ExaWizards, an AI start-up, has developed an AI-based model for predicting the level of care needed using the care-related data of local governments.

ExaWizards, an AI start-up, has developed an AI-based model for predicting
the level of care needed using the care-related data of local governments.

– This development project has been adopted by the Kanagawa Prefecture ME-BYO Living Lab. –

 

ExaWizards Inc. (Minato-ku, Tokyo, Representative Director & President: Ko Ishiyama, hereafter “ExaWizards”) started a project to develop AI for predicting the level of care needed using care-related data in local governments, and this has been adopted as a demonstration project by the Kanagawa Prefecture ME-BYO Living Lab.

 

Under this demonstration project, ExaWizards is working in collaboration with Kanagawa Prefecture to establish an evaluation platform for realizing scientific-evidence based care in cooperation with specific municipalities in the prefecture. In detail, ExaWizards is developing an AI-based model for predicting the level of individual care needed and is analyzing the causes of disease aggravation in care recipients and identifying characteristics by level of care needed to help municipalities effectively formulate their care policies.

 

About the Kanagawa Prefecture ME-BYO Living Lab

To tackle the super-aging society, Kanagawa Prefecture has been encouraging changes in the awareness and actions of citizens and sustainable development of “non-disease (ME-BYO)” industries based on the ME-BYO concept and has been promoting Healthcare New Frontier policies to extend healthy life. The Kanagawa Prefecture ME-BYO Living Lab promotes the commercialization, industrialization and social implementation of ME-BYO related products and services that contribute to the solution of health issues in local communities and workplaces and the establishment of a new social system, ensuring that citizens in the prefecture can easily make ME-BYO improvements. Kanagawa Prefecture is working in collaboration with municipalities in the prefecture, companies, academia and various other parties who implement the CHO concept (health management) to provide demonstration sites for examining the functions, effects, and other appropriate elements of products and services and evaluating the demonstration results.

 

Background of developing AI for predicting the level of care needed

As the number of patients with dementia is expected to reach seven million people by 2025 due to the declining birthrate and aging population, it is necessary to handle complex issues such as optimizing social security expenses due to the increase in care expenses and establishing future-oriented social systems. On the other hand, as it is difficult to identify the actual situations and issues related to care and quantitatively examine the cost-effectiveness of intervention methods, progress in accumulating data and establishing evidence-based care remains insufficient.

 

Also, as the state of individual care recipients changes due to various factors over time, it is not easy to examine the effects of intervention by appropriately separating them from other factors, and this is one of the reasons that make it hard to identify the actual situation.

 

Overview of the demonstration project

This demonstration project predicts the level of individual care needed in the future by applying ExaWizards’ AI technology to the care-related data owned by local governments. As this future prediction separates the effects inherent to the intervention method from the changing state of care recipients over time, it examines the difference between predicted and actual values in the case with and without intervention by using the predicted future state of how the patient will change in the future with the same state transition as it is.

 

Also, attributes, independence level, behavioral characteristics and other appropriate elements of targets in the specific segment (by level of care needed, etc.) are quantitatively identified. These measures help to review the effects of intervention policies in the future and to formulate effective care policies with higher cost-performance.

Contents of demonstration project: Development of AI for predicting the level of care needed using the care-related data of local governments

Data to be used to build the AI model: Care requirement judgment data and care receipts

Procedure:

1. Data provided by local governments^*1 are used to build the AI model and predict the level of individual care needed and care expenses.
2. The AI model is applied to the data of past years and other appropriate data to examine the prediction accuracy of the AI model.
3. By analyzing the segment information by level of care needed, the causes of disease aggravation of care recipients are analyzed and characteristics of targets such as attributes, independence level and behavioral characteristics are extracted.

As we consider that the measures to be implemented by this demonstration program will contribute to the efforts of the Cross-ministerial Strategic Innovation Promotion Program (SIP)^*2 which has already adopted the program, we aim to create an evaluation platform for achieving care based on scientific evidence by explicitly presenting care-related evidence, which has not been sufficiently identified before.

 

*1) All of the data provided by local governments under this demonstration project are personal information that has been anonymized so that a specific individual cannot be identified.

*2) It has been adopted as the theme: R&D and social implementation of AI for self-reliance support by multimodal human-interaction technology “with emphasis on patients with dementia and their family’s views,” in the field of “Nursing Care Support Technology” of the Cabinet Office’s “Cross-ministerial Strategic Innovation Promotion Program (SIP) Second Phase / Big-data and AI-enabled Cyberspace Technologies.”

 

 

[Profile of ExaWizards Inc.]

Company name: ExaWizards Inc.

Address: 5F, Sumitomo Hamamatsucho Bldg., Hamamatsu-cho 1-18-16, Minato-ku, Tokyo

Founded: February 2016

Representative: Representative Director & President: Ko Ishiyama

Business: Development of AI-enabled services for industrial innovation and solving social problems

URL: https://exawizards.com/