publications

@article{9b13f3c6d25842a9bd3efe7343c24a41,

title = {Systematic review of patients’ and healthcare professionals’ views on patient‐initiated follow‐up in treated cancer patients},

author = {Janine Dretzke and Ava Lorenc and Ada Adriano and Clare Herd and Hisham Mehanna and Paul Nankivell and David J. Moore and Andreas Karwath and Barry Main and Charlotte Firth and Claire Gaunt and Colin Greaves and Eila Watson and Georgios Gkoutos and Gozde Ozakinci and Jane Wolstenholme and Jo Brett and Joan Duda and Lauren Matheson and Louise‐Rae Cherrill and Melanie Calvert and Philip Kiely and Piers Gaunt and Saisakul Chernbumroong and Saloni Mittal and Steve Thomas and Stuart Winter and Wai Lup Wong and PETNECK2 Research Team },

doi = {10.1002/cam4.6243},

issn = {2045-7634},

year  = {2023},

date = {2023-06-16},

urldate = {2023-06-16},

journal = {Cancer Medicine},

publisher = {John Wiley & Sons},

abstract = {Background: Current follow‐up models in cancer are seen to be unsustainable and inflexible, and there is growing interest in alternative models, such as patient‐initiated follow‐up (PIFU). It is therefore important to understand whether PIFU is acceptable to patients and healthcare professionals (HCPs). Methods: Standard systematic review methodology aimed at limiting bias was used for study identification (to January 2022), selection and data extraction. Thematic synthesis was undertaken for qualitative data, and survey findings were tabulated and described. Results: Nine qualitative studies and 22 surveys were included, mainly in breast and endometrial cancer. Women treated for breast or endometrial cancer and HCPs were mostly supportive of PIFU. Facilitators for PIFU included convenience, control over own health and avoidance of anxiety‐inducing clinic appointments. Barriers included loss of reassurance from scheduled visits and lack of confidence in self‐management. HCPs were supportive of PIFU but concerned about resistance to change, unsuitability of PIFU for some patients and costs. Conclusion: PIFU is viewed mostly positively by women treated for breast or endometrial cancer, and by HCPs, but further evidence is needed from a wider range of cancers, men, and more representative samples. A protocol was registered with PROSPERO (CRD42020181412).},

keywords = {cancer, health data science, medicine, systematic review},

pubstate = {published},

tppubtype = {article}

}

@article{Taib_2023,

title = {Artificial intelligence in the management and treatment of burns: A systematic review and meta-analyses},

author = {Bilal Gani Taib and Andreas Karwath and K. Wensley and L. Minku and G. V. Gkoutos and N. Moiemen},

url = {https://doi.org/10.1016%2Fj.bjps.2022.11.049},

doi = {10.1016/j.bjps.2022.11.049},

year  = {2023},

date = {2023-02-01},

urldate = {2023-02-01},

journal = {Journal of Plastic, Reconstructive & Aesthetic Surgery},

volume = {77},

pages = {133--161},

publisher = {Elsevier BV},

keywords = {burns, health data science, medicine, systematic review},

pubstate = {published},

tppubtype = {article}

}

@article{Slater_2023,

title = {Klarigi: Characteristic explanations for semantic biomedical data},

author = {Luke T. Slater and John A. Williams and Paul N. Schofield and Sophie Russell and Samantha C. Pendleton and Andreas Karwath and Hilary Fanning and Simon Ball and Robert Hoehndorf and Georgios V. Gkoutos},

url = {https://doi.org/10.1016%2Fj.compbiomed.2022.106425},

doi = {10.1016/j.compbiomed.2022.106425},

year  = {2023},

date = {2023-02-01},

urldate = {2023-02-01},

journal = {Computers in Biology and Medicine},

volume = {153},

pages = {106425},

publisher = {Elsevier BV},

keywords = {artificial intelligence, health data science, NLP},

pubstate = {published},

tppubtype = {article}

}

@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{Wu_2022,

title = {A survey on clinical natural language processing in the United Kingdom from 2007 to 2022},

author = {Honghan Wu and Minhong Wang and Jinge Wu and Farah Francis and Yun-Hsuan Chang and Alex Shavick and Hang Dong and Michael T. C. Poon and Natalie Fitzpatrick and Adam P. Levine and Luke T. Slater and Alex Handy and Andreas Karwath and Georgios V. Gkoutos and Claude Chelala and Anoop Dinesh Shah and Robert Stewart and Nigel Collier and Beatrice Alex and William Whiteley and Cathie Sudlow and Angus Roberts and Richard J. B. Dobson},

url = {https://doi.org/10.1038%2Fs41746-022-00730-6},

doi = {10.1038/s41746-022-00730-6},

year  = {2022},

date = {2022-12-01},

urldate = {2022-12-01},

journal = {npj Digital Medicine},

volume = {5},

number = {1},

publisher = {Springer Science and Business Media LLC},

keywords = {artificial intelligence, health data science, NLP},

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{K_ppel_2022,

title = {Learning to rank Higgs boson candidates},

author = {Marius Köppel and Alexander Segner and Martin Wagener and Lukas Pensel and Andreas Karwath and Christian Schmitt and Stefan Kramer},

url = {https://doi.org/10.1038/s41598-022-10383-w},

doi = {10.1038/s41598-022-10383-w},

year  = {2022},

date = {2022-07-01},

urldate = {2022-07-01},

journal = {Scientific Reports},

volume = {12},

number = {1},

publisher = {Springer Science and Business Media LLC},

keywords = {learning to rank},

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{Lorenc_2022,

title = {Clinicians' Views of Patient-initiated Follow-up in Head and Neck Cancer: a Qualitative Study to Inform the PETNECK2 Trial},

author = {A Lorenc and M Wells and T Fulton-Lieuw and P Nankivell and H Mehanna and M Jepson and Andreas Karwath and B Main and C Firth and C Gaunt and C Greaves and D Moore and E Watson and G Gkoutos and G Ozakinci and J Wolstenholme and J Dretzke and J Brett and J Duda and L Matheson and L -R Cherrill and M Calvert and P Kiely and P Gaunt and S Chernbumroong and S. Mittal and S. Thomas and S. Winter and W. Wong},

url = {https://doi.org/10.1016%2Fj.clon.2021.11.010},

doi = {10.1016/j.clon.2021.11.010},

year  = {2022},

date = {2022-04-01},

urldate = {2022-04-01},

journal = {Clinical Oncology},

volume = {34},

number = {4},

pages = {230--240},

publisher = {Elsevier BV},

keywords = {cancer, medicine},

pubstate = {published},

tppubtype = {article}

}

@article{44ac2137c0fa4666839a213d0fc6175c,

title = {Inflammation and brain structure in schizophrenia and other neuropsychiatric disorders: A Mendelian randomization study},

author = {John Williams and Stephen Burgess and John Suckling and Paris Alexandros Lalousis and Fatima Batool and Lowri Griffiths and Edward Palmer and Andreas Karwath and Andrey Barsky and Georgios Gkoutos and Stephen Wood and Nicholas Barnes and Anthony S David and Gary Donohoe and Joanna Neill and Bill Deakin and Golam Khandaker and Rachel Upthegrove and PIMS collaboration},

doi = {10.1001/jamapsychiatry.2022.0407},

issn = {2168-622X},

year  = {2022},

date = {2022-03-30},

urldate = {2022-03-30},

journal = {JAMA psychiatry},

volume = {2022},

pages = {1--11},

publisher = {Ämerican Medical Association},

abstract = {Importance: Previous in vitro and postmortem research suggests that inflammation may lead to structural brain changes via activation of microglia and/or astrocytic dysfunction in a range of neuropsychiatric disorders. Objective: To investigate the relationship between inflammation and changes in brain structures in vivo and to explore a transcriptome-driven functional basis with relevance to mental illness. Design, Setting, and Participants: This study used multistage linked analyses, including mendelian randomization (MR), gene expression correlation, and connectivity analyses. A total of 20688 participants in the UK Biobank, which includes clinical, genomic, and neuroimaging data, and 6 postmortem brains from neurotypical individuals in the Allen Human Brain Atlas (AHBA), including RNA microarray data. Data were extracted in February 2021 and analyzed between March and October 2021. Exposures: Genetic variants regulating levels and activity of circulating interleukin 1 (IL-1), IL-2, IL-6, C-reactive protein (CRP), and brain-derived neurotrophic factor (BDNF) were used as exposures in MR analyses. Main Outcomes and Measures: Brain imaging measures, including gray matter volume (GMV) and cortical thickness (CT), were used as outcomes. Associations were considered significant at a multiple testing-corrected threshold of P < 1.1 × 10-4. Differential gene expression in AHBA data was modeled in brain regions mapped to areas significant in MR analyses; genes were tested for biological and disease overrepresentation in annotation databases and for connectivity in protein-protein interaction networks. Results: Of 20688 participants in the UK Biobank sample, 10828 (52.3%) were female, and the mean (SD) age was 55.5 (7.5) years. In the UK Biobank sample, genetically predicted levels of IL-6 were associated with GMV in the middle temporal cortex (z score, 5.76; P = 8.39 × 10-9), inferior temporal (z score, 3.38; P = 7.20 × 10-5), fusiform (z score, 4.70; P = 2.60 × 10-7), and frontal (z score, -3.59; P = 3.30 × 10-5) cortex together with CT in the superior frontal region (z score, -5.11; P = 3.22 × 10-7). No significant associations were found for IL-1, IL-2, CRP, or BDNF after correction for multiple comparison. In the AHBA sample, 5 of 6 participants (83%) were male, and the mean (SD) age was 42.5 (13.4) years. Brain-wide coexpression analysis showed a highly interconnected network of genes preferentially expressed in the middle temporal gyrus (MTG), which further formed a highly connected protein-protein interaction network with IL-6 (enrichment test of expected vs observed network given the prevalence and degree of interactions in the STRING database: 43 nodes/30 edges observed vs 8 edges expected; mean node degree, 1.4; genome-wide significanc},

keywords = {artificial intelligence, health data science, medicine},

pubstate = {published},

tppubtype = {article}

}

@article{6b64a2f714094b7abb9373ccb6d527e0,

title = {Evaluating semantic similarity methods for comparison of text-derived phenotype profiles},

author = {Luke T Slater and Sophie Russell and Silver Makepeace and Alexander Carberry and Andreas Karwath and John A Williams and Hilary Fanning and Simon Ball and Robert Hoehndorf and Georgios V Gkoutos},

doi = {10.1186/s12911-022-01770-4},

issn = {1472-6947},

year  = {2022},

date = {2022-02-05},

urldate = {2022-02-05},

journal = {BMC Medical Informatics and Decision Making},

volume = {22},

number = {1},

publisher = {Springer},

abstract = {BACKGROUND: Semantic similarity is a valuable tool for analysis in biomedicine. When applied to phenotype profiles derived from clinical text, they have the capacity to enable and enhance 'patient-like me' analyses, automated coding, differential diagnosis, and outcome prediction. While a large body of work exists exploring the use of semantic similarity for multiple tasks, including protein interaction prediction, and rare disease differential diagnosis, there is less work exploring comparison of patient phenotype profiles for clinical tasks. Moreover, there are no experimental explorations of optimal parameters or better methods in the area.METHODS: We develop a platform for reproducible benchmarking and comparison of experimental conditions for patient phentoype similarity. Using the platform, we evaluate the task of ranking shared primary diagnosis from uncurated phenotype profiles derived from all text narrative associated with admissions in the medical information mart for intensive care (MIMIC-III).RESULTS: 300 semantic similarity configurations were evaluated, as well as one embedding-based approach. On average, measures that did not make use of an external information content measure performed slightly better, however the best-performing configurations when measured by area under receiver operating characteristic curve and Top Ten Accuracy used term-specificity and annotation-frequency measures.CONCLUSION: We identified and interpreted the performance of a large number of semantic similarity configurations for the task of classifying diagnosis from text-derived phenotype profiles in one setting. We also provided a basis for further research on other settings and related tasks in the area.},

keywords = {differential diagnosis, health data science, MIMIC-III, ontology, semantic similarity, semantic web},

pubstate = {published},

tppubtype = {article}

}

@article{Wehr_2022,

title = {RespiraTox – Development of a QSAR model to predict human respiratory irritants},

author = {Matthias M. Wehr and Satinder S. Sarang and Martijn Rooseboom and Peter J. Boogaard and Andreas Karwath and Sylvia E. Escher},

url = {https://doi.org/10.1016%2Fj.yrtph.2021.105089},

doi = {10.1016/j.yrtph.2021.105089},

year  = {2022},

date = {2022-02-01},

urldate = {2022-02-01},

journal = {Regulatory Toxicology and Pharmacology},

volume = {128},

pages = {105089},

publisher = {Elsevier BV},

keywords = {cheminformatics, machine learning, QSAR},

pubstate = {published},

tppubtype = {article}

}

@article{14598610a01b4af99802a4b22e67a119,

title = {Multi-faceted semantic clustering with text-derived phenotypes},

author = {Luke T. Slater and John A. Williams and Andreas Karwath and Hilary Fanning and Simon Ball and Paul N. Schofield and Robert Hoehndorf and Georgios V. Gkoutos},

doi = {10.1016/j.compbiomed.2021.104904},

issn = {0010-4825},

year  = {2021},

date = {2021-11-01},

urldate = {2021-11-01},

journal = {Computers in biology and medicine},

publisher = {Elsevier},

abstract = {Identification of ontology concepts in clinical narrative text enables the creation of phenotype profiles that can be associated with clinical entities, such as patients or drugs. Constructing patient phenotype profiles using formal ontologies enables their analysis via semantic similarity, in turn enabling the use of background knowledge in clustering or classification analyses. However, traditional semantic similarity approaches collapse complex relationships between patient phenotypes into a unitary similarity scores for each pair of patients. Moreover, single scores may be based only on matching terms with the greatest information content (IC), ignoring other dimensions of patient similarity. This process necessarily leads to a loss of information in the resulting representation of patient similarity, and is especially apparent when using very large text-derived and highly multi-morbid phenotype profiles. Moreover, it renders finding a biological explanation for similarity very difficult; the black box problem. In this article, we explore the generation of multiple semantic similarity scores for patients based on different facets of their phenotypic manifestation, which we define through different sub-graphs in the Human Phenotype Ontology. We further present a new methodology for deriving sets of qualitative class descriptions for groups of entities described by ontology terms. Leveraging this strategy to obtain meaningful explanations for our semantic clusters alongside other evaluation techniques, we show that semantic clustering with ontology-derived facets enables the representation, and thus identification of, clinically relevant phenotype relationships not easily recoverable using overall clustering alone. In this way, we demonstrate the potential of faceted semantic clustering for gaining a deeper and more nuanced understanding of text-derived patient phenotypes.},

keywords = {cluster explanation, clustering, health data science, MIMIC-III, ontology, semantic similarity},

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}

}

@article{Pendleton_2021,

title = {Development and application of the ocular immune-mediated inflammatory diseases ontology enhanced with synonyms from online patient support forum conversation},

author = {Samantha C. Pendleton and Luke T. Slater and Andreas Karwath and Rose M. Gilbert and Nicola Davis and Konrad Pesudovs and Xiaoxuan Liu and Alastair K. Denniston and Georgios V. Gkoutos and Tasanee Braithwaite},

url = {https://doi.org/10.1016%2Fj.compbiomed.2021.104542},

doi = {10.1016/j.compbiomed.2021.104542},

year  = {2021},

date = {2021-08-01},

urldate = {2021-08-01},

journal = {Computers in Biology and Medicine},

volume = {135},

pages = {104542},

publisher = {Elsevier BV},

keywords = {health data science, NLP, semantic similarity},

pubstate = {published},

tppubtype = {article}

}

@article{Slater_2021,

title = {Towards similarity-based differential diagnostics for common diseases},

author = {Luke T Slater and Andreas Karwath and John A Williams and Sophie Russell and Silver Makepeace and Alexander Carberry and Robert Hoehndorf and Georgios V Gkoutos},

url = {https://doi.org/10.1016%2Fj.compbiomed.2021.104360},

doi = {10.1016/j.compbiomed.2021.104360},

year  = {2021},

date = {2021-06-01},

urldate = {2021-06-01},

journal = {Computers in Biology and Medicine},

volume = {133},

pages = {104360},

publisher = {Elsevier BV},

keywords = {artificial intelligence, health data science, NLP, semantic similarity},

pubstate = {published},

tppubtype = {article}

}

@article{RN19,

title = {Evaluation and improvement of the National Early Warning Score (NEWS2) for COVID-19: a multi-hospital study},

author = {E Carr and R Bendayan and D Bean and M Stammers and W Wang and H Zhang and T Searle and Z Kraljevic and A Shek and H T T Phan and W Muruet and R K Gupta and A J Shinton and M Wyatt and T Shi and X Zhang and A Pickles and D Stahl and R Zakeri and M Noursadeghi and K O'Gallagher and M Rogers and A Folarin and Andreas Karwath and K E Wickstrøm and A Köhn-Luque and L Slater and V R Cardoso and C Bourdeaux and A R Holten and S Ball and C McWilliams and L Roguski and F Borca and J Batchelor and E K Amundsen and X Wu and G V Gkoutos and J Sun and A Pinto and B Guthrie and C Breen and A Douiri and H Wu and V Curcin and J T Teo and A M Shah and R J B Dobson},

doi = {10.1186/s12916-020-01893-3},

issn = {1741-7015},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {BMC Med},

volume = {19},

number = {1},

pages = {23},

keywords = {artificial intelligence, COVID-19, early warning score, health data science, machine learning},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:33692093,

title = {Improving the diagnosis of heart failure in patients with atrial fibrillation.},

author = {Bunting KV and Gill SK and Sitch A and Mehta S and O'Connor K and Lip GY and Kirchhof P and Strauss VY and Rahimi K and Camm AJ and Stanbury M and Griffith M and Townend JN and Gkoutos GV and RAte Therapy Evaluation Atrial Fibrillation (RATE-AF) control in permanent trial group},

doi = {10.1136/heartjnl-2020-318557},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {Heart (British Cardiac Society)},

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

pubstate = {published},

tppubtype = {article}

}

@article{RN17,

title = {Time extrapolation in regulatory risk assessment: The impact of study differences on the extrapolation factors},

author = {S E Escher and I Mangelsdorf and S Hoffmann-Doerr and F Partosch and Andreas Karwath and K Schroeder and A Zapf and M Batke},

doi = {10.1016/j.yrtph.2020.104584},

issn = {0273-2300},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {Regul Toxicol Pharmacol},

volume = {112},

pages = {104584},

keywords = {cheminformatics, QSAR},

pubstate = {published},

tppubtype = {article}

}

@article{RN18,

title = {Ensemble learning for poor prognosis predictions: a case study on SARS-CoV2},

author = {H Wu and H Zhang and Andreas Karwath and Z Ibrahim and T Shi and X Zhang and K Wang and J Sun and K Dhaliwal and D Bean and V R Cardoso and K Li and J T Teo and A Banerjee and F Gao-Smith and T Whitehouse and T Veenith and G V Gkoutos and X Wu and R Dobson and B Guthrie},

doi = {10.1093/jamia/ocaa295},

issn = {1067-5027 (Print) 1067-5027},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {J Am Med Inform Assoc},

keywords = {artificial intelligence, COVID-19, health data science, machine learning},

pubstate = {published},

tppubtype = {article}

}

@article{koeppel2019,

title = {Pairwise Learning to Rank by Neural Networks  Revisited: Reconstruction, Theoretical Analysis and  Practical Performance},

author = {Marius Köppel and Alexander Segner and Martin Wagener and Lukas Pensel and Andreas Karwath and Stefan Kramer},

url = {http://arxiv.org/abs/1909.02768},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

journal = {CoRR},

keywords = {artificial intelligence, learning to rank},

pubstate = {published},

tppubtype = {article}

}

@article{RN16,

title = {Ontology-based prediction of cancer driver genes},

author = {Sara Althubaiti and Andreas Karwath and Ashraf Dallol and Adeeb Noor and Shadi Salem Alkhayyat and Rolina Alwassia and Katsuhiko Mineta and Takashi Gojobori and Andrew D Beggs and Paul N Schofield and Georgios V Gkoutos and Robert Hoehndorf},

url = {https://doi.org/10.1038/s41598-019-53454-1},

doi = {10.1038/s41598-019-53454-1},

issn = {2045-2322},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

journal = {Scientific Reports},

volume = {9},

number = {1},

pages = {17405},

keywords = {bioinformatics, cancer, health data science},

pubstate = {published},

tppubtype = {article}

}

@article{geilke2018a,

title = {Online estimation of discrete, continuous, and conditional joint densities using classifier chains},

author = {Michael Geilke and Andreas Karwath and Eibe Frank and Stefan Kramer},

url = {https://doi.org/10.1007/s10618-017-0546-6},

doi = {10.1007/s10618-017-0546-6},

issn = {1384-5810},

year  = {2018},

date = {2018-05-01},

urldate = {2018-05-01},

journal = {Data Mining and Knowledge Discovery},

volume = {32},

number = {3},

pages = {561-603},

publisher = {Springer US},

abstract = {We address the problem of estimating discrete, continuous, and conditional joint densities online, i.e., the algorithm is only provided the current example and its current estimate for its update. The family of proposed online density estimators, estimation of densities online (EDO), uses classifier chains to model dependencies among features, where each classifier in the chain estimates the probability of one particular feature. Because a single chain may not provide a reliable estimate, we also consider ensembles of classifier chains and ensembles of weighted classifier chains. For all density estimators, we provide consistency proofs and propose algorithms to perform certain inference tasks. The empirical evaluation of the estimators is conducted in several experiments and on datasets of up to several millions of instances. In the discrete case, we compare our estimators to density estimates computed by Bayesian structure learners. In the continuous case, we compare them to a state-of-the-art online density estimator. Our experiments demonstrate that, even though designed to work online, EDO delivers estimators of competitive accuracy compared to other density estimators (batch Bayesian structure learners on discrete datasets and the state-of-the-art online density estimator on continuous datasets). Besides achieving similar performance in these cases, EDO is also able to estimate densities with mixed types of variables, i.e., discrete and continuous random variables.},

keywords = {artificial intelligence, data mining, density estimation, machine learning, stream mining},

pubstate = {published},

tppubtype = {article}

}

@article{gutlein2014,

title = {CheS-Mapper 2.0 for visual validation of (Q)SAR models},

author = {Martin Gütlein and Andreas Karwath and Stefan Kramer},

url = {http://dx.doi.org/10.1186/s13321-014-0041-7},

doi = {10.1186/s13321-014-0041-7},

year  = {2014},

date = {2014-09-23},

journal = {J. Cheminformatics},

volume = {6},

number = {1},

pages = {41},

abstract = {Background



Sound statistical validation is important to evaluate and compare the overall performance of (Q)SAR models. However, classical validation does not support the user in better understanding the properties of the model or the underlying data. Even though, a number of visualization tools for analyzing (Q)SAR information in small molecule datasets exist, integrated visualization methods that allow the investigation of model validation results are still lacking.



Results



We propose visual validation, as an approach for the graphical inspection of (Q)SAR model validation results. The approach applies the 3D viewer CheS-Mapper, an open-source application for the exploration of small molecules in virtual 3D space. The present work describes the new functionalities in CheS-Mapper 2.0, that facilitate the analysis of (Q)SAR information and allows the visual validation of (Q)SAR models. The tool enables the comparison of model predictions to the actual activity in feature space. The approach is generic: It is model-independent and can handle physico-chemical and structural input features as well as quantitative and qualitative endpoints.



Conclusions



Visual validation with CheS-Mapper enables analyzing (Q)SAR information in the data and indicates how this information is employed by the (Q)SAR model. It reveals, if the endpoint is modeled too specific or too generic and highlights common properties of misclassified compounds. Moreover, the researcher can use CheS-Mapper to inspect how the (Q)SAR model predicts activity cliffs. The CheS-Mapper software is freely available at http://​ches-mapper.​org.



Graphical abstract



Comparing actual and predicted activity values with CheS-Mapper.},

keywords = {cheminformatics, data mining, graph mining, validation, visualization},

pubstate = {published},

tppubtype = {article}

}

@article{guetlein2013,

title = {A Large-Scale Empirical Evaluation of Cross-Validation and External Test Set Validation in (Q)SAR},

author = {Martin Gütlein and Christoph Helma and Andreas Karwath and Stefan Kramer},

url = {http://onlinelibrary.wiley.com/doi/10.1002/minf.201200134/abstract},

doi = {10.1002/minf.201200134},

year  = {2013},

date = {2013-10-14},

urldate = {2013-10-14},

journal = {Molecular Informatics},

volume = {32},

number = {5-6},

pages = {516-528},

abstract = {(Q)SAR model validation is essential to ensure the quality of inferred models and to indicate future model predictivity on unseen compounds. Proper validation is also one of the requirements of regulatory authorities in order to accept the (Q)SAR model, and to approve its use in real world scenarios as alternative testing method. However, at the same time, the question of how to validate a (Q)SAR model, in particular whether to employ variants of cross-validation or external test set validation, is still under discussion. In this paper, we empirically compare a k-fold cross-validation with external test set validation. To this end we introduce a workflow allowing to realistically simulate the common problem setting of building predictive models for relatively small datasets. The workflow allows to apply the built and validated models on large amounts of unseen data, and to compare the performance of the different validation approaches. The experimental results indicate that cross-validation produces higher performant (Q)SAR models than external test set validation, reduces the variance of the results, while at the same time underestimates the performance on unseen compounds. The experimental results reported in this paper suggest that, contrary to current conception in the community, cross-validation may play a significant role in evaluating the predictivity of (Q)SAR models.},

keywords = {cheminformatics, crossvalidation, external validation, QSAR, validation},

pubstate = {published},

tppubtype = {article}

}

@article{gutlein2012,

title = {CheS-Mapper - Chemical Space Mapping and Visualization in 3D},

author = {Martin Gütlein and Andreas Karwath and Stefan Kramer},

url = {http://dx.doi.org/10.1186/1758-2946-4-7},

doi = {10.1186/1758-2946-4-7},

year  = {2012},

date = {2012-03-17},

journal = {J. Cheminformatics},

volume = {4},

pages = {7},

abstract = {Analyzing chemical datasets is a challenging task for scientific researchers in the field of chemoinformatics. It is important, yet difficult to understand the relationship between the structure of chemical compounds, their physico-chemical properties, and biological or toxic effects. To that respect, visualization tools can help to better comprehend the underlying correlations. Our recently developed 3D molecular viewer CheS-Mapper (Chemical Space Mapper) divides large datasets into clusters of similar compounds and consequently arranges them in 3D space, such that their spatial proximity reflects their similarity. The user can indirectly determine similarity, by selecting which features to employ in the process. The tool can use and calculate different kind of features, like structural fragments as well as quantitative chemical descriptors. These features can be highlighted within CheS-Mapper, which aids the chemist to better understand patterns and regularities and relate the observations to established scientific knowledge. As a final function, the tool can also be used to select and export specific subsets of a given dataset for further analysis.

},

keywords = {cheminformatics, clustering, dimensionality reduction, QSAR, visualization},

pubstate = {published},

tppubtype = {article}

}

@article{grzonka2012,

title = {Activity-Based Estimation of Human Trajectories},

author = {Slawomir Grzonka and Andreas Karwath and Frederic Dijoux and Wolfram Burgard},

url = {http://dx.doi.org/10.1109/TRO.2011.2165372},

doi = {10.1109/TRO.2011.2165372},

year  = {2012},

date = {2012-02-02},

urldate = {2012-02-02},

journal = {IEEE Transactions on Robotics},

volume = {28},

number = {1},

pages = {234-245},

abstract = {We present a novel approach to incrementally determine the trajectory of a person in 3-D based on its motions and activities in real time. In our algorithm, we estimate the motions and activities of the user given the data that are obtained from a motion capture suit equipped with several inertial measurement units. These activities include walking up and down staircases, as well as opening and closing doors. We interpret the first two types of activities as motion constraints and door-handling events as landmark detections in a graph-based simultaneous localization and mapping (SLAM) framework. Since we cannot distinguish between individual doors, we employ a multihypothesis tracking approach on top of the SLAM procedure to deal with the high data-association uncertainty. As a result, we are able to accurately and robustly recover the trajectory of the person. Additionally, we present an algorithm to build approximate geometrical and topological maps based on the estimated trajectory and detected activities. We evaluate our approach in practical experiments that are carried out with different subjects and in various environments.},

keywords = {activity recognition, artificial intelligence, machine learning, simultaneous localization and mapping},

pubstate = {published},

tppubtype = {article}

}

@article{hardy2010,

title = {Collaborative development of predictive toxicology applications},

author = {Barry J. Hardy and Nicki Douglas and Christoph Helma and Micha Rautenberg and Nina Jeliazkova and Vedrin Jeliazkov and Ivelina Nikolova and Romualdo Benigni and Olga Tcheremenskaia and Stefan Kramer and Tobias Girschick and Fabian Buchwald and Jörg Wicker and Andreas Karwath and Martin Gütlein and Andreas Maunz and Haralambos Sarimveis and Georgia Melagraki and Antreas Afantitis and Pantelis Sopasakis and David Gallagher and Vladimir Poroikov and Dmitry Filimonov and Alexey V. Zakharov and Alexey Lagunin and Tatyana Gloriozova and Sergey Novikov and Natalia Skvortsova and Dmitry Druzhilovsky and Sunil Chawla and Indira Ghosh and Surajit Ray and Hitesh Patel and Sylvia Escher},

url = {http://dx.doi.org/10.1186/1758-2946-2-7},

doi = {10.1186/1758-2946-2-7},

year  = {2010},

date = {2010-08-31},

urldate = {2010-08-31},

journal = {J. Cheminformatics},

volume = {2},

pages = {7},

abstract = {OpenTox provides an interoperable, standards-based Framework for the support of predictive toxicology data management, algorithms, modelling, validation and reporting. It is relevant to satisfying the chemical safety assessment requirements of the REACH legislation as it supports access to experimental data, (Quantitative) Structure-Activity Relationship models, and toxicological information through an integrating platform that adheres to regulatory requirements and OECD validation principles. Initial research defined the essential components of the Framework including the approach to data access, schema and management, use of controlled vocabularies and ontologies, architecture, web service and communications protocols, and selection and integration of algorithms for predictive modelling. OpenTox provides end-user oriented tools to non-computational specialists, risk assessors, and toxicological experts in addition to Application Programming Interfaces (APIs) for developers of new applications. OpenTox actively supports public standards for data representation, interfaces, vocabularies and ontologies, Open Source approaches to core platform components, and community-based collaboration approaches, so as to progress system interoperability goals.



The OpenTox Framework includes APIs and services for compounds, datasets, features, algorithms, models, ontologies, tasks, validation, and reporting which may be combined into multiple applications satisfying a variety of different user needs. OpenTox applications are based on a set of distributed, interoperable OpenTox API-compliant REST web services. The OpenTox approach to ontology allows for efficient mapping of complementary data coming from different datasets into a unifying structure having a shared terminology and representation.



Two initial OpenTox applications are presented as an illustration of the potential impact of OpenTox for high-quality and consistent structure-activity relationship modelling of REACH-relevant endpoints: ToxPredict which predicts and reports on toxicities for endpoints for an input chemical structure, and ToxCreate which builds and validates a predictive toxicity model based on an input toxicology dataset. Because of the extensible nature of the standardised Framework design, barriers of interoperability between applications and content are removed, as the user may combine data, models and validation from multiple sources in a dependable and time-effective way.},

keywords = {crossvalidation, data mining, QSAR, scientific knowledge, validation},

pubstate = {published},

tppubtype = {article}

}

@article{karwath06c,

title = {SMIREP: Predicting Chemical Activity from SMILES},

author = {Andreas Karwath and De Raedt, Luc},

url = {http://pubs.acs.org/doi/abs/10.1021/ci060159g},

doi = {10.1021/ci060159g},

year  = {2006},

date = {2006-10-12},

journal = {Journal of Chemical Information and Modeling},

volume = {46},

number = {6},

pages = {2432 - 2444},

abstract = {Most approaches to structure-activity-relationship (SAR) prediction proceed in two steps. In the first step, a typically large set of fingerprints, or fragments of interest, is constructed (either by hand or by some recent data mining techniques). In the second step, machine learning techniques are applied to obtain a predictive model. The result is often not only a highly accurate but also hard to interpret model. In this paper, we demonstrate the capabilities of a novel SAR algorithm, SMIREP, which tightly integrates the fragment and model generation steps and which yields simple models in the form of a small set of IF-THEN rules. These rules contain SMILES fragments, which are easy to understand to the computational chemist. SMIREP combines ideas from the well-known IREP rule learner with a novel fragmentation algorithm for SMILES strings. SMIREP has been evaluated on three problems: the prediction of binding activities for the estrogen receptor (Environmental Protection Agency's (EPA's) Distributed Structure-Searchable Toxicity (DSSTox) National Center for Toxicological Research estrogen receptor (NCTRER) Database), the prediction of mutagenicity using the carcinogenic potency database (CPDB), and the prediction of biodegradability on a subset of the Environmental Fate Database (EFDB). In these applications, SMIREP has the advantage of producing easily interpretable rules while having predictive accuracies that are comparable to those of alternative state-of-the-art techniques.},

keywords = {cheminformatics, graph mining, machine learning, QSAR, relational learning, scientific knowledge},

pubstate = {published},

tppubtype = {article}

}

@article{karwath06a,

title = {Functional bioinformatics for Arabidopsis thaliana},

author = {Amanda Clare and Andreas Karwath and Helen Ougham and Ross D. King},

url = {https://bioinformatics.oxfordjournals.org/content/22/9/1130.full.pdf+html},

doi = {10.1093/bioinformatics/btl051},

year  = {2006},

date = {2006-01-01},

journal = {Bioinformatics},

volume = {22},

number = {9},

pages = {1130-1136},

abstract = {Motivation: The genome of Arabidopsis thaliana, which has the best understood plant genome, still has approximately one-third of its genes with no functional annotation at all from either MIPS or TAIR. We have applied our Data Mining Prediction (DMP) method to the problem of predicting the functional classes of these protein sequences. This method is based on using a hybrid machine-learning/data-mining method to identify patterns in the bioinformatic data about sequences that are predictive of function. We use data about sequence, predicted secondary structure, predicted structural domain, InterPro patterns, sequence similarity profile and expressions data.



Results: We predicted the functional class of a high percentage of the Arabidopsis genes with currently unknown function. These predictions are interpretable and have good test accuracies. We describe in detail seven of the rules produced.



Availability: Rulesets are available at http://www.aber.ac.uk/compsci/Research/bio/dss/arabpreds/ and predictions are available at http://www.genepredictions.org



Contact:afc@aber.ac.uk},

keywords = {bioinformatics, data mining, inductive logic programming, machine learning, relational learning, scientific knowledge},

pubstate = {published},

tppubtype = {article}

}

@article{backofen2006,

title = {A Bottom-up approach to Grid-Computing at a University: the Black-Forest-Grid Initiative},

author = {Rolf Backofen and Hans-Gunther Borrmann and Werner Deck and Andreas Dedner and De Raedt, Luc and Klaus Desch and Markus Diesmann and Martin Geier and Andreas Greiner and Wolfgang R. Hess and Josef Honerkamp and Stefan Jankowski and Ingo Krossing and Andreas W. Liehr and Andreas Karwath and Robert Klöfkorn and Raphaël Pesché and Tobias C. Potjans and Michael C. Röttger and Lars Schmidt-Thieme and Gerhard Schneider and Björn Voß and Bernd Wiebelt and Peter Wienemann and Volker-Henning Winterer},

url = {http://dx.doi.org/10.1515/PIKO.2006.81},

doi = {10.1515/PIKO.2006.81},

year  = {2006},

date = {2006-01-01},

journal = {Praxis der Informationsverarbeitung und Kommunikation},

volume = {29},

number = {2},

pages = {81-87},

abstract = {Recent years have seen a rapid increase in the need for highperformance computing. These demands come from disciplines such as particle physics traditionally relying on High Performance Computing (HPC) but lately also from the various branches of life science that have matured into quantitative disciplines. The classical infrastructure of university computer centres results to be unsuited to cope with the new requirements for a multitude of reasons. Here we discuss the causes of this failure and present a solution developed at the University of Freiburg in a collaborative effort of several faculties. We demonstrate that using state of the art grid computing technology the problem can now be addressed in a bottom-up approach. The organizational, technical, and financial components of our framework, the Black Forest Grid Initiative (BFG) are described and results of its implementation are presented. In the process, a number of new questions have emerged which the next phase of our project needs to address.},

keywords = {data mining, HPC},

pubstate = {published},

tppubtype = {article}

}