FRONTEO Inc. (Headquarters: Minato-ku, Tokyo, President: Masahiro Morimoto) is a member of the Life Science AI Business Headquarters (Hiroyoshi Toyoshiba, Life Science AI CTO, Professor Kimihiro Hino) and Tomohide Yamada, Visiting Professor of Kings College London, UK. We are pleased to announce that the results of the joint research by the research group on improving the work efficiency of systematic reviews using the "Concept Encoder" have been accepted by the international medical journal "Journal of Medical Internet Research (JMIR)".

　The Journal of Medical Internet Research is one of the international peer-reviewed open-access medical journals published by JMIR Publications, focusing on clinical computer science, health and healthcare big data, electronic medical records, and medical infrastructure.The impact factor (literature citation rate) of JMIR in the journal evaluation analysis tool Journal Citation Reports 2020 is 5.03, which is ranked as Q1 which is the highest among the ranks of Q4-1.

The paper accepted this time is a summary of joint research by the following members.

title:

“Deep neural network-based machine learning reduces the screening workload for systematic review: Investigation based on recent clinical guidelines”

Responsible author:

Tomohide Yamada King's College London Faculty of Life Science and Medicine University Institute for Population Health, Department of Diabetes and Metabolism, University of Tokyo

Co-author:

Daisuke Yoneoka St. Luke's International University Graduate School of Public Health

Hisashi Noma Data Science Research Institute, Institute of Statistical Mathematics

Yuuo Hiraike Department of Cell Biology, Harvard University

Toshimasa Yamauchi Department of Diabetes and Metabolism, University of Tokyo

Nobuhiro Shojima Department of Diabetes and Metabolism, University of Tokyo

Hiroyoshi Toyoshiba FRONTEO Inc. Life Science AI Business Headquarters Life Science AI CTO, Ph.D. (Mathematics)

Kimihiro Hino FRONTEO Inc. Life Science AI Business Headquarters Research and Development Department Research Team Researcher, Doctor of Engineering

This study considers the efficiency of systematic reviews and meta-analysis by utilizing artificial intelligence.

Systematic review is a method for researching and analyzing literature without bias, and meta-analysis is a statistical analysis method that integrates and analyzes the results of multiple studies.Both are important procedures in "Evidence-based Medicine", which is the way of medical treatment that uses the latest and most reliable medical knowledge. FRONTEO's life science AI solution is also being developed based on this EBM concept.

In this study, 8 randomized controlled trials^■In conducting a systematic review of, we used FRONTEO's natural language processing AI engine "Concept Encoder" to compare the workload of manual screening and screening by AI.As a result, it was proved that "Concept Encoder" can not only reduce the workload to less than 10/1, but also perform accurate reviews.The study also shows that training the right treatises with AI can improve accuracy.

At FRONTEO, we aim to realize a society where everyone can access reliable medical care by supporting efficient and innovative choices and decisions by all people involved in medical care, including research, development, clinical practice, and pharmaceuticals, with AI. I will.

* Randomized trial: A method in which research subjects are randomly divided into two groups, one of which is an intervention such as treatment that the study wants to evaluate, and the other is another intervention method to verify the effect.Improve the quality of evidence and reflect it in clinical guidelines by collecting multiple randomized controlled trials, reviewing them (systematic reviews), and analyzing them (meta-analysis).

■ About Concept Encoder

URL:https://lifescience.fronteo.com/technology/conceptencoder/

"Concept Encoder (registered trademark: concept encoder ®, reading: concept encoder)" is a natural language analysis AI (artificial intelligence) developed by FRONTEO specially in the life science field.It was developed in 2018 with the aim of effectively analyzing and utilizing medical data containing a large amount of free-form text data based on evidence. "Concept Encoder" can be co-analyzed with data other than text, and we are conducting research on co-analysis with numerical data such as gene expression information, vitals and various test values ​​accumulated in the life science field.Patent registration number: Patent No. 6346367

■FRONTEOabout　URL: https://www.fronteo.com/

FRONTEO supports corporate business by extracting meaningful and important information from a huge amount of text data using the in-house developed AI engine "KIBIT®" and "concept encoder®" that specialize in natural language processing. It is a data analysis company. Since its establishment in August 2003, it has been expanding globally to Japan, the United States, South Korea, and Taiwan, with a focus on legal tech businesses such as "e-discovery (electronic discovery)" and "digital forensic investigation" that support international litigation of companies. Has been deployed.Based on the AI ​​technology cultivated in the legal tech business, we will expand the business field to the life science field and business intelligence field from 8, and use AI to "turn text data into knowledge" to support drug discovery. , Dementia diagnosis support, financial, personnel, sales support, etc., contributing to solving various corporate issues. Listed on TSE Mothers on June 2014, 2007.The capital is 6 thousand yen (as of March 26, 2,568,651).