1
|
Dubey S, Chan A, Adebajo AO, Walker D, Bukhari M. Artificial intelligence and machine learning in rheumatology. Rheumatology (Oxford) 2024; 63:2040-2041. [PMID: 38321364 DOI: 10.1093/rheumatology/keae092] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2023] [Revised: 11/28/2023] [Accepted: 02/01/2024] [Indexed: 02/08/2024] Open
Affiliation(s)
- Shirish Dubey
- Department of Rheumatology, Oxford University Hospitals NHS FT, Oxford, UK
- Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford, UK
| | - Antoni Chan
- Department of Rheumatology, Royal Berkshire NHS Foundation Trust, Reading, UK
- Henley Business School, University of Reading, Reading, UK
| | - Adewale O Adebajo
- Faculty of Medicine Dentistry and Health, University of Sheffield, Sheffield, UK
| | - David Walker
- Northumbria Healthcare NHS Foundation Trust, Newcastle upon Tyne, UK
| | - Marwan Bukhari
- Lancaster University, Lancaster, UK
- Rheumatology Department, Royal Lancaster Infirmary, Lancaster, UK
| |
Collapse
|
2
|
Duminuco A, Au Yeung J, Vaghela R, Virdee S, Woodley C, Asirvatham S, Curto‐Garcia N, Sriskandarajah P, O'Sullivan J, de Lavallade H, Radia D, Kordasti S, Palumbo G, Harrison C, Harrington P. Development of a natural language processing pipeline for assessment of cardiovascular risk in myeloproliferative neoplasms. Hemasphere 2024; 8:e143. [PMID: 39131900 PMCID: PMC11310405 DOI: 10.1002/hem3.143] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2024] [Revised: 06/18/2024] [Accepted: 07/16/2024] [Indexed: 08/13/2024] Open
Affiliation(s)
- Andrea Duminuco
- Department of HaematologyGuy's and St Thomas' NHS Foundation TrustLondonUK
- Haematology Unit with BMTA.O.U. Policlinico “G. Rodolico‐San Marco”CataniaItaly
| | | | - Raj Vaghela
- Department of HaematologyGuy's and St Thomas' NHS Foundation TrustLondonUK
| | - Sukhraj Virdee
- Department of HaematologyGuy's and St Thomas' NHS Foundation TrustLondonUK
| | - Claire Woodley
- Department of HaematologyGuy's and St Thomas' NHS Foundation TrustLondonUK
| | - Susan Asirvatham
- Department of HaematologyGuy's and St Thomas' NHS Foundation TrustLondonUK
| | | | | | | | | | - Deepti Radia
- Department of HaematologyGuy's and St Thomas' NHS Foundation TrustLondonUK
| | - Shahram Kordasti
- Department of HaematologyGuy's and St Thomas' NHS Foundation TrustLondonUK
- School of Cancer and Pharmaceutical Science, King's College LondonLondonUK
| | - Giuseppe Palumbo
- Haematology Unit with BMTA.O.U. Policlinico “G. Rodolico‐San Marco”CataniaItaly
| | - Claire Harrison
- Department of HaematologyGuy's and St Thomas' NHS Foundation TrustLondonUK
- School of Cancer and Pharmaceutical Science, King's College LondonLondonUK
| | - Patrick Harrington
- Department of HaematologyGuy's and St Thomas' NHS Foundation TrustLondonUK
- School of Cancer and Pharmaceutical Science, King's College LondonLondonUK
| |
Collapse
|
3
|
Kraljevic Z, Bean D, Shek A, Bendayan R, Hemingway H, Yeung JA, Deng A, Baston A, Ross J, Idowu E, Teo JT, Dobson RJB. Foresight-a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study. Lancet Digit Health 2024; 6:e281-e290. [PMID: 38519155 PMCID: PMC11220626 DOI: 10.1016/s2589-7500(24)00025-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2023] [Revised: 12/20/2023] [Accepted: 02/05/2024] [Indexed: 03/24/2024]
Abstract
BACKGROUND An electronic health record (EHR) holds detailed longitudinal information about a patient's health status and general clinical history, a large portion of which is stored as unstructured, free text. Existing approaches to model a patient's trajectory focus mostly on structured data and a subset of single-domain outcomes. This study aims to evaluate the effectiveness of Foresight, a generative transformer in temporal modelling of patient data, integrating both free text and structured formats, to predict a diverse array of future medical outcomes, such as disorders, substances (eg, to do with medicines, allergies, or poisonings), procedures, and findings (eg, relating to observations, judgements, or assessments). METHODS Foresight is a novel transformer-based pipeline that uses named entity recognition and linking tools to convert EHR document text into structured, coded concepts, followed by providing probabilistic forecasts for future medical events, such as disorders, substances, procedures, and findings. The Foresight pipeline has four main components: (1) CogStack (data retrieval and preprocessing); (2) the Medical Concept Annotation Toolkit (structuring of the free-text information from EHRs); (3) Foresight Core (deep-learning model for biomedical concept modelling); and (4) the Foresight web application. We processed the entire free-text portion from three different hospital datasets (King's College Hospital [KCH], South London and Maudsley [SLaM], and the US Medical Information Mart for Intensive Care III [MIMIC-III]), resulting in information from 811 336 patients and covering both physical and mental health institutions. We measured the performance of models using custom metrics derived from precision and recall. FINDINGS Foresight achieved a precision@10 (ie, of 10 forecasted candidates, at least one is correct) of 0·68 (SD 0·0027) for the KCH dataset, 0·76 (0·0032) for the SLaM dataset, and 0·88 (0·0018) for the MIMIC-III dataset, for forecasting the next new disorder in a patient timeline. Foresight also achieved a precision@10 value of 0·80 (0·0013) for the KCH dataset, 0·81 (0·0026) for the SLaM dataset, and 0·91 (0·0011) for the MIMIC-III dataset, for forecasting the next new biomedical concept. In addition, Foresight was validated on 34 synthetic patient timelines by five clinicians and achieved a relevancy of 33 (97% [95% CI 91-100]) of 34 for the top forecasted candidate disorder. As a generative model, Foresight can forecast follow-on biomedical concepts for as many steps as required. INTERPRETATION Foresight is a general-purpose model for biomedical concept modelling that can be used for real-world risk forecasting, virtual trials, and clinical research to study the progression of disorders, to simulate interventions and counterfactuals, and for educational purposes. FUNDING National Health Service Artificial Intelligence Laboratory, National Institute for Health and Care Research Biomedical Research Centre, and Health Data Research UK.
Collapse
Affiliation(s)
- Zeljko Kraljevic
- Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK; National Institute for Health and Care Research (NIHR) Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King's College London, London, UK
| | - Dan Bean
- Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK; National Institute for Health and Care Research (NIHR) Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King's College London, London, UK
| | - Anthony Shek
- Department of Neurology, King's College Hospital National Health Service (NHS) Foundation Trust, London, UK; Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Rebecca Bendayan
- Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK; National Institute for Health and Care Research (NIHR) Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King's College London, London, UK
| | - Harry Hemingway
- Health Data Research UK London and Institute of Health Informatics, University College London, London, UK; NIHR Biomedical Research Centre at University College London Hospitals NHS Foundation Trust, London, UK
| | - Joshua Au Yeung
- Department of Neurology, King's College Hospital National Health Service (NHS) Foundation Trust, London, UK; Guy's and St Thomas' NHS Foundation Trust, London, UK
| | | | - Alfred Baston
- Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Jack Ross
- Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Esther Idowu
- Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - James T Teo
- Department of Neurology, King's College Hospital National Health Service (NHS) Foundation Trust, London, UK; Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Richard J B Dobson
- Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK; Health Data Research UK London and Institute of Health Informatics, University College London, London, UK; National Institute for Health and Care Research (NIHR) Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King's College London, London, UK; NIHR Biomedical Research Centre at University College London Hospitals NHS Foundation Trust, London, UK.
| |
Collapse
|
4
|
Wu J, Biswas D, Ryan M, Bernstein BS, Rizvi M, Fairhurst N, Kaye G, Baral R, Searle T, Melikian N, Sado D, Lüscher TF, Grocott-Mason R, Carr-White G, Teo J, Dobson R, Bromage DI, McDonagh TA, Shah AM, O'Gallagher K. Artificial intelligence methods for improved detection of undiagnosed heart failure with preserved ejection fraction. Eur J Heart Fail 2024; 26:302-310. [PMID: 38152863 DOI: 10.1002/ejhf.3115] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Revised: 10/20/2023] [Accepted: 12/07/2023] [Indexed: 12/29/2023] Open
Abstract
AIM Heart failure with preserved ejection fraction (HFpEF) remains under-diagnosed in clinical practice despite accounting for nearly half of all heart failure (HF) cases. Accurate and timely diagnosis of HFpEF is crucial for proper patient management and treatment. In this study, we explored the potential of natural language processing (NLP) to improve the detection and diagnosis of HFpEF according to the European Society of Cardiology (ESC) diagnostic criteria. METHODS AND RESULTS In a retrospective cohort study, we used an NLP pipeline applied to the electronic health record (EHR) to identify patients with a clinical diagnosis of HF between 2010 and 2022. We collected demographic, clinical, echocardiographic and outcome data from the EHR. Patients were categorized according to the left ventricular ejection fraction (LVEF). Those with LVEF ≥50% were further categorized based on whether they had a clinician-assigned diagnosis of HFpEF and if not, whether they met the ESC diagnostic criteria. Results were validated in a second, independent centre. We identified 8606 patients with HF. Of 3727 consecutive patients with HF and LVEF ≥50% on echocardiogram, only 8.3% had a clinician-assigned diagnosis of HFpEF, while 75.4% met ESC criteria but did not have a formal diagnosis of HFpEF. Patients with confirmed HFpEF were hospitalized more frequently; however the ESC criteria group had a higher 5-year mortality, despite being less comorbid and experiencing fewer acute cardiovascular events. CONCLUSIONS This study demonstrates that patients with undiagnosed HFpEF are an at-risk group with high mortality. It is possible to use NLP methods to identify likely HFpEF patients from EHR data who would likely then benefit from expert clinical review and complement the use of diagnostic algorithms.
Collapse
Affiliation(s)
- Jack Wu
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
| | - Dhruva Biswas
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- King's College Hospital NHS Foundation Trust, London, UK
| | - Matthew Ryan
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- King's College Hospital NHS Foundation Trust, London, UK
| | - Brett S Bernstein
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- King's College Hospital NHS Foundation Trust, London, UK
| | - Maleeha Rizvi
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- Guy's and St Thomas' Hospital, Guy's and St Thomas' NHS Foundation Trust, London, UK
| | | | - George Kaye
- King's College Hospital NHS Foundation Trust, London, UK
| | - Ranu Baral
- King's College Hospital NHS Foundation Trust, London, UK
| | - Tom Searle
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
| | - Narbeh Melikian
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- King's College Hospital NHS Foundation Trust, London, UK
| | - Daniel Sado
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- King's College Hospital NHS Foundation Trust, London, UK
| | - Thomas F Lüscher
- Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Richard Grocott-Mason
- Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Gerald Carr-White
- Guy's and St Thomas' Hospital, Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - James Teo
- King's College Hospital NHS Foundation Trust, London, UK
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
| | - Richard Dobson
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
| | - Daniel I Bromage
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- King's College Hospital NHS Foundation Trust, London, UK
| | - Theresa A McDonagh
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- King's College Hospital NHS Foundation Trust, London, UK
| | - Ajay M Shah
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- King's College Hospital NHS Foundation Trust, London, UK
| | - Kevin O'Gallagher
- School of Cardiovascular and Metabolic Medicine & Sciences, British Heart Foundation Centre of Research Excellence, King's College London, London, UK
- King's College Hospital NHS Foundation Trust, London, UK
| |
Collapse
|
5
|
Au Yeung J, Wang YY, Kraljevic Z, Teo JTH. Artificial intelligence (AI) for neurologists: do digital neurones dream of electric sheep? Pract Neurol 2023; 23:476-488. [PMID: 37977806 DOI: 10.1136/pn-2023-003757] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/29/2023] [Indexed: 11/19/2023]
Abstract
Artificial intelligence (AI) is routinely mentioned in journals and newspapers, and non-technical outsiders may have difficulty in distinguishing hyperbole from reality. We present a practical guide to help non-technical neurologists to understand healthcare AI. AI is being used to support clinical decisions in treating neurological disorders. We introduce basic concepts of AI, such as machine learning and natural language processing, and explain how AI is being used in healthcare, giving examples its benefits and challenges. We also cover how AI performance is measured, and its regulatory aspects in healthcare. An important theme is that AI is a general-purpose technology like medical statistics, with broad utility applicable in various scenarios, such that niche approaches are outpaced by approaches that are broadly applicable in many disease areas and specialties. By understanding AI basics and its potential applications, neurologists can make informed decisions when evaluating AI used in their clinical practice. This article was written by four humans, with generative AI helping with formatting and image generation.
Collapse
Affiliation(s)
- Joshua Au Yeung
- CogStack team, Guy's and St Thomas' NHS Foundation Trust, London, UK
- CogStack team, King's College Hospital NHS Foundation Trust, London, London, UK
| | - Yang Yang Wang
- Medicine, Guy's and St Thomas' Hospitals NHS Trust, London, London, UK
| | - Zeljko Kraljevic
- Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
| | - James T H Teo
- CogStack team, Guy's and St Thomas' NHS Foundation Trust, London, UK
- CogStack team, King's College Hospital NHS Foundation Trust, London, London, UK
- Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
| |
Collapse
|