Japan – Genequest and Fujitsu discover brand-new insights into genetics-lifestyle relationships through high-speed, trusted causal AI from Fujitsu Kozuchi

Genequest and Fujitsu discover brand-new insights into genetics-lifestyle relationships through high-speed, trusted causal AI from Fujitsu Kozuchi

Tokyo and Kawasaki, Japan, October 9, 2025- (JCN Newswire)-Genequest Inc. and Fujitsu Limited today revealed the discovery of brand-new insights into the causal relationships in between genes and way of life. The research study made use of causal AI, a core innovation of Fujitsu’s AI service Fujitsu Kozuchi.

Causal AI includes 3 primary functions: high-speed causal discovery, which approximates the causal relationships in between information around 1,000 x faster than traditional innovations (1) dependability improvement, which boosts information with the addition of recognized causal understanding (e.g., skilled understanding and previous speculative outcomes) and determine proposition which not just envisions causal relationships through standard analysis however likewise proposes ideal procedures.

By making use of causal AI, the celebrations obtained a multi-faceted causal structure relating to not just specific connections however likewise the relationship in between choice for sweet foods, coffee and alcohol usage frequency, and their involved hereditary characteristics, along with the effect of hereditary aspects on body mass index (BMI). Furthermore, by repurposing the Hirosaki Health Checkup Causal Network Model (2 ), established by Kyoto University and Hirosaki University in partnership with the latter’s Iwaki Health Promotion Project COI-NEXT, and using it to the dependability improvement function, the research study had the ability to recommend more exact causal relationships in between way of life routines, health, and background aspects. The usage of the Hirosaki Health Checkup Causal Network Model was enabled through the collective research study course Large Scale Medical AI (Fujitsu Research Lab.) (3) by Kyoto University and Fujitsu.

Based upon these approximated causal relationships, it is hoped that the step proposition function will have the ability to recommend separately enhanced health steps customized to individual food choices, way of life practices, body, and hereditary attributes.

Moving on, Genequest will continue to advance multi-faceted research study by integrating surveys, health examinations, and medical details and intends to add to the expedition of tailored health promo and illness avoidance methods.

Fujitsu’s causal AI is an effective tool for drawing out brand-new insights from complicated information and supporting decision-making throughout a large range of fields, not restricted to medical and hereditary domains. Fujitsu will accelerate its efforts to fix obstacles and produce brand-new worth in numerous markets.

Yasushi Okuno, Professor, Graduate School of Medicine, Kyoto University remarks:

“The onset of diseases is deeply intertwined with genetic function and living environment. However, the relationship between these two factors and disease onset is complex, and many aspects remain unknown. This initiative is an important step towards elucidating objective causes of disease based on data and deepening our understanding of disease onset. We have high expectations that this will contribute to the realization of personalized preventive measures and effective approaches.”

Koichi Murashita, Vice-President, Professor Vice-Director, Institute of Global Well-being Science Director-General, Research Institute of Health Innovation Hirosaki University remarks:

“At Hirosaki University COI-NEXT, we are working to additional reinforce the research study and social worth of our thorough real-world information platform, fixated the multi-dimensional health huge information (3,000 products) collected through the Iwaki Health Promotion Project health examinations, and to produce real social development. We are extremely happy that the research study results using our huge information have actually combined with advanced innovation to develop brand-new understanding. We have high expectations that these outcomes will add to the advancement of preventive medication and the enhancement of international wellness.”

Figure: Overview of the research study

Research study Overview

With developments in genome science, lots of connections in between genes and physical constitution/behavior have actually been reported. Diving much deeper into causal relationships– what triggers what, and through what systems impacts take place– has actually been challenging as it needs thinking about the impact of several aspects. Especially in locations including complicated aspects such as food choices, way of life practices, and body, accurate information analysis is needed.

In this research study, Genequest’s comprehensive hereditary and survey information were integrated with Fujitsu’s causal AI, making use of Fujitsu’s high-speed causal discovery function to examine these intricate causal systems more deeply. This showed the capability to exactly evaluate covert aspects within complicated relationships and the interactions in between numerous aspects, adding to the production of brand-new worth.

Outcomes

In this research study, causal analysis was performed mostly in the following 2 locations, utilizing hereditary information and survey information from around 4,000 consenting people, and leveraging the dependability improvement function and step proposition operates offered by Fujitsu’s causal AI.

1. Relationship in between hereditary qualities connected to alcohol metabolic process and consuming routines
While hereditary aspects were formerly recommended to affect a choice for sweet foods and coffee consumption, analysis utilizing causal AI exposed that the association is most likely moderated mostly by drinking frequency, instead of entirely by hereditary alcohol tolerance. For coffee intake frequency, no direct link to drinking frequency was observed, recommending that hereditary alcohol tolerance might be an influencing element. This highlights the possible effect of particular hereditary characteristics on a person’s drink options.
2. Relationship in between hereditary characteristics connected to body, consuming practices, and BMI
Utilizing polygenic ratings, an index incorporating many hereditary elements associated with BMI, the causal relationship in between hereditary predisposition to weight problems, consuming routines, and BMI was evaluated. The outcomes recommended a direct association in between hereditary predisposition to weight problems and BMI, with its analytical effect being equivalent to that of sex and age. Small associations were likewise observed with food choices such as for fatty and sweet foods.

Especially, in the analysis using the dependability improvement function by repurposing the Hirosaki Health Checkup Causal Network Model, more accurate outcomes were gotten. The impact of meal amount, formerly recommended as a significant consider BMI modification after polygenic ratings in earlier analyses, reduced reasonably, while choices for fatty and umami tastes were recommended as more prominent aspects. Aspects formerly outside the scope of analysis, such as household medical history (cancer, high blood pressure, heart illness, and so on), the topic’s height, and work status, were recommended as possible surprise typical causes in between variables.

In addition, the research study results suggest that the causal AI step proposition function might be made use of to present concrete actions for attaining private objectives (e.g., BMI decrease, enhancement of particular consuming routines) based upon causal relationships, thinking about specific qualities.

(1) Fujitsu’s exclusive high-speed causal discovery technique:
H. Suzuki, LayeredLiNGAM: A Practical and Fast Method for Learning a Linear Non-gaussian Structural Equation Model (ECML PKDD 2024)
(2) Hirosaki Health Checkup Causal Network Model:
An extremely trustworthy causal network built by Kyoto University’s research study group using its special Bayesian network innovation to the multi-dimensional health huge information acquired from the Iwaki Health Promotion Project health examinations by Hirosaki University COI-NEXT.
(3) Collaborative research study course Large Scale Medical AI (Fujitsu Research Lab.):
Carries out research study and advancement of brand-new AI innovations to fix difficulties in the health and medical fields. This is among Fujitsu’s Fujitsu Small Research Lab efforts, where Fujitsu scientists are stationed at universities in Japan and abroad to take part in industry-academia partnership activities.

About Genequest

Established in 2014, Genequest was the very first business in Japan to provide massive hereditary screening services straight to customers. The service offered over 350 hereditary products associated with illness threats and physical qualities, making it possible for users to examine genes related to different conditions and qualities. With a vision to advance hereditary research study, promote the accountable usage of hereditary info, and improve individuals’s lives, Genequest actively carries out research study using its collected genomic information.

Authorities site: https://genequest.jp/forbiz/en

About Fujitsu

Fujitsu’s function is to make the world more sustainable by constructing rely on society through development. As the digital change partner of option for clients around the world, our 113,000 staff members work to deal with a few of the best difficulties dealing with humankind. Our series of services and services make use of 5 essential innovations: AI, Computing, Networks, Data & & Security, and Converging Technologies, which we unite to provide sustainability improvement. Fujitsu Limited (TSE:6702) reported combined profits of 3.6 trillion yen (US$ 23 billion) for the ended March 31, 2025 and stays the leading digital services business in Japan by market share. Learn more: global.fujitsu

Press Contacts