K. Ishii’s Next-Generation Big Data Lab., Department of Applied Information Engineering, Faculty of Engineering, Suwa University of Science
From Healthcare Big Data to Information Dynamics: Understanding Complex Systems through Causal Inference and Data Science
The Ishii Laboratory conducts interdisciplinary research at the intersection of healthcare, environmental science, artificial intelligence, and theoretical information science.
Our mission is to understand complex real-world systems through data and to develop methodologies that move beyond prediction toward causal understanding and informed intervention.
We combine large-scale observational data, causal inference, machine learning, and mathematical modeling to address challenges in healthcare, environmental sustainability, and societal systems.
In parallel, we pursue foundational research in Theoretical Information Science and Information Dynamics, aiming to establish a unified framework for understanding how information is observed, transformed, propagated, and aligned across complex systems.
Modern data science has achieved remarkable success in prediction.
However, many critical questions remain unanswered:
What causes observed phenomena?
What happens if we intervene?
How does information evolve over time?
How can we distinguish observation from reality?
Our laboratory seeks answers to these questions through the integration of:
Causal Inference
Machine Learning
Statistical Computing
Information Theory
Information Dynamics
We believe that understanding causality and information structure is essential for the next generation of data science.
Our primary research area is healthcare big data analytics using nationwide-scale medical databases.
Current topics include:
Cardio-Kidney-Metabolic (CKM) Syndrome
Dementia epidemiology
Pharmacoepidemiology
Healthcare policy analysis
Treatment effect estimation
Counterfactual analysis
We analyze data from millions of patients to identify causal relationships among diseases, medications, lifestyle factors, and health outcomes.
We investigate environmental systems using sensor networks, remote sensing, drone platforms, and meteorological data.
Topics include:
Climate and ecosystem interactions
Smart agriculture
Environmental sustainability
Remote sensing analytics
Nonlinear system modeling
Our goal is to support evidence-based environmental decision-making through causal and predictive modeling.
We develop next-generation healthcare delivery systems for rural and aging societies.
Research topics include:
Medical drone logistics
Healthcare digital transformation (DX)
Disaster medicine logistics
Remote healthcare infrastructure
Healthcare accessibility optimization
These projects aim to bridge technological innovation and social implementation.
Beyond applications, we investigate the fundamental behavior of information itself.
Current topics include:
Information observation and representation
Information transformation and degradation
Information propagation
Causal structures of information
AI hallucination and echo chambers
Alignment and intervention dynamics
Information Dynamics
Our long-term goal is to establish Information Dynamics as a theoretical framework for understanding complex information systems in AI, science, and society.
Our laboratory provides a reproducible and computationally intensive research environment.
Linux-based research infrastructure
Python and R ecosystem
GPU computing
High-memory servers
Cloud computing platforms
Nationwide healthcare databases
Health examination databases
Environmental sensor data
Meteorological data
Drone and remote sensing data
We emphasize:
Reproducible research
Open-source tools
Data-driven discovery
Interdisciplinary collaboration
We actively collaborate with universities, research institutes, hospitals, governmental organizations, and industry partners.
Current collaborations include projects in:
Japan
Germany
Indonesia
Southeast Asia
We welcome international students, visiting researchers, and collaborative research proposals.
Areas of particular interest include:
Healthcare Big Data
Causal Inference
Smart Agriculture
Medical DX
Drone Logistics
Theoretical Information Science
Information Dynamics
We are looking for students and researchers who are interested in:
Data Science
Causal Inference
Machine Learning
Healthcare Analytics
Environmental Informatics
Information Theory
Information Dynamics
Prior experience is helpful but not required. Curiosity, motivation, and willingness to tackle challenging problems are valued most.
Healthcare Big Data • Causal Inference • CKM Syndrome • Pharmacoepidemiology • Medical DX • Environmental Informatics • Smart Agriculture • Remote Sensing • Drone Systems • Machine Learning • Deep Learning • Statistical Computing • Theoretical Information Science • Information Dynamics • Complex Systems
Profile: Professor of Suwa University of Science, visiting associate professor of Division of Cardiovascular Medicine, Department of Internal Medicine, Kurume University School of Medicine.
Detailed achievements: Google Schalor, ORCID, Researchmap
Reference IDs: DA18461433, NDL: 00980363, VIAF ID: 256308865, WorldCat Identities: lccn-n2018006921, KAKEN: 60449238, Webcat Plus, Amazon
Contact: Kazuo Ishii, Ph.D.
Department of Applied Information Engineering,
Faculty of Engineering, Suwa University of Science,
5000-1 Toyohira, Chino-shi, Nagano 391-0292, JAPAN.
Tel.(+81)-266-73-1201