2025
Emotion Estimation × Education Support AI "EMOTIP"
Exhibition at the Osaka-Kansai Expo
: Initiatives to Improve Care Quality and Reduce Turnover Rates in Nursing Care Settings Using AI Video Analysis

Background

The nursing care industry is facing a chronic labor shortage. When we interviewed over 500 caregivers, the reasons for leaving within 3 years were "no prospects for the future" (15.4%) and "current salary" (14.9%), confirming that future uncertainty and working conditions are the leading causes of turnover.
In addition, difficulties in communicating with users who have trouble expressing emotions, such as dementia patients, were a major source of stress for both users and caregivers.

Challenge

A system is needed to correctly understand the emotions of care recipients and provide appropriate support, thereby reducing the stress of residents and the burden on care staff. Instead of traditional observation and record-based evaluations, there was a demand to visualize the quality of care and support self-evaluation of care skills, thereby reducing the burden of staff training and leading to a lower turnover rate.

Tasks

We exhibited at the "Future Life Experience" (July 8 - July 14) of the 2025 Osaka-Kansai Expo, and promoted a project to entrust the future visions envisioned by everyone to the "Tree of Future Shining with Life" and broadcast it to the world.

2024
Predicting Clinical Trial Success of Immune Checkpoint Inhibitors
: AI Utilization for Efficient and Effective Drug Development

Background

Drug development requires over ten years and costs hundreds of billions to trillions of yen, with success probabilities declining from 1 in 15,000 a decade ago to 1 in 30,000 today. In this context, optimizing and accelerating clinical trials and resource allocation has long been a challenge for the industry. Particularly, the transition success rate from Phase II to Phase III is only 24.6%, leaving room for significant improvement.

Challenges

We worked on predicting the success probability of Phase III clinical trials for immune checkpoint inhibitors. Applying the concept of "acquiring representations from observed information" of the world model, we visualized and verified the precision improvement using patient blood and vital data.

2023
Realizing Personal NFTs That Are Rentable but Non-Transferable
: Building a Transparent Data Management System for Medical Data Utilization

Background

In the modern medical field, the utilization of data remains underdeveloped. I focused on transforming data managed by medical institutions into "data that individuals can recognize the value of and utilize." However, this concept necessitates the construction of mechanisms that ensure both security and transparency. To date, there have been no successful cases of such implementation, leaving numerous technical and operational challenges unresolved.

Challenges

While individuals providing health checkup data wish to limit items and the duration of data sharing, insurance companies require a system that ensures data accuracy while enabling its business utilization.