CHRONOSIG: Digital Triage for Secondary Mental Healthcare using Natural Language Processing - Rationale and Protocol

Abstract

Accessing specialist secondary mental health care in the NHS in England requires a referral, usually from primary or acute care. Community mental health teams triage these referrals deciding on the most appropriate team to meet patients needs. Referrals require resource-intensive review by clinicians and often, collation and review of the patient’s history with services captured in their electronic health records (EHR). Triage processes are, however, opaque and often result in patients not receiving appropriate and timely access to care that is a particular concern for some minority and under-represented groups. Our project, funded by the National Institute of Health Research (NIHR) will develop a clinical decision support tool (CDST) to deliver accurate, explainable and justified triage recommendations to assist clinicians and expedite access to secondary mental health care. Our proposed CDST will be trained on narrative free-text data combining referral documentation and historical EHR records for patients in the UK-CRIS database. This high-volume data set will enable training of end-to-end neural network natural language processing (NLP) to extract ‘signatures’ of patients who were (historically) triaged to different treatment teams. The resulting algorithm will be externally validated using data from different NHS trusts (Nottinghamshire Healthcare, Southern Health, West London and Oxford Health). We will use an explicit algorithmic fairness framework to mitigate risk of unintended harm evident in some artificial intelligence (AI) healthcare applications. Consequently, the performance of the CDST will be explicitly evaluated in simulated triage team scenarios where the tool augments clinician’s decision making, in contrast to traditional “human versus AI” performance metrics. The proposed CDST represents an important test-case for AI applied to real-world process improvement in mental health. The project leverages recent advances in NLP while emphasizing the risks and benefits for patients of AI-augmented clinical decision making. The project’s ambition is to deliver a CDST that is scalable and can be deployed to any mental health trust in England to assist with digital triage.

Dan W Joyce

Clinical Research Fellow

My research explores how computational methods can be used to improve personalisation of care for patients with mental illness

Andrey Kormilitzin

Senior Researcher

My research is centred around translating advances in mathematics, statistical machine learning and deep learning to address challenges involved in learning, inference and ethical decision making using complex biomedical and health data.

Julia Hamer-Hunt

Patient and Public Involvement Lead

I work within the Department of Psychiatry and the Oxford Health Biomedical Research Centre to promote patient and public involvement and engagement (PPI/E) in research.

Tony James

Consultant Child and Adolescent Psychiatrist

Dr Anthony James has been Consultant Child and Adolescent Psychiatrist at the Highfield Unit for 25 years. Dr James qualified at St Bartholomew’s Hospital London, undertook postgraduate medical training at St Bartholomew’s Hospital and specialist training in child and adolescent psychiatry at the Maudsley and Bethlem Hospitals. He has qualified in child psychotherapy and family therapy. His research work includes ADHD, psychopharmacology, epidemiology, psychosis using MRI, DTI and MEG, the care system, OCD, bipolar disorder, anxiety and depression. He has help set up the DBT service.

Alejo J Nevado-Holgado

Associate Professor

I am an Associate Professor of the Department of Psychiatry and the Big Data Institute, and part of Dementia Research Oxford. I am very glad to supervise the AI team in the TNDR, formed by 10 excellent machine learners and bioinformaticians. Our focus is on the applications of machine learning and bioinformatics to mental health care. In addition, I also hold a position at the Big Data Institute, where we collaborate in the application of machine learning to genomics and target discovery. I am also consultant to a number of AI companies.

Andrea Cipriani

Professor of Psychiatry

My main research interest is evidence-based mental health and precision psychiatry. My research focuses on the evaluation of pharmacological, psychological and psychosocial interventions, mainly about major depression, bipolar disorder and schizophrenia