Laboratory of High-Dimensional Causal Inference and Big Data Analytics

■ Research Overview

Our laboratory focuses on the development and application of causal inference methods for large-scale datasets, particularly in medical big data, as well as environmental data.

While modern data science has primarily advanced through improvements in predictive accuracy, what is crucial for medical policy and real-world implementation is to understand:

• what causes what,

• and what changes when an intervention is applied.

Based on statistics, machine learning, and mathematical modeling, we aim to go beyond correlation and develop causal understanding of complex systems. In particular, we currently focus on the integrated analysis of medical big data centered on CKM (Cardio-Kidney-Metabolic) syndrome, which describes the interconnection between cardiovascular, kidney, and metabolic disorders.

■ Research Features

• Causal inference methods for high-dimensional, nonlinear, and incomplete real-world data

• Estimation of intervention effects and counterfactual analysis from observational data

• Cross-domain integration of medical and environmental datasets

• Unified approaches combining machine learning and causal inference

• Reproducible large-scale analytics using high-performance computing environments

■ Research Objectives

The objective of this laboratory is to establish practical causal inference methodologies applicable to real-world problems, thereby supporting evidence-based decision-making in healthcare and environmental domains.

We also aim to train researchers who can understand and implement high-dimensional data analysis and causal inference techniques.

Furthermore, we seek to reinterpret the 5Vs of big data (Volume, Variety, Velocity, Veracity, Value) from a causal inference perspective.

■ Main Research Topics

1. Medical Big Data and CKM Syndrome Analysis

This is the core research theme of the laboratory. Using large-scale healthcare datasets (claims and health checkup data covering tens of millions of individuals), we analyze causal interactions among diabetes, kidney disease, and cardiovascular disease.

• Elucidation of causal structures in disease progression

• Estimation of effects of drugs and lifestyle interventions

• Applications to preventive medicine and health policy

We go beyond prediction to evaluate what would happen under intervention.

2. Environmental, Climate, and Agricultural Data Analysis

We analyze the impact of environmental change on ecosystems and agriculture using sensor data, drone data, and meteorological data.

• Modeling of nonlinear and nonequilibrium systems

• Analysis of climate change impacts on productivity

• Design of sustainable agriculture and environmental policy

■ Research Environment

The laboratory is based on Linux environments and uses Python and R for large-scale data analysis. We utilize high-performance computing systems and cloud platforms to ensure reproducible research based on real-world data.

Quantum computing is currently positioned as a supplementary tool for educational and theoretical understanding. While not yet central to computation, it is explored as a conceptual framework to expand perspectives beyond classical computing in big data analysis.

■ Interdisciplinarity and International Collaboration

We promote interdisciplinary research across medical and environmental fields, collaborating with universities, research institutes, and industry partners in Japan and abroad.

We are also actively involved in international collaborative projects, particularly in Southeast Asia.

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