Committed to connecting the world

Advanced Search

TG Falls: Topic Group on "Falls Among the Elderly"

Scope

This FG-AI4H topic group is dedicated to using artificial intelligence methods to prevent falls amongst the elderly.

How to join: Call for topic group participation
Topic description & status report

Management and Contact

Topic driver:

Inês Sousa (Fraunhofer Portugal)

Secretariat:

tsbfgai4h@itu.int

Activities

E-meetings

All parent group meetings

Participating

Documentation
Mailing list: fgai4h@lists.itu.int
Join the mailing list (ITU account needed):
Experts | Step-by-step
Collaboration site (ITU account needed - instructions)
Templates: Documents | Liaison Statements

Background

The FG-AI4H Topic Group on Falls Amongst the Elderly (TG-Falls) is dedicated to AI to prevent 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. Falls are also considered one of the main causes for loss of independence and institutionalization. In 10% of cases falls result in fractures, thus contributing to significant increases in morbidity and mortality. Direct health care costs associated with this phenomenon are high, reaching yearly costs of 25 billion euros in the European Union and 31 billion dollars in the United States of America. Falls have a multifactorial origin, however most of the fall risk factors are amendable by implementing falls prevention programs based on improving strength and balance and modifying behaviours. Even though, fall risk screenings and the implementation of such falls prevention programs are rarely part of the community-dwelling elder’s routine.

The current state of the art assessment of fall risk factors is based mainly in applying clinical scales, such as the Morse Fall Scale, Berg Balance Scale, and Performance Oriented Assessment of Mobility Problems in Elderly Patients. Despite being recommended by international health bodies, such as the National Institute for Health and Care excellence (NICE)1 , multifactorial assessment of fall risk factors is still not widespread in the clinical practice. One of the reasons for this shortcoming is the difficulty in combining the multiple parameters evaluated in a meaningful scale that is able to differentiate those who are more likely to fall in a period of time following the assessment. Artificial Intelligence (AI) techniques can be of great value in generating models that combine multiple sources of data and enable the implementation and standardization of a multifactorial assessment of the risk of falling. This would enable to raise awareness for multifactorial assessment of fall risk factors, contribute to standardize fall risk assessment and create tools to easily implement it in the clinical practice.