronic medical claims database show that the proposed method outperforms state-of-the-art models by a significant margin.

1 November 2018 in IBM Journal of Research and Development
Verified
Journal Article
Closed access
JSJ. Shim
J. Shim
HLH. Luo
H. Luo
PZP. Zhang
P. Zhang
YLY. Li
Y. Li

19 February 2018 in arXiv
Verified
Preprint
Open access
PDF file
BLBin Liu
Bin Liu
YLYing Li
Ying Li
SGSoumya Ghosh
Soumya Ghosh
ZSZhaonan Sun
Zhaonan Sun
KNKenney Ng
Kenney Ng
JHJianying Hu
Jianying Hu
Type 2 diabetes mellitus (T2DM) is a chronic disease that often results in multiple complications. Risk prediction and profiling of T2DM complications is critical for healthcare professionals to design personalized treatment plans for patients in diabetes care for improved outcomes. In this paper, we study the risk of developing complications after the initial T2DM diagnosis from longitudinal patient records. We propose a novel multi-task learning approach to simultaneously model multiple complications where each task corresponds to the risk modeling of one complication. Specifically, the proposed method strategically captures the relationships (1) between the risks of multiple T2DM complications, (2) between the different risk factors, and (3) between the risk factor selection patterns. The method uses coefficient shrinkage to identify an informative subset of risk factors from high-dimensional data, and uses a hierarchical Bayesian framework to allow domain knowledge to be incorporated as priors. The proposed method is favorable for healthcare applications because in additional to improved prediction performance, relationships among the different risks and risk factors are also identified. Extensive experimental results on a large electronic medical claims database show that the proposed method outperforms state-of-the-art models by a significant margin. Furthermore, we show that the risk associations learned and the risk factors identified lead to meaningful clinical insights.

7 October 2026 in JMIR Preprints
Verified
Preprint
Open access
YLYing Li
Ying Li
KQKristin Qi
Kristin Qi
LHLiang-Chin Huang
Liang-Chin Huang
JZJianguang Zhuang
Jianguang Zhuang
SWSiwei Wang
Siwei Wang
YXYingxin Xu
Yingxin Xu
BACKGROUND Accurate digitization of Kaplan-Meier (KM) curves and reconstruction of individual patient data (IPD) from published graphs are important for health technology assessment and evidence synthesis but remain technically challenging. OBJECTIVE To develop and validate a human-in-the-loop system that uses generative artificial intelligence and computer vision to digitize published KM curves and reconstruct IPD for downstream health technology assessment and evidence synthesis. METHODS We developed a KM-Vision system that integrates figure quality control screening, metadata extraction using a large language model (LLM), computer vision (CV)-based curve tracing, IPD reconstruction using an enhanced Guyot-based algorithm, and an accuracy assessment panel. We evaluated performance using published KM figures, synthetic KM figures with known ground truth, expert-digitized figures, and clinical trial patient-level records. On these datasets, we compared KM-Vision with general-purpose LLM models (GPT-4o and Claude 3.7), KM-GPT (a published automated KM digitization pipeline), and expert manual digitization. RESULTS KM-Vision outperformed general-purpose LLMs and KM-GPT on published figures and synthetic data. For published dual-arm KM figures, mean median survival time (MST) deviation was 0.092 months and mean hazard ratio (HR) error was 0.017, substantially lower than GPT-4o (18.910 and 0.423) and Claude 3.7 (24.090 and 0.277). Performance was also comparable to expert digitization, with similar MST deviations (0.384 and 0.029 vs 0.076 and 0.035) and HR errors (0.071 and 0.022 vs 0.029 and 0.016) across published figures and trial data. CONCLUSIONS KM-Vision, a high-accuracy, verifiable LLM-CV pipeline, enables expert-level reconstruction of IPD from published KM curves for use in cost-effectiveness analyses (CEA) and indirect treatment comparisons (ITC).