AI4Health

Artificial Intelligence for Health

The ITU/WHO Focus Group on artificial intelligence for health (FG-AI4H) works in partnership with the World Health Organization (WHO) to establish a standardized assessment framework for the evaluation of AI-based methods for health, diagnosis, triage or treatment decisions. Participation in the FG-AI4H is free of charge and open to all. The group was established by ITU-T Study Group 16 at its meeting in Ljubljana, Slovenia, 9-20 July 2018.

The FG scope and general process are described in a commentary in The Lancet and a white paper. The documentation of all previous meetings can be found on the collaboration site.

Participation in the Focus Group is primarily through its online platforms such as the mailing list, the collaboration site, and e-meetings.

12th ITU/WHO Focus Group on AI for Health meeting

Virtual meeting, 19-21 May 2021

The goal of the Focus Group is to establish a standardized assessment framework for the evaluation of AI-based method for health. Participation is open and free of charge.

Developing a benchmarking process for health AI models that can act as an international, independent, standard evaluation framework. To establish this evaluation and benchmarking process, FG-AI4H is calling for participation from medical, public health, AI, data analytics, and policy experts.

Topic groups are being formed by communities of stakeholders allowing FG-AI4H to develop its processes for AI evaluation and benchmarking specific for each health topic. Each topic use case will be reviewed for its relevance and should impact a large and diverse part of the global population or solve a health problem that is difficult or expensive.

A multi-stakeholder, inter-disciplinary approach…

GOVERNMENT

INDUSTRY

UN AGENCIES

CIVIL SOCIETY

INTERNATIONAL ORGANIZATIONS

ACADEMIA

Topic Areas

Dermatology

One in every three cancers diagnosed is a skin cancer, and every year approximately 3 million new cases of skin cancer is detected worldwide, more than breast cancer, prostate cancer, lung cancer and colon cancer combined.

Falls among the elderly

Falls are one of the most common health problems in the elderly population, about a third of community-dwelling adults aged 65 years or older fall each year, and these events represent more than 50% of the hospitalizations due to lesions in this age group.

Ophthalmology

Dedicated to using artificial intelligence for the detection and diagnostics of ophthalmological diseases and conditions, in particular Diabetic Retinopathy (DR), from retinal images.

Psychiatry

Psychiatric disorders are among the most common and debilitating illnesses across the lifespan and begin usually prior to age 24, which emphasizes the need for increased focus on studies of the developing brain.

Symptom assessment

AI-based symptom assessment is one of the most promising applications in the field of AI4H. The World Health Organization estimates the shortage of Global Health workers to increase from 7.2 million in 2013 to 12.9 million by 2035.

Tuberculosis

Tuberculosis (TB) is a huge problem worldwide with about 50 % of the cases in BRICS countries. With an estimated 2.3 million reported cases in 2011 and an additional 1 million undocumented cases, India has the highest prevalence of TB in the world.

Snakebite and snake identification

Snakebite envenoming is a major global health issue and neglected humanitarian crisis. Today, 5 million snake bites occur globally every year causing 125,000 deaths and 400,000 victims of disability/disfigurement.

Cardiovascular disease risk prediction

Histopathology

Neuro-cognitive diseases

Outbreak dete​ction

Radiotherapy

Volumetric chest computed tomography​

Management Team

Chair of ITU/WHO Focus Group on AI for Health
,
Fraunhofer Heinrich Hertz Institute (HHI)
Senior Adviser, Division of data, analytics and delivery for impact
,
World Health Organization (WHO)
Lead AI for health
,
World Health Organization (WHO)
Chairman & Managing General Partner
,
REDDS Capital
Senior Editor of The Lancet and Vice-Chair of the ITU-WHO Focus Group on AI for Health
,
The Lancet Journal
| Products
365
Days
500
Speakers
25000
Community
152
+
Countries
45
% Women

Working Groups

WG-DAISAM

Data and AI solution assessment methods

WG-DASH

Data and AI solution ​handling

WG-O

Operations

WG-ETHICS

Ethical Considerations

WG-RC

Regulatory considerations on AI for health

WG-CE

Clinical Evaluation of AI for Health

How to Register

An ITU user account is required to register your interest in the AI for health activities.

Already have an ITU user account?


1. Log-in and complete the form to register for the FG-AI4H meeting.

– TIES access is not necessary to register.
– Indicate whether you will be participating on-site or remotely.
– Please note that visa assistance is only available for ITU members.


2. You will receive a confirmation email that you have been registered to the FG-AI4H meeting.

Not an ITU member?
Don’t have an account?


1. Visit the ITU User Account Log-in page and select “I am a new user”.

– If your organization is an ITU member, select the right category
(Attention! The Academia bullet is only for Academia members).
– If your organization is not an ITU member, choose “Non ITU members


2. Fill in the rest of the information. Once completed, you will immediately receive an email to activate your ITU user account.


3. Log-in and complete the form to register for the AI for FG-AI4H meeting

Subscribe to the Mailing List

Subscribe to the FG-AI4H mailing list to receive updat​es and announcements.

AI for Health mailing list


1. Click here to open ​the AI4H service directory​​.​


2. Select ​fgai4h mailing list and click Subscribe.​

Sign up online for a free ITU account


Follow the online process here; if any doubts, please see the video or PDF​ online guides; or ask the secretariat​)


NOTES​: Persons NOT working for an ITU member should select the option “Media/Non-member”. “Academia” in that page means academic institutions that are members of ITU. If in doubt, check the ​search page for ITU member organizations​.