publications

@article{9b9767f517a040f4822591145f8c61a8,

title = {Artificial intelligence to enhance clinical value across the spectrum of cardiovascular healthcare: artificial intelligence framework},

author = {Simrat Gill and Andreas Karwath and Hae-Won Uh and Victor Roth Cardoso and Zhujie Gu and Andrey Barsky and Luke Slater and Animesh Acharjee and Jinming Duan and Lorenzo DallÓlio and Said el Bouhaddani and Saisakul Chernbumroong and Mary Stanbury and Sandra Haynes and Folkert W Asselbergs and Diederick Grobbee and Marinus Eijkemans and Georgios Gkoutos and Dipak Kotecha and group BigData@Heart Consortium },

doi = {10.1093/eurheartj/ehac758},

issn = {0195-668X},

year  = {2023},

date = {2023-01-11},

urldate = {2023-01-11},

journal = {European Heart Journal},

publisher = {Öxford University Press},

abstract = {Artificial intelligence (AI) is increasingly being utilized in healthcare. This article provides clinicians and researchers with a step-wise foundation for high-value AI that can be applied to a variety of different data modalities. The aim is to improve the transparency and application of AI methods, with the potential to benefit patients in routine cardiovascular care. Following a clear research hypothesis, an AI-based workflow begins with data selection and pre-processing prior to analysis, with the type of data (structured, semi-structured, or unstructured) determining what type of pre-processing steps and machine-learning algorithms are required. Algorithmic and data validation should be performed to ensure the robustness of the chosen methodology, followed by an objective evaluation of performance. Seven case studies are provided to highlight the wide variety of data modalities and clinical questions that can benefit from modern AI techniques, with a focus on applying them to cardiovascular disease management.Despite the growing use of AI, further education for healthcare workers, researchers, and the public are needed to aid understanding of how AI works and to close the existing gap in knowledge. In addition, issues regarding data access, sharing, and security must be addressed to ensure full engagement by patients and the public. The application of AI within healthcare provides an opportunity for clinicians to deliver a more personalized approach to medical care by accounting for confounders, interactions, and the rising prevalence of multi-morbidity."},

note = {textcopyright The Author(s) 2023. Published by Oxford University Press on behalf of the European Society of Cardiology.},

keywords = {artificial intelligence, cardiology, EHR, health data science},

pubstate = {published},

tppubtype = {article}

}

@article{Manley_2022,

title = {Use of HbA1c for new diagnosis of diabetes in those with hyperglycaemia on admission to or attendance at hospital urgently requires research},

author = {Susan Elisabeth Manley and Andreas Karwath and John Williams and Peter Nightingale and Jonathan Webber and Rajeev Raghavan and Alison Barratt and Craig Webster and Rachel Round and Irene Stratton and Georgios Gkoutos and Graham Roberts and Samiul Mostafa and Sandip Ghosh},

url = {https://doi.org/10.15277%2Fbjd.2022.386},

doi = {10.15277/bjd.2022.386},

year  = {2022},

date = {2022-12-01},

urldate = {2022-12-01},

journal = {British Journal of Diabetes},

volume = {22},

number = {2},

pages = {95--104},

publisher = {ABCD Diabetes Care, Ltd.},

keywords = {diabetes, EHR, health data science, medicine},

pubstate = {published},

tppubtype = {article}

}

@article{WILLIAMS_2022,

title = {133-LB: Relationship of HbA1c and Glucose by Ethnicity in UK Biobank},

author = {John A. Williams and Andreas Karwath and Rachel A. Round and Irene M. Stratton and Sandip Ghosh and Samiul Mostafa and Graham Roberts and Jonathan Webber and Georgios Gkoutos and Susan E. Manley},

url = {https://doi.org/10.2337%2Fdb22-133-lb},

doi = {10.2337/db22-133-lb},

year  = {2022},

date = {2022-06-01},

urldate = {2022-06-01},

journal = {Diabetes},

volume = {71},

number = {Supplement_1},

publisher = {American Diabetes Association},

keywords = {diabetes, EHR, health data science, medicine, UKBiobank},

pubstate = {published},

tppubtype = {article}

}

@article{KARWATH_2022,

title = {973-P: By How Much Does Red Blood Cell Status Affect the Accuracy of HbA1c?},

author = {Andreas Karwath and John A. Williams and Rachel A. Round and Irene M. Stratton and Georgios Gkoutos and Samiul Mostafa and Graham Roberts and Jonathan Webber and Susan E. Manley},

url = {https://doi.org/10.2337%2Fdb22-973-p},

doi = {10.2337/db22-973-p},

year  = {2022},

date = {2022-06-01},

urldate = {2022-06-01},

journal = {Diabetes},

volume = {71},

number = {Supplement_1},

publisher = {American Diabetes Association},

keywords = {diabetes, EHR, health data science, medicine},

pubstate = {published},

tppubtype = {article}

}

@article{Chapman_2021,

title = {Desiderata for the development of next-generation electronic health record phenotype libraries},

author = {Martin Chapman and Shahzad Mumtaz and Luke V Rasmussen and Andreas Karwath and Georgios V Gkoutos and Chuang Gao and Dan Thayer and Jennifer A Pacheco and Helen Parkinson and Rachel L Richesson and Emily Jefferson and Spiros Denaxas and Vasa Curcin},

url = {https://doi.org/10.1093%2Fgigascience%2Fgiab059},

doi = {10.1093/gigascience/giab059},

year  = {2021},

date = {2021-09-01},

urldate = {2021-09-01},

journal = {GigaScience},

volume = {10},

number = {9},

publisher = {Oxford University Press (OUP)},

keywords = {EHR, health data science, phenotypes, validation},

pubstate = {published},

tppubtype = {article}

}

@article{Karwath_2021,

title = {Redefining beta-blocker response in heart failure patients with sinus rhythm and atrial fibrillation: a machine learning cluster analysis},

author = {Andreas Karwath and Karina V Bunting and Simrat K Gill and Otilia Tica and Samantha Pendleton and Furqan Aziz and Andrey D Barsky and Saisakul Chernbumroong and Jinming Duan and Alastair R Mobley and Victor Roth Cardoso and Luke Slater and John A Williams and Emma-Jane Bruce and Xiaoxia Wang and Marcus D Flather and Andrew J S Coats and Georgios V Gkoutos and Dipak Kotecha},

url = {https://doi.org/10.1016%2Fs0140-6736%2821%2901638-x},

doi = {10.1016/s0140-6736(21)01638-x},

year  = {2021},

date = {2021-08-01},

urldate = {2021-08-01},

journal = {The Lancet},

publisher = {Elsevier BV},

abstract = {Background

Mortality remains unacceptably high in patients with heart failure and reduced left ventricular ejection fraction (LVEF) despite advances in therapeutics. We hypothesised that a novel artificial intelligence approach could better assess multiple and higher-dimension interactions of comorbidities, and define clusters of β-blocker efficacy in patients with sinus rhythm and atrial fibrillation.

Methods

Neural network-based variational autoencoders and hierarchical clustering were applied to pooled individual patient data from nine double-blind, randomised, placebo-controlled trials of β blockers. All-cause mortality during median 1·3 years of follow-up was assessed by intention to treat, stratified by electrocardiographic heart rhythm. The number of clusters and dimensions was determined objectively, with results validated using a leave-one-trial-out approach. This study was prospectively registered with ClinicalTrials.gov (NCT00832442) and the PROSPERO database of systematic reviews (CRD42014010012).

Findings

15 659 patients with heart failure and LVEF of less than 50% were included, with median age 65 years (IQR 56–72) and LVEF 27% (IQR 21–33). 3708 (24%) patients were women. In sinus rhythm (n=12 822), most clusters demonstrated a consistent overall mortality benefit from β blockers, with odds ratios (ORs) ranging from 0·54 to 0·74. One cluster in sinus rhythm of older patients with less severe symptoms showed no significant efficacy (OR 0·86, 95% CI 0·67–1·10; p=0·22). In atrial fibrillation (n=2837), four of five clusters were consistent with the overall neutral effect of β blockers versus placebo (OR 0·92, 0·77–1·10; p=0·37). One cluster of younger atrial fibrillation patients at lower mortality risk but similar LVEF to average had a statistically significant reduction in mortality with β blockers (OR 0·57, 0·35–0·93; p=0·023). The robustness and consistency of clustering was confirmed for all models (p<0·0001 vs random), and cluster membership was externally validated across the nine independent trials.

Interpretation

An artificial intelligence-based clustering approach was able to distinguish prognostic response from β blockers in patients with heart failure and reduced LVEF. This included patients in sinus rhythm with suboptimal efficacy, as well as a cluster of patients with atrial fibrillation where β blockers did reduce mortality.

Funding

Medical Research Council, UK, and EU/EFPIA Innovative Medicines Initiative BigData@Heart.},

keywords = {artificial intelligence, clustering, crossvalidation, deep learning, EHR, health data science, phenotypes, validation},

pubstate = {published},

tppubtype = {article}

}