User profiles for "author:Joshua Au Yeung"

Joshua Au Yeung

King's College Hospital NHS Trust
Verified email at nhs.net
Cited by 84

[HTML][HTML] AI chatbots not yet ready for clinical use

J Au Yeung, Z Kraljevic, A Luintel, A Balston… - Frontiers in digital …, 2023 - frontiersin.org
As large language models (LLMs) expand and become more advanced, so do the natural
language processing capabilities of conversational AI, or 'chatbots'. OpenAI's recent release …

[HTML][HTML] Foresight—a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study

Z Kraljevic, D Bean, A Shek, R Bendayan… - The Lancet Digital …, 2024 - thelancet.com
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 …

Artificial intelligence (AI) for neurologists: do digital neurones dream of electric sheep?

JA Yeung, YY Wang, Z Kraljevic, JTH Teo - Practical neurology, 2023 - pn.bmj.com
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 …

Foresight--generative pretrained transformer (GPT) for modelling of patient timelines using Ehrs

Z Kraljevic, D Bean, A Shek, R Bendayan… - arXiv preprint arXiv …, 2022 - arxiv.org
Background: Electronic Health Records hold detailed longitudinal information about each
patient's health status and general clinical history, a large portion of which is stored within …

Machine learning‐enabled multitrust audit of stroke comorbidities using natural language processing

A Shek, Z Jiang, J Teo, J Au Yeung… - European Journal of …, 2021 - Wiley Online Library
Background and purpose With the increasing adoption of electronic records in the health
system, machine learning‐enabled techniques offer the opportunity for greater computer …

Dietary nitrate prevents progression of carotid subclinical atherosclerosis through blood pressure‐independent mechanisms in patients with or at risk of type 2 …

F Morselli, L Faconti, CE Mills, S Morant… - British Journal of …, 2021 - Wiley Online Library
Aims To test if 6 months' intervention with dietary nitrate and spironolactone could affect
carotid subclinical atherosclerosis and stiffness, respectively, vs. placebo/doxazosin, to …

[HTML][HTML] Streams, rivers and data lakes: an introduction to understanding modern electronic healthcare records

EAA Idowu, J Teo, S Salih, J Valverde… - Clinical Medicine, 2023 - ncbi.nlm.nih.gov
As foundation doctors, we have often found ourselves informing patients that a certain
aspect of their medical information cannot be immediately found, either because it is on an …

Validating transformers for redaction of text from electronic health records in real-world healthcare

Z Kraljevic, A Shek, JA Yeung… - 2023 IEEE 11th …, 2023 - ieeexplore.ieee.org
Protecting patient privacy in healthcare records is a top priority, and redaction is a commonly
used method for obscuring directly identifiable information in text. Rule-based methods have …

Enhanced Cardiovascular Risk Assessment Incorporating Natural Language Processing and Qrisk-3 Score Determination in Patients with Essential …

P Harrington, A Duminuco, JA Yeung, SS Virdee… - Blood, 2023 - Elsevier
Introduction: Fundamental to management of patients with essential thrombocythaemia (ET)
is assessment, and reduction of thrombotic risk. We present a machine learning approach to …

[PDF][PDF] Foresight-Deep Generative Modelling of Patient Timelines using Electronic Health Records

Z Kraljevic, D Bean, A Shek, R Bendayan, JA Yeung… - CoRR, 2022 - kclpure.kcl.ac.uk
Abstract Background: Electronic Health Records (EHRs) hold detailed longitudinal
information about each patient's health status and general clinical history, a large portion of …