1
|
Shirali A, Schubert A, Alaa A. Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care. IEEE J Biomed Health Inform 2024; 28:6268-6279. [PMID: 38885106 DOI: 10.1109/jbhi.2024.3415115] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/20/2024]
Abstract
Medical treatments often involve a sequence of decisions, each informed by previous outcomes. This process closely aligns with reinforcement learning (RL), a framework for optimizing sequential decisions to maximize cumulative rewards under unknown dynamics. While RL shows promise for creating data-driven treatment plans, its application in medical contexts is challenging due to the frequent need to use sparse rewards, primarily defined based on mortality outcomes. This sparsity can reduce the stability of offline estimates, posing a significant hurdle in fully utilizing RL for medical decision-making. We introduce a deep Q-learning approach to obtain more reliable critical care policies by integrating relevant but noisy frequently measured biomarker signals into the reward specification without compromising the optimization of the main outcome. Our method prunes the action space based on all available rewards before training a final model on the sparse main reward. This approach minimizes potential distortions of the main objective while extracting valuable information from intermediate signals to guide learning. We evaluate our method in off-policy and offline settings using simulated environments and real health records from intensive care units. Our empirical results demonstrate that our method outperforms common offline RL methods such as conservative Q-learning and batch-constrained deep Q-learning. By disentangling sparse rewards and frequently measured reward proxies through action pruning, our work represents a step towards developing reliable policies that effectively harness the wealth of available information in data-intensive critical care environments.
Collapse
|
2
|
Khajuria R, Sarwar A. Review of reinforcement learning applications in segmentation, chemotherapy, and radiotherapy of cancer. Micron 2024; 178:103583. [PMID: 38185018 DOI: 10.1016/j.micron.2023.103583] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2023] [Revised: 10/16/2023] [Accepted: 12/20/2023] [Indexed: 01/09/2024]
Abstract
Owing to early diagnosis and treatment of cancer as a prerequisite in recent times, the role of machine learning has been increased substantially. The mathematically powerful and optimized solutions for the detection and cure of cancer are constantly being explored and novel models based upon standard algorithms are also being developed. Leveraging one such solution is Reinforcement Learning (RL), which is a semi-supervised type of learning. The paper presents a detailed discussion on the various RL techniques, algorithms, and open issues, in addition to the review of literature for diagnosis and treatment of cancer. A smaller number of publications for diagnosis and treatment of cancer have been reported before 2011 but now after the success of Deep Learning (DL) and the advent of Deep Reinforcement Learning (DRL), the publications have grown in number from 2017 onwards. The scope of RL for cancer diagnosis and treatment is also demystified and provides the research community with the insights of how to formulate RL problem as a Cancer diagnostic problem. RL has been found successful for landmark detection in medical images and optimal control of drugs and radiations.
Collapse
|
3
|
Zhang A, Wu Z, Wu E, Wu M, Snyder MP, Zou J, Wu JC. Leveraging physiology and artificial intelligence to deliver advancements in health care. Physiol Rev 2023; 103:2423-2450. [PMID: 37104717 PMCID: PMC10390055 DOI: 10.1152/physrev.00033.2022] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2022] [Revised: 03/06/2023] [Accepted: 04/25/2023] [Indexed: 04/29/2023] Open
Abstract
Artificial intelligence in health care has experienced remarkable innovation and progress in the last decade. Significant advancements can be attributed to the utilization of artificial intelligence to transform physiology data to advance health care. In this review, we explore how past work has shaped the field and defined future challenges and directions. In particular, we focus on three areas of development. First, we give an overview of artificial intelligence, with special attention to the most relevant artificial intelligence models. We then detail how physiology data have been harnessed by artificial intelligence to advance the main areas of health care: automating existing health care tasks, increasing access to care, and augmenting health care capabilities. Finally, we discuss emerging concerns surrounding the use of individual physiology data and detail an increasingly important consideration for the field, namely the challenges of deploying artificial intelligence models to achieve meaningful clinical impact.
Collapse
Affiliation(s)
- Angela Zhang
- Stanford Cardiovascular Institute, School of Medicine, Stanford University, Stanford, California, United States
- Department of Genetics, School of Medicine, Stanford University, Stanford, California, United States
- Greenstone Biosciences, Palo Alto, California, United States
| | - Zhenqin Wu
- Department of Chemistry, Stanford University, Stanford, California, United States
| | - Eric Wu
- Department of Electrical Engineering, Stanford University, Stanford, California, United States
| | - Matthew Wu
- Greenstone Biosciences, Palo Alto, California, United States
| | - Michael P Snyder
- Department of Genetics, School of Medicine, Stanford University, Stanford, California, United States
| | - James Zou
- Department of Biomedical Informatics, School of Medicine, Stanford University, Stanford, California, United States
- Department of Computer Science, Stanford University, Stanford, California, United States
| | - Joseph C Wu
- Stanford Cardiovascular Institute, School of Medicine, Stanford University, Stanford, California, United States
- Greenstone Biosciences, Palo Alto, California, United States
- Division of Cardiovascular Medicine, Department of Medicine, Stanford University, Stanford, California, United States
- Department of Radiology, School of Medicine, Stanford University, Stanford, California, United States
| |
Collapse
|
4
|
Lee H, Yoon HK, Kim J, Park JS, Koo CH, Won D, Lee HC. Development and validation of a reinforcement learning model for ventilation control during emergence from general anesthesia. NPJ Digit Med 2023; 6:145. [PMID: 37580410 PMCID: PMC10425339 DOI: 10.1038/s41746-023-00893-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2023] [Accepted: 08/03/2023] [Indexed: 08/16/2023] Open
Abstract
Ventilation should be assisted without asynchrony or cardiorespiratory instability during anesthesia emergence until sufficient spontaneous ventilation is recovered. In this multicenter cohort study, we develop and validate a reinforcement learning-based Artificial Intelligence model for Ventilation control during Emergence (AIVE) from general anesthesia. Ventilatory and hemodynamic parameters from 14,306 surgical cases at an academic hospital between 2016 and 2019 are used for training and internal testing of the model. The model's performance is also evaluated on the external validation cohort, which includes 406 cases from another academic hospital in 2022. The estimated reward of the model's policy is higher than that of the clinicians' policy in the internal (0.185, the 95% lower bound for best AIVE policy vs. -0.406, the 95% upper bound for clinicians' policy) and external validation (0.506, the 95% lower bound for best AIVE policy vs. 0.154, the 95% upper bound for clinicians' policy). Cardiorespiratory instability is minimized as the clinicians' ventilation matches the model's ventilation. Regarding feature importance, airway pressure is the most critical factor for ventilation control. In conclusion, the AIVE model achieves higher estimated rewards with fewer complications than clinicians' ventilation control policy during anesthesia emergence.
Collapse
Affiliation(s)
- Hyeonhoon Lee
- Department of Anesthesiology and Pain Medicine, Seoul National University Hospital, Seoul, Republic of Korea
- Biomedical Research Institute, Seoul National University Hospital, Seoul, Republic of Korea
| | - Hyun-Kyu Yoon
- Department of Anesthesiology and Pain Medicine, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Republic of Korea
| | - Jaewon Kim
- Center for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, Republic of Korea
| | - Ji Soo Park
- Department of Pediatrics, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Republic of Korea
| | - Chang-Hoon Koo
- Department of Anesthesiology and Pain Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
| | - Dongwook Won
- Department of Anesthesiology and Pain Medicine, SMG-SNU Boramae Medical Center, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Hyung-Chul Lee
- Department of Anesthesiology and Pain Medicine, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
| |
Collapse
|
5
|
Feng X, Wang D, Pan Q, Yan M, Liu X, Shen Y, Fang L, Cai G, Ning G. Reinforcement Learning Model for Managing Noninvasive Ventilation Switching Policy. IEEE J Biomed Health Inform 2023; 27:4120-4130. [PMID: 37159312 DOI: 10.1109/jbhi.2023.3274568] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/11/2023]
Abstract
Noninvasive ventilation (NIV) has been recognized as a first-line treatment for respiratory failure in patients with chronic obstructive pulmonary disease (COPD) and hypercapnia respiratory failure, which can reduce mortality and burden of intubation. However, during the long-term NIV process, failure to respond to NIV may cause overtreatment or delayed intubation, which is associated with increased mortality or costs. Optimal strategies for switching regime in the course of NIV treatment remain to be explored.For the goal of reducing 28-day mortality of the patients undergoing NIV, Double Dueling Deep Q Network (D3QN) of offline-reinforcement learning algorithm was adopted to develop an optimal regime model for making treatment decisions of discontinuing ventilation, continuing NIV, or intubation. The model was trained and tested using the data from Multi-Parameter Intelligent Monitoring in Intensive Care III (MIMIC-III) and evaluated by the practical strategies. Furthermore, the applicability of the model in majority disease subgroups (Catalogued by International Classification of Diseases, ICD) was investigated. Compared with physician's strategies, the proposed model achieved a higher expected return score (4.25 vs. 2.68) and its recommended treatments reduced the expected mortality from 27.82% to 25.44% in all NIV cases. In particular, for these patients finally received intubation in practice, if the model also supported the regime, it would warn of switching to intubation 13.36 hours earlier than clinicians (8.64 vs. 22 hours after the NIV treatment), granting a 21.7% reduction in estimated mortality. In addition, the model was applicable across various disease groups with distinguished achievement in dealing with respiratory disorders. The proposed model is promising to dynamically provide personalized optimal NIV switching regime for patients undergoing NIV with the potential of improving treatment outcomes.
Collapse
|
6
|
Kim YJ, Chi M. Time-aware deep reinforcement learning with multi-temporal abstraction. APPL INTELL 2023. [DOI: 10.1007/s10489-022-04392-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/28/2023]
|
7
|
Yu C, Huang Q. Towards more efficient and robust evaluation of sepsis treatment with deep reinforcement learning. BMC Med Inform Decis Mak 2023; 23:43. [PMID: 36859257 PMCID: PMC9979564 DOI: 10.1186/s12911-023-02126-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2022] [Accepted: 01/30/2023] [Indexed: 03/03/2023] Open
Abstract
BACKGROUND In recent years, several studies have applied advanced AI methods, i.e., deep reinforcement learning, in discovering more efficient treatment policies for sepsis. However, due to a paucity of understanding of sepsis itself, the existing approaches still face a severe evaluation challenge, that is, how to properly evaluate the goodness of treatments during the learning process and the effectiveness of the final learned treatment policies. METHODS We propose a deep inverse reinforcement learning with mini-tree model that integrates different aspects of factors into the reward formulation, including the critical factors in causing mortality and the key indicators in the existing sepsis treatment guidelines, in order to provide a more comprehensive evaluation of treatments during learning. A new off-policy evaluation method is then proposed to enable more robust evaluation of the learned policies by considering the weighted averaged value functions estimated until the current step. RESULTS Results in the MIMIC-III dataset show that the proposed methods can achieve more efficient treatment policies with higher reliability compared to those used by the clinicians. CONCLUSIONS A more sound and comprehensive evaluation of treatments of sepsis should consider the most critical factors in infulencing the mortality during treatment as well as those key indicators in the existing sepsis diagnosis guidelines.
Collapse
Affiliation(s)
- Chao Yu
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China.
| | - Qikai Huang
- Fudan University Pudong Medical Center, Shanghai Pudong Hospital, Shanghai, China.
| |
Collapse
|
8
|
Morris AH, Horvat C, Stagg B, Grainger DW, Lanspa M, Orme J, Clemmer TP, Weaver LK, Thomas FO, Grissom CK, Hirshberg E, East TD, Wallace CJ, Young MP, Sittig DF, Suchyta M, Pearl JE, Pesenti A, Bombino M, Beck E, Sward KA, Weir C, Phansalkar S, Bernard GR, Thompson BT, Brower R, Truwit J, Steingrub J, Hiten RD, Willson DF, Zimmerman JJ, Nadkarni V, Randolph AG, Curley MAQ, Newth CJL, Lacroix J, Agus MSD, Lee KH, deBoisblanc BP, Moore FA, Evans RS, Sorenson DK, Wong A, Boland MV, Dere WH, Crandall A, Facelli J, Huff SM, Haug PJ, Pielmeier U, Rees SE, Karbing DS, Andreassen S, Fan E, Goldring RM, Berger KI, Oppenheimer BW, Ely EW, Pickering BW, Schoenfeld DA, Tocino I, Gonnering RS, Pronovost PJ, Savitz LA, Dreyfuss D, Slutsky AS, Crapo JD, Pinsky MR, James B, Berwick DM. Computer clinical decision support that automates personalized clinical care: a challenging but needed healthcare delivery strategy. J Am Med Inform Assoc 2022; 30:178-194. [PMID: 36125018 PMCID: PMC9748596 DOI: 10.1093/jamia/ocac143] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Revised: 07/27/2022] [Accepted: 08/22/2022] [Indexed: 12/15/2022] Open
Abstract
How to deliver best care in various clinical settings remains a vexing problem. All pertinent healthcare-related questions have not, cannot, and will not be addressable with costly time- and resource-consuming controlled clinical trials. At present, evidence-based guidelines can address only a small fraction of the types of care that clinicians deliver. Furthermore, underserved areas rarely can access state-of-the-art evidence-based guidelines in real-time, and often lack the wherewithal to implement advanced guidelines. Care providers in such settings frequently do not have sufficient training to undertake advanced guideline implementation. Nevertheless, in advanced modern healthcare delivery environments, use of eActions (validated clinical decision support systems) could help overcome the cognitive limitations of overburdened clinicians. Widespread use of eActions will require surmounting current healthcare technical and cultural barriers and installing clinical evidence/data curation systems. The authors expect that increased numbers of evidence-based guidelines will result from future comparative effectiveness clinical research carried out during routine healthcare delivery within learning healthcare systems.
Collapse
Affiliation(s)
- Alan H Morris
- Department of Internal Medicine, University of Utah, Salt Lake City, Utah, USA
- Department of Internal Medicine, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - Christopher Horvat
- Department of Critical Care Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | - Brian Stagg
- Department of Ophthalmology and Visual Sciences, Moran Eye Center, University of Utah, Salt Lake City, Utah, USA
| | - David W Grainger
- Department of Biomedical Engineering, University of Utah, Salt Lake City, Utah, USA
| | - Michael Lanspa
- Department of Internal Medicine, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - James Orme
- Department of Internal Medicine, University of Utah, Salt Lake City, Utah, USA
- Department of Internal Medicine, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - Terry P Clemmer
- Department of Internal Medicine (Critical Care), Intermountain Healthcare, Salt Lake City, Utah, USA
| | - Lindell K Weaver
- Department of Internal Medicine, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - Frank O Thomas
- Department of Internal Medicine, University of Utah, Salt Lake City, Utah, USA
| | - Colin K Grissom
- Department of Internal Medicine, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - Ellie Hirshberg
- Department of Internal Medicine, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - Thomas D East
- SYNCRONYS - Chief Executive Officer, Albuquerque, New Mexico, USA
| | - Carrie Jane Wallace
- Department of Internal Medicine, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - Michael P Young
- Department of Critical Care, Renown Regional Medical Center, Reno, Nevada, USA
| | - Dean F Sittig
- School of Biomedical Informatics, University of Texas Health Science Center, Houston, Texas, USA
| | - Mary Suchyta
- Department of Internal Medicine, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - James E Pearl
- Department of Internal Medicine, University of Utah, Salt Lake City, Utah, USA
- Department of Internal Medicine, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - Antinio Pesenti
- Faculty of Medicine and Surgery—Anesthesiology, University of Milan, Milano, Lombardia, Italy
| | - Michela Bombino
- Department of Emergency and Intensive Care, San Gerardo Hospital, Monza (MB), Italy
| | - Eduardo Beck
- Faculty of Medicine and Surgery - Anesthesiology, University of Milan, Ospedale di Desio, Desio, Lombardia, Italy
| | - Katherine A Sward
- Department of Biomedical Informatics, College of Nursing, University of Utah, Salt Lake City, Utah, USA
| | - Charlene Weir
- Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, USA
| | - Shobha Phansalkar
- Wolters Kluwer Health—Clinical Solutions—Medical Informatics, Wolters Kluwer Health, Newton, Massachusetts, USA
| | - Gordon R Bernard
- Vanderbilt University School of Medicine, Nashville, Tennessee, USA
| | - B Taylor Thompson
- Pulmonary and Critical Care Division, Department of Internal Medicine, Harvard Medical School, Boston, Massachusetts, USA
| | - Roy Brower
- Department of Medicine, Johns Hopkins School of Medicine, Baltimore, Maryland, USA
| | - Jonathon Truwit
- Department of Internal Medicine, Pulmonary and Critical Care, Medical College of Wisconsin, Milwaukee, Wisconsin, USA
| | - Jay Steingrub
- Department of Internal Medicine, Pulmonary and Critical Care, University of Massachusetts Medical School, Baystate Campus, Springfield, Massachusetts, USA
| | - R Duncan Hiten
- Department of Internal Medicine, Pulmonary and Critical Care, University of Cincinnati College of Medicine, Cincinnati, Ohio, USA
| | - Douglas F Willson
- Pediatric Critical Care, Department of Pediatrics, Virginia Commonwealth University, Richmond, Virginia, USA
| | - Jerry J Zimmerman
- Division of Pediatric Critical Care Medicine, Department of Pediatrics, University of Washington School of Medicine, Seattle, Washington, USA
| | - Vinay Nadkarni
- Department of Anesthesiology and Critical Care Medicine, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA
| | - Adrienne G Randolph
- Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children's Hospital, Boston, Massachusetts, USA
| | - Martha A Q Curley
- University of Pennsylvania School of Nursing, Philadelphia, Pennsylvania, USA
| | - Christopher J L Newth
- Childrens Hospital Los Angeles, Department of Anesthesiology and Critical Care, University of Southern California Keck School of Medicine, Los Angeles, California, USA
| | - Jacques Lacroix
- Division of Pediatric Critical Care Medicine, Department of Pediatrics, Université de Montréal Faculté de Médecine, Montreal, Quebec, Canada
| | - Michael S D Agus
- Division of Medical Pediatric Critical Care, Department of Pediatrics, Boston Children’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Kang Hoe Lee
- Department of Intensive Care Medicine, Ng Teng Fong Hospital and National University Centre of Transplantation, National University Singapore Yong Loo Lin School of Medicine, Singapore
| | - Bennett P deBoisblanc
- Department of Internal Medicine, Pulmonary and Critical Care, Louisiana State University Health Sciences Center, New Orleans, Louisiana, USA
| | - Frederick Alan Moore
- Department of Surgery, University of Florida College of Medicine, Gainesville, Florida, USA
| | - R Scott Evans
- Department of Medical Informatics, Intermountain Healthcare, and Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, USA
| | - Dean K Sorenson
- Department of Medical Informatics, Intermountain Healthcare, Salt Lake City, Utah, USA
| | - Anthony Wong
- Department of Data Science Ann and Robert H Lurie Children's Hospital of Chicago, Chicago, Illinois, USA
| | - Michael V Boland
- Department of Ophthalmology, Massachusetts Ear and Eye Infirmary, Harvard Medical School, Boston, Massachusetts, USA
| | - Willard H Dere
- Endocrinology and Metabolism Division, Department of Internal Medicine, University of Utah, Salt Lake City, Utah, USA
| | - Alan Crandall
- Department of Ophthalmology and Visual Sciences, Moran Eye Center, University of Utah, Salt Lake City, Utah, USA
- Posthumous
| | - Julio Facelli
- Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, USA
| | - Stanley M Huff
- Department of Medical Informatics, Intermountain Healthcare, Department of Biomedical Informatics, University of Utah, and Graphite Health, Salt Lake City, Utah, USA
| | - Peter J Haug
- Department of Medical Informatics, Intermountain Healthcare, and Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, USA
| | - Ulrike Pielmeier
- Aalborg University Faculty of Engineering and Science - Department of Health Science and Technology, Respiratory and Critical Care Group, Aalborg, Nordjylland, Denmark
| | - Stephen E Rees
- Aalborg University Faculty of Engineering and Science - Department of Health Science and Technology, Respiratory and Critical Care Group, Aalborg, Nordjylland, Denmark
| | - Dan S Karbing
- Aalborg University Faculty of Engineering and Science - Department of Health Science and Technology, Respiratory and Critical Care Group, Aalborg, Nordjylland, Denmark
| | - Steen Andreassen
- Aalborg University Faculty of Engineering and Science - Department of Health Science and Technology, Respiratory and Critical Care Group, Aalborg, Nordjylland, Denmark
| | - Eddy Fan
- Internal Medicine, Pulmonary and Critical Care Division, Institute of Health Policy, Management and Evaluation, University of Toronto Faculty of Medicine, Toronto, Ontario, Canada
| | - Roberta M Goldring
- Department of Internal Medicine, Pulmonary and Critical Care, New York University School of Medicine, New York, New York, USA
| | - Kenneth I Berger
- Department of Internal Medicine, Pulmonary and Critical Care, New York University School of Medicine, New York, New York, USA
| | - Beno W Oppenheimer
- Department of Internal Medicine, Pulmonary and Critical Care, New York University School of Medicine, New York, New York, USA
| | - E Wesley Ely
- Internal Medicine, Pulmonary and Critical Care, Critical Illness, Brain Dysfunction, and Survivorship (CIBS) Center, Vanderbilt University Medical Center, Nashville, Tennessee, USA
- Tennessee Valley Veteran’s Affairs Geriatric Research Education Clinical Center (GRECC), Nashville, Tennessee, USA
| | - Brian W Pickering
- Department of Anesthesiology, Mayo Clinic, Rochester, Minnesota, USA
| | - David A Schoenfeld
- Biostatistics Center, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Irena Tocino
- Department of Radiology, Yale University School of Medicine, New Haven, Connecticut, USA
| | - Russell S Gonnering
- Department of Ophthalmology and Visual Sciences, Medical College of Wisconsin, Milwaukee, Wisconsin, USA
| | - Peter J Pronovost
- Department of Anesthesiology and Critical Care Medicine, University Hospitals, Highland Hills, Case Western Reserve University School of Medicine, Cleveland, Ohio, USA
| | - Lucy A Savitz
- Northwest Center for Health Research, Kaiser Permanente, Oakland, California, USA
| | - Didier Dreyfuss
- Assistance Publique—Hôpitaux de Paris, Université de Paris, Sorbonne Université - INSERM unit UMR S_1155 (Common and Rare Kidney Diseases), Paris, France
| | - Arthur S Slutsky
- Interdepartmental Division of Critical Care Medicine, Keenan Research Center, Li Ka Shing Knowledge Institute, St. Michael’s Hospital, University of Toronto, Toronto, Ontario, Canada
| | - James D Crapo
- Department of Internal Medicine, National Jewish Health, Denver, Colorado, USA
| | - Michael R Pinsky
- Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA
| | - Brent James
- Department of Internal Medicine, Clinical Excellence Research Center (CERC), Stanford University School of Medicine, Stanford, California, USA
| | - Donald M Berwick
- Institute for Healthcare Improvement, Cambridge, Massachusetts, USA
| |
Collapse
|
9
|
Closed-Loop Controlled Fluid Administration Systems: A Comprehensive Scoping Review. J Pers Med 2022; 12:jpm12071168. [PMID: 35887665 PMCID: PMC9315597 DOI: 10.3390/jpm12071168] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2022] [Revised: 07/14/2022] [Accepted: 07/15/2022] [Indexed: 02/07/2023] Open
Abstract
Physiological Closed-Loop Controlled systems continue to take a growing part in clinical practice, offering possibilities of providing more accurate, goal-directed care while reducing clinicians’ cognitive and task load. These systems also provide a standardized approach for the clinical management of the patient, leading to a reduction in care variability across multiple dimensions. For fluid management and administration, the advantages of closed-loop technology are clear, especially in conditions that require precise care to improve outcomes, such as peri-operative care, trauma, and acute burn care. Controller design varies from simplistic to complex designs, based on detailed physiological models and adaptive properties that account for inter-patient and intra-patient variability; their maturity level ranges from theoretical models tested in silico to commercially available, FDA-approved products. This comprehensive scoping review was conducted in order to assess the current technological landscape of this field, describe the systems currently available or under development, and suggest further advancements that may unfold in the coming years. Ten distinct systems were identified and discussed.
Collapse
|
10
|
Awasthi R, Guliani KK, Khan SA, Vashishtha A, Gill MS, Bhatt A, Nagori A, Gupta A, Kumaraguru P, Sethi T. VacSIM: Learning effective strategies for COVID-19 vaccine distribution using reinforcement learning. INTELLIGENCE-BASED MEDICINE 2022; 6:100060. [PMID: 35610985 PMCID: PMC9119863 DOI: 10.1016/j.ibmed.2022.100060] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/15/2021] [Revised: 12/18/2021] [Accepted: 03/29/2022] [Indexed: 12/18/2022]
Abstract
A COVID-19 vaccine is our best bet for mitigating the ongoing onslaught of the pandemic. However, vaccine is also expected to be a limited resource. An optimal allocation strategy, especially in countries with access inequities and temporal separation of hot-spots, might be an effective way of halting the disease spread. We approach this problem by proposing a novel pipeline VacSIM that dovetails Deep Reinforcement Learning models into a Contextual Bandits approach for optimizing the distribution of COVID-19 vaccine. Whereas the Reinforcement Learning models suggest better actions and rewards, Contextual Bandits allow online modifications that may need to be implemented on a day-to-day basis in the real world scenario. We evaluate this framework against a naive allocation approach of distributing vaccine proportional to the incidence of COVID-19 cases in five different States across India (Assam, Delhi, Jharkhand, Maharashtra and Nagaland) and demonstrate up to 9039 potential infections prevented and a significant increase in the efficacy of limiting the spread over a period of 45 days through the VacSIM approach. Our models and the platform are extensible to all states of India and potentially across the globe. We also propose novel evaluation strategies including standard compartmental model-based projections and a causality-preserving evaluation of our model. Since all models carry assumptions that may need to be tested in various contexts, we open source our model VacSIM and contribute a new reinforcement learning environment compatible with OpenAI gym to make it extensible for real-world applications across the globe. 2
Collapse
Affiliation(s)
- Raghav Awasthi
- Indraprastha Institute of Information Technology Delhi, India
| | | | - Saif Ahmad Khan
- Indraprastha Institute of Information Technology Delhi, India
| | | | | | - Arshita Bhatt
- Bhagwan Parshuram Institute of Technology, New Delhi, India
| | - Aditya Nagori
- CSIR-Institute of Genomics and Integrative Biology, New Delhi, India
| | - Aniket Gupta
- Indraprastha Institute of Information Technology Delhi, India
| | | | | |
Collapse
|
11
|
Artificial Intelligence for Medical Decisions. Artif Intell Med 2022. [DOI: 10.1007/978-3-030-64573-1_28] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
12
|
Dellinger RP, Levy MM, Schorr CA, Townsend SR. 50 Years of Sepsis Investigation/Enlightenment Among Adults-The Long and Winding Road. Crit Care Med 2021; 49:1606-1625. [PMID: 34342304 DOI: 10.1097/ccm.0000000000005203] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Affiliation(s)
- R Phillip Dellinger
- Cooper Medical School of Rowan University and Cooper University Health, Camden, NJ
| | | | - Christa A Schorr
- Cooper Medical School of Rowan University and Cooper University Health, Camden, NJ
| | - Sean R Townsend
- University of California Pacific Medical Center, (Sutter Health), San Francisco, CA
| |
Collapse
|
13
|
Wei WQ, Zhao J, Roden DM, Peterson JF. Machine Learning Challenges in Pharmacogenomic Research. Clin Pharmacol Ther 2021; 110:552-554. [PMID: 34217153 DOI: 10.1002/cpt.2329] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2021] [Accepted: 05/25/2021] [Indexed: 12/23/2022]
Affiliation(s)
- Wei-Qi Wei
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| | - Juan Zhao
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| | - Dan M Roden
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.,Division of Cardiovascular Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA.,Oates Institute for Experimental Therapeutics, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| | - Josh F Peterson
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.,Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| |
Collapse
|
14
|
Pepic I, Feldt R, Ljungström L, Torkar R, Dalevi D, Maurin Söderholm H, Andersson LM, Axelson-Fisk M, Bohm K, Sjöqvist BA, Candefjord S. Early detection of sepsis using artificial intelligence: a scoping review protocol. Syst Rev 2021; 10:28. [PMID: 33453724 PMCID: PMC7811741 DOI: 10.1186/s13643-020-01561-w] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/15/2020] [Accepted: 12/17/2020] [Indexed: 12/12/2022] Open
Abstract
BACKGROUND Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection. To decrease the high case fatality rates and morbidity for sepsis and septic shock, there is a need to increase the accuracy of early detection of suspected sepsis in prehospital and emergency department settings. This may be achieved by developing risk prediction decision support systems based on artificial intelligence. METHODS The overall aim of this scoping review is to summarize the literature on existing methods for early detection of sepsis using artificial intelligence. The review will be performed using the framework formulated by Arksey and O'Malley and further developed by Levac and colleagues. To identify primary studies and reviews that are suitable to answer our research questions, a comprehensive literature collection will be compiled by searching several sources. Constrictions regarding time and language will have to be implemented. Therefore, only studies published between 1 January 1990 and 31 December 2020 will be taken into consideration, and foreign language publications will not be considered, i.e., only papers with full text in English will be included. Databases/web search engines that will be used are PubMed, Web of Science Platform, Scopus, IEEE Xplore, Google Scholar, Cochrane Library, and ACM Digital Library. Furthermore, clinical studies that have completed patient recruitment and reported results found in the database ClinicalTrials.gov will be considered. The term artificial intelligence is viewed broadly, and a wide range of machine learning and mathematical models suitable as base for decision support will be evaluated. Two members of the team will test the framework on a sample of included studies to ensure that the coding framework is suitable and can be consistently applied. Analysis of collected data will provide a descriptive summary and thematic analysis. The reported results will convey knowledge about the state of current research and innovation for using artificial intelligence to detect sepsis in early phases of the medical care chain. ETHICS AND DISSEMINATION The methodology used here is based on the use of publicly available information and does not need ethical approval. It aims at aiding further research towards digital solutions for disease detection and health innovation. Results will be extracted into a review report for submission to a peer-reviewed scientific journal. Results will be shared with relevant local and national authorities and disseminated in additional appropriate formats such as conferences, lectures, and press releases.
Collapse
Affiliation(s)
- Ivana Pepic
- Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, 412 96, Sweden
| | - Robert Feldt
- Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, 412 96, Sweden
| | - Lars Ljungström
- Department of Infectious Diseases, Institute of Biomedicine, Sahlgrenska Academy, Gothenburg University, Gothenburg, Sweden.,Region Västra Götaland, Skaraborg Hospital, Department of Infectious Diseases, Skövde, Sweden
| | - Richard Torkar
- Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, 412 96, Sweden
| | | | | | - Lars-Magnus Andersson
- Department of Infectious Diseases, Institute of Biomedicine, Sahlgrenska Academy, Gothenburg University, Gothenburg, Sweden
| | - Marina Axelson-Fisk
- Department of Mathematical Sciences, Chalmers University of Technology, Gothenburg, 412 96, Sweden
| | - Katarina Bohm
- Karolinska Institute, Department of Clinical Science and Education, South General Hospital, Stockholm, Sweden.,Department of Emergency medicine, South General Hospital, Stockholm, Sweden
| | - Bengt Arne Sjöqvist
- Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, 412 96, Sweden.,MedTech West, Sahlgrenska University Hospital, Gothenburg, 413 45, Sweden
| | - Stefan Candefjord
- Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, 412 96, Sweden. .,MedTech West, Sahlgrenska University Hospital, Gothenburg, 413 45, Sweden.
| |
Collapse
|
15
|
Buchard A, Richens JG. Artificial Intelligence for Medical Decisions. Artif Intell Med 2021. [DOI: 10.1007/978-3-030-58080-3_28-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
16
|
Golovenkin SE, Bac J, Chervov A, Mirkes EM, Orlova YV, Barillot E, Gorban AN, Zinovyev A. Trajectories, bifurcations, and pseudo-time in large clinical datasets: applications to myocardial infarction and diabetes data. Gigascience 2020; 9:giaa128. [PMID: 33241287 PMCID: PMC7688475 DOI: 10.1093/gigascience/giaa128] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2020] [Revised: 09/30/2020] [Accepted: 10/22/2020] [Indexed: 12/31/2022] Open
Abstract
BACKGROUND Large observational clinical datasets are becoming increasingly available for mining associations between various disease traits and administered therapy. These datasets can be considered as representations of the landscape of all possible disease conditions, in which a concrete disease state develops through stereotypical routes, characterized by "points of no return" and "final states" (such as lethal or recovery states). Extracting this information directly from the data remains challenging, especially in the case of synchronic (with a short-term follow-up) observations. RESULTS Here we suggest a semi-supervised methodology for the analysis of large clinical datasets, characterized by mixed data types and missing values, through modeling the geometrical data structure as a bouquet of bifurcating clinical trajectories. The methodology is based on application of elastic principal graphs, which can address simultaneously the tasks of dimensionality reduction, data visualization, clustering, feature selection, and quantifying the geodesic distances (pseudo-time) in partially ordered sequences of observations. The methodology allows a patient to be positioned on a particular clinical trajectory (pathological scenario) and the degree of progression along it to be characterized with a qualitative estimate of the uncertainty of the prognosis. We developed a tool ClinTrajan for clinical trajectory analysis implemented in the Python programming language. We test the methodology in 2 large publicly available datasets: myocardial infarction complications and readmission of diabetic patients data. CONCLUSIONS Our pseudo-time quantification-based approach makes it possible to apply the methods developed for dynamical disease phenotyping and illness trajectory analysis (diachronic data analysis) to synchronic observational data.
Collapse
Affiliation(s)
- Sergey E Golovenkin
- Prof. V.F. Voino-Yasenetsky Krasnoyarsk State Medical University, 660022 Krasnoyarsk, Russia
| | - Jonathan Bac
- Institut Curie, PSL Research University, F-75005 Paris, France
- INSERM, U900, F-75005 Paris, France
- CBIO-Centre for Computational Biology, Mines ParisTech, PSL Research University, 75006 Paris, France
| | - Alexander Chervov
- Institut Curie, PSL Research University, F-75005 Paris, France
- INSERM, U900, F-75005 Paris, France
- CBIO-Centre for Computational Biology, Mines ParisTech, PSL Research University, 75006 Paris, France
| | - Evgeny M Mirkes
- Centre for Artificial Intelligence, Data Analytics and Modelling, University of Leicester, LE1 7RH Leicester, UK
- Laboratory of advanced methods for high-dimensional data analysis, Lobachevsky University, 603000 Nizhny Novgorod, Russia
| | - Yuliya V Orlova
- Prof. V.F. Voino-Yasenetsky Krasnoyarsk State Medical University, 660022 Krasnoyarsk, Russia
| | - Emmanuel Barillot
- Institut Curie, PSL Research University, F-75005 Paris, France
- INSERM, U900, F-75005 Paris, France
- CBIO-Centre for Computational Biology, Mines ParisTech, PSL Research University, 75006 Paris, France
| | - Alexander N Gorban
- Centre for Artificial Intelligence, Data Analytics and Modelling, University of Leicester, LE1 7RH Leicester, UK
- Laboratory of advanced methods for high-dimensional data analysis, Lobachevsky University, 603000 Nizhny Novgorod, Russia
| | - Andrei Zinovyev
- Institut Curie, PSL Research University, F-75005 Paris, France
- INSERM, U900, F-75005 Paris, France
- CBIO-Centre for Computational Biology, Mines ParisTech, PSL Research University, 75006 Paris, France
| |
Collapse
|