Publications
92 results found
Daniel C, Rulan Z, Komorowski M, 2024, Infections during long duration space missions: a narrative review, The Lancet Microbe, ISSN: 2666-5247
As plans for deep space exploration and colonisation are announced by space agencies and private companies, it is crucial to prioritise medical preparedness. Among all medical conditions, infections pose one of the highest threats to astronaut health and mission success.To gain a comprehensive understanding of these risks, we conducted a narrative review, analysing measured and estimated infections incidence in space, the impact of the space environment on the human immune system and microbial behaviour, current preventive and management strategies for infections, and future perspectives for diagnosis and treatment.This research will enable space agencies to enhance their comprehension of the infectious risk in space, highlight gaps in knowledge, improve crew preparation, while also potentially contribute to sepsis management in terrestrial settings, including in isolated or austere environments but also in conventional clinical settings.
Catling FJR, Nagendran M, Festor P, et al., 2024, Can machine learning personalise cardiovascular therapy in sepsis?, Critical Care Explorations, ISSN: 2639-8028
Smit JM, Krijthe JH, Kant WMR, et al., 2023, Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice, npj Digital Medicine, Vol: 6
This scoping review focuses on the essential role of models for causal inference in shaping actionable artificial intelligence (AI) designed to aid clinicians in decision-making. The objective was to identify and evaluate the reporting quality of studies introducing models for causal inference in intensive care units (ICUs), and to provide recommendations to improve the future landscape of research practices in this domain. To achieve this, we searched various databases including Embase, MEDLINE ALL, Web of Science Core Collection, Google Scholar, medRxiv, bioRxiv, arXiv, and the ACM Digital Library. Studies involving models for causal inference addressing time-varying treatments in the adult ICU were reviewed. Data extraction encompassed the study settings and methodologies applied. Furthermore, we assessed reporting quality of target trial components (i.e., eligibility criteria, treatment strategies, follow-up period, outcome, and analysis plan) and main causal assumptions (i.e., conditional exchangeability, positivity, and consistency). Among the 2184 titles screened, 79 studies met the inclusion criteria. The methodologies used were G methods (61%) and reinforcement learning methods (39%). Studies considered both static (51%) and dynamic treatment regimes (49%). Only 30 (38%) of the studies reported all five target trial components, and only seven (9%) studies mentioned all three causal assumptions. To achieve actionable AI in the ICU, we advocate careful consideration of the causal question of interest, describing this research question as a target trial emulation, usage of appropriate causal inference methods, and acknowledgement (and examination of potential violations of) the causal assumptions.
Sonawane U, Komorowski M, 2023, Artificial Intelligence in medicine: Potential applications and barriers to deployment, Beyond Quantity: Research with Subsymbolic AI, Pages: 155-178, ISBN: 9783837667660
- Cite
- Citations: 1
Nagendran M, Festor P, Komorowski M, et al., 2023, Quantifying the impact of AI recommendations with explanations on prescription decision making, npj Digital Medicine, Vol: 6, ISSN: 2398-6352
The influence of AI recommendations on physician behaviour remains poorly characterised. We assess how clinicians' decisions may be influenced by additional information more broadly, and how this influence can be modified by either the source of the information (human peers or AI) and the presence or absence of an AI explanation (XAI, here using simple feature importance). We used a modified between-subjects design where intensive care doctors (N=86) were presented on a computer for each of 16 trials with a patient case and prompted to prescribe continuous values for two drugs. We used a multi-factorial experimental design with four arms, where each clinician experienced all four arms on different subsets of our 24 patients. The four arms were (i) baseline (control), (ii) peer human clinician scenario showing what doses had been prescribed by other doctors, (iii) AI suggestion and (iv) XAI suggestion. We found that additional information (peer, AI or XAI) had a strong influence on prescriptions (significantly for AI, not so for peers) but simple XAI did not have higher influence than AI alone. There was no correlation between attitudes to AI or clinical experience on the AI-supported decisions and nor was there correlation between what doctors self-reported about how useful they found the XAI and whether the XAI actually influenced their prescriptions. Our findings suggest that the marginal impact of simple XAI was low in this setting and we also cast doubt on the utility of self-reports as a valid metric for assessing XAI in clinical experts.
Thierry S, Jaulin F, Starck C, et al., 2023, Evaluation of free-floating tracheal intubation in weightlessness via ice-pick position with a direct laryngoscopy and classic approach with indirect videolaryngoscopy, NPJ MICROGRAVITY, Vol: 9
Smit JM, Krijthe JH, van Bommel J, et al., 2023, The future of artificial intelligence in intensive care: moving from predictive to actionable AI, Intensive Care Medicine, Vol: 49, Pages: 1114-1116, ISSN: 0342-4642
Artificial intelligence (AI) research in the intensive care unit (ICU) mainly focuses on developing models (from linear regression to deep learning) to predict outcomes, such as mortality or sepsis [1, 2]. However, there is another important aspect of AI that is typically not framed as AI (although it may be more worthy of the name), which is the prediction of patient outcomes or events that would result from different actions, known as causal inference [3, 4]. This aspect of AI is crucial for decision-making in the ICU. To emphasize the importance of causal inference, we propose to refer to any data-driven model used for causal inference tasks as ‘actionable AI’, as opposed to ‘predictive AI’, and discuss how these models could provide meaningful decision support in the ICU.
Cheung HC, De Louche C, Komorowski M, 2023, Artificial Intelligence Applications in Space Medicine., Aerosp Med Hum Perform, Vol: 94, Pages: 610-622
INTRODUCTION:During future interplanetary space missions, a number of health conditions may arise, owing to the hostile environment of space and the myriad of stressors experienced by the crew. When managing these conditions, crews will be required to make accurate, timely clinical decisions at a high level of autonomy, as telecommunication delays and increasing distances restrict real-time support from the ground. On Earth, artificial intelligence (AI) has proven successful in healthcare, augmenting expert clinical decision-making or enhancing medical knowledge where it is lacking. Similarly, deploying AI tools in the context of a space mission could improve crew self-reliance and healthcare delivery.METHODS: We conducted a narrative review to discuss existing AI applications that could improve the prevention, recognition, evaluation, and management of the most mission-critical conditions, including psychological and mental health, acute radiation sickness, surgical emergencies, spaceflight-associated neuro-ocular syndrome, infections, and cardiovascular deconditioning.RESULTS: Some examples of the applications we identified include AI chatbots designed to prevent and mitigate psychological and mental health conditions, automated medical imaging analysis, and closed-loop systems for hemodynamic optimization. We also discuss at length gaps in current technologies, as well as the key challenges and limitations of developing and deploying AI for space medicine to inform future research and innovation. Indeed, shifts in patient cohorts, space-induced physiological changes, limited size and breadth of space biomedical datasets, and changes in disease characteristics may render the models invalid when transferred from ground settings into space.Cheung HC, De Louche C, Komorowski M. Artificial intelligence applications in space medicine. Aerosp Med Hum Perform. 2023; 94(8):610-622.
Komorowski M, Arias Lopez MDP, Chang AC, 2023, How could ChatGPT impact my practice as an intensivist? An overview of potential applications, risks and limitations, INTENSIVE CARE MEDICINE, Vol: 49, Pages: 844-847, ISSN: 0342-4642
- Author Web Link
- Cite
- Citations: 3
Pan P, Komorowski M, Shen L, et al., 2023, Editorial: Clinical teaching and practice in intensive care medicine and anesthesiology, Frontiers in Medicine, Vol: 10, Pages: 1-2, ISSN: 2296-858X
Marshall DC, Zhang J, Hao S, et al., 2023, Early Vs Late Initiation of Vasopressors in Sepsis: An Augmented Inverse Probability Weighting Approach, International Conference of the American-Thoracic-Society (ATS), Publisher: AMER THORACIC SOC, ISSN: 1073-449X
Scott RT, Sanders LM, Antonsen EL, et al., 2023, Biomonitoring and precision health in deep space supported by artificial intelligence, Nature Machine Intelligence, Vol: 5, Pages: 196-207
Human exploration of deep space will involve missions of substantial distance and duration. To effectively mitigate health hazards, paradigm shifts in astronaut health systems are necessary to enable Earth-independent healthcare, rather than Earth-reliant. Here we present a summary of decadal recommendations from a workshop organized by NASA on artificial intelligence, machine learning and modelling applications that offer key solutions toward these space health challenges. The workshop recommended various biomonitoring approaches, biomarker science, spacecraft/habitat hardware, intelligent software and streamlined data management tools in need of development and integration to enable humanity to thrive in deep space. Participants recommended that these components culminate in a maximally automated, autonomous and intelligent Precision Space Health system, to monitor, aggregate and assess biomedical statuses.
Sanders LM, Scott RT, Yang JH, et al., 2023, Biological research and self-driving labs in deep space supported by artificial intelligence, Nature Machine Intelligence, Vol: 5, Pages: 208-219
Space biology research aims to understand fundamental spaceflight effects on organisms, develop foundational knowledge to support deep space exploration and, ultimately, bioengineer spacecraft and habitats to stabilize the ecosystem of plants, crops, microbes, animals and humans for sustained multi-planetary life. To advance these aims, the field leverages experiments, platforms, data and model organisms from both spaceborne and ground-analogue studies. As research is extended beyond low Earth orbit, experiments and platforms must be maximally automated, light, agile and intelligent to accelerate knowledge discovery. Here we present a summary of decadal recommendations from a workshop organized by the National Aeronautics and Space Administration on artificial intelligence, machine learning and modelling applications that offer solutions to these space biology challenges. The integration of artificial intelligence into the field of space biology will deepen the biological understanding of spaceflight effects, facilitate predictive modelling and analytics, support maximally automated and reproducible experiments, and efficiently manage spaceborne data and metadata, ultimately to enable life to thrive in deep space.
Rosario E, Ross T, Komorowski M, et al., 2023, Coronavirus disease tracheostomy complications: a scoping review., J Laryngol Otol, Vol: 137, Pages: 7-16
BACKGROUND: Coronavirus disease 2019 increased the numbers of patients requiring prolonged mechanical ventilation, with a subsequent increase in tracheostomy procedures. Coronavirus disease 2019 patients are high risk for surgical complications. This review examines open surgical and percutaneous tracheostomy complications in coronavirus disease 2019 patients. METHODS: Medline and Embase databases were searched (November 2021), and the abstracts of relevant articles were screened. Data were collected regarding tracheostomy technique and complications. Complication rates were compared between percutaneous and open surgical tracheostomy. RESULTS: Percutaneous tracheostomy was higher risk for bleeding, pneumothorax and false passage. Surgical tracheostomy was higher risk for peri-operative hypoxia. The most common complication for both techniques was post-operative bleeding. CONCLUSION: Coronavirus disease 2019 patients undergoing tracheostomy are at higher risk of bleeding and peri-operative hypoxia than non-coronavirus disease patients. High doses of anti-coagulants may partially explain this. Reasons for higher bleeding risk in percutaneous over open surgical technique remain unclear. Further research is required to determine the causes of differences found and to establish mitigating strategies.
Zhang M, Wu Y, Zhang H, et al., 2023, Multi-site, Multi-domain Airway Tree Modeling
Komorowski M, Green A, Tatham KC, et al., 2022, Sepsis biomarkers and diagnostic tools with a focus on machine learning., EBioMedicine, Vol: 86, Pages: 1-10, ISSN: 2352-3964
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.
Schmitz J, Komorowski M, Russomano T, et al., 2022, Sixty years of manned spaceflight—incidents and accidents involving astronauts between launch and landing, Aerospace, Vol: 9, Pages: 675-675, ISSN: 2226-4310
Introduction: Since Gagarin became the first human to travel into space and complete one orbit around the Earth, on 12 April 1961, the number of manned spaceflights has increased significantly. Spaceflight is still complex and has potential risk for incidents and accidents. The aim of this study was to analyze how safe it is for humans to travel in space. Objectives: This paper, therefore, summarizes incidents and accidents covering the six decades of manned spaceflight (1961–2020). Material and methods: Extensive PubMed, Cochrane, and Google Scholar searches were made with search strings of “incidents”, “accident”, “spaceflight”, and “orbit”, and including all vehicles so far. Search terms were combined by AND or OR in search strings. Of the results obtained, studies which evaluated manned spaceflight were included in the study. Data from the National Aeronautics Space Agency (NASA), the Russian Space Agency (ROSCOSMOS), the European Space Agency (ESA), and the Chinese Space Agency (CNSA), as well as from the Virgin Galactic and the SpaceX databases, were searched to complete data and to identify all the accomplished manned spaceflights, as well as all incidents and accidents that have occurred in the specific period. Search results were compared to findings on Wikipedia, Encyclopedia Astronautica, and other public webpages. Reference lists of included articles/homepages were also included for further potential data. Results: From 1961–2020, our data revealed an increasing number of manned space flights, n = 327. The number of times an astronaut has been sent to space, n = 1294, resulted in an accumulated n = 19,414 days spent in space. The number of days spent in orbit has constantly increased from 1961 until today. The number of incidents (altogether n = 36) and accidents (altogether n = 5) has constantly decreased. The number of astronauts who have died during spaceflight is represented by n = 19. The c
Smit JM, Krijthe JH, van Bommel J, et al., 2022, Causal inference using observational intensive care unit data: a systematic review and recommendations for future practice
<jats:sec><jats:title>Aim</jats:title><jats:p>To review and appraise the quality of studies that present models for causal inference of time-varying treatment effects in the adult intensive care unit (ICU) and give recommendations to improve future research practice.</jats:p></jats:sec><jats:sec><jats:title>Methods</jats:title><jats:p>We searched Embase, MEDLINE ALL, Web of Science Core Collection, Google Scholar, medRxiv, and bioRxiv up to March 2, 2022. Studies that present models for causal inference that deal with time-varying treatments in adult ICU patients were included. From the included studies, data was extracted about the study setting and applied methodology. Quality of reporting (QOR) of target trial components and causal assumptions (ie, conditional exchangeability, positivity and consistency) were assessed.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>1,714 titles were screened and 60 studies were included, of which 36 (60%) were published in the last 5 years. G methods were the most commonly used (n=40/60, 67%), further divided into inverse-probability-of-treatment weighting (n=36/40, 90%) and the parametric G formula (n=4/40, 10%). The remaining studies (n=20/60, 33%) used reinforcement learning methods. Overall, most studies (n=36/60, 60%) considered static treatment regimes. Only ten (17%) studies fully reported all five target trial components (ie, eligibility criteria, treatment strategies, follow-up period, outcome and analysis plan). The ‘treatment strategies’ and ‘analysis plan’ components were not (fully) reported in 38% and 48% of the studies, respectively. The ‘causal assumptions’ (ie, conditional exchangeability, positivity and consistency) remained unmentioned in 35%, 68% and 88% of the studies, respectively. All three causal assumptions were mentioned (or a check for potential violat
Vasey B, Nagendran M, Campbell B, et al., 2022, Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI (May, 10.1038/s41591-022-01772-9, 2022), NATURE MEDICINE, Vol: 28, Pages: 2218-2218, ISSN: 1078-8956
Festor P, Jia Y, Gordon A, et al., 2022, Assuring the safety of AI-based clinical decision support systems: a case study of the AI Clinician for sepsis treatment, BMJ Health & Care Informatics, Vol: 29, ISSN: 2632-1009
Study objectives: Establishing confidence in the safety of 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 and created safety constraints, 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 MIMIC-III database, we demonstrated that our previously published “AI Clinician” recommended fewer hazardous decisions than human clinicians in three out of our four pre-defined 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 was 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.
Lemyze M, Komorowski M, Mallat J, et al., 2022, Early intensive physical rehabilitation combined with a protocolized decannulation process in tracheostomized survivors from severe COVID-19 pneumonia with chronic critical illness, Journal of Clinical Medicine, Vol: 11, Pages: 3921-3921, ISSN: 2077-0383
(1) Background: Intensive care unit (ICU) survivors from severe COVID-19 acute respiratory distress syndrome (CARDS) with chronic critical illness (CCI) may be considered vast resource consumers with a poor prognosis. We hypothesized that a holistic approach combining an early intensive rehabilitation with a protocol of difficult weaning would improve patient outcomes (2) Methods: A single-center retrospective study in a five-bed post-ICU weaning and intensive rehabilitation center with a dedicated fitness room specifically equipped to safely deliver physical activity sessions in frail patients with CCI. (3) Results: Among 502 CARDS patients admitted to the ICU from March 2020 to March 2022, 50 consecutive tracheostomized patients were included in the program. After a median of 39 ICU days, 25 days of rehabilitation were needed to restore patients’ autonomy (ADL, from 0 to 6; p < 0.001), to significantly improve their aerobic capacity (6-min walking test distance, from 0 to 253 m; p < 0.001) and to reduce patients’ vulnerability (frailty score, from 7 to 3; p < 0.001) and hospital anxiety and depression scale (HADS, from 18 to 10; p < 0.001). Forty-eight decannulated patients (96%) were discharged home. (4) Conclusions: A protocolized weaning strategy combined with early intensive rehabilitation in a dedicated specialized center boosted the physical and mental recovery.
Vasey B, Nagendran M, Campbell B, et al., 2022, Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI, Nature Medicine, Vol: 28, Pages: 924-933, ISSN: 1078-8956
A growing number of artificial intelligence (AI)-based clinical decision support systems are showing promising performance in preclinical, in silico evaluation, but few have yet demonstrated real benefit to patient care. Early-stage clinical evaluation is important to assess an AI system's actual clinical performance at small scale, ensure its safety, evaluate the human factors surrounding its use and pave the way to further large-scale trials. However, the reporting of these early studies remains inadequate. The present statement provides a multi-stakeholder, consensus-based reporting guideline for the Developmental and Exploratory Clinical Investigations of DEcision support systems driven by Artificial Intelligence (DECIDE-AI). We conducted a two-round, modified Delphi process to collect and analyze expert opinion on the reporting of early clinical evaluation of AI systems. Experts were recruited from 20 pre-defined stakeholder categories. The final composition and wording of the guideline was determined at a virtual consensus meeting. The checklist and the Explanation & Elaboration (E&E) sections were refined based on feedback from a qualitative evaluation process. In total, 123 experts participated in the first round of Delphi, 138 in the second round, 16 in the consensus meeting and 16 in the qualitative evaluation. The DECIDE-AI reporting guideline comprises 17 AI-specific reporting items (made of 28 subitems) and ten generic reporting items, with an E&E paragraph provided for each. Through consultation and consensus with a range of stakeholders, we developed a guideline comprising key items that should be reported in early-stage clinical studies of AI-based decision support systems in healthcare. By providing an actionable checklist of minimal reporting items, the DECIDE-AI guideline will facilitate the appraisal of these studies and replicability of their findings.
Salciccioli JD, Komorowski M, Marshall DC, 2022, Characteristics and outcomes for adult patients with asthma admitted to intensive care: a retrospective analysis, International Conference of the American-Thoracic-Society, Publisher: American Thoracic Society, ISSN: 1073-449X
Marshall DC, Salciccioli JD, Hao S, et al., 2022, Does the tidal volume matter? A retrospective analysis of ventilation parameters in severe acute lung injury patients, International Conference of the American-Thoracic-Society, Publisher: American Thoracic Society, ISSN: 1073-449X
Schmitz J, Ahlback A, DuCanto J, et al., 2022, Randomized Comparison of Two New Methods for Chest Compressions during CPR in Microgravity-A Manikin Study, JOURNAL OF CLINICAL MEDICINE, Vol: 11
- Author Web Link
- Cite
- Citations: 1
Komorowski M, 2022, Anesthesia and Surgery in Space: Reply, ANESTHESIOLOGY, Vol: 136, Pages: 400-+, ISSN: 0003-3022
Komorowski M, Joosten A, 2022, AIM in Anesthesiology, Artificial Intelligence in Medicine, Pages: 1453-1467, ISBN: 9783030645724
This chapter focuses on applications of artificial intelligence (AI) in anesthesiology. Anesthesiology is the field of healthcare involved with providing a state of controlled, temporary loss of sensation or awareness that is induced for medical purposes such as a surgical intervention. It may include a combination of various components including analgesia, amnesia, unconsciousness, and muscle relaxation. Anesthesiology is mostly a technical field, heavily protocolized and data-intensive (due to all the monitoring equipment in place), which makes it the perfect environment to deploy AI tools. In this chapter, we review in detail the main applications of AI in the operating room, sorted in four main domains: (1) monitoring of the depth of anesthesia, (2) control of administration of anesthetic drugs (hypnotics, opioids, and/or muscle relaxants), (3) hemodynamic control (mostly titration of fluids and vasopressor therapy), and (4) risk prediction and prediction of events (e.g., predict surgery length or postoperative complications). In addition, we analyzed the degree of maturity of these various technologies. While many of these applications can have a large impact on quality and safety of care surrounding anesthesia, the maturity of these technologies is in general very low, and most of the applications published describe tools that have not received prospective evaluation. Only a handful of randomized trials comparing standard of care to the tandem AI doctor could be identified. Finally, we conclude with an assessment of the current practical implications of AI for practicing anesthesiologists.
Marshall DC, Komorowski M, 2021, Is artificial intelligence ready to solve mechanical ventilation? Computer says blow, British Journal of Anaesthesia, Vol: 128, Pages: 231-233, ISSN: 0007-0912
Artificial intelligence (AI) has the potential to identify treatable phenotypes, optimise ventilation strategies, and provide clinical decision support for patients who require mechanical ventilation. Gallifant and colleagues performed a systematic review to identify studies using AI to solve a diverse range of clinical problems in the ventilated patient. They identify 95 studies, the majority of which were reported in the last 5 yr. Their findings indicate that the majority of studies have significant methodological bias and are a long way from deployment
Festor P, Habil I, Jia Y, et al., 2021, Levels of Autonomy & Safety Assurance forAI-based Clinical Decision Systems, WAISE 2021 : 4th International Workshop on Artificial Intelligence Safety Engineering
Festor P, Luise G, Komorowski M, et al., 2021, Enabling risk-aware Reinforcement Learning for medical interventions through uncertainty decomposition, ICML2021 workshop on Interpretable Machine Learning in Healthcare
Reinforcement Learning (RL) is emerging as toolfor tackling complex control and decision-makingproblems. However, in high-risk environmentssuch as healthcare, manufacturing, automotive oraerospace, it is often challenging to bridge the gapbetween an apparently optimal policy learned byan agent and its real-world deployment, due to theuncertainties and risk associated with it. Broadlyspeaking RL agents face two kinds of uncertainty,1. aleatoric uncertainty, which reflects randomness or noise in the dynamics of the world, and 2.epistemic uncertainty, which reflects the boundedknowledge of the agent due to model limitationsand finite amount of information/data the agenthas acquired about the world. These two typesof uncertainty carry fundamentally different implications for the evaluation of performance andthe level of risk or trust. Yet these aleatoric andepistemic uncertainties are generally confoundedas standard and even distributional RL is agnosticto this difference. Here we propose how a distributional approach (UA-DQN) can be recast torender uncertainties by decomposing the net effects of each uncertainty . We demonstrate theoperation of this method in grid world examplesto build intuition and then show a proof of concept application for an RL agent operating as aclinical decision support system in critical care.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.