Discriminating pituitary from glaucomatous visual fields

  • Research type

    Research Study

  • Full title

    Using machine learning to explore automated discrimination between visual field loss caused by pituitary pathology and glaucoma.

  • IRAS ID

    232104

  • Contact name

    Peter Thomas

  • Contact email

    peterthomas2@nhs.net

  • Sponsor organisation

    Cambridge University Hospitals Foundation Trust

  • Duration of Study in the UK

    0 years, 9 months, 1 days

  • Research summary

    Many diseases of the eye and brain can cause patients to lose areas of vision in one or both eyes. We assess these by performing a visual field test. Different diseases cause different, often characteristic, patterns of visual field loss. The most common disease affecting visual fields is glaucoma. However, it is a known clinical pitfall that some patients with non-glaucoma diseases can end up being treated for glaucoma.

    In this study, we aim to apply machine learning (artificial intelligence) techniques to train computers to discriminate visual field defects caused by glaucoma from visual field defects caused by diseases (generally tumours) of the pituitary gland. This could allow automatic detection of visual field loss related to non-glaucoma diseases, and thus enhance patient safety.

  • REC name

    South West - Cornwall & Plymouth Research Ethics Committee

  • REC reference

    17/SW/0197

  • Date of REC Opinion

    16 Aug 2017

  • REC opinion

    Favourable Opinion