AI-Enabled Mobile App for Safe Eating in Older Adults With Dysphagia

Overview

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 a smartphone application powered by artificial intelligence (AI) 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, and the app then estimates the texture level and provides guidance to help ensure it is safe to swallow. It also gives simple prompts to double-check food texture when needed. 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 16 weeks. Participants will continue their daily eating routines at home. The main question this study is trying to answer is: Does using the AI-enabled mobile app improve how often people eat foods that match their recommended safe texture level compared with usual care alone? The study will also examine whether the app helps reduce swallowing-related problems (such as choking), improves quality of life, and supports better overall eating ability. In addition, the study will evaluate how easy the app is to use and whether it places any burden on users. Hypothesis: The researchers hypothesize that participants who use the AI-enabled app, in addition to usual care, will more consistently follow recommended food texture guidelines and experience safer eating compared with those who receive usual care alone.

Dysphagia (swallowing impairment) is a highly prevalent condition in older adults and is associated with increased risks of aspiration, malnutrition, dehydration, and reduced quality of life. While the International Dysphagia Diet Standardization Initiative (IDDSI) framework provides standardized terminology and practical methods for modifying food and liquid textures, ensuring accurate and consistent adherence to prescribed texture levels remains challenging in community settings. In particular, adherence is often limited by the lack of real-time feedback, variable caregiver skills, and difficulties in verifying food texture during routine meal preparation. This study evaluates a novel, implementation-oriented digital health intervention designed to address these barriers. The intervention is an AI-enabled mobile application that supports real-time classification of food and liquid textures using smartphone-based image capture. The application incorporates a safety-first decision logic, providing conservative classification outputs alongside prompts encouraging users to verify textures using established IDDSI field tests (e.g., flow test, fork pressure test) when classification uncertainty is detected. The system is designed to function within everyday meal preparation workflows, thereby targeting behavioral adherence at the point of consumption rather than relying solely on retrospective education. The trial adopts a pragmatic, community-based randomized controlled design to assess real-world effectiveness under typical home-use conditions. The intervention is delivered over a defined period of active use, during which participants and/or caregivers may engage with the application during meal preparation, food purchase, or consumption. The application records usage metrics (e.g., frequency of image captures, classification outputs, and uncertainty prompts), enabling evaluation of engagement and fidelity. The intervention is supported by structured onboarding and ongoing technical support to ensure usability among older adults and their caregivers. The comparator reflects current standard practice in community dysphagia management and allows evaluation of the incremental benefit of digital decision support beyond education alone. The study is designed under a superiority framework to determine whether access to the AI-enabled tool results in meaningful improvements in behavioral adherence, which is considered the proximal mechanism linking dietary modification to downstream clinical outcomes. By focusing on adherence as the primary target, the study aligns with an implementation science perspective, recognizing that efficacy of dietary recommendations depends on their consistent and correct application in daily life. In addition to assessing behavioral outcomes, the trial incorporates a multidimensional evaluation framework spanning symptom burden, functional oral intake, health-related quality of life, and safety events. These domains provide a comprehensive understanding of both intended benefits and potential unintended consequences, including risks related to misclassification, over-reliance on automated guidance, or increased user burden. A subsample will undergo instrumental swallowing assessments to explore potential changes in swallowing physiology associated with improved adherence, thereby linking behavioral and mechanistic outcomes. The study also integrates human-technology interaction considerations, including usability and perceived workload, to evaluate implementation feasibility and scalability. These measures are important for determining whether the intervention can be sustainably adopted in routine practice, particularly among older populations with varying levels of digital literacy. From an analytical perspective, the trial is designed to estimate real-world effectiveness using an intention-to-treat framework, capturing the impact of offering the intervention under typical conditions rather than ideal adherence scenarios. Exploratory analyses will examine associations between engagement metrics and clinical outcomes, as well as potential effect modifiers such as baseline functional status, cognitive factors, and living arrangements. This research addresses a critical gap in dysphagia care by evaluating a scalable, technology-assisted approach that operationalizes standardized dietary guidelines in real-world settings. It also contributes to the emerging field of AI in healthcare by providing rigorous evidence from a randomized controlled trial conducted outside of highly controlled clinical environments. The findings are expected to inform both clinical practice and public health strategies aimed at improving safe eating behaviors among community-dwelling older adults with dysphagia.