Food quantification using a novel, user friendly plate imaging system.

  • Research type

    Research Study

  • Full title

    Using a novel, user friendly plate imaging system to quantify food consumption in hospitals.

  • IRAS ID

    343406

  • Contact name

    Caroline Childs

  • Contact email

    c.e.childs@soton.ac.uk

  • Sponsor organisation

    University of Southampton

  • Duration of Study in the UK

    0 years, 6 months, 30 days

  • Research summary


    Accurate dietary intake monitoring is essential to provide appropriate treatment for patients at risk of malnutrition, but collection of food intake data in hospital is a difficult and resource-intensive task. Paper food record charts are often inaccurate or incomplete due to competing responsibilities and tasks at mealtimes, inadequate training, or removal of food trays before staff have observed intakes. Malnutrition within the hospital setting therefore continues to be under-identified and under-treated. In line with the NHS long-term plan and the UHS digital team's plan for a paperless digital Trust, a digital dietary assessment tool would provide a valid and reliable tool to accurately monitor dietary intakes. Electronic records will enable examination of longitudinal changes in intakes and/or dietary quality, and to identify patterns of intakes associated with positive or negative clinical outcomes. There is therefore a novel opportunity to use a system based on Artificial Intelligence to automatically measure dietary intake in hospitals to transform patient care.

    A plate imaging system prototype has been developed by researchers within the Faculty of Medicine and the Faculty of Electronics and Computer Sciences. The system automates the process of recording patient food intake by using a range of sensors and AI algorithms to estimate nutritional intake from meals. The system is composed of a camera, a user-interface/screen and a tray holder with a QR code and weight sensor. A QR code links a patient’s ID number to a patient’s tray. The data generated is stored on a server for analysis.

    The pilot study will take place at University Hospital Southampton. Participants in the study are patients on a stroke rehabilitation ward. The study is planned for a duration of 12 weeks. Patients meals before and after consumption will be photographed using a plate imaging system by a researcher and away from the patients.

  • REC name

    South Central - Hampshire A Research Ethics Committee

  • REC reference

    25/SC/0183

  • Date of REC Opinion

    5 Aug 2025

  • REC opinion

    Further Information Favourable Opinion