Search

Your search keyword '"Petrungaro, Bruno"' showing total 12 results
Start Over Author "Petrungaro, Bruno"
12 results on '"Petrungaro, Bruno"'

1. Investigating potential causes of Sepsis with Bayesian network structure learning

Author

Petrungaro, Bruno, Kitson, Neville K., and Constantinou, Anthony C.

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Sepsis is a life-threatening and serious global health issue. This study combines knowledge with available hospital data to investigate the potential causes of Sepsis that can be affected by policy decisions. We investigate the underlying causal structure of this problem by combining clinical expertise with score-based, constraint-based, and hybrid structure learning algorithms. A novel approach to model averaging and knowledge-based constraints was implemented to arrive at a consensus structure for causal inference. The structure learning process highlighted the importance of exploring data-driven approaches alongside clinical expertise. This includes discovering unexpected, although reasonable, relationships from a clinical perspective. Hypothetical interventions on Chronic Obstructive Pulmonary Disease, Alcohol dependence, and Diabetes suggest that the presence of any of these risk factors in patients increases the likelihood of Sepsis. This finding, alongside measuring the effect of these risk factors on Sepsis, has potential policy implications. Recognising the importance of prediction in improving Sepsis related health outcomes, the model built is also assessed in its ability to predict Sepsis. The predictions generated by the consensus model were assessed for their accuracy, sensitivity, and specificity. These three indicators all had results around 70%, and the AUC was 80%, which means the causal structure of the model is reasonably accurate given that the models were trained on data available for commissioning purposes only.

Published
2024

2. Open problems in causal structure learning: A case study of COVID-19 in the UK

Author

Constantinou, Anthony, Kitson, Neville K., Liu, Yang, Chobtham, Kiattikun, Hashemzadeh, Arian, Nanavati, Praharsh A., Mbuvha, Rendani, and Petrungaro, Bruno

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Causal machine learning (ML) algorithms recover graphical structures that tell us something about cause-and-effect relationships. The causal representation praovided by these algorithms enables transparency and explainability, which is necessary for decision making in critical real-world problems. Yet, causal ML has had limited impact in practice compared to associational ML. This paper investigates the challenges of causal ML with application to COVID-19 UK pandemic data. We collate data from various public sources and investigate what the various structure learning algorithms learn from these data. We explore the impact of different data formats on algorithms spanning different classes of learning, and assess the results produced by each algorithm, and groups of algorithms, in terms of graphical structure, model dimensionality, sensitivity analysis, confounding variables, predictive and interventional inference. We use these results to highlight open problems in causal structure learning and directions for future research. To facilitate future work, we make all graphs, models, data sets, and source code publicly available online.

Published
2023

5. Open problems in causal structure learning: A case study of COVID-19 in the UK

Author

Constantinou, Anthony C., Kitson, Neville K., Liu, Yang, Chobtham, Kiattikun, Hashemzadeh, Arian, Nanavati, Praharsh A., Mbuvha, Rendani, and Petrungaro, Bruno

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Machine Learning (cs.LG)
Abstract

Causal machine learning (ML) algorithms recover graphical structures that tell us something about cause-and-effect relationships. The causal representation provided by these algorithms enables transparency and explainability, which is necessary in critical real-world problems. Yet, causal ML has had limited impact in practice compared to associational ML. This paper investigates the challenges of causal ML with application to COVID-19 UK pandemic data. We collate data from various public sources and investigate what the various structure learning algorithms learn from these data. We explore the impact of different data formats on algorithms spanning different classes of learning, and assess the results produced by each algorithm, and groups of algorithms, in terms of graphical structure, model dimensionality, sensitivity analysis, confounding variables, predictive and interventional inference. We use these results to highlight open problems in causal structure learning and directions for future research. To facilitate future work, we make all graphs, models and data sets publicly available online.

Published
2023
Full Text
View/download PDF

8. Hospital admissions for stroke and bleeding in Hounslow following a quality improvement initiative

Author

Wong, Kam Ying, primary, Davies, Bethan, additional, Adeleke, Yewande, additional, Woodcock, Thomas, additional, Matthew, Dionne, additional, Sekelj, Sara, additional, Orlowski, Andi, additional, Porter, Bradley, additional, Hashmy, Sophia, additional, Mathew, Ammu, additional, Grant, Ron, additional, Kaba, Agnes, additional, Unger-Graeber, Brigitte, additional, Petrungaro, Bruno, additional, Wallace, Jordan, additional, Bell, Derek, additional, Cowie, Martin R, additional, and Khan, Sadia, additional

Published
2021
Full Text
View/download PDF

11. Clinical and budget impacts of changes in oral anticoagulation prescribing for atrial fibrillation.

Author

Orlowski, Andi, Gale, Chris P, Ashton, Rachel, Petrungaro, Bruno, Slater, Ruth, Nadarajah, Ramesh, Cowan, J Campbell, Buck, Jackie, Smith, Wayne, and Wu, Jianhua

Subjects
STROKE prevention, STROKE, WARFARIN, ATRIAL fibrillation, ANTICOAGULANTS, MEDICAL care costs, QUESTIONNAIRES, BUDGET, LONGITUDINAL method, DISEASE complications
Abstract

Objective: To assess temporal clinical and budget impacts of changes in atrial fibrillation (AF)-related prescribing in England.Methods: Data on AF prevalence, AF-related stroke incidence and prescribing for all National Health Service general practices, hospitals and registered patients with hospitalised AF-related stroke in England were obtained from national databases. Stroke care costs were based on published data. We compared changes in oral anticoagulation prescribing (warfarin or direct oral anticoagulants (DOACs)), incidence of hospitalised AF-related stroke, and associated overall and per-patient costs in the periods January 2011-June 2014 and July 2014-December 2017.Results: Between 2011-2014 and 2014-2017, recipients of oral anticoagulation for AF increased by 86.5% from 1 381 170 to 2 575 669. The number of patients prescribed warfarin grew by 16.1% from 1 313 544 to 1 525 674 and those taking DOACs by 1452.7% from 67 626 to 1 049 995. Prescribed items increased by 5.9% for warfarin (95% CI 2.9% to 8.9%) but by 2004.8% for DOACs (95% CI 1848.8% to 2160.7%). Oral anticoagulation prescription cost rose overall by 781.2%, from £87 313 310 to £769 444 028, (£733,466,204 with warfarin monitoring) and per patient by 50.7%, from £293 to £442, giving an incremental cost of £149. Nevertheless, as AF-related stroke incidence fell by 11.3% (95% CI -11.5% to -11.1%) from 86 467 in 2011-2014 to 76 730 in 2014-2017 with adjustment for AF prevalence, the overall per-patient cost reduced from £1129 to £840, giving an incremental per-patient saving of £289.Conclusions: Despite nearly one million additional DOAC prescriptions and substantial associated spending in the latter part of this study, the decline in AF-related stroke led to incremental savings at the national level. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

12. Budget impact analysis of a machine learning algorithm to predict high risk of atrial fibrillation among primary care patients.

Author

Szymanski T, Ashton R, Sekelj S, Petrungaro B, Pollock KG, Sandler B, Lister S, Hill NR, and Farooqui U

Subjects
Algorithms, Electrocardiography, Humans, Machine Learning, Primary Health Care, State Medicine, Atrial Fibrillation diagnosis, Atrial Fibrillation epidemiology, Stroke diagnosis, Stroke epidemiology, Stroke etiology
Abstract

Aims: We investigated whether the use of an atrial fibrillation (AF) risk prediction algorithm could improve AF detection compared with opportunistic screening in primary care and assessed the associated budget impact., Methods and Results: Eligible patients were registered with a general practice in UK, aged 65 years or older in 2018/19, and had complete data for weight, height, body mass index, and systolic and diastolic blood pressure recorded within 1 year. Three screening scenarios were assessed: (i) opportunistic screening and diagnosis (standard care); (ii) standard care replaced by the use of the algorithm; and (iii) combined use of standard care and the algorithm. The analysis considered a 3-year time horizon, and the budget impact for the National Health Service (NHS) costs alone or with personal social services (PSS) costs. Scenario 1 would identify 79 410 new AF cases (detection gap reduced by 22%). Scenario 2 would identify 70 916 (gap reduced by 19%) and Scenario 3 would identify 99 267 new cases (gap reduction 27%). These rates translate into 2639 strokes being prevented in Scenario 1, 2357 in Scenario 2, and 3299 in Scenario 3. The 3-year NHS budget impact of Scenario 1 would be £45.3 million, £3.6 million (difference ‒92.0%) with Scenario 2, and £46.3 million (difference 2.2%) in Scenario 3, but for NHS plus PSS would be ‒£48.8 million, ‒£80.4 million (64.8%), and ‒£71.3 million (46.1%), respectively., Conclusion: Implementation of an AF risk prediction algorithm alongside standard opportunistic screening could close the AF detection gap and prevent strokes while substantially reducing NHS and PSS combined care costs., Competing Interests: Conflict of interest: T.S. and R.A. are and S.S. and B.P. were, during the study, employees of Imperial College Health Partners, which received funding from BMS to undertake this study. K.G.P., B.S., S.L., N.R.H., and U.F. are employees of Bristol Myers Squibb Pharmaceuticals Ltd., (Published on behalf of the European Society of Cardiology. All rights reserved. © The Author(s) 2022. For permissions, please email: journals.permissions@oup.com.)

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results