1
|
Cowen D, Zhang R, Komorowski M. Infections in long-duration space missions. THE LANCET. MICROBE 2024; 5:100875. [PMID: 38861994 DOI: 10.1016/s2666-5247(24)00098-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Revised: 03/25/2024] [Accepted: 04/09/2024] [Indexed: 06/13/2024]
Abstract
As government space agencies and private companies announce plans for deep space exploration and colonisation, prioritisation of medical preparedness is becoming crucial. Among all medical conditions, infections pose one of the biggest threats to astronaut health and mission success. To gain a comprehensive understanding of these risks, we review the measured and estimated incidence of infections in space, effect of 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 information will enable space agencies to enhance their comprehension of the risk of infection in space, highlight gaps in knowledge, aid better crew preparation, and potentially contribute to sepsis management in terrestrial settings, including not only isolated or austere environments but also conventional clinical settings.
Collapse
Affiliation(s)
- Daniel Cowen
- School of Medicine, Faculty of Medicine, Imperial College London, London SW7 2AZ, UK
| | | | - Matthieu Komorowski
- Department of Surgery and Cancer, Division of Anaesthetics, Pain Medicine, and Intensive Care, Faculty of Medicine, Imperial College London, London SW7 2AZ, UK.
| |
Collapse
|
2
|
McLennan S, Fiske A, Celi LA. Building a house without foundations? A 24-country qualitative interview study on artificial intelligence in intensive care medicine. BMJ Health Care Inform 2024; 31:e101052. [PMID: 38642921 PMCID: PMC11033632 DOI: 10.1136/bmjhci-2024-101052] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2024] [Accepted: 04/08/2024] [Indexed: 04/22/2024] Open
Abstract
OBJECTIVES To explore the views of intensive care professionals in high-income countries (HICs) and lower-to-middle-income countries (LMICs) regarding the use and implementation of artificial intelligence (AI) technologies in intensive care units (ICUs). METHODS Individual semi-structured qualitative interviews were conducted between December 2021 and August 2022 with 59 intensive care professionals from 24 countries. Transcripts were analysed using conventional content analysis. RESULTS Participants had generally positive views about the potential use of AI in ICUs but also reported some well-known concerns about the use of AI in clinical practice and important technical and non-technical barriers to the implementation of AI. Important differences existed between ICUs regarding their current readiness to implement AI. However, these differences were not primarily between HICs and LMICs, but between a small number of ICUs in large tertiary hospitals in HICs, which were reported to have the necessary digital infrastructure for AI, and nearly all other ICUs in both HICs and LMICs, which were reported to neither have the technical capability to capture the necessary data or use AI, nor the staff with the right knowledge and skills to use the technology. CONCLUSION Pouring massive amounts of resources into developing AI without first building the necessary digital infrastructure foundation needed for AI is unethical. Real-world implementation and routine use of AI in the vast majority of ICUs in both HICs and LMICs included in our study is unlikely to occur any time soon. ICUs should not be using AI until certain preconditions are met.
Collapse
Affiliation(s)
- Stuart McLennan
- Institute of History and Ethics in Medicine, Department of Preclinical Medicine, TUM School of Medicine and Health, Technical University of Munich, Munich, Bavaria, Germany
- Institute for Biomedical Ethics, University of Basel, Basel, Switzerland
| | - Amelia Fiske
- Institute of History and Ethics in Medicine, Department of Preclinical Medicine, TUM School of Medicine and Health, Technical University of Munich, Munich, Bavaria, Germany
| | - Leo Anthony Celi
- Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
- Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02215, USA
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
| |
Collapse
|
3
|
Teele SA, Tremoulet P, Laussen PC, Danaher-Garcia N, Salvin JW, White BAA. Complex decision making in an intensive care environment: Perceived practice versus observed reality. J Eval Clin Pract 2024; 30:337-345. [PMID: 37767761 DOI: 10.1111/jep.13930] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/12/2023] [Revised: 09/01/2023] [Accepted: 09/14/2023] [Indexed: 09/29/2023]
Abstract
RATIONALE Advancing our understanding of how decisions are made in cognitively, socially and technologically complex hospital environments may reveal opportunities to improve healthcare delivery, medical education and the experience of patients, families and clinicians. AIMS AND OBJECTIVES Explore factors impacting clinician decision making in the Boston Children's Hospital Cardiac Intensive Care Unit. METHODS A convergent mixed methods design was used. Quantitative and qualitative data sources consisted of a faculty survey, direct observations of clinical rounds in a specific patient population identified by a clinical decision support system (CDSS) and semistructured interviews (SSIs). Deductive and inductive coding was used for qualitative data. Qualitative data were translated into images using social network analysis which illustrate the frequency and connectivity of the codes in each data set. RESULTS A total of 25 observations of eight faculty-led interprofessional teams were performed between 12 February and 31 March 2021. Individual patient characteristics were noted by faculty in SSIs to be the most important factor in their decision making, yet ethnographic observations suggested faculty cognitive traits, team expertise and value-based decisions were more heavily weighted. The development of expertise was impacted by role modeling. Decisions were perceived to be influenced by the system and environment. CONCLUSIONS Clinician perception of decision making was not congruent with the observed behaviours in a complicated and dynamic system. This study identifies important considerations in clinical curricula as well as the design and implementation of CDSS. Our method of using social network analysis to visualize components of decision making could be adopted to explore other complex environments.
Collapse
Affiliation(s)
- Sarah A Teele
- Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA
- Massachusetts General Hospital Institute of Health Professions, Boston, Massachusetts, USA
| | | | - Peter C Laussen
- Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Nicole Danaher-Garcia
- Massachusetts General Hospital Institute of Health Professions, Boston, Massachusetts, USA
| | - Joshua W Salvin
- Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Bobbie Ann A White
- Massachusetts General Hospital Institute of Health Professions, Boston, Massachusetts, USA
| |
Collapse
|
4
|
Smit JM, Krijthe JH, Kant WMR, Labrecque JA, Komorowski M, Gommers DAMPJ, van Bommel J, Reinders MJT, van Genderen ME. Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice. NPJ Digit Med 2023; 6:221. [PMID: 38012221 PMCID: PMC10682453 DOI: 10.1038/s41746-023-00961-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2023] [Accepted: 11/05/2023] [Indexed: 11/29/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- J M Smit
- Department of Intensive Care, Erasmus University Medical Center, Rotterdam, The Netherlands.
- Pattern Recognition & Bioinformatics group, EEMCS, Delft University of Technology, Delft, The Netherlands.
| | - J H Krijthe
- Pattern Recognition & Bioinformatics group, EEMCS, Delft University of Technology, Delft, The Netherlands
| | - W M R Kant
- Data Science group, Institute for Computing and Information Sciences, Radboud University, Nijmegen, The Netherlands
| | - J A Labrecque
- Department of Epidemiology, Erasmus Medical Center, Rotterdam, The Netherlands
| | - M Komorowski
- Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK
- Intensive Care Unit, Charing Cross Hospital, Imperial College Healthcare NHS Trust, London, UK
| | - D A M P J Gommers
- Department of Intensive Care, Erasmus University Medical Center, Rotterdam, The Netherlands
| | - J van Bommel
- Department of Intensive Care, Erasmus University Medical Center, Rotterdam, The Netherlands
| | - M J T Reinders
- Pattern Recognition & Bioinformatics group, EEMCS, Delft University of Technology, Delft, The Netherlands
| | - M E van Genderen
- Department of Intensive Care, Erasmus University Medical Center, Rotterdam, The Netherlands
| |
Collapse
|
5
|
Liu X, Barreto EF, Dong Y, Liu C, Gao X, Tootooni MS, Song X, Kashani KB. Discrepancy between perceptions and acceptance of clinical decision support Systems: implementation of artificial intelligence for vancomycin dosing. BMC Med Inform Decis Mak 2023; 23:157. [PMID: 37568134 PMCID: PMC10416522 DOI: 10.1186/s12911-023-02254-9] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2022] [Accepted: 07/31/2023] [Indexed: 08/13/2023] Open
Abstract
BACKGROUND Artificial intelligence (AI) tools are more effective if accepted by clinicians. We developed an AI-based clinical decision support system (CDSS) to facilitate vancomycin dosing. This qualitative study assesses clinicians' perceptions regarding CDSS implementation. METHODS Thirteen semi-structured interviews were conducted with critical care pharmacists, at Mayo Clinic (Rochester, MN), from March through April 2020. Eight clinical cases were discussed with each pharmacist (N = 104). Following initial responses, we revealed the CDSS recommendations to assess participants' reactions and feedback. Interviews were audio-recorded, transcribed, and summarized. RESULTS The participants reported considerable time and effort invested daily in individualizing vancomycin therapy for hospitalized patients. Most pharmacists agreed that such a CDSS could favorably affect (N = 8, 62%) or enhance (9, 69%) their ability to make vancomycin dosing decisions. In case-based evaluations, pharmacists' empiric doses differed from the CDSS recommendation in most cases (88/104, 85%). Following revealing the CDSS recommendations, we noted 78% (69/88) discrepant doses. In discrepant cases, pharmacists indicated they would not alter their recommendations. The reasons for declining the CDSS recommendation were general distrust of CDSS, lack of dynamic evaluation and in-depth analysis, inability to integrate all clinical data, and lack of a risk index. CONCLUSION While pharmacists acknowledged enthusiasm about the advantages of AI-based models to improve drug dosing, they were reluctant to integrate the tool into clinical practice. Additional research is necessary to determine the optimal approach to implementing CDSS at the point of care acceptable to clinicians and effective at improving patient outcomes.
Collapse
Affiliation(s)
- Xinyan Liu
- Division of Pulmonary and Critical Care Medicine, Department of Medicine, Mayo Clinic, Rochester, MN, 55905, USA
- ICU, DongE Hospital Affiliated to Shandong First Medical University, Liaocheng, Shandong, 252200, China
| | - Erin F Barreto
- Department of Pharmacy, Mayo Clinic, Rochester, MN, 55905, USA
| | - Yue Dong
- Department of Anesthesiology and Perioperative Medicine, Mayo Clinic, Rochester, MN, 55905, USA
| | - Chang Liu
- Division of Pulmonary and Critical Care Medicine, Department of Medicine, Mayo Clinic, Rochester, MN, 55905, USA
- Department of Critical Care Medicine, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, 430071, China
| | - Xiaolan Gao
- Division of Pulmonary and Critical Care Medicine, Department of Medicine, Mayo Clinic, Rochester, MN, 55905, USA
- Department of Critical Care Medicine, Division of Life Sciences and Medicine, The First Affiliated Hospital of USTC, University of Science and Technology of China, Hefei, Anhui, 230001, China
| | - Mohammad Samie Tootooni
- Health Informatics and Data Science. Health Sciences Campus, Loyola University, Chicago, IL, 60611, USA
| | - Xuan Song
- ICU, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, 250098, China.
| | - Kianoush B Kashani
- Division of Pulmonary and Critical Care Medicine, Department of Medicine, Mayo Clinic, Rochester, MN, 55905, USA.
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA.
| |
Collapse
|
6
|
Behling AH, Wilson BC, Ho D, Virta M, O'Sullivan JM, Vatanen T. Addressing antibiotic resistance: computational answers to a biological problem? Curr Opin Microbiol 2023; 74:102305. [PMID: 37031568 DOI: 10.1016/j.mib.2023.102305] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2022] [Revised: 03/01/2023] [Accepted: 03/02/2023] [Indexed: 04/11/2023]
Abstract
The increasing prevalence of infections caused by antibiotic-resistant bacteria is a global healthcare crisis. Understanding the spread of resistance is predicated on the surveillance of antibiotic resistance genes within an environment. Bioinformatics and artificial intelligence (AI) methods applied to metagenomic sequencing data offer the capacity to detect known and infer yet-unknown resistance mechanisms, and predict future outbreaks of antibiotic-resistant infections. Machine learning methods, in particular, could revive the waning antibiotic discovery pipeline by helping to predict the molecular structure and function of antibiotic resistance compounds, and optimising their interactions with target proteins. Consequently, AI has the capacity to play a central role in guiding antibiotic stewardship and future clinical decision-making around antibiotic resistance.
Collapse
Affiliation(s)
- Anna H Behling
- Liggins Institute, University of Auckland, Auckland, New Zealand
| | - Brooke C Wilson
- Liggins Institute, University of Auckland, Auckland, New Zealand
| | - Daniel Ho
- Liggins Institute, University of Auckland, Auckland, New Zealand
| | - Marko Virta
- Department of Microbiology, University of Helsinki, Helsinki, Finland
| | - Justin M O'Sullivan
- Liggins Institute, University of Auckland, Auckland, New Zealand; The Maurice Wilkins Centre, The University of Auckland, Private Bag 92019, Auckland, New Zealand; Australian Parkinsons Mission, Garvan Institute of Medical Research, Sydney, New South Wales, 384 Victoria Street, Darlinghurst, NSW 2010, Australia; MRC Lifecourse Epidemiology Unit, University of Southampton, Southampton SO16 6YD, United Kingdom; Singapore Institute for Clinical Sciences, Agency for Science Technology and Research, Singapore.
| | - Tommi Vatanen
- Liggins Institute, University of Auckland, Auckland, New Zealand; Department of Microbiology, University of Helsinki, Helsinki, Finland; Research Program for Clinical and Molecular Metabolism, Faculty of Medicine, University of Helsinki, Helsinki, Finland; Broad Institute of MIT and Harvard, Cambridge, MA, USA.
| |
Collapse
|
7
|
Iwase S, Nakada TA, Shimada T, Oami T, Shimazui T, Takahashi N, Yamabe J, Yamao Y, Kawakami E. Prediction algorithm for ICU mortality and length of stay using machine learning. Sci Rep 2022; 12:12912. [PMID: 35902633 PMCID: PMC9334583 DOI: 10.1038/s41598-022-17091-5] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2022] [Accepted: 07/20/2022] [Indexed: 11/09/2022] Open
Abstract
Machine learning can predict outcomes and determine variables contributing to precise prediction, and can thus classify patients with different risk factors of outcomes. This study aimed to investigate the predictive accuracy for mortality and length of stay in intensive care unit (ICU) patients using machine learning, and to identify the variables contributing to the precise prediction or classification of patients. Patients (n = 12,747) admitted to the ICU at Chiba University Hospital were randomly assigned to the training and test cohorts. After learning using the variables on admission in the training cohort, the area under the curve (AUC) was analyzed in the test cohort to evaluate the predictive accuracy of the supervised machine learning classifiers, including random forest (RF) for outcomes (primary outcome, mortality; secondary outcome, length of ICU stay). The rank of the variables that contributed to the machine learning prediction was confirmed, and cluster analysis of the patients with risk factors of mortality was performed to identify the important variables associated with patient outcomes. Machine learning using RF revealed a high predictive value for mortality, with an AUC of 0.945 (95% confidence interval [CI] 0.922–0.977). In addition, RF showed high predictive value for short and long ICU stays, with AUCs of 0.881 (95% CI 0.876–0.908) and 0.889 (95% CI 0.849–0.936), respectively. Lactate dehydrogenase (LDH) was identified as a variable contributing to the precise prediction in machine learning for both mortality and length of ICU stay. LDH was also identified as a contributing variable to classify patients into sub-populations based on different risk factors of mortality. The machine learning algorithm could predict mortality and length of stay in ICU patients with high accuracy. LDH was identified as a contributing variable in mortality and length of ICU stay prediction and could be used to classify patients based on mortality risk.
Collapse
Affiliation(s)
- Shinya Iwase
- Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chuo-ku, Chiba, Chiba, 260-8677, Japan
| | - Taka-Aki Nakada
- Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chuo-ku, Chiba, Chiba, 260-8677, Japan. .,Smart 119 Inc., 7th floor, Chiba Chuo Twin Building No. 2, 2-5-1 Chuo, Chiba, Japan.
| | - Tadanaga Shimada
- Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chuo-ku, Chiba, Chiba, 260-8677, Japan
| | - Takehiko Oami
- Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chuo-ku, Chiba, Chiba, 260-8677, Japan
| | - Takashi Shimazui
- Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chuo-ku, Chiba, Chiba, 260-8677, Japan
| | - Nozomi Takahashi
- Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chuo-ku, Chiba, Chiba, 260-8677, Japan
| | - Jun Yamabe
- Smart 119 Inc., 7th floor, Chiba Chuo Twin Building No. 2, 2-5-1 Chuo, Chiba, Japan
| | - Yasuo Yamao
- Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chuo-ku, Chiba, Chiba, 260-8677, Japan.,Smart 119 Inc., 7th floor, Chiba Chuo Twin Building No. 2, 2-5-1 Chuo, Chiba, Japan
| | - Eiryo Kawakami
- Department of Artificial Intelligence Medicine, Chiba University Graduate School of Medicine, Chiba, Japan.,Medical Sciences Innovation Hub Program, RIKEN, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama, Kanagawa, Japan
| |
Collapse
|
8
|
Artificial intelligence for prediction of treatment outcomes in breast cancer: Systematic review of design, reporting standards, and bias. Cancer Treat Rev 2022; 108:102410. [DOI: 10.1016/j.ctrv.2022.102410] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2022] [Accepted: 05/16/2022] [Indexed: 12/24/2022]
|
9
|
Kharat A, Ribeiro C, Er B, Fisser C, López-Padilla D, Chatzivasiloglou F, Heunks LMA, Patout M, D'Cruz RF. ERS International Congress, Virtual 2021: Highlights from the Respiratory Intensive Care Assembly Early Career Members. ERJ Open Res 2022; 8:00016-2022. [PMID: 35615411 PMCID: PMC9124870 DOI: 10.1183/23120541.00016-2022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2022] [Accepted: 03/10/2022] [Indexed: 11/19/2022] Open
Abstract
Early Career Members of Assembly 2 (Respiratory Intensive Care) attended the European Respiratory Society International Congress through a virtual platform in 2021. Sessions of interest to our assembly members included symposia on the implications of acute respiratory distress syndrome phenotyping on diagnosis and treatment, safe applications of noninvasive ventilation in hypoxaemic respiratory failure, and new developments in mechanical ventilation and weaning, and a guidelines session on applying high-flow therapy in acute respiratory failure. These sessions are summarised in this article. Early Career Members of @ERSAssembly2 attended the #ERSCongress 2021, and reported on symposia on ARDS phenotyping, noninvasive ventilation in hypoxic respiratory failure, ventilator weaning and high-flow therapy in acute respiratory failurehttps://bit.ly/3D68r50
Collapse
|
10
|
Wu CL, Liu SF, Yu TL, Shih SJ, Chang CH, Yang Mao SF, Li YS, Chen HJ, Chen CC, Chao WC. Deep Learning-Based Pain Classifier Based on the Facial Expression in Critically Ill Patients. Front Med (Lausanne) 2022; 9:851690. [PMID: 35372435 PMCID: PMC8968070 DOI: 10.3389/fmed.2022.851690] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2022] [Accepted: 02/17/2022] [Indexed: 11/13/2022] Open
Abstract
ObjectivePain assessment based on facial expressions is an essential issue in critically ill patients, but an automated assessment tool is still lacking. We conducted this prospective study to establish the deep learning-based pain classifier based on facial expressions.MethodsWe enrolled critically ill patients during 2020–2021 at a tertiary hospital in central Taiwan and recorded video clips with labeled pain scores based on facial expressions, such as relaxed (0), tense (1), and grimacing (2). We established both image- and video-based pain classifiers through using convolutional neural network (CNN) models, such as Resnet34, VGG16, and InceptionV1 and bidirectional long short-term memory networks (BiLSTM). The performance of classifiers in the test dataset was determined by accuracy, sensitivity, and F1-score.ResultsA total of 63 participants with 746 video clips were eligible for analysis. The accuracy of using Resnet34 in the polychromous image-based classifier for pain scores 0, 1, 2 was merely 0.5589, and the accuracy of dichotomous pain classifiers between 0 vs. 1/2 and 0 vs. 2 were 0.7668 and 0.8593, respectively. Similar accuracy of image-based pain classifier was found using VGG16 and InceptionV1. The accuracy of the video-based pain classifier to classify 0 vs. 1/2 and 0 vs. 2 was approximately 0.81 and 0.88, respectively. We further tested the performance of established classifiers without reference, mimicking clinical scenarios with a new patient, and found the performance remained high.ConclusionsThe present study demonstrates the practical application of deep learning-based automated pain assessment in critically ill patients, and more studies are warranted to validate our findings.
Collapse
Affiliation(s)
- Chieh-Liang Wu
- Department of Critical Care Medicine, Taichung Veterans General Hospital, Taichung, Taiwan
- Department of Industrial Engineering and Enterprise Information, Tunghai University, Taichung, Taiwan
- Artificial Intelligence Studio, Taichung Veterans General Hospital, Taichung, Taiwan
- Colledge of Medicine, National Chung Hsing University, Taichung, Taiwan
| | - Shu-Fang Liu
- Department of Nursing, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Tian-Li Yu
- Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan
| | - Sou-Jen Shih
- Department of Nursing, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Chih-Hung Chang
- Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan
| | - Shih-Fang Yang Mao
- Electronic and Optoelectronic System Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan
| | - Yueh-Se Li
- Electronic and Optoelectronic System Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan
| | - Hui-Jiun Chen
- Department of Nursing, Taichung Veterans General Hospital, Taichung, Taiwan
| | - Chia-Chen Chen
- Electronic and Optoelectronic System Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan
- *Correspondence: Chia-Chen Chen
| | - Wen-Cheng Chao
- Department of Critical Care Medicine, Taichung Veterans General Hospital, Taichung, Taiwan
- Colledge of Medicine, National Chung Hsing University, Taichung, Taiwan
- Department of Automatic Control Engineering, Feng Chia University, Taichung, Taiwan
- Big Data Center, National Chung Hsing University, Taichung, Taiwan
- Wen-Cheng Chao
| |
Collapse
|
11
|
van de Sande D, Van Genderen ME, Smit JM, Huiskens J, Visser JJ, Veen RER, van Unen E, Ba OH, Gommers D, Bommel JV. Developing, implementing and governing artificial intelligence in medicine: a step-by-step approach to prevent an artificial intelligence winter. BMJ Health Care Inform 2022; 29:bmjhci-2021-100495. [PMID: 35185012 PMCID: PMC8860016 DOI: 10.1136/bmjhci-2021-100495] [Citation(s) in RCA: 31] [Impact Index Per Article: 15.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2021] [Accepted: 01/24/2022] [Indexed: 12/23/2022] Open
Abstract
Objective Although the role of artificial intelligence (AI) in medicine is increasingly studied, most patients do not benefit because the majority of AI models remain in the testing and prototyping environment. The development and implementation trajectory of clinical AI models are complex and a structured overview is missing. We therefore propose a step-by-step overview to enhance clinicians’ understanding and to promote quality of medical AI research. Methods We summarised key elements (such as current guidelines, challenges, regulatory documents and good practices) that are needed to develop and safely implement AI in medicine. Conclusion This overview complements other frameworks in a way that it is accessible to stakeholders without prior AI knowledge and as such provides a step-by-step approach incorporating all the key elements and current guidelines that are essential for implementation, and can thereby help to move AI from bytes to bedside.
Collapse
Affiliation(s)
- Davy van de Sande
- Department of Adult Intensive Care, Erasmus Medical Center, Rotterdam, The Netherlands
| | - Michel E Van Genderen
- Department of Adult Intensive Care, Erasmus Medical Center, Rotterdam, The Netherlands
| | - Jim M Smit
- Department of Adult Intensive Care, Erasmus Medical Center, Rotterdam, The Netherlands.,Pattern Recognition and Bioinformatics group, EEMCS, Delft University of Technology, Delft, The Netherlands
| | | | - Jacob J Visser
- Department of Radiology and Nuclear Medicine, Erasmus Medical Center, Rotterdam, The Netherlands.,Department of Information Technology, Chief Medical Information Officer, Erasmus Medical Center, Rotterdam, The Netherlands
| | - Robert E R Veen
- Department of Information Technology, theme Research Suite, Erasmus Medical Center, Rotterdam, The Netherlands
| | | | - Oliver Hilgers Ba
- Active Medical Devices/Medical Device Software, CE Plus GmbH, Badenweiler, Germany
| | - Diederik Gommers
- Department of Adult Intensive Care, Erasmus Medical Center, Rotterdam, The Netherlands
| | - Jasper van Bommel
- Department of Adult Intensive Care, Erasmus Medical Center, Rotterdam, The Netherlands
| |
Collapse
|
12
|
Odenstedt Hergès H, Vithal R, El‐Merhi A, Naredi S, Staron M, Block L. Machine learning analysis of heart rate variability to detect delayed cerebral ischemia in subarachnoid hemorrhage. Acta Neurol Scand 2022; 145:151-159. [PMID: 34677832 DOI: 10.1111/ane.13541] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2021] [Revised: 09/26/2021] [Accepted: 09/30/2021] [Indexed: 12/14/2022]
Abstract
OBJECTIVES Approximately 30% of patients with aneurysmal subarachnoid hemorrhage (aSAH) develop delayed cerebral ischemia (DCI). DCI is associated with increased mortality and persistent neurological deficits. This study aimed to analyze heart rate variability (HRV) data from patients with aSAH using machine learning to evaluate whether specific patterns could be found in patients developing DCI. MATERIAL & METHODS This is an extended, in-depth analysis of all HRV data from a previous study wherein HRV data were collected prospectively from a cohort of 64 patients with aSAH admitted to Sahlgrenska University Hospital, Gothenburg, Sweden, from 2015 to 2016. The method used for analyzing HRV is based on several data processing steps combined with the random forest supervised machine learning algorithm. RESULTS HRV data were available in 55 patients, but since data quality was significantly low in 19 patients, these were excluded. Twelve patients developed DCI. The machine learning process identified 71% of all DCI cases. However, the results also demonstrated a tendency to identify DCI in non-DCI patients, resulting in a specificity of 57%. CONCLUSIONS These data suggest that machine learning applied to HRV data might help identify patients with DCI in the future; however, whereas the sensitivity in the present study was acceptable, the specificity was low. Possible confounders such as severity of illness and therapy may have affected the result. Future studies should focus on developing a robust method for detecting DCI using real-time HRV data and explore the limits of this technology in terms of its reliability and accuracy.
Collapse
Affiliation(s)
- Helena Odenstedt Hergès
- Department of Anaesthesiology and Intensive Care Institute of Clinical Science Sahlgrenska Academy University of Gothenburg Gothenburg Sweden
- Department of Anaesthesia and Intensive Care Region Västra Götaland Sahlgrenska University Hospital Gothenburg Sweden
| | - Richard Vithal
- Department of Anaesthesiology and Intensive Care Institute of Clinical Science Sahlgrenska Academy University of Gothenburg Gothenburg Sweden
- Department of Anaesthesia and Intensive Care Region Västra Götaland Sahlgrenska University Hospital Gothenburg Sweden
| | - Ali El‐Merhi
- Department of Anaesthesiology and Intensive Care Institute of Clinical Science Sahlgrenska Academy University of Gothenburg Gothenburg Sweden
- Department of Anaesthesia and Intensive Care Region Västra Götaland Sahlgrenska University Hospital Gothenburg Sweden
| | - Silvana Naredi
- Department of Anaesthesiology and Intensive Care Institute of Clinical Science Sahlgrenska Academy University of Gothenburg Gothenburg Sweden
- Department of Anaesthesia and Intensive Care Region Västra Götaland Sahlgrenska University Hospital Gothenburg Sweden
| | - Miroslaw Staron
- Department of Computer Science and Engineering IT Faculty Chalmers University of Gothenburg Gothenburg Sweden
| | - Linda Block
- Department of Anaesthesiology and Intensive Care Institute of Clinical Science Sahlgrenska Academy University of Gothenburg Gothenburg Sweden
- Department of Anaesthesia and Intensive Care Region Västra Götaland Sahlgrenska University Hospital Gothenburg Sweden
| |
Collapse
|
13
|
Gallifant J, Zhang J, Del Pilar Arias Lopez M, Zhu T, Camporota L, Celi LA, Formenti F. Artificial intelligence for mechanical ventilation: systematic review of design, reporting standards, and bias. Br J Anaesth 2022; 128:343-351. [PMID: 34772497 PMCID: PMC8792831 DOI: 10.1016/j.bja.2021.09.025] [Citation(s) in RCA: 25] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Revised: 09/09/2021] [Accepted: 09/27/2021] [Indexed: 02/03/2023] Open
Abstract
BACKGROUND Artificial intelligence (AI) has the potential to personalise mechanical ventilation strategies for patients with respiratory failure. However, current methodological deficiencies could limit clinical impact. We identified common limitations and propose potential solutions to facilitate translation of AI to mechanical ventilation of patients. METHODS A systematic review was conducted in MEDLINE, Embase, and PubMed Central to February 2021. Studies investigating the application of AI to patients undergoing mechanical ventilation were included. Algorithm design and adherence to reporting standards were assessed with a rubric combining published guidelines, satisfying the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis [TRIPOD] statement. Risk of bias was assessed by using the Prediction model Risk Of Bias ASsessment Tool (PROBAST), and correspondence with authors to assess data and code availability. RESULTS Our search identified 1,342 studies, of which 95 were included: 84 had single-centre, retrospective study design, with only one randomised controlled trial. Access to data sets and code was severely limited (unavailable in 85% and 87% of studies, respectively). On request, data and code were made available from 12 and 10 authors, respectively, from a list of 54 studies published in the last 5 yr. Ethnicity was frequently under-reported 18/95 (19%), as was model calibration 17/95 (18%). The risk of bias was high in 89% (85/95) of the studies, especially because of analysis bias. CONCLUSIONS Development of algorithms should involve prospective and external validation, with greater code and data availability to improve confidence in and translation of this promising approach. TRIAL REGISTRATION NUMBER PROSPERO - CRD42021225918.
Collapse
Affiliation(s)
- Jack Gallifant
- Centre for Human and Applied Physiological Sciences, School of Basic and Medical Biosciences, King's College London, London, UK.
| | - Joe Zhang
- Department of Adult Critical Care, Guy's and St Thomas' NHS Foundation Trust, King's Health Partners, London, UK; Institute of Global Health Innovation, Imperial College London, London, UK
| | | | - Tingting Zhu
- Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK
| | - Luigi Camporota
- Centre for Human and Applied Physiological Sciences, School of Basic and Medical Biosciences, King's College London, London, UK; Department of Adult Critical Care, Guy's and St Thomas' NHS Foundation Trust, King's Health Partners, London, UK
| | - Leo A Celi
- Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA, USA; Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA; Department of Biostatistics, Harvard T.H. Chan School of Public Health, Harvard University, Boston, MA, USA.
| | - Federico Formenti
- Centre for Human and Applied Physiological Sciences, School of Basic and Medical Biosciences, King's College London, London, UK; Nuffield Division of Anaesthetics, University of Oxford, Oxford, UK; Department of Biomechanics, University of Nebraska Omaha, Omaha, NE, USA
| |
Collapse
|
14
|
Naseri Jahfari A, Tax D, Reinders M, van der Bilt I. Machine Learning for Cardiovascular Outcomes From Wearable Data: Systematic Review From a Technology Readiness Level Point of View. JMIR Med Inform 2022; 10:e29434. [PMID: 35044316 PMCID: PMC8811688 DOI: 10.2196/29434] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2021] [Revised: 11/22/2021] [Accepted: 12/04/2021] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Wearable technology has the potential to improve cardiovascular health monitoring by using machine learning. Such technology enables remote health monitoring and allows for the diagnosis and prevention of cardiovascular diseases. In addition to the detection of cardiovascular disease, it can exclude this diagnosis in symptomatic patients, thereby preventing unnecessary hospital visits. In addition, early warning systems can aid cardiologists in timely treatment and prevention. OBJECTIVE This study aims to systematically assess the literature on detecting and predicting outcomes of patients with cardiovascular diseases by using machine learning with data obtained from wearables to gain insights into the current state, challenges, and limitations of this technology. METHODS We searched PubMed, Scopus, and IEEE Xplore on September 26, 2020, with no restrictions on the publication date and by using keywords such as "wearables," "machine learning," and "cardiovascular disease." Methodologies were categorized and analyzed according to machine learning-based technology readiness levels (TRLs), which score studies on their potential to be deployed in an operational setting from 1 to 9 (most ready). RESULTS After the removal of duplicates, application of exclusion criteria, and full-text screening, 55 eligible studies were included in the analysis, covering a variety of cardiovascular diseases. We assessed the quality of the included studies and found that none of the studies were integrated into a health care system (TRL<6), prospective phase 2 and phase 3 trials were absent (TRL<7 and 8), and group cross-validation was rarely used. These issues limited these studies' ability to demonstrate the effectiveness of their methodologies. Furthermore, there seemed to be no agreement on the sample size needed to train these studies' models, the size of the observation window used to make predictions, how long participants should be observed, and the type of machine learning model that is suitable for predicting cardiovascular outcomes. CONCLUSIONS Although current studies show the potential of wearables to monitor cardiovascular events, their deployment as a diagnostic or prognostic cardiovascular clinical tool is hampered by the lack of a realistic data set and proper systematic and prospective evaluation.
Collapse
Affiliation(s)
- Arman Naseri Jahfari
- Pattern Recognition and Bioinformatics, Delft University of Technology, Delft, Netherlands
- Department of Cardiology, Haga Teaching Hospital, The Hague, Netherlands
| | - David Tax
- Pattern Recognition and Bioinformatics, Delft University of Technology, Delft, Netherlands
| | - Marcel Reinders
- Pattern Recognition and Bioinformatics, Delft University of Technology, Delft, Netherlands
| | - Ivo van der Bilt
- Department of Cardiology, Haga Teaching Hospital, The Hague, Netherlands
| |
Collapse
|
15
|
Diaz-Soto JC, Couture EJ, Nabzdyk CG. Quo Vadis CASUS? From predicting to impacting outcomes in cardiac surgery. J Cardiothorac Vasc Anesth 2022; 36:995-997. [DOI: 10.1053/j.jvca.2022.01.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/05/2022] [Accepted: 01/07/2022] [Indexed: 11/11/2022]
|
16
|
AIM in Anesthesiology. Artif Intell Med 2022. [DOI: 10.1007/978-3-030-64573-1_246] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
17
|
Ehrmann D, Harish V, Morgado F, Rosella L, Johnson A, Mema B, Mazwi M. Ignorance Isn't Bliss: We Must Close the Machine Learning Knowledge Gap in Pediatric Critical Care. Front Pediatr 2022; 10:864755. [PMID: 35620143 PMCID: PMC9127438 DOI: 10.3389/fped.2022.864755] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Accepted: 04/18/2022] [Indexed: 12/02/2022] Open
Abstract
Pediatric intensivists are bombarded with more patient data than ever before. Integration and interpretation of data from patient monitors and the electronic health record (EHR) can be cognitively expensive in a manner that results in delayed or suboptimal medical decision making and patient harm. Machine learning (ML) can be used to facilitate insights from healthcare data and has been successfully applied to pediatric critical care data with that intent. However, many pediatric critical care medicine (PCCM) trainees and clinicians lack an understanding of foundational ML principles. This presents a major problem for the field. We outline the reasons why in this perspective and provide a roadmap for competency-based ML education for PCCM trainees and other stakeholders.
Collapse
Affiliation(s)
- Daniel Ehrmann
- Department of Critical Care Medicine, Hospital for Sick Children, Toronto, ON, Canada.,Temerty Centre for Artificial Intelligence Research and Education in Medicine, University of Toronto, Toronto, ON, Canada
| | - Vinyas Harish
- Temerty Centre for Artificial Intelligence Research and Education in Medicine, University of Toronto, Toronto, ON, Canada.,MD/PhD Program, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada.,Institute for Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada
| | - Felipe Morgado
- Temerty Centre for Artificial Intelligence Research and Education in Medicine, University of Toronto, Toronto, ON, Canada.,MD/PhD Program, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada.,Department of Medical Biophysics, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada
| | - Laura Rosella
- MD/PhD Program, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada.,Institute for Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada
| | - Alistair Johnson
- MD/PhD Program, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada.,Program in Child Health Evaluative Sciences, The Hospital for Sick Children, Toronto, ON, Canada
| | - Briseida Mema
- Department of Critical Care Medicine, Hospital for Sick Children, Toronto, ON, Canada
| | - Mjaye Mazwi
- Department of Critical Care Medicine, Hospital for Sick Children, Toronto, ON, Canada.,MD/PhD Program, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada
| |
Collapse
|
18
|
Predicting 30-day readmissions in patients with heart failure using administrative data: a machine learning approach. J Card Fail 2021; 28:710-722. [PMID: 34936894 DOI: 10.1016/j.cardfail.2021.12.004] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2021] [Revised: 12/02/2021] [Accepted: 12/09/2021] [Indexed: 12/23/2022]
Abstract
AIMS To develop machine-learning (ML) models trained on administrative data which predict risk of readmission in heart failure (HF) patients; evaluate and compare the ML model with the currently used LaCE score using clinically informative metrics. METHODS AND RESULTS This prognostic study was conducted in Alberta, Canada on 9,845 patients with confirmed HF admitted to hospital between 2012-2019. The outcome was unplanned all-cause hospital readmission within 30-days of discharge. 80% of the data was used for ML model development and 20% for independent validation. We reported, using the validation set, c-statistics (AUROCs)and performance metrics (likelihood ratio [LR], positive predictive values [PPV]) for the XGBoost model and a modified LaCE score within their respective predictive thresholds. Boosted tree-based classifiers had higher AUROCs (0.65 for XGBoost) compared to others (0.58 for Neural Network) and 0.57 for the modified LaCE. Within the predicted threshold range of the XGBoost classifier, the positive LR was 1.00 at the low end of predicted risk and 6.12 at the high end, resulting in a PPV (post-test probability) range of 21-62%; the pre-test probability of readmission was 20.9% using prevalence. The corresponding positive LRs and PPVs across LaCE score thresholds were 1.00-1.20 and 21-24%, respectively. CONCLUSION Despite predicting readmissions better than the LaCE, even the best ML model trained on administrative health data (XGBoost) did not provide substantially informative prediction performance as it only generated a moderate shift from pre to post-test probability. Health systems wishing to deploy such a tool should consider training ML models with additional data. Adding other techniques like Natural Language Processing, along with ML, to use other clinical information (like chart notes) might improve prediction performance.
Collapse
|
19
|
Brossard C, Lemasson B, Attyé A, de Busschère JA, Payen JF, Barbier EL, Grèze J, Bouzat P. Contribution of CT-Scan Analysis by Artificial Intelligence to the Clinical Care of TBI Patients. Front Neurol 2021; 12:666875. [PMID: 34177773 PMCID: PMC8222716 DOI: 10.3389/fneur.2021.666875] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2021] [Accepted: 04/15/2021] [Indexed: 01/29/2023] Open
Abstract
The gold standard to diagnose intracerebral lesions after traumatic brain injury (TBI) is computed tomography (CT) scan, and due to its accessibility and improved quality of images, the global burden of CT scan for TBI patients is increasing. The recent developments of automated determination of traumatic brain lesions and medical-decision process using artificial intelligence (AI) represent opportunities to help clinicians in screening more patients, identifying the nature and volume of lesions and estimating the patient outcome. This short review will summarize what is ongoing with the use of AI and CT scan for patients with TBI.
Collapse
Affiliation(s)
| | - Benjamin Lemasson
- Université Grenoble Alpes, Inserm, CHU Grenoble Alpes, U1216, Grenoble Institut Neurosciences, Grenoble, France
| | | | | | | | | | | | | |
Collapse
|
20
|
Barchitta M, Maugeri A, Favara G, Riela PM, Gallo G, Mura I, Agodi A. A machine learning approach to predict healthcare-associated infections at intensive care unit admission: findings from the SPIN-UTI project. J Hosp Infect 2021; 112:77-86. [PMID: 33676936 DOI: 10.1016/j.jhin.2021.02.025] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2020] [Revised: 01/27/2021] [Accepted: 02/26/2021] [Indexed: 12/13/2022]
Abstract
BACKGROUND Identifying patients at higher risk of healthcare-associated infections (HAIs) in intensive care units (ICUs) represents a major challenge for public health. Machine learning could improve patient risk stratification and lead to targeted infection prevention and control interventions. AIM To evaluate the performance of the Simplified Acute Physiology Score (SAPS) II for HAI risk prediction in ICUs, using both traditional statistical and machine learning approaches. METHODS Data for 7827 patients from the 'Italian Nosocomial Infections Surveillance in Intensive Care Units' project were used in this study. The Support Vector Machines (SVM) algorithm was applied to classify patients according to sex, patient origin, non-surgical treatment for acute coronary disease, surgical intervention, SAPS II at admission, presence of invasive devices, trauma, impaired immunity, and antibiotic therapy in 48 h preceding ICU admission. FINDINGS The performance of SAPS II for predicting HAI risk provides a receiver operating characteristic curve with an area under the curve of 0.612 (P<0.001) and accuracy of 56%. Considering SAPS II along with other characteristics at ICU admission, the SVM classifier was found to have accuracy of 88% and an AUC of 0.90 (P<0.001) for the test set. The predictive ability was lower when considering the same SVM model but with the SAPS II variable removed (accuracy 78%, AUC 0.66). CONCLUSIONS This study suggested that the SVM model is a useful tool for early prediction of patients at higher risk of HAIs at ICU admission.
Collapse
Affiliation(s)
- M Barchitta
- Department of Medical and Surgical Sciences and Advanced Technologies 'GF Ingrassia', University of Catania, Catania, Italy; GISIO-SItI (Italian Study Group of Hospital Hygiene), Italian Society of Hygiene, Preventive Medicine and Public Health, Italy
| | - A Maugeri
- Department of Medical and Surgical Sciences and Advanced Technologies 'GF Ingrassia', University of Catania, Catania, Italy; GISIO-SItI (Italian Study Group of Hospital Hygiene), Italian Society of Hygiene, Preventive Medicine and Public Health, Italy
| | - G Favara
- Department of Medical and Surgical Sciences and Advanced Technologies 'GF Ingrassia', University of Catania, Catania, Italy
| | - P M Riela
- Department of Mathematics and Informatics, University of Catania, Catania, Italy
| | - G Gallo
- Department of Mathematics and Informatics, University of Catania, Catania, Italy
| | - I Mura
- GISIO-SItI (Italian Study Group of Hospital Hygiene), Italian Society of Hygiene, Preventive Medicine and Public Health, Italy; Department of Biomedical Sciences, University of Sassari, Sassari, Italy
| | - A Agodi
- Department of Medical and Surgical Sciences and Advanced Technologies 'GF Ingrassia', University of Catania, Catania, Italy; GISIO-SItI (Italian Study Group of Hospital Hygiene), Italian Society of Hygiene, Preventive Medicine and Public Health, Italy.
| | | |
Collapse
|
21
|
Barchitta M, Maugeri A, Favara G, Riela PM, Gallo G, Mura I, Agodi A. Early Prediction of Seven-Day Mortality in Intensive Care Unit Using a Machine Learning Model: Results from the SPIN-UTI Project. J Clin Med 2021; 10:992. [PMID: 33801207 PMCID: PMC7957866 DOI: 10.3390/jcm10050992] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2020] [Revised: 02/09/2021] [Accepted: 02/12/2021] [Indexed: 12/18/2022] Open
Abstract
Patients in intensive care units (ICUs) were at higher risk of worsen prognosis and mortality. Here, we aimed to evaluate the ability of the Simplified Acute Physiology Score (SAPS II) to predict the risk of 7-day mortality, and to test a machine learning algorithm which combines the SAPS II with additional patients' characteristics at ICU admission. We used data from the "Italian Nosocomial Infections Surveillance in Intensive Care Units" network. Support Vector Machines (SVM) algorithm was used to classify 3782 patients according to sex, patient's origin, type of ICU admission, non-surgical treatment for acute coronary disease, surgical intervention, SAPS II, presence of invasive devices, trauma, impaired immunity, antibiotic therapy and onset of HAI. The accuracy of SAPS II for predicting patients who died from those who did not was 69.3%, with an Area Under the Curve (AUC) of 0.678. Using the SVM algorithm, instead, we achieved an accuracy of 83.5% and AUC of 0.896. Notably, SAPS II was the variable that weighted more on the model and its removal resulted in an AUC of 0.653 and an accuracy of 68.4%. Overall, these findings suggest the present SVM model as a useful tool to early predict patients at higher risk of death at ICU admission.
Collapse
Affiliation(s)
- Martina Barchitta
- Department of Medical and Surgical Sciences and Advanced Technologies “GF Ingrassia”, University of Catania, 95123 Catania, Italy; (M.B.); (A.M.); (G.F.)
- GISIO-SItI—Italian Study Group of Hospital Hygiene—Italian Society of Hygiene, Preventive Medicine and Public Health, 00144 Roma, Italy;
| | - Andrea Maugeri
- Department of Medical and Surgical Sciences and Advanced Technologies “GF Ingrassia”, University of Catania, 95123 Catania, Italy; (M.B.); (A.M.); (G.F.)
- GISIO-SItI—Italian Study Group of Hospital Hygiene—Italian Society of Hygiene, Preventive Medicine and Public Health, 00144 Roma, Italy;
| | - Giuliana Favara
- Department of Medical and Surgical Sciences and Advanced Technologies “GF Ingrassia”, University of Catania, 95123 Catania, Italy; (M.B.); (A.M.); (G.F.)
| | - Paolo Marco Riela
- Department of Mathematics and Informatics, University of Catania, 95123 Catania, Italy; (P.M.R.); (G.G.)
| | - Giovanni Gallo
- Department of Mathematics and Informatics, University of Catania, 95123 Catania, Italy; (P.M.R.); (G.G.)
| | - Ida Mura
- GISIO-SItI—Italian Study Group of Hospital Hygiene—Italian Society of Hygiene, Preventive Medicine and Public Health, 00144 Roma, Italy;
- Department of Biomedical Sciences, University of Sassari, 07100 Sassari, Italy
| | - Antonella Agodi
- Department of Medical and Surgical Sciences and Advanced Technologies “GF Ingrassia”, University of Catania, 95123 Catania, Italy; (M.B.); (A.M.); (G.F.)
- GISIO-SItI—Italian Study Group of Hospital Hygiene—Italian Society of Hygiene, Preventive Medicine and Public Health, 00144 Roma, Italy;
| | | |
Collapse
|
22
|
Wulff A, Montag S, Rübsamen N, Dziuba F, Marschollek M, Beerbaum P, Karch A, Jack T. Clinical evaluation of an interoperable clinical decision-support system for the detection of systemic inflammatory response syndrome in critically ill children. BMC Med Inform Decis Mak 2021; 21:62. [PMID: 33602206 PMCID: PMC7889709 DOI: 10.1186/s12911-021-01428-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2020] [Accepted: 02/03/2021] [Indexed: 11/11/2022] Open
Abstract
Background Systemic inflammatory response syndrome (SIRS) is defined as a non-specific inflammatory process in the absence of infection. SIRS increases susceptibility for organ dysfunction, and frequently affects the clinical outcome of affected patients. We evaluated a knowledge-based, interoperable clinical decision-support system (CDSS) for SIRS detection on a pediatric intensive care unit (PICU). Methods The CDSS developed retrieves routine data, previously transformed into an interoperable format, by using model-based queries and guideline- and knowledge-based rules. We evaluated the CDSS in a prospective diagnostic study from 08/2018–03/2019. 168 patients from a pediatric intensive care unit of a tertiary university hospital, aged 0 to 18 years, were assessed for SIRS by the CDSS and by physicians during clinical routine. Sensitivity and specificity (when compared to the reference standard) with 95% Wald confidence intervals (CI) were estimated on the level of patients and patient-days. Results Sensitivity and specificity was 91.7% (95% CI 85.5–95.4%) and 54.1% (95% CI 45.4–62.5%) on patient level, and 97.5% (95% CI 95.1–98.7%) and 91.5% (95% CI 89.3–93.3%) on the level of patient-days. Physicians’ SIRS recognition during clinical routine was considerably less accurate (sensitivity of 62.0% (95% CI 56.8–66.9%)/specificity of 83.3% (95% CI 80.4–85.9%)) when measurd on the level of patient-days. Evaluation revealed valuable insights for the general design of the CDSS as well as specific rule modifications. Despite a lower than expected specificity, diagnostic accuracy was higher than the one in daily routine ratings, thus, demonstrating high potentials of using our CDSS to help to detect SIRS in clinical routine. Conclusions We successfully evaluated an interoperable CDSS for SIRS detection in PICU. Our study demonstrated the general feasibility and potentials of the implemented algorithms but also some limitations. In the next step, the CDSS will be optimized to overcome these limitations and will be evaluated in a multi-center study. Trial registration: NCT03661450 (ClinicalTrials.gov); registered September 7, 2018. Supplementary Information The online version contains supplementary material available at 10.1186/s12911-021-01428-7.
Collapse
Affiliation(s)
- Antje Wulff
- Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Karl-Wiechert-Allee 3, 30625, Hannover, Germany.
| | - Sara Montag
- Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Karl-Wiechert-Allee 3, 30625, Hannover, Germany.
| | - Nicole Rübsamen
- Institute of Epidemiology and Social Medicine, University of Muenster, Domagkstr. 3, 48149, Muenster, Germany
| | - Friederike Dziuba
- Department of Pediatric Cardiology and Intensive Care Medicine, Hannover Medical School, Carl-Neuberg-Str. 1, 30625, Hannover, Germany
| | - Michael Marschollek
- Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Karl-Wiechert-Allee 3, 30625, Hannover, Germany
| | - Philipp Beerbaum
- Department of Pediatric Cardiology and Intensive Care Medicine, Hannover Medical School, Carl-Neuberg-Str. 1, 30625, Hannover, Germany
| | - André Karch
- Institute of Epidemiology and Social Medicine, University of Muenster, Domagkstr. 3, 48149, Muenster, Germany
| | - Thomas Jack
- Department of Pediatric Cardiology and Intensive Care Medicine, Hannover Medical School, Carl-Neuberg-Str. 1, 30625, Hannover, Germany
| |
Collapse
|
23
|
Komorowski M, Joosten A. AIM in Anesthesiology. Artif Intell Med 2021. [DOI: 10.1007/978-3-030-58080-3_246-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
24
|
Soussi S, Collins GS, Jüni P, Mebazaa A, Gayat E, Le Manach Y. Evaluation of Biomarkers in Critical Care and Perioperative Medicine: A Clinician’s Overview of Traditional Statistical Methods and Machine Learning Algorithms. Anesthesiology 2021; 134:15-25. [PMID: 33216849 DOI: 10.1097/aln.0000000000003600] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022]
Abstract
Interest in developing and using novel biomarkers in critical care and perioperative medicine is increasing. Biomarkers studies are often presented with flaws in the statistical analysis that preclude them from providing a scientifically valid and clinically relevant message for clinicians. To improve scientific rigor, the proper application and reporting of traditional and emerging statistical methods (e.g., machine learning) of biomarker studies is required. This Readers' Toolbox article aims to be a starting point to nonexpert readers and investigators to understand traditional and emerging research methods to assess biomarkers in critical care and perioperative medicine.
Collapse
|
25
|
Transatlantic transferability of a new reinforcement learning model for optimizing haemodynamic treatment for critically ill patients with sepsis. Artif Intell Med 2020; 112:102003. [PMID: 33581824 DOI: 10.1016/j.artmed.2020.102003] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2020] [Revised: 11/16/2020] [Accepted: 12/08/2020] [Indexed: 11/23/2022]
Abstract
INTRODUCTION In recent years, reinforcement learning (RL) has gained traction in the healthcare domain. In particular, RL methods have been explored for haemodynamic optimization of septic patients in the Intensive Care Unit. Most hospitals however, lack the data and expertise for model development, necessitating transfer of models developed using external datasets. This approach assumes model generalizability across different patient populations, the validity of which has not previously been tested. In addition, there is limited knowledge on safety and reliability. These challenges need to be addressed to further facilitate implementation of RL models in clinical practice. METHOD We developed and validated a new reinforcement learning model for hemodynamic optimization in sepsis on the MIMIC intensive care database from the USA using a dueling double deep Q network. We then transferred this model to the European AmsterdamUMCdb intensive care database. T-Distributed Stochastic Neighbor Embedding and Sequential Organ Failure Assessment scores were used to explore the differences between the patient populations. We apply off-policy policy evaluation methods to quantify model performance. In addition, we introduce and apply a novel deep policy inspection to analyse how the optimal policy relates to the different phases of sepsis and sepsis treatment to provide interpretable insight in order to assess model safety and reliability. RESULTS The off-policy evaluation revealed that the optimal policy outperformed the physician policy on both datasets despite marked differences between the two patient populations and physician's policies. Our novel deep policy inspection method showed insightful results and unveiled that the model could initiate therapy adequately and adjust therapy intensity to illness severity and disease progression which indicated safe and reliable model behaviour. Compared to current physician behavior, the developed policy prefers a more liberal use of vasopressors with a more restrained use of fluid therapy in line with previous work. CONCLUSION We created a reinforcement learning model for optimal bedside hemodynamic management and demonstrated model transferability between populations from the USA and Europe for the first time. We proposed new methods for deep policy inspection integrating expert domain knowledge. This is expected to facilitate progression to bedside clinical decision support for the treatment of critically ill patients.
Collapse
|
26
|
Dupuis C, Timsit JF. Antibiotics in the first hour: is there new evidence? Expert Rev Anti Infect Ther 2020; 19:45-54. [PMID: 32799580 DOI: 10.1080/14787210.2020.1810567] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
Abstract
INTRODUCTION International guidelines have recommended for many years to start antimicrobials as early as possible in sepsis and shock. This concept has been challenged by the controversial results of experimental studies and clinical cohorts and resulted in intense debate in the literature. This review aims to summarize the available knowledge on early antimicrobial therapy and to consider perspectives. AREAS COVERED First, after a research using MEDLINE, we reviewed the studies that advocated the implementation of early antimicrobial therapy. We then discussed the drawbacks of these studies. Finally, we suggested possible explanations of the benefit and then absence of the prognostic impact of early antimicrobial therapy i.e. confounding factors, irreversibility of the inflammatory process, non-control of the source of the infection, pharmacodynamic considerations and the harmful effect of antimicrobial drugs. EXPERT OPINION Sepsis is very heterogeneous. The first antimicrobial therapy should be personalized. The sickest patients should be given early antimicrobial therapy, whereas a 'watch and wait process' should be preferred for less severe patients, to allow confirmation of sepsis, identification of pathogens and administration of adequate antimicrobial therapy. We propose steps to personalize the first antimicrobial therapy. New early diagnostic tools will assist the physicians in the future.
Collapse
Affiliation(s)
- Claire Dupuis
- Medical Intensive Care Unit, Gabriel Montpied University Hospital , Clermont-Ferrand, France.,Umr 1137, Iame Université De Paris , Paris, France.,APHP, Medical and Infectious Diseases ICU (MI2), Bichat Claude Bernard Hospital , Paris, France
| | - Jean-Francois Timsit
- Umr 1137, Iame Université De Paris , Paris, France.,APHP, Medical and Infectious Diseases ICU (MI2), Bichat Claude Bernard Hospital , Paris, France
| |
Collapse
|
27
|
Mamdani M, Slutsky AS. Artificial intelligence in intensive care medicine. Intensive Care Med 2020; 47:147-149. [PMID: 32767073 DOI: 10.1007/s00134-020-06203-2] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2020] [Accepted: 07/24/2020] [Indexed: 11/28/2022]
Affiliation(s)
- Muhammad Mamdani
- Unity Health Toronto, Li Ka Shing Knowledge Institute, St. Michael's Hospital, 30 Bond Street, Toronto, ON, M5B 1W8, Canada. .,Faculty of Medicine, University of Toronto, Toronto, Canada. .,Leslie Dan Faculty of Pharmacy, University of Toronto, Toronto, Canada.
| | - Arthur S Slutsky
- Keenan Research Center for Biological Science, Li Ka Shing Knowledge Institute, St. Michael's Hospital, Unity Health Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada. .,Interdepartmental Division of Critical Care Medicine, University of Toronto, Toronto, Canada.
| |
Collapse
|
28
|
Poncette AS, Mosch L, Spies C, Schmieding M, Schiefenhövel F, Krampe H, Balzer F. Improvements in Patient Monitoring in the Intensive Care Unit: Survey Study. J Med Internet Res 2020; 22:e19091. [PMID: 32459655 PMCID: PMC7307326 DOI: 10.2196/19091] [Citation(s) in RCA: 43] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2020] [Revised: 05/05/2020] [Accepted: 05/13/2020] [Indexed: 01/12/2023] Open
Abstract
BACKGROUND Due to demographic change and, more recently, coronavirus disease (COVID-19), the importance of modern intensive care units (ICU) is becoming apparent. One of the key components of an ICU is the continuous monitoring of patients' vital parameters. However, existing advances in informatics, signal processing, or engineering that could alleviate the burden on ICUs have not yet been applied. This could be due to the lack of user involvement in research and development. OBJECTIVE This study focused on the satisfaction of ICU staff with current patient monitoring and their suggestions for future improvements. We aimed to identify aspects of monitoring that interrupt patient care, display devices for remote monitoring, use cases for artificial intelligence (AI), and whether ICU staff members are willing to improve their digital literacy or contribute to the improvement of patient monitoring. We further aimed to identify differences in the responses of different professional groups. METHODS This survey study was performed with ICU staff from 4 ICUs of a German university hospital between November 2019 and January 2020. We developed a web-based 36-item survey questionnaire, by analyzing a preceding qualitative interview study with ICU staff, about the clinical requirements of future patient monitoring. Statistical analyses of questionnaire results included median values with their bootstrapped 95% confidence intervals, and chi-square tests to compare the distributions of item responses of the professional groups. RESULTS In total, 86 of the 270 ICU physicians and nurses completed the survey questionnaire. The majority stated they felt confident using the patient monitoring equipment, but that high rates of false-positive alarms and the many sensor cables interrupted patient care. Regarding future improvements, respondents asked for wireless sensors, a reduction in the number of false-positive alarms, and hospital standard operating procedures for alarm management. Responses to the display devices proposed for remote patient monitoring were divided. Most respondents indicated it would be useful for earlier alerting or when they were responsible for multiple wards. AI for ICUs would be useful for early detection of complications and an increased risk of mortality; in addition, the AI could propose guidelines for therapy and diagnostics. Transparency, interoperability, usability, and staff training were essential to promote the use of AI. The majority wanted to learn more about new technologies for the ICU and required more time for learning. Physicians had fewer reservations than nurses about AI-based intelligent alarm management and using mobile phones for remote monitoring. CONCLUSIONS This survey study of ICU staff revealed key improvements for patient monitoring in intensive care medicine. Hospital providers and medical device manufacturers should focus on reducing false alarms, implementing hospital alarm standard operating procedures, introducing wireless sensors, preparing for the use of AI, and enhancing the digital literacy of ICU staff. Our results may contribute to the user-centered transfer of digital technologies into practice to alleviate challenges in intensive care medicine. TRIAL REGISTRATION ClinicalTrials.gov NCT03514173; https://clinicaltrials.gov/ct2/show/NCT03514173.
Collapse
Affiliation(s)
- Akira-Sebastian Poncette
- Department of Anesthesiology and Intensive Care Medicine, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany.,Einstein Center Digital Future, Berlin, Germany
| | - Lina Mosch
- Department of Anesthesiology and Intensive Care Medicine, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany
| | - Claudia Spies
- Department of Anesthesiology and Intensive Care Medicine, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany
| | - Malte Schmieding
- Department of Anesthesiology and Intensive Care Medicine, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany.,Einstein Center Digital Future, Berlin, Germany
| | - Fridtjof Schiefenhövel
- Department of Anesthesiology and Intensive Care Medicine, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany.,Einstein Center Digital Future, Berlin, Germany
| | - Henning Krampe
- Department of Anesthesiology and Intensive Care Medicine, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany
| | - Felix Balzer
- Department of Anesthesiology and Intensive Care Medicine, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany.,Einstein Center Digital Future, Berlin, Germany
| |
Collapse
|
29
|
Goodwin AJ, Eytan D, Greer RW, Mazwi M, Thommandram A, Goodfellow SD, Assadi A, Jegatheeswaran A, Laussen PC. A practical approach to storage and retrieval of high-frequency physiological signals. Physiol Meas 2020; 41:035008. [PMID: 32131060 DOI: 10.1088/1361-6579/ab7cb5] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2023]
Abstract
OBJECTIVE Storage of physiological waveform data for retrospective analysis presents significant challenges. Resultant data can be very large, and therefore becomes expensive to store and complicated to manage. Traditional database approaches are not appropriate for large scale storage of physiological waveforms. Our goal was to apply modern time series compression and indexing techniques to the problem of physiological waveform storage and retrieval. APPROACH We deployed a vendor-agnostic data collection system and developed domain-specific compression approaches that allowed long term storage of physiological waveform data and other associated clinical and medical device data. The database (called AtriumDB) also facilitates rapid retrieval of retrospective data for high-performance computing and machine learning applications. MAIN RESULTS A prototype system has been recording data in a 42-bed pediatric critical care unit at The Hospital for Sick Children in Toronto, Ontario since February 2016. As of December 2019, the database contains over 720,000 patient-hours of data collected from over 5300 patients, all with complete waveform capture. One year of full resolution physiological waveform storage from this 42-bed unit can be losslessly compressed and stored in less than 300 GB of disk space. Retrospective data can be delivered to analytical applications at a rate of up to 50 million time-value pairs per second. SIGNIFICANCE Stored data are not pre-processed or filtered. Having access to a large retrospective dataset with realistic artefacts lends itself to the process of anomaly discovery and understanding. Retrospective data can be replayed to simulate a realistic streaming data environment where analytical tools can be rapidly tested at scale.
Collapse
Affiliation(s)
- Andrew J Goodwin
- Department of Critical Care Medicine, The Hospital for Sick Children, Toronto, Ontario, Canada. School of Biomedical Engineering, University of Sydney, Sydney, New South Wales, Australia
| | | | | | | | | | | | | | | | | |
Collapse
|
30
|
Clinical management of sepsis can be improved by artificial intelligence: no. Intensive Care Med 2020; 46:378-380. [PMID: 32016531 DOI: 10.1007/s00134-020-05947-1] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2019] [Accepted: 01/22/2020] [Indexed: 12/11/2022]
|
31
|
Early diagnosis of bloodstream infections in the intensive care unit using machine-learning algorithms. Intensive Care Med 2020; 46:454-462. [PMID: 31912208 DOI: 10.1007/s00134-019-05876-8] [Citation(s) in RCA: 33] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2019] [Accepted: 11/17/2019] [Indexed: 02/06/2023]
Abstract
PURPOSE We aimed to develop a machine-learning (ML) algorithm that can predict intensive care unit (ICU)-acquired bloodstream infections (BSI) among patients suspected of infection in the ICU. METHODS The study was based on patients' electronic health records at Beth Israel Deaconess Medical Center (BIDMC) in Boston, Massachusetts, USA, and at Rambam Health Care Campus (RHCC), Haifa, Israel. We included adults from whom blood cultures were collected for suspected BSI at least 48 h after admission. Clinical data, including time-series variables and their interactions, were analyzed by an ML algorithm at each site. Prediction ability for ICU-acquired BSI was assessed by the area under the receiver operating characteristics (AUROC) of ten-fold cross-validation and validation sets with 95% confidence intervals. RESULTS The datasets comprised 2351 patients from BIDMC (151 with BSI) and 1021 from RHCC (162 with BSI). The median (inter-quartile range) age was 62 (51-75) and 56 (38-69) years, respectively; the median Acute Physiology and Chronic Health Evaluation II scores were 26 (21-32) and 24 (20-29), respectively. The means of the cross-validation AUROCs were 0.87 ± 0.02 for BIDMC and 0.93 ± 0.03 for RHCC. AUROCs of 0.89 ± 0.01 and 0.92 ± 0.02 were maintained in both centers with internal validation, while external validation deteriorated. Valuable predictors were mainly the trends of time-series variables such as laboratory results and vital signs. CONCLUSION An ML approach that uses temporal and site-specific data achieved high performance in recognizing BC samples with a high probability for ICU-acquired BSI.
Collapse
|
32
|
Ethical considerations about artificial intelligence for prognostication in intensive care. Intensive Care Med Exp 2019; 7:70. [PMID: 31823128 PMCID: PMC6904702 DOI: 10.1186/s40635-019-0286-6] [Citation(s) in RCA: 39] [Impact Index Per Article: 7.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2019] [Accepted: 11/28/2019] [Indexed: 11/25/2022] Open
Abstract
Background Prognosticating the course of diseases to inform decision-making is a key component of intensive care medicine. For several applications in medicine, new methods from the field of artificial intelligence (AI) and machine learning have already outperformed conventional prediction models. Due to their technical characteristics, these methods will present new ethical challenges to the intensivist. Results In addition to the standards of data stewardship in medicine, the selection of datasets and algorithms to create AI prognostication models must involve extensive scrutiny to avoid biases and, consequently, injustice against individuals or groups of patients. Assessment of these models for compliance with the ethical principles of beneficence and non-maleficence should also include quantification of predictive uncertainty. Respect for patients’ autonomy during decision-making requires transparency of the data processing by AI models to explain the predictions derived from these models. Moreover, a system of continuous oversight can help to maintain public trust in this technology. Based on these considerations as well as recent guidelines, we propose a pathway to an ethical implementation of AI-based prognostication. It includes a checklist for new AI models that deals with medical and technical topics as well as patient- and system-centered issues. Conclusion AI models for prognostication will become valuable tools in intensive care. However, they require technical refinement and a careful implementation according to the standards of medical ethics.
Collapse
|