Ruoqi Liu

Short Biography

I am a postdoctoral researcher at Stanford University working with Dr. Jonathan H. Chen. I earned my Ph.D. in Computer Science and Engineering at The Ohio State University, advised by Prof. Ping Zhang. My research lies at the intersection of AI/ML and causal inference, with applications in healthcare and biomedicine. I am particularly interested in estimating treatment effects to derive evidence-based, actionable healthcare decisions using real-world patient data.

News

• [Jan 2025] Our paper “Treatment effect estimation with multiple treatments and multiple outcomes for antihypertensive drug combinations” has been accepted to Cell Reports Medicine!
• [Sep 2024] Honored to be selected as one of the Rising Stars in Data Science 2024!
• [May 2024] Our paper “CURE: A deep learning framework pre-trained on large-scale patient data for treatment effect estimation” has been accepted to Patterns
• [Dec 2023] Our paper “KG-TREAT: Pre-training for treatment effect estimation by synergizing patient data with knowledge graphs” has been accepted to AAAI 2024.
• [Nov 2023] Honored to receive the Presidential Fellowship from OSU Graduate School!
• [Oct 2023] Honored to be selected as Rising Star in EECS!
• [Apr 2023] Our paper “Estimating treatment effects for time-to-treatment antibiotic stewardship in sepsis” has been accepted to Nature Machine Intelligence.

Selected Publications

*: Equal Contributions

• Teach multimodal LLMs to comprehend electrocardiographic images
  Ruoqi Liu*, Yuelin Bai*, Xiang Yue, Ping Zhang
  arXiv 2024
  [Project Page][arXiv][Code][HF Data]

• Treatment effect estimation with multiple treatments and multiple outcomes for antihypertensive drug combinations
  Ruoqi Liu, Lang Li, Ping Zhang
  Cell Reports Medicine, 2025 (Impact factor: 11.7)
  [medRxiv]

• A deep subgrouping framework for precision drug repurposing via emulating clinical trials on real-world patient data
  Seungyeon Lee, Ruoqi Liu, Feixiong Cheng, Ping Zhang
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025 (Acceptance rate: 62/285 = 22%, applied data science track)
  

• CURE: A deep learning framework pre-trained on large-scale patient data for treatment effect estimation
  Ruoqi Liu, Pin-Yu Chen, Ping Zhang
  Patterns, 2024
  [Paper] [Code]
  Selected media coverage: OHIO STATE NEWS, Clinical Research News, MedicalXpress, AZoRobotics

• KG-TREAT: Pre-training for treatment effect estimation by synergizing patient data with knowledge graphs
  Ruoqi Liu, Lingfei Wu, Ping Zhang
  AAAI Conference on Artificial Intelligence (AAAI), 2024 (Acceptance rate: 2342/9862 = 23.7%, main track, oral presentation)
  [Paper][Code]

• Estimating treatment effects for time-to-treatment antibiotic stewardship in sepsis
  Ruoqi Liu, Katherine Hunold, Jeffrey Caterino, Ping Zhang
  Nature Machine Intelligence, 2023 (Impact factor: 25.898)
  [Paper] [Code]
  Selected media coverage: OHIO STATE NEWS, HealthITAnalytics, MIT Technology Review Chinese Edition. Featured on AMIA 2024 Informatics Summit Artificial Intelligence and Data Science Year-in-Review

• Deconfounding actor-critic network with policy adaptation for dynamic treatment regimes
  Changchang Yin, Ruoqi Liu, Jeffrey Caterino, Ping Zhang
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022 (Acceptance rate: 254/1695 = 15.0%, research track)
  [Paper]

• A deep learning framework for drug repurposing via emulating clinical trials on real world patient data
  Ruoqi Liu, Lai Wei, Ping Zhang
  Nature Machine Intelligence 3:68–75, 2021 (Impact factor: 25.898)
  [Paper] [Code]
  Selected media coverage: IN BRIEF of Nature Reviews Drug Discovery, Headline of OHIO STATE NEWS, Top 5% of all research ouputs scores by Altmetric

• Estimating individual treatment effects with time-varying confounders
  Ruoqi Liu, Changchang Yin, Ping Zhang
  IEEE International Conference on Data Mining (ICDM), 2020 (Acceptance rate: 91/930 = 9.8%, regular paper, oral presentation)
  [Paper] [Code]

• Identifying sepsis subphenotypes via time-aware multi-modal auto-encoder
  Changchang Yin, Ruoqi Liu, Dongdong Zhang, Ping Zhang
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020 (Acceptance rate: 216/1279 = 16.9%, research track, oral presentation)
  [Paper] [Code] [Video]

Services

• Conference reviewer: ICLR, KDD, ICDM, SDM, AMIA
• Journal reviewer: Communications Medicine, Bioinformatics, BMC Medical Informatics and Decision Making
• Journal sub reviewer: Nature Communication, Nature Computational Science, Nature Machine Intelligence, Lancet Digital Health

Powered by Jekyll and Minimal Light theme.