Matthieu Komorowski

Matthieu Komorowski

Auto-generated profile, based on publicly available information

Matthieu Komorowski

Department of Surgery and Cancer, Imperial College London, London, UK

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 October 2018 in Nature Medicine
Verified
Journal Article
Open access
PDF file
MKMatthieu Komorowski
Matthieu Komorowski
LCLeo Anthony Celi
Leo Anthony Celi
OBOmar Badawi
Omar Badawi
AGAnthony C. Gordon
Anthony C. Gordon
AFA. Aldo Faisal
A. Aldo Faisal
Sepsis is the third leading cause of death worldwide and the main cause of mortality in hospitals1,2,3, but the best treatment strategy remains uncertain. In particular, evidence suggests that current practices in the administration of intravenous fluids and vasopressors are suboptimal and likely induce harm in a proportion of patients1,4,5,6. To tackle this sequential decision-making problem, we developed a reinforcement learning agent, the Artificial Intelligence (AI) Clinician, which extracted implicit knowledge from an amount of patient data that exceeds by many-fold the life-time experience of human clinicians and learned optimal treatment by analyzing a myriad of (mostly suboptimal) treatment decisions. We demonstrate that the value of the AI Clinician’s selected treatment is on average reliably higher than human clinicians. In a large validation cohort independent of the training data, mortality was lowest in patients for whom clinicians’ actual doses matched the AI decisions. Our model provides individualized and clinically interpretable treatment decisions for sepsis that could improve patient outcomes.

7 January 2019 in Nature Medicine
Verified
Journal Article
Closed access
OGOmer Gottesman
Omer Gottesman
FJFredrik Johansson
Fredrik Johansson
MKMatthieu Komorowski
Matthieu Komorowski
AFAldo Faisal
Aldo Faisal
DSDavid Sontag
David Sontag
LCLeo Anthony Celi
Leo Anthony Celi

2 December 2022 in EBioMedicine
Verified
Journal Article
Open access
MKMatthieu Komorowski
Matthieu Komorowski
AGAshleigh Green
Ashleigh Green
KTKate C. Tatham
Kate C. Tatham
CSChristopher Seymour
Christopher Seymour
DADavid Antcliffe
David Antcliffe
Over the last years, there have been advances in the use of data-driven techniques to improve the definition, early recognition, subtypes characterisation, prognostication and treatment personalisation of sepsis. Some of those involve the discovery or evaluation of biomarkers or digital signatures of sepsis or sepsis sub-phenotypes. It is hoped that their identification may improve timeliness and accuracy of diagnosis, suggest physiological pathways and therapeutic targets, inform targeted recruitment into clinical trials, and optimise clinical management. Given the complexities of the sepsis response, panels of biomarkers or models combining biomarkers and clinical data are necessary, as well as specific data analysis methods, which broadly fall under the scope of machine learning. This narrative review gives a brief overview of the main machine learning techniques (mainly in the realms of supervised and unsupervised methods) and published applications that have been used to create sepsis diagnostic tools and identify biomarkers.

24 June 2019 in Intensive Care Medicine
Verified
Journal Article
Closed access
PDF file
MKMatthieu Komorowski
Matthieu Komorowski

4 May 2018 in Respiratory Research
Verified
Journal Article
Open access
PDF file
DMDominic C. Marshall
Dominic C. Marshall
RGRoss J. Goodson
Ross J. Goodson
YXYiwang Xu
Yiwang Xu
MKMatthieu Komorowski
Matthieu Komorowski
JSJoseph Shalhoub
Joseph Shalhoub
JSJustin D. Salciccioli
Justin D. Salciccioli
Pneumonia is responsible for approximately 230,000 deaths in Europe, annually. Comprehensive and comparable reports on pneumonia mortality trends across the European Union (EU) are lacking. A temporal analysis of national mortality statistics to compare trends in pneumonia age-standardised death rates (ASDR) of EU countries between 2001 and 2014 was performed. International Classification of Diseases version 10 (ICD-10) codes were used to extract data from the World Health Organisation European Detailed Mortality Database and trends were analysed using Joinpoint regression. Median pneumonia mortality across the EU for the last recorded observation was 19.8 / 100,000 and 6.9 / 100,000 for males and females, respectively. Mortality was higher in males across all EU countries, most notably in Estonia and Lithuania where the ratio of male to female ASDR was 4.0 and 3.7, respectively. Gender mortality differences were lowest in the UK and Demark with ASDR ratios of 1.1 and 1.5, respectively. Pneumonia mortality across all countries decreased by a median of 31.0% over the observation period. Countries that demonstrated an increase in pneumonia mortality were Poland (males + 33.1%, females + 10.2%), and Lithuania (males + 6.0%). Mortality from pneumonia is improving in most EU countries, however substantial variation in trends remains between countries and between genders.

14 July 2022 in BMJ Health & Care Informatics
Verified
Journal Article
Open access
PDF file
PFPaul Festor
Paul Festor
YJYan Jia
Yan Jia
AGAnthony C Gordon
Anthony C Gordon
AFA. Aldo Faisal
A. Aldo Faisal
IHIbrahim Habli
Ibrahim Habli
MKMatthieu Komorowski
Matthieu Komorowski
Objectives Establishing confidence in the safety of Artificial Intelligence (AI)-based clinical decision support systems is important prior to clinical deployment and regulatory approval for systems with increasing autonomy. Here, we undertook safety assurance of the AI Clinician, a previously published reinforcement learning-based treatment recommendation system for sepsis. Methods As part of the safety assurance, we defined four clinical hazards in sepsis resuscitation based on clinical expert opinion and the existing literature. We then identified a set of unsafe scenarios, intended to limit the action space of the AI agent with the goal of reducing the likelihood of hazardous decisions. Results Using a subset of the Medical Information Mart for Intensive Care (MIMIC-III) database, we demonstrated that our previously published ‘AI clinician’ recommended fewer hazardous decisions than human clinicians in three out of our four predefined clinical scenarios, while the difference was not statistically significant in the fourth scenario. Then, we modified the reward function to satisfy our safety constraints and trained a new AI Clinician agent. The retrained model shows enhanced safety, without negatively impacting model performance. Discussion While some contextual patient information absent from the data may have pushed human clinicians to take hazardous actions, the data were curated to limit the impact of this confounder. Conclusion These advances provide a use case for the systematic safety assurance of AI-based clinical systems towards the generation of explicit safety evidence, which could be replicated for other AI applications or other clinical contexts, and inform medical device regulatory bodies.