Using Behavioural AI for the Early Detection of Brain Cancer

  • Research type

    Research Study

  • Full title

    Using Behavioural AI for the Early Detection of Brain Cancer



  • Contact name

    Ryan Mathew

  • Contact email

  • Sponsor organisation

    University of Leeds

  • Duration of Study in the UK

    5 years, 0 months, 1 days

  • Research summary

    Rationale: We propose that since brain cancer is a solid, structural lesion affecting a person’s most functionally eloquent organ, its presence will cause differences in language processing, speech, personality and cognition, which can be detected using AI techniques. If changes in speech, language processing, personality and cognition are able to be detected, these may be used to develop an assistive behavioural AI tool to help diagnose brain tumours earlier and would allow for rapid testing in a clinical environment to help guide clinicians as to whether patients should be referred for further investigation. Using a tool to detect these changes earlier, or longitudinally over a short period of time, may allow for earlier imaging with a higher detection rate on imaging. Any technological device that helps stratify which patients with suspected brain cancer should be referred for further investigation would have substantial beneficial impacts on the healthcare service (e.g. increased patient safety and more efficient, cost-effective and evidence-based use of NHS resources), psychological wellbeing of patients and potentially result in better outcomes.

    Objective: We aim to explore the feasibility of a custom behavioural AI tool as an early detector of brain tumours which will support early diagnosis and more effective treatment of people with brain tumours.

    Study design: Feasibility study with semi-structured interviews.

    Study population: 450 adult (≥16 years of age) participants (imaging positive for a newly diagnosed brain tumour = c.150, imaging positive for a recurrent brain tumour = c.150 and imaging negative for brain tumour = c.150) in an outpatient setting.

    Intervention: Not applicable.

  • REC name

    North West - Greater Manchester West Research Ethics Committee

  • REC reference


  • Date of REC Opinion

    6 Oct 2021

  • REC opinion

    Further Information Favourable Opinion