Yejin Jaylynn Kim
Assistant Professor
School of Biomedical Informatics
University of Texas Health Science Center at Houston
7000 Fannin, Suite 600
Houston, Texas 77030
Yejin Kim is an assistant professor in the School of Biomedical Informatics at University of Texas Health Science Center (UTHealth) and a founding faculty of Center for Secure Artificial Intelligence for Healthcare since 2018. Her research interest is on data mining and machine learning for healthcare applications, particularly treatment effect estimation, network representation, and computational phenotyping.
Innovating biomedical research via machine learning requires blending biological/clinical insight into algorithmic thinking. My background in machine learning and in biomedical informatics gives me a unique perspective for discovering, defining, and solving biomedical challenges. Before joining UTHealth, I received my PhD in computer science (from Big Data and Artificial Intelligence Laboratory at Pohang University of Science and Technology). I expanded my research areas to translational drug development and disease subtyping using advanced machine learning. My pioneering computational phenotyping model was funded by the Robert Woods Johnson foundation as principal investigator. My tensor factorization models for drug repurposing significantly contributed to my team obtaining NIA R01 (Co-I) and CPRIT Rising Star awards (Co-I). During the last five years I authored 30+ articles with 400+ citations as a primary author. I have strong publication records from prestigious data science conferences (such as KDD, CIKM, and IJCAI) and high-impact translational journals (such as Scientific Reports, JBI, JAMIA, PLoS one); the PLoS one publication was selected as the top 10% most cited article in 2016. My publication covers diverse scientific inquiry (from drug development to medication regimen), data modality (from transcriptome to free text), and methodology (from causal inference to deep learning) to address critical biomedical challenges. I am mentoring 8 pre- and postdoctoral trainees from various backgrounds such as mathematics, computer science, biostatistics, pharmaceutics, and pharmacology. For professional service, I am the organizer of the SBMI Machine Learning Datathon series in Texas Medical Center since 2019. I have served as a program committee of prestigious data science and/or medical informatics conferences such as AAAI, IJCAI, KDD Applied Data Science, WWW, AMIA, IEEE-BCB, IEEE-BIBM.
Research Interests
- Heterogeneous treatment effect analysis
- Computational phenotyping with longitudinal data
- Sequential decision making models
- Knowledge graph representation
News
- Top 10% most cited PLoS One article in 2016 [paper]
- Selected as AAIC 2020 highlighted poster
- Vaccine and Alzheimer studies in AAIC 2020 was covered in major news media NPR, CNN
Service
- Reviewer, JAMA Open Network, Cell Reports, Nature Scientific Reports, J. Biomedical Informatics, J. Am. Medical Informatics, Knowledge and Information System, Briefing in Bioinformatics
- Program Committee Member, AAAI AI for Social Impact, IJCAI, 2018-, AAAI, 2018-, BIBM IEEE International Conference on Bioinformatics & Biomedicine,AMIA Knowledge Discovery and Data Mining Working Group,IEEE International Conference on Healthcare Informatics, 2020-,WSDM Health Day, KDD Applied Data Science for Healthcare,IEEE BIBM International Conference on Bioinformatics and Biomedicine,World Wide Web Conference, 2018, AMIA Annual Symposium, 2017-, AMIA Informatics Summit, 2019-, ACM-BCB Conference on Bioinformatics, Computational Biology, and Health Informatics
- Co-organizer, SBMI Machine Learning Hackathon 2019-
Selected publications
Full publication list is available at google scholar
- Yan Ding, Xiaoqian Jiang, and Yejin Kim, Relational graph convolutional networks for predicting blood-brain barrier penetration of drug molecules, Bioinformatics. 2022 (accepted)
- Yejin Kim, Kai Zhang, Sean I. Savitz, Luyao Chen, Paul E. Schulz, and Xiaoqian Jiang. Counterfactual analysis of differential comorbidity risk factors in Alzheimer’s disease and related dementias. PLoS Digital Health. 2022 [paper]
- Kang-Lin Hsieh, Yinyin Wang, Luyao Chen, Zhongming Zhao, Sean Savitz, Xiaoqian Jiang, Jing Tang, and Yejin Kim. Drug Repurposing for COVID-19 using Graph Neural Network and Harmonizing Multiple Evidence. Nature Scientific Reports. 2021. [paper]
- Ziyi Li, Xiaoqian Jiang, Yizhou Wang, and Yejin Kim. Applied machine learning in Alzheimer’s disease research: omics, imaging, and clinical data. Emerging Topic in Life Science. 2021. [paper]
- Yejin Kim, Jessika Suescun, Mya Schiess, and Xiaoqian Jiang. Computational medication regimen for Parkinson’s disease using reinforcement learning. Nature Scientific Reports. 2021. [paper]
- Yejin Kim, Xiaoqian Jiang, Samden D Lhatoo, Guo-Qiang Zhang, Shiqiang Tao, Licong Cui, Xiaojin Li, Robert D Jolly 3rd, Luyao Chen, Michael Phan, Cung Ha, Marijane Detranaltes, and Jiajie Zhang. A community effort for automatic detection of postictal generalized EEG suppressioin in epilepsy. BMC Medical Informatics and Decision Making. 2020. [paper]
- Yejin Kim, Shuyu Zheng, Jing Tang, W. Jim Zheng, Zhao Li, and Xiaoqian Jiang. Anticancer drug synergy prediction in understudied tissues using transfer learning. Journal of American Medical Informatics. 2020. [paper]
- Yejin Kim, Samden D Lhatoo, GQ Zhang, Luyao Chen, and Xiaoqian Jiang. Temporal Phenotyping for Transitional Disease Progress: an Application to Epilepsy and Alzheimer’s Disease. Journal of Biomedical Informatics. 2020 [paper]
- Yejin Kim, Xiaoqian Jiang, Luca Giancardo, Danilo Pena, Avram S. Bukhbinder, Albert Y. Amran, and Paul E. Schulz. Multimodal Phenotyping of Alzheimer’s Disease with Longitudinal Magnetic Resonance Imaging and Cognitive Function Data. Scientific Reports, 2020 [paper]
- Yejin Kim, Xiaoqian Jiang, Luyao Chen, Xiaojin Li, and Licong Cui. Discriminative Sleep Patterns of Alzheimer’s Disease via Tensor Factorization. AMIA Annual Symposium. 2019. [paper]
- Yejin Kim, Kwangseob Kim, Chanyoung Park, and Hwanjo Yu. Sequential and Diverse Recommendation with Long Tail. IJCAI 2019. [paper] [slides]
- Yejin Kim, Luca Giancardo, Danilo Pena, and Xiaoqian Jiang. Finding Discriminative Subgroups of Brain Regions using Tensor Factorization. ACM KDD workshop on Applied Data Science for Healthcare. 2019. [paper]
- Jingyun Choi, Yejin Kim, HS Kim, In Young Choi, and Hwanjo Yu, Phenotyping of Korean patients with better-than-expected efficacy of moderate-intensity statins using tensor factorization, PLoS One. 2018. [paper]
- Yejin Kim, Jimeng Sun, Hwanjo Yu, and Xiaoqian Jiang. Federated Tensor Factorization for Computational Phenotyping. KDD 17 [paper] [slides] [video]
- Yejin Kim, Jingyun Choi , Yosep Chong, Xiaoqian Jiang, and Hwanjo Yu. DiagTree: Diagnostic Tree for Differential Diagnosis. CIKM 17 [paper] [slides]
- Yejin Kim, Robert El-Kareh, Jimeng Sun, Hwanjo Yu, and Xiaoqian Jiang. Discriminative and distinct phenotype by constrained tensor factorization. Scientific Reports 2017. [paper] [slides]
- Jingyun Choi, Mi Jung Rho, Yejin Kim, In Hye Yook, Hwanjo Yu, Dai-Jin Kim, and In Young Choi, Smartphone Over-dependence Classification using Tensor Factorization. PLoS One 2017. [paper]
- Jingyun Choi, Yejin Kim, HS Kim, In Young Choi, and Hwanjo Yu, Tensor-Factorization-Based Phenotyping using Group Information: Case Study on the Efficacy of Statins. ACM BCB 17 [paper]
- Yejin Kim, YongHyun Park, JY Lee, In Young Choi, and Hwanjo Yu. Discovery of prostate specic antigen pattern to predict castration resistant prostate cancer of androgen deprivation therapy. BMC Decision Making and Medical Informatics 2016 [paper] [slides]
- YongHyun Park, Yejin Kim, Hwanjo Yu, In Young Choi, Byun SS, Kwak C, Chung BH, Lee HM, Kim CS, and Lee JY. Is lymphovascular invasion a powerful predictor for biochemical recurrence in pT3 N0 prostate cancer? Results from the K-CaP database. Scientific reports. 2016 [paper]
- Yejin Kim, JE Jeong, H Cho , DJ Jung, M Kwak, MJ Rho, Hwanjo Yu, Dai-Jin Kim, In Young Choi. Personality factors predicting smartphone addiction predisposition: behavioral inhibition and activation systems, impulsivity, and self-control. PLoS One. 2016 [paper]
Selected presentation
- “Prediction of Individual Treatment Effects of Rehabiliation for Post-stroke Patients”, World Stroke Congress, 2021.
- “Population-based Drug Repurposing to Treat Thrombosis in COVID-19 Patients”. ISC 2021 ePoster
- “Literature Mining Approach to Extract Drug Effectiveness in Clinical Trials. An Application to Alzheimer’s Disease” AMIA Informatics Summit, 2021
- “Causal Pathway to Analyze Racial Disparities in Alzheimer’s Disease and Related Dementia”, Alzheimer’s Association International Conference (AAIC), 2020 video
- “Influenza Vaccination is associated with a reduced incidence of Alzheimer’s Disease”, AAIC, 2020
- “Temporal Phenotyping for Transitional Disease Progress: an Application to Epilepsy and Alzheimer’s Disease”, WSDM Workshop Healthcare Day 2020, Houston, Texas
- “Discriminative Sleep Patterns of Alzheimer’s Disease via Tensor Factorization”, AMIA 2019, Washington D.C.
- “Optimized Medication Regimen for Parkinson’s Disease”, Rice Data Science Conference October 15, 2019, Houston, Texas
- “Sequential and Diverse Recommendation with Long Tail”, International Joint Conference on Artificial Intelligence August 14, 2019, Macau, China
- “Finding Discriminative Subgroups of Brain Regions using Tensor Factorization”, ACM KDD workshop on Applied Data Science for Healthcare. August 4, 2019, Anchorage, Alaska
- “Discovering Underlying Concepts with Tensor Factorization”, Center for Health Security and Phenotyping, School of Biomedical Informatics, University of Texas Health Science Center at Houston, Jan 18, 2019, Houston, Texas
- “Interpretable and Federated Tensor Factorization for Computational Phenotyping”, Department of Computer Engineering, Hong Kong Baptist University, June 20 2018, Hong Kong
- “Tensor Factorization for Computational Phenotyping”, School of Biomedical Informatics, University of Texas Health Science Center at Houston, Nov 28 2018, Houston, Texas
- “Data Science and Applications”, Department of Management Engineering, Ulsan National Institute of Science and Technology, May 29 2018, Ulsan, Korea
- “Data Science and Applications”, Korea University WISET, Sep 12 2018, Seoul, Korea
- “Tensor Factorization for Computational Phenotyping”, KCC 2017 Spotlight Session for Young Women Scholars Jun 21 2017, Jeju, Korea
- “Tutorial: Matrix/Tensor factorization and its applications”, Department of Medical Informatics, Catholic University of Korea, Nov 20 2017, Seoul, Korea
- “DiagTree: Diagnostic Tree for Differential Diagnosis”, The Korea Society of Medical Informatics, Nov 17 2017, Seoul, Korea
- “DiagTree: Diagnostic Tree for Differential Diagnosis”, International Conference on Information and Management, Nov 12 2017, Singapore
- “Federated Tensor Factorization for Computational Phenotyping (poster)”. The 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Aug 14, 2017, Halifax, Nova Scotia, Canada
- “Discovery of prostate specific antigen pattern to predict castration resistant prostate cancer of androgen deprivation therapy”, ACM Ninth International Workshop on Data and Text Mining in Biomedical Informatics in conjunction with CIKM, Oct 23, 2015, Melbourne, Australia
Media Coverage
Alzheimer’s disease and Flu shot. NPR, CNN