Clinical Research Directory
Browse clinical research sites, groups, and studies.
AI-Enabled Mobile App for Safe Eating in Older Adults With Dysphagia
Sponsor: KAM Chi Shan Anna
Summary
Difficulty swallowing (called dysphagia) is common in older adults and can make eating and drinking unsafe. It may lead to serious problems such as choking, lung infections, poor nutrition, and reduced quality of life. One common way to reduce these risks is to modify food and drink textures (for example, making foods softer or liquids thicker). However, people often find it difficult to prepare food at the correct texture level in everyday life, especially at home, which may reduce the effectiveness of this approach. This study aims to test whether an artificial intelligence (AI)- powered smartphone application can help older adults with swallowing difficulties eat more safely. The app allows users (or their caregivers) to take a photo of food or drinks, then estimates the texture level and provides guidance to help them follow their recommended food texture level. It also gives simple prompts to double-check food texture when needed. The app is intended as a decision-support tool and does not replace clinical advice or prescribed dietary recommendations. In this clinical trial, community-dwelling adults aged 60 years or above with swallowing difficulties will be randomly assigned to one of two groups. One group will receive usual care, which includes education about safe swallowing and written instructions on appropriate food textures. The other group will receive the same usual care plus access to the AI-enabled mobile app for 12 weeks. Participants will continue their daily eating routines at home. Participants will also be followed for an additional 8 weeks after the 12-week intervention period. The main question this study aims to answer is: Does using the AI-enabled mobile app increase the frequency with which people eat foods that match their recommended safe texture level compared with usual care alone? This will be assessed at Week 12 using a structured 3-day dietary record and accompanying meal photographs. The study will also examine whether the app helps reduce swallowing-related symptoms and adverse events, improves swallowing-related quality of life, and increases confidence in managing swallowing difficulties. In addition, the study will evaluate how easy the app is to use and whether it places any burden on users. Hypothesis: Participants who use the AI-enabled app, in addition to usual care, will more consistently follow recommended food texture guidelines than those who receive usual care alone.
Official title: Efficacy of an AI-enabled Mobile Application for Safe Eating in Community-dwelling Older Adults With Dysphagia: a Randomized Controlled Trial
Key Details
Gender
All
Age Range
60 Years - Any
Study Type
INTERVENTIONAL
Enrollment
332
Start Date
2028-01
Completion Date
2030-12
Last Updated
2026-09-23
Healthy Volunteers
No
Conditions
Interventions
AI-Enabled Mobile Application plus Standard Care
A smartphone-based application that uses artificial intelligence to classify food and liquid textures from images captured by the user. The application provides real-time guidance aligned with standardized dysphagia diet levels and delivers safety-focused prompts to verify texture using simple methods when needed. The tool is designed to support safe meal preparation and improve adherence to prescribed texture-modified diets in daily home settings. Participants receive onboarding and use the application during meals throughout the intervention period.
Standard Dysphagia Education
A structured education session providing guidance on safe swallowing practices and preparation of texture-modified foods and liquids. Participants receive printed educational materials describing appropriate food textures and simple methods for checking consistency. This reflects usual care in community dysphagia management and does not include digital or automated decision support.
Locations (1)
The Education University of Hong Kong
Hong Kong, Hong Kong