1
|
Pahud de Mortanges A, Luo H, Shu SZ, Kamath A, Suter Y, Shelan M, Pöllinger A, Reyes M. Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging. NPJ Digit Med 2024; 7:195. [PMID: 39039248 PMCID: PMC11263688 DOI: 10.1038/s41746-024-01190-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: 09/16/2023] [Accepted: 07/15/2024] [Indexed: 07/24/2024] Open
Abstract
Explainable artificial intelligence (XAI) has experienced a vast increase in recognition over the last few years. While the technical developments are manifold, less focus has been placed on the clinical applicability and usability of systems. Moreover, not much attention has been given to XAI systems that can handle multimodal and longitudinal data, which we postulate are important features in many clinical workflows. In this study, we review, from a clinical perspective, the current state of XAI for multimodal and longitudinal datasets and highlight the challenges thereof. Additionally, we propose the XAI orchestrator, an instance that aims to help clinicians with the synopsis of multimodal and longitudinal data, the resulting AI predictions, and the corresponding explainability output. We propose several desirable properties of the XAI orchestrator, such as being adaptive, hierarchical, interactive, and uncertainty-aware.
Collapse
Affiliation(s)
| | - Haozhe Luo
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland
| | - Shelley Zixin Shu
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland
| | - Amith Kamath
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland
| | - Yannick Suter
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland
- Department of Radiation Oncology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Mohamed Shelan
- Department of Radiation Oncology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Alexander Pöllinger
- Department of Diagnostic, Interventional and Pediatric Radiology, Inselspital, Bern University Hospital, Bern, Switzerland
| | - Mauricio Reyes
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland
- Department of Radiation Oncology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| |
Collapse
|
2
|
Wong DCW, Bonnici T, Gerry S, Birks J, Watkinson PJ. Effect of Digital Early Warning Scores on Hospital Vital Sign Observation Protocol Adherence: Stepped-Wedge Evaluation. J Med Internet Res 2024; 26:e46691. [PMID: 38900529 PMCID: PMC11224703 DOI: 10.2196/46691] [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: 02/21/2023] [Revised: 11/17/2023] [Accepted: 04/08/2024] [Indexed: 06/21/2024] Open
Abstract
BACKGROUND Early warning scores (EWS) are routinely used in hospitals to assess a patient's risk of deterioration. EWS are traditionally recorded on paper observation charts but are increasingly recorded digitally. In either case, evidence for the clinical effectiveness of such scores is mixed, and previous studies have not considered whether EWS leads to changes in how deteriorating patients are managed. OBJECTIVE This study aims to examine whether the introduction of a digital EWS system was associated with more frequent observation of patients with abnormal vital signs, a precursor to earlier clinical intervention. METHODS We conducted a 2-armed stepped-wedge study from February 2015 to December 2016, over 4 hospitals in 1 UK hospital trust. In the control arm, vital signs were recorded using paper observation charts. In the intervention arm, a digital EWS system was used. The primary outcome measure was time to next observation (TTNO), defined as the time between a patient's first elevated EWS (EWS ≥3) and subsequent observations set. Secondary outcomes were time to death in the hospital, length of stay, and time to unplanned intensive care unit admission. Differences between the 2 arms were analyzed using a mixed-effects Cox model. The usability of the system was assessed using the system usability score survey. RESULTS We included 12,802 admissions, 1084 in the paper (control) arm and 11,718 in the digital EWS (intervention) arm. The system usability score was 77.6, indicating good usability. The median TTNO in the control and intervention arms were 128 (IQR 73-218) minutes and 131 (IQR 73-223) minutes, respectively. The corresponding hazard ratio for TTNO was 0.99 (95% CI 0.91-1.07; P=.73). CONCLUSIONS We demonstrated strong clinical engagement with the system. We found no difference in any of the predefined patient outcomes, suggesting that the introduction of a highly usable electronic system can be achieved without impacting clinical care. Our findings contrast with previous claims that digital EWS systems are associated with improvement in clinical outcomes. Future research should investigate how digital EWS systems can be integrated with new clinical pathways adjusting staff behaviors to improve patient outcomes.
Collapse
Affiliation(s)
- David Chi-Wai Wong
- Leeds Institute of Health Sciences, School of Medicine, University of Leeds, Leeds, United Kingdom
| | - Timothy Bonnici
- Critical Care Division, University College Hospital London NHS Foundation Trust, London, United Kingdom
| | - Stephen Gerry
- Centre for Statistics in Medicine, University of Oxford, Oxford, United Kingdom
| | - Jacqueline Birks
- Centre for Statistics in Medicine, University of Oxford, Oxford, United Kingdom
| | - Peter J Watkinson
- Oxford University Hospitals NHS Trust, Oxford, United Kingdom
- NIHR Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, United Kingdom
- Nuffield Department of Clinical Neurosciences, Kadoorie Centre for Critical Care Research and Education, University of Oxford, Oxford, United Kingdom
| |
Collapse
|
3
|
De Backer D, Deutschman CS, Hellman J, Myatra SN, Ostermann M, Prescott HC, Talmor D, Antonelli M, Pontes Azevedo LC, Bauer SR, Kissoon N, Loeches IM, Nunnally M, Tissieres P, Vieillard-Baron A, Coopersmith CM. Surviving Sepsis Campaign Research Priorities 2023. Crit Care Med 2024; 52:268-296. [PMID: 38240508 DOI: 10.1097/ccm.0000000000006135] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/23/2024]
Abstract
OBJECTIVES To identify research priorities in the management, epidemiology, outcome, and pathophysiology of sepsis and septic shock. DESIGN Shortly after publication of the most recent Surviving Sepsis Campaign Guidelines, the Surviving Sepsis Research Committee, a multiprofessional group of 16 international experts representing the European Society of Intensive Care Medicine and the Society of Critical Care Medicine, convened virtually and iteratively developed the article and recommendations, which represents an update from the 2018 Surviving Sepsis Campaign Research Priorities. METHODS Each task force member submitted five research questions on any sepsis-related subject. Committee members then independently ranked their top three priorities from the list generated. The highest rated clinical and basic science questions were developed into the current article. RESULTS A total of 81 questions were submitted. After merging similar questions, there were 34 clinical and ten basic science research questions submitted for voting. The five top clinical priorities were as follows: 1) what is the best strategy for screening and identification of patients with sepsis, and can predictive modeling assist in real-time recognition of sepsis? 2) what causes organ injury and dysfunction in sepsis, how should it be defined, and how can it be detected? 3) how should fluid resuscitation be individualized initially and beyond? 4) what is the best vasopressor approach for treating the different phases of septic shock? and 5) can a personalized/precision medicine approach identify optimal therapies to improve patient outcomes? The five top basic science priorities were as follows: 1) How can we improve animal models so that they more closely resemble sepsis in humans? 2) What outcome variables maximize correlations between human sepsis and animal models and are therefore most appropriate to use in both? 3) How does sepsis affect the brain, and how do sepsis-induced brain alterations contribute to organ dysfunction? How does sepsis affect interactions between neural, endocrine, and immune systems? 4) How does the microbiome affect sepsis pathobiology? 5) How do genetics and epigenetics influence the development of sepsis, the course of sepsis and the response to treatments for sepsis? CONCLUSIONS Knowledge advances in multiple clinical domains have been incorporated in progressive iterations of the Surviving Sepsis Campaign guidelines, allowing for evidence-based recommendations for short- and long-term management of sepsis. However, the strength of existing evidence is modest with significant knowledge gaps and mortality from sepsis remains high. The priorities identified represent a roadmap for research in sepsis and septic shock.
Collapse
Affiliation(s)
- Daniel De Backer
- Department of Intensive Care, CHIREC Hospitals, Université Libre de Bruxelles, Brussels, Belgium
| | - Clifford S Deutschman
- Department of Pediatrics, Cohen Children's Medical Center, Northwell Health, New Hyde Park, NY
- Sepsis Research Lab, the Feinstein Institutes for Medical Research, Manhasset, NY
| | - Judith Hellman
- Department of Anesthesia and Perioperative Care, University of California, San Francisco, CA
| | - Sheila Nainan Myatra
- Department of Anaesthesiology, Critical Care and Pain, Tata Memorial Hospital, Homi Bhabha National Institute, Mumbai, India
| | - Marlies Ostermann
- Department of Critical Care, King's College London, Guy's & St Thomas' Hospital, London, United Kingdom
| | - Hallie C Prescott
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI
| | - Daniel Talmor
- Department of Anesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA
| | - Massimo Antonelli
- Department of Intensive Care, Emergency Medicine and Anesthesiology, Fondazione Policlinico Universitario A.Gemelli IRCCS, Rome, Italy
- Istituto di Anestesiologia e Rianimazione, Università Cattolica del Sacro Cuore, Rome, Italy
| | | | - Seth R Bauer
- Department of Pharmacy, Cleveland Clinic, Cleveland, OH
| | - Niranjan Kissoon
- Department of Pediatrics, University of British Columbia, Vancouver, BC, Canada
| | - Ignacio-Martin Loeches
- Department of Intensive Care Medicine, Multidisciplinary Intensive Care Research Organization (MICRO), St James's Hospital, Leinster, Dublin, Ireland
| | | | - Pierre Tissieres
- Pediatric Intensive Care, Neonatal Medicine and Pediatric Emergency, AP-HP Paris Saclay University, Bicêtre Hospital, Le Kremlin-Bicêtre, France
| | - Antoine Vieillard-Baron
- Service de Medecine Intensive Reanimation, Hopital Ambroise Pare, Universite Paris-Saclay, Le Kremlin-Bicêtre, France
| | | |
Collapse
|
4
|
Brann F, Sterling NW, Frisch SO, Schrager JD. Sepsis Prediction at Emergency Department Triage Using Natural Language Processing: Retrospective Cohort Study. JMIR AI 2024; 3:e49784. [PMID: 38875594 PMCID: PMC11041457 DOI: 10.2196/49784] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/08/2023] [Revised: 08/15/2023] [Accepted: 12/16/2023] [Indexed: 06/16/2024]
Abstract
BACKGROUND Despite its high lethality, sepsis can be difficult to detect on initial presentation to the emergency department (ED). Machine learning-based tools may provide avenues for earlier detection and lifesaving intervention. OBJECTIVE The study aimed to predict sepsis at the time of ED triage using natural language processing of nursing triage notes and available clinical data. METHODS We constructed a retrospective cohort of all 1,234,434 consecutive ED encounters in 2015-2021 from 4 separate clinically heterogeneous academically affiliated EDs. After exclusion criteria were applied, the final cohort included 1,059,386 adult ED encounters. The primary outcome criteria for sepsis were presumed severe infection and acute organ dysfunction. After vectorization and dimensional reduction of triage notes and clinical data available at triage, a decision tree-based ensemble (time-of-triage) model was trained to predict sepsis using the training subset (n=950,921). A separate (comprehensive) model was trained using these data and laboratory data, as it became available at 1-hour intervals, after triage. Model performances were evaluated using the test (n=108,465) subset. RESULTS Sepsis occurred in 35,318 encounters (incidence 3.45%). For sepsis prediction at the time of patient triage, using the primary definition, the area under the receiver operating characteristic curve (AUC) and macro F1-score for sepsis were 0.94 and 0.61, respectively. Sensitivity, specificity, and false positive rate were 0.87, 0.85, and 0.15, respectively. The time-of-triage model accurately predicted sepsis in 76% (1635/2150) of sepsis cases where sepsis screening was not initiated at triage and 97.5% (1630/1671) of cases where sepsis screening was initiated at triage. Positive and negative predictive values were 0.18 and 0.99, respectively. For sepsis prediction using laboratory data available each hour after ED arrival, the AUC peaked to 0.97 at 12 hours. Similar results were obtained when stratifying by hospital and when Centers for Disease Control and Prevention hospital toolkit for adult sepsis surveillance criteria were used to define sepsis. Among septic cases, sepsis was predicted in 36.1% (1375/3814), 49.9% (1902/3814), and 68.3% (2604/3814) of encounters, respectively, at 3, 2, and 1 hours prior to the first intravenous antibiotic order or where antibiotics where not ordered within the first 12 hours. CONCLUSIONS Sepsis can accurately be predicted at ED presentation using nursing triage notes and clinical information available at the time of triage. This indicates that machine learning can facilitate timely and reliable alerting for intervention. Free-text data can improve the performance of predictive modeling at the time of triage and throughout the ED course.
Collapse
Affiliation(s)
- Felix Brann
- Vital Software, Inc, Claymont, DE, United States
| | | | | | - Justin D Schrager
- Vital Software, Inc, Claymont, DE, United States
- Department of Emergency Medicine, Emory University School of Medicine, Atlanta, GA, United States
| |
Collapse
|
5
|
Patton MJ, Liu VX. Predictive Modeling Using Artificial Intelligence and Machine Learning Algorithms on Electronic Health Record Data: Advantages and Challenges. Crit Care Clin 2023; 39:647-673. [PMID: 37704332 DOI: 10.1016/j.ccc.2023.02.001] [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] [Indexed: 09/15/2023]
Abstract
The rapid adoption of electronic health record (EHR) systems in US hospitals from 2008 to 2014 produced novel data elements for analysis. Concurrent innovations in computing architecture and machine learning (ML) algorithms have made rapid consumption of health data feasible and a powerful engine for clinical innovation. In critical care research, the net convergence of these trends has resulted in an exponential increase in outcome prediction research. In the following article, we explore the history of outcome prediction in the intensive care unit (ICU), the growing use of EHR data, and the rise of artificial intelligence and ML (AI) in critical care.
Collapse
Affiliation(s)
- Michael J Patton
- Medical Scientist Training Program, Heersink School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA; Hugh Kaul Precision Medicine Institute at the University of Alabama at Birmingham, 720 20th Street South, Suite 202, Birmingham, Alabama, 35233, USA.
| | - Vincent X Liu
- Kaiser Permanente Division of Research, Oakland, CA, USA.
| |
Collapse
|
6
|
Yang Z, Cui X, Song Z. Predicting sepsis onset in ICU using machine learning models: a systematic review and meta-analysis. BMC Infect Dis 2023; 23:635. [PMID: 37759175 PMCID: PMC10523763 DOI: 10.1186/s12879-023-08614-0] [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: 05/21/2023] [Accepted: 09/15/2023] [Indexed: 09/29/2023] Open
Abstract
BACKGROUND Sepsis is a life-threatening condition caused by an abnormal response of the body to infection and imposes a significant health and economic burden worldwide due to its high mortality rate. Early recognition of sepsis is crucial for effective treatment. This study aimed to systematically evaluate the performance of various machine learning models in predicting the onset of sepsis. METHODS We conducted a comprehensive search of the Cochrane Library, PubMed, Embase, and Web of Science databases, covering studies from database inception to November 14, 2022. We used the PROBAST tool to assess the risk of bias. We calculated the predictive performance for sepsis onset using the C-index and accuracy. We followed the PRISMA guidelines for this study. RESULTS We included 23 eligible studies with a total of 4,314,145 patients and 26 different machine learning models. The most frequently used models in the studies were random forest (n = 9), extreme gradient boost (n = 7), and logistic regression (n = 6) models. The random forest (test set n = 9, acc = 0.911) and extreme gradient boost (test set n = 7, acc = 0.957) models were the most accurate based on our analysis of the predictive performance. In terms of the C-index outcome, the random forest (n = 6, acc = 0.79) and extreme gradient boost (n = 7, acc = 0.83) models showed the highest performance. CONCLUSION Machine learning has proven to be an effective tool for predicting sepsis at an early stage. However, to obtain more accurate results, additional machine learning methods are needed. In our research, we discovered that the XGBoost and random forest models exhibited the best predictive performance and were most frequently utilized for predicting the onset of sepsis. TRIAL REGISTRATION CRD42022384015.
Collapse
Affiliation(s)
- Zhenyu Yang
- Kunming Medical University, Kunming, Yunnan, China
| | - Xiaoju Cui
- Chengyang District People's Hospital, Qingdao, Shandong, China
| | - Zhe Song
- Qinghai University, Xining, Qinghai, China.
| |
Collapse
|
7
|
van den Berg MAM, Medina OOAG, Loohuis IIP, van der Flier MM, Dudink JJ, Benders MMJNL, Bartels RRT, Vijlbrief DDC. Development and clinical impact assessment of a machine-learning model for early prediction of late-onset sepsis. Comput Biol Med 2023; 163:107156. [PMID: 37369173 DOI: 10.1016/j.compbiomed.2023.107156] [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: 02/01/2023] [Revised: 05/24/2023] [Accepted: 06/07/2023] [Indexed: 06/29/2023]
Abstract
BACKGROUND AND AIM Preterm infants are prone to neonatal infections such as late-onset sepsis (LOS). The consequences of LOS can be severe and potentially life-threatening. Unfortunately, LOS often presents with unspecific symptoms, and early screening laboratory tests have limited diagnostic value and are often late. This study aimed to build a predictive algorithm to aid doctors in the early detection of LOS in very preterm infants. METHODS In a retrospective cohort study, all consecutively admitted preterm infants (GA ≤ 32 weeks) from 2008 until 2019 were included. They were classified as LOS or control according to blood culture results, currently the gold standard. To generate features, routine and continuously measured oxygen saturation and heart rate data with a minute-by-minute sampling rate were extracted from electronic medical records. Care was taken not to include variables indicative of existing LOS suspicion. The timing of a positive blood culture served as a proxy for LOS-onset. An equivalent timestamp was generated in gestational-age-matched control patients without a positive blood culture. Three machine learning (ML) techniques (generalized additive models, logistic regression, and XGBoost) were used to build a classification algorithm. To simulate the performance of the algorithm in clinical practice, a simulation using multiple alarm thresholds was performed on hourly predictions for the total hospitalization period. RESULTS 292 infants with LOS were matched to 1497 controls. The median gestational age before matching was 28.1 and 30.3 weeks, respectively. Evaluation of the overall discriminative power of the LR algorithm yielded an AUC of 0.73 (p < 0.05) at the moment of clinical suspicion (t = 0). In the longitudinal simulation, our algorithm detects LOS in at least 47% of the patients before clinical suspicion without exceeding the alarm fatigue threshold of 3 alarms per day. Furthermore, medical experts evaluated the algorithm as clinically relevant regarding the feature contributions in the model explanations. CONCLUSIONS An ML algorithm was trained for the early detection of LOS. Performance was evaluated on both prediction horizons and in a clinical impact simulation. To the best of our knowledge, our assessment of clinical impact with a retrospective simulation on longitudinal data is the most extensive in the literature on LOS prediction to date. The clinically relevant algorithm, based on routinely collected data, can potentially accelerate clinical decisions in the early detection of LOS, even with limited inputs.
Collapse
Affiliation(s)
- Merel A M van den Berg
- Department of Neonatology, Wilhelmina Children's Hospital, UMC Utrecht, Utrecht, the Netherlands
| | | | | | - Michiel M van der Flier
- Department of Pediatric Infectious Disease, Wilhelmina Children's Hospital, UMC Utrecht, Utrecht, the Netherlands
| | - Jeroen J Dudink
- Department of Neonatology, Wilhelmina Children's Hospital, UMC Utrecht, Utrecht, the Netherlands
| | - Manon M J N L Benders
- Department of Neonatology, Wilhelmina Children's Hospital, UMC Utrecht, Utrecht, the Netherlands
| | | | - Daniel D C Vijlbrief
- Department of Neonatology, Wilhelmina Children's Hospital, UMC Utrecht, Utrecht, the Netherlands.
| |
Collapse
|
8
|
Islam KR, Prithula J, Kumar J, Tan TL, Reaz MBI, Sumon MSI, Chowdhury MEH. Machine Learning-Based Early Prediction of Sepsis Using Electronic Health Records: A Systematic Review. J Clin Med 2023; 12:5658. [PMID: 37685724 PMCID: PMC10488449 DOI: 10.3390/jcm12175658] [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: 07/13/2023] [Revised: 08/13/2023] [Accepted: 08/23/2023] [Indexed: 09/10/2023] Open
Abstract
BACKGROUND Sepsis, a life-threatening infection-induced inflammatory condition, has significant global health impacts. Timely detection is crucial for improving patient outcomes as sepsis can rapidly progress to severe forms. The application of machine learning (ML) and deep learning (DL) to predict sepsis using electronic health records (EHRs) has gained considerable attention for timely intervention. METHODS PubMed, IEEE Xplore, Google Scholar, and Scopus were searched for relevant studies. All studies that used ML/DL to detect or early-predict the onset of sepsis in the adult population using EHRs were considered. Data were extracted and analyzed from all studies that met the criteria and were also evaluated for their quality. RESULTS This systematic review examined 1942 articles, selecting 42 studies while adhering to strict criteria. The chosen studies were predominantly retrospective (n = 38) and spanned diverse geographic settings, with a focus on the United States. Different datasets, sepsis definitions, and prevalence rates were employed, necessitating data augmentation. Heterogeneous parameter utilization, diverse model distribution, and varying quality assessments were observed. Longitudinal data enabled early sepsis prediction, and quality criteria fulfillment varied, with inconsistent funding-article quality correlation. CONCLUSIONS This systematic review underscores the significance of ML/DL methods for sepsis detection and early prediction through EHR data.
Collapse
Affiliation(s)
- Khandaker Reajul Islam
- Department of Physiology, Faculty of Medicine, University Kebangsaan Malaysia, Kuala Lumpur 56000, Malaysia
| | - Johayra Prithula
- Department of Electrical and Electronics Engineering, University of Dhaka, Dhaka 1000, Bangladesh
| | - Jaya Kumar
- Department of Physiology, Faculty of Medicine, University Kebangsaan Malaysia, Kuala Lumpur 56000, Malaysia
| | - Toh Leong Tan
- Department of Emergency Medicine, Faculty of Medicine, Universiti Kebangsaan Malaysia, Kuala Lumpur 56000, Malaysia
| | - Mamun Bin Ibne Reaz
- Department of Electrical and Electronic Engineering, Independent University, Bangladesh Bashundhara, Dhaka 1229, Bangladesh
| | - Md. Shaheenur Islam Sumon
- Department of Biomedical Engineering, Military Institute of Science and Technology (MIST), Dhaka 1216, Bangladesh
| | | |
Collapse
|
9
|
Huang Y, Wang M, Zheng Z, Ma M, Fei X, Wei L, Chen H. Representation of time-varying and time-invariant EMR data and its application in modeling outcome prediction for heart failure patients. J Biomed Inform 2023; 143:104427. [PMID: 37339714 DOI: 10.1016/j.jbi.2023.104427] [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: 01/06/2023] [Revised: 04/18/2023] [Accepted: 06/15/2023] [Indexed: 06/22/2023]
Abstract
OBJECTIVE To represent a patient record with both time-invariant and time-varying features as a single vector using an end-to-end deep learning model, and further to predict the kidney failure (KF) status and mortality of heart failure (HF) patients. MATERIALS AND METHODS The time-invariant EMR data included demographic information and comorbidities, and the time-varying EMR data were lab tests. We used a Transformer encoder module to represent the time-invariant data, and refined a long short-term memory (LSTM) with a Transformer encoder attached to the top to represent the time-varying data, taking the original measured values and their corresponding embedding vectors, masking vectors, and two types of time intervals as inputs. The proposed representations of patients with time-invariant and time-varying data were used to predict KF status (949 out of 5268 HF patients diagnosed with KF) and mortality (463 in-hospital deaths) for HF patients. Comparative experiments were conducted between the proposed model and some representative machine learning models. Ablation experiments were also performed around the time-varying data representation, including replacing the refined LSTM with the standard LSTM, GRU-D and T-LSTM, respectively, and removing the Transformer encoder and the time-varying data representation module, respectively. The visualization of the attention weights of the time-invariant and time-varying features was used to clinically interpret the predictive performance. We used the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), and the F1-score to evaluate the predictive performance of the models. RESULTS The proposed model achieved superior performance, with average AUROCs, AUPRCs and F1-scores of 0.960, 0.610 and 0.759 for KF prediction and 0.937, 0.353 and 0.537 for mortality prediction, respectively. Predictive performance improved with the addition of time-varying data from longer time periods. The proposed model outperformed the comparison and ablation references in both prediction tasks. CONCLUSIONS Both time-invariant and time-varying EMR data of patients could be efficiently represented by the proposed unified deep learning model, which shows higher performance in clinical prediction tasks. The way to use time-varying data in the current study is hopeful to be used in other kinds of time-varying data and other clinical tasks.
Collapse
Affiliation(s)
- Yanqun Huang
- School of Biomedical Engineering, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China; Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China.
| | - Muyu Wang
- School of Biomedical Engineering, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China; Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China.
| | - Zhimin Zheng
- School of Biomedical Engineering, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China; Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China.
| | - Moxuan Ma
- School of Biomedical Engineering, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China; Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China.
| | - Xiaolu Fei
- Information Center, Xuanwu Hospital, Capital Medical University, No.45 Changchun Street, Xicheng District, Beijing 100053, China.
| | - Lan Wei
- Information Center, Xuanwu Hospital, Capital Medical University, No.45 Changchun Street, Xicheng District, Beijing 100053, China.
| | - Hui Chen
- School of Biomedical Engineering, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China; Beijing Key Laboratory of Fundamental Research on Biomechanics in Clinical Application, Capital Medical University, No.10, Xitoutiao, You An Men, Fengtai District, Beijing 100069, China.
| |
Collapse
|
10
|
Amrollahi F, Shashikumar SP, Yhdego H, Nayebnazar A, Yung N, Wardi G, Nemati S. Predicting Hospital Readmission among Patients with Sepsis Using Clinical and Wearable Data. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-4. [PMID: 38083775 PMCID: PMC10805334 DOI: 10.1109/embc40787.2023.10341165] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
Sepsis is a life-threatening condition that occurs due to a dysregulated host response to infection. Recent data demonstrate that patients with sepsis have a significantly higher readmission risk than other common conditions, such as heart failure, pneumonia and myocardial infarction and associated economic burden. Prior studies have demonstrated an association between a patient's physical activity levels and readmission risk. In this study, we show that distribution of activity level prior and post-discharge among patients with sepsis are predictive of unplanned rehospitalization in 90 days (P-value<1e-3). Our preliminary results indicate that integrating Fitbit data with clinical measurements may improve model performance on predicting 90 days readmission.Clinical relevance Sepsis, Activity level, Hospital readmission, Wearable data.
Collapse
Affiliation(s)
- Fatemeh Amrollahi
- Division of Biomedical Informatics, University of California San Diego, La Jolla, CA 92093
| | | | - Haben Yhdego
- Division of Biomedical Informatics, University of California San Diego, La Jolla, CA 92093
| | - Arshia Nayebnazar
- Division of Biomedical Informatics, University of California San Diego, La Jolla, CA 92093
| | - Nathan Yung
- Department of Emergency Medicine, UC San Diego Health, La Jolla, CA 92093
- Division of Pulmonary, Critical Care and Sleep Medicine, UC San Diego Health, La Jolla, CA 92093
| | - Gabriel Wardi
- Department of Emergency Medicine, UC San Diego Health, La Jolla, CA 92093
- Division of Pulmonary, Critical Care and Sleep Medicine, UC San Diego Health, La Jolla, CA 92093
| | - Shamim Nemati
- Division of Biomedical Informatics, University of California San Diego, La Jolla, CA 92093
| |
Collapse
|
11
|
Kaya U, Yılmaz A, Aşar S. Sepsis Prediction by Using a Hybrid Metaheuristic Algorithm: A Novel Approach for Optimizing Deep Neural Networks. Diagnostics (Basel) 2023; 13:2023. [PMID: 37370918 DOI: 10.3390/diagnostics13122023] [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: 02/07/2023] [Revised: 05/11/2023] [Accepted: 05/21/2023] [Indexed: 06/29/2023] Open
Abstract
The early diagnosis of sepsis reduces the risk of the patient's death. Gradient-based algorithms are applied to the neural network models used in the estimation of sepsis in the literature. However, these algorithms become stuck at the local minimum in solution space. In recent years, swarm intelligence and an evolutionary approach have shown proper results. In this study, a novel hybrid metaheuristic algorithm was proposed for optimization with regard to the weights of the deep neural network and applied for the early diagnosis of sepsis. The proposed algorithm aims to reach the global minimum with a local search strategy capable of exploring and exploiting particles in Particle Swarm Optimization (PSO) and using the mental search operator of the Human Mental Search algorithm (HMS). The benchmark functions utilized to compare the performance of HMS, PSO, and HMS-PSO revealed that the proposed approach is more reliable, durable, and adjustable than other applied algorithms. HMS-PSO is integrated with a deep neural network (HMS-PSO-DNN). The study focused on predicting sepsis with HMS-PSO-DNN, utilizing a dataset of 640 patients aged 18 to 60. The HMS-PSO-DNN model gave a better mean squared error (MSE) result than other algorithms in terms of accuracy, robustness, and performance. We obtained the MSE value of 0.22 with 30 independent runs.
Collapse
Affiliation(s)
- Umut Kaya
- Faculty of Engineering and Architecture, Department of Software Engineering, İstanbul Beykent University, Istanbul 34398, Turkey
| | - Atınç Yılmaz
- Faculty of Engineering and Architecture, Department of Computer Engineering, İstanbul Beykent University, Istanbul 34398, Turkey
| | - Sinan Aşar
- Intensive Care Unit, Bakirkoy Dr. Sadi Konuk Training and Research Hospital, Istanbul 34147, Turkey
| |
Collapse
|
12
|
Amrollahi F, Shashikumar SP, Yhdego H, Nayebnazar A, Yung N, Wardi G, Nemati S. Predicting Hospital Readmission among Patients with Sepsis using Clinical and Wearable Data. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.04.10.23288368. [PMID: 37090521 PMCID: PMC10120792 DOI: 10.1101/2023.04.10.23288368] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/25/2023]
Abstract
Sepsis is a life-threatening condition that occurs due to a dysregulated host response to infection. Recent data demonstrate that patients with sepsis have a significantly higher readmission risk than other common conditions, such as heart failure, pneumonia and myocardial infarction and associated economic burden. Prior studies have demonstrated an association between a patient's physical activity levels and readmission risk. In this study, we show that distribution of activity level prior and post-discharge among patients with sepsis are predictive of unplanned rehospitalization in 90 days (P-value<1e-3). Our preliminary results indicate that integrating Fitbit data with clinical measurements may improve model performance on predicting 90 days readmission.
Collapse
Affiliation(s)
- Fatemeh Amrollahi
- Division of Biomedical Informatics, University of California San Diego, La Jolla, CA 92093
| | | | - Haben Yhdego
- Division of Biomedical Informatics, University of California San Diego, La Jolla, CA 92093
| | - Arshia Nayebnazar
- Division of Biomedical Informatics, University of California San Diego, La Jolla, CA 92093
| | - Nathan Yung
- Department of Emergency Medicine, UC San Diego Health, La Jolla, CA 92093
- Division of Pulmonary, Critical Care and Sleep Medicine, UC San Diego Health, La Jolla, CA 92093
| | - Gabriel Wardi
- Department of Emergency Medicine, UC San Diego Health, La Jolla, CA 92093
- Division of Pulmonary, Critical Care and Sleep Medicine, UC San Diego Health, La Jolla, CA 92093
| | - Shamim Nemati
- Division of Biomedical Informatics, University of California San Diego, La Jolla, CA 92093
| |
Collapse
|
13
|
Liu R, Hunold KM, Caterino JM, Zhang P. Estimating treatment effects for time-to-treatment antibiotic stewardship in sepsis. NAT MACH INTELL 2023; 5:421-431. [PMID: 37125081 PMCID: PMC10135432 DOI: 10.1038/s42256-023-00638-0] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2021] [Accepted: 03/02/2023] [Indexed: 05/02/2023]
Abstract
Sepsis is a life-threatening condition with a high in-hospital mortality rate. The timing of antibiotic administration poses a critical problem for sepsis management. Existing work studying antibiotic timing either ignores the temporality of the observational data or the heterogeneity of the treatment effects. Here we propose a novel method (called T4) to estimate treatment effects for time-to-treatment antibiotic stewardship in sepsis. T4 estimates individual treatment effects by recurrently encoding temporal and static variables as potential confounders, and then decoding the outcomes under different treatment sequences. We propose mini-batch balancing matching that mimics the randomized controlled trial process to adjust the confounding. The model achieves interpretability through a global-level attention mechanism and a variable-level importance examination. Meanwhile, we equip T4 with an uncertainty quantification to help prevent overconfident recommendations. We demonstrate that T4 can identify effective treatment timing with estimated individual treatment effects for antibiotic stewardship on two real-world datasets. Moreover, comprehensive experiments on a synthetic dataset exhibit the outstanding performance of T4 compared with the state-of-the-art models on estimation of individual treatment effect.
Collapse
Affiliation(s)
- Ruoqi Liu
- Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA
| | - Katherine M. Hunold
- Department of Emergency Medicine, The Ohio State University, Columbus, OH, USA
| | - Jeffrey M. Caterino
- Department of Emergency Medicine, The Ohio State University, Columbus, OH, USA
| | - Ping Zhang
- Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA
- Department of Biomedical Informatics, The Ohio State University, Columbus, OH, USA
- Translational Data Analytics institute, The Ohio State University, Columbus, OH, USA
| |
Collapse
|
14
|
Duan Y, Huo J, Chen M, Hou F, Yan G, Li S, Wang H. Early prediction of sepsis using double fusion of deep features and handcrafted features. APPL INTELL 2023; 53:1-17. [PMID: 36685641 PMCID: PMC9843111 DOI: 10.1007/s10489-022-04425-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 12/21/2022] [Indexed: 01/19/2023]
Abstract
Sepsis is a life-threatening medical condition that is characterized by the dysregulated immune system response to infections, having both high morbidity and mortality rates. Early prediction of sepsis is critical to the decrease of mortality. This paper presents a novel early warning model called Double Fusion Sepsis Predictor (DFSP) for sepsis onset. DFSP is a double fusion framework that combines the benefits of early and late fusion strategies. First, a hybrid deep learning model that combines both the convolutional and recurrent neural networks to extract deep features is proposed. Second, deep features and handcrafted features, such as clinical scores, are concatenated to build the joint feature representation (early fusion). Third, several tree-based models based on joint feature representation are developed to generate the risk scores of sepsis onset that are combined with an End-to-End neural network for final sepsis detection (late fusion). To evaluate DFSP, a retrospective study was conducted, which included patients admitted to the ICUs of a hospital in Shanghai China. The results demonstrate that the DFSP outperforms state-of-the-art approaches in early sepsis prediction.
Collapse
Affiliation(s)
- Yongrui Duan
- School of Economics & Management, Tongji University, Shanghai, China
| | - Jiazhen Huo
- School of Economics & Management, Tongji University, Shanghai, China
| | - Mingzhou Chen
- School of Economics & Management, Tongji University, Shanghai, China
| | - Fenggang Hou
- Department of Oncology, Shanghai Municipal Hospital of Traditional Chinese Medicine, Shanghai, China
| | - Guoliang Yan
- Department of Geriatrics, Shanghai Municipal Hospital of Traditional Chinese Medicine, Shanghai, China
| | - Shufang Li
- Emergency Department, Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Haihui Wang
- Department of Geriatrics, Shanghai Municipal Hospital of Traditional Chinese Medicine, Shanghai, China
| |
Collapse
|
15
|
CATNet: Cross-event attention-based time-aware network for medical event prediction. Artif Intell Med 2022; 134:102440. [PMID: 36462902 DOI: 10.1016/j.artmed.2022.102440] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2021] [Revised: 09/13/2022] [Accepted: 10/28/2022] [Indexed: 12/14/2022]
Abstract
Medical event prediction (MEP) is a fundamental task in the healthcare domain, which needs to predict medical events, including medications, diagnosis codes, laboratory tests, procedures, outcomes, and so on, according to historical medical records of patients. Many researchers have tried to build MEP models to overcome the challenges caused by the heterogeneous and irregular temporal characteristics of EHR data. However, most of them consider the heterogenous and temporal medical events separately and ignore the correlations among different types of medical events, especially relations between heterogeneous historical medical events and target medical events. In this paper, we propose a novel neural network based on attention mechanism called Cross-event Attention-based Time-aware Network (CATNet) for MEP. It is a time-aware, event-aware and task-adaptive method with the following advantages: 1) modeling heterogeneous information and temporal information in a unified way and considering irregular temporal characteristics locally and globally respectively, 2) taking full advantage of correlations among different types of events via cross-event attention. Experiments on two public datasets (MIMIC-III and eICU) show CATNet outperforms other state-of-the-art methods on various MEP tasks. The source code of CATNet is released at https://github.com/sherry6247/CATNet.git.
Collapse
|
16
|
Di Martino F, Delmastro F. Explainable AI for clinical and remote health applications: a survey on tabular and time series data. Artif Intell Rev 2022; 56:5261-5315. [PMID: 36320613 PMCID: PMC9607788 DOI: 10.1007/s10462-022-10304-3] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
Abstract
AbstractNowadays Artificial Intelligence (AI) has become a fundamental component of healthcare applications, both clinical and remote, but the best performing AI systems are often too complex to be self-explaining. Explainable AI (XAI) techniques are defined to unveil the reasoning behind the system’s predictions and decisions, and they become even more critical when dealing with sensitive and personal health data. It is worth noting that XAI has not gathered the same attention across different research areas and data types, especially in healthcare. In particular, many clinical and remote health applications are based on tabular and time series data, respectively, and XAI is not commonly analysed on these data types, while computer vision and Natural Language Processing (NLP) are the reference applications. To provide an overview of XAI methods that are most suitable for tabular and time series data in the healthcare domain, this paper provides a review of the literature in the last 5 years, illustrating the type of generated explanations and the efforts provided to evaluate their relevance and quality. Specifically, we identify clinical validation, consistency assessment, objective and standardised quality evaluation, and human-centered quality assessment as key features to ensure effective explanations for the end users. Finally, we highlight the main research challenges in the field as well as the limitations of existing XAI methods.
Collapse
|
17
|
Adams R, Henry KE, Sridharan A, Soleimani H, Zhan A, Rawat N, Johnson L, Hager DN, Cosgrove SE, Markowski A, Klein EY, Chen ES, Saheed MO, Henley M, Miranda S, Houston K, Linton RC, Ahluwalia AR, Wu AW, Saria S. Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis. Nat Med 2022; 28:1455-1460. [PMID: 35864252 DOI: 10.1038/s41591-022-01894-0] [Citation(s) in RCA: 74] [Impact Index Per Article: 37.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2021] [Accepted: 06/08/2022] [Indexed: 12/20/2022]
Abstract
Early recognition and treatment of sepsis are linked to improved patient outcomes. Machine learning-based early warning systems may reduce the time to recognition, but few systems have undergone clinical evaluation. In this prospective, multi-site cohort study, we examined the association between patient outcomes and provider interaction with a deployed sepsis alert system called the Targeted Real-time Early Warning System (TREWS). During the study, 590,736 patients were monitored by TREWS across five hospitals. We focused our analysis on 6,877 patients with sepsis who were identified by the alert before initiation of antibiotic therapy. Adjusting for patient presentation and severity, patients in this group whose alert was confirmed by a provider within 3 h of the alert had a reduced in-hospital mortality rate (3.3%, confidence interval (CI) 1.7, 5.1%, adjusted absolute reduction, and 18.7%, CI 9.4, 27.0%, adjusted relative reduction), organ failure and length of stay compared with patients whose alert was not confirmed by a provider within 3 h. Improvements in mortality rate (4.5%, CI 0.8, 8.3%, adjusted absolute reduction) and organ failure were larger among those patients who were additionally flagged as high risk. Our findings indicate that early warning systems have the potential to identify sepsis patients early and improve patient outcomes and that sepsis patients who would benefit the most from early treatment can be identified and prioritized at the time of the alert.
Collapse
Affiliation(s)
- Roy Adams
- Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, MD, USA.,Department of Psychiatry and Behavioral Science, Johns Hopkins School of Medicine, Baltimore, MD, USA
| | - Katharine E Henry
- Department of Psychiatry and Behavioral Science, Johns Hopkins School of Medicine, Baltimore, MD, USA.,Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | | | - Hossein Soleimani
- Health Informatics, University of California, San Francisco, CA, USA
| | - Andong Zhan
- Department of Psychiatry and Behavioral Science, Johns Hopkins School of Medicine, Baltimore, MD, USA.,Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
| | - Nishi Rawat
- Armstrong Institute for Patient Safety and Quality, Johns Hopkins School of Medicine, Baltimore, MD, USA
| | - Lauren Johnson
- Department of Quality Improvement, Johns Hopkins Hospital, Baltimore, MD, USA
| | - David N Hager
- Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA
| | - Sara E Cosgrove
- Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA
| | | | - Eili Y Klein
- Department of Emergency Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA
| | - Edward S Chen
- Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA
| | - Mustapha O Saheed
- Department of Emergency Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA
| | - Maureen Henley
- Department of Quality Improvement, Johns Hopkins Hospital, Baltimore, MD, USA
| | - Sheila Miranda
- Department of Medicine, Johns Hopkins Hospital, Baltimore, MD, USA
| | - Katrina Houston
- Department of Quality Improvement, Johns Hopkins Hospital, Baltimore, MD, USA
| | | | | | - Albert W Wu
- Armstrong Institute for Patient Safety and Quality, Johns Hopkins School of Medicine, Baltimore, MD, USA. .,Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA. .,Department of Health Policy and Management, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA. .,Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA. .,Department of International Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA.
| | - Suchi Saria
- Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, MD, USA. .,Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA. .,Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA. .,Department of Health Policy and Management, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA. .,Bayesian Health, New York, NY, USA.
| |
Collapse
|
18
|
Rajmohan R, Kumar TA, Julie EG, Robinson YH, Vimal S, Kadry S, Crespo RG. G-Sep: A Deep Learning Algorithm for Detection of Long-Term Sepsis Using Bidirectional Gated Recurrent Unit. INT J UNCERTAIN FUZZ 2022. [DOI: 10.1142/s0218488522400013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Sepsis is a common and deadly condition that must be treated eloquently within 19 hours. Numerous deep learning techniques, including Recurrent Neural Networks, Convolution Neural Networks, Long Short-Term Memory, and Gated Recurrent Units, have been suggested for diagnosing long-term sepsis. Regardless, a sizable portion of them are computationally risky and have precision problems. The primary issue described is that output will degrade, and resource utilization will expand proportionately as the volume of dependencies grows. To overcome these issues, we propose a G-Sep technique utilizing Bidirectional Gated Recurrent Unit Algorithm, which consumes much less resource to detect the disease and in a short time with better accuracy than the existing methods to diagnose the sepsis. AI models could assist with distinguishing potential clinical factors and give better than existing conventional low-execution models. The proposed model is implemented utilizing Conda and Tensorflow Framework using the California Inpatient Severe Sepsis (CISS) Patient Dataset. The comparative simulation of the various existing models and the proposed G-Sep model is done using Conda and Tensor frameworks. The simulation results revealed that the proposed model had outperformed other frameworks in terms of mean average precision (mAP), receiver operating characteristic curve (ROC), and Area under the ROC Curve (AUROC) metrics linearly.
Collapse
Affiliation(s)
- R. Rajmohan
- Department of Computer Science and Engineering, IFET College of Engineering, Villupuram, Tamil Nadu, India
| | - T. Ananth Kumar
- Department of Computer Science and Engineering, IFET College of Engineering, Villupuram, Tamil Nadu, India
| | - E. Golden Julie
- Department of Computer Science and Engineering, Anna University Regional Campus, Tirunelveli, Tamil Nadu, India
| | - Y. Harold Robinson
- School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India
| | - S. Vimal
- Department of Computer Science and Engineering, Ramco Institute of Technology, Rajapalayam, Tamil Nadu, India
| | - Seifidine Kadry
- Faculty of Applied Computing and Technology, Noroff University College, Kristiansand, Norway
| | - Ruben Gonzalez Crespo
- Department of Engineering, School of Engineering and Technology, Universidad Internacional de la Rioja (UNIR), Logroño, Spain
| |
Collapse
|
19
|
Machine Learning Models for Early Prediction of Sepsis on Large Healthcare Datasets. ELECTRONICS 2022. [DOI: 10.3390/electronics11091507] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Sepsis is a highly lethal syndrome with heterogeneous clinical manifestation that can be hard to identify and treat. Early diagnosis and appropriate treatment are critical to reduce mortality and promote survival in suspected cases and improve the outcomes. Several screening prediction systems have been proposed for evaluating the early detection of patient deterioration, but the efficacy is still limited at individual level. The increasing amount and the versatility of healthcare data suggest implementing machine learning techniques to develop models for predicting sepsis. This work presents an experimental study of some machine-learning-based models for sepsis prediction considering vital signs, laboratory test results, and demographics using Medical Information Mart for Intensive Care III (MIMIC-III) (v1.4), a publicly available dataset. The experimental results demonstrate an overall higher performance of machine learning models over the commonly used Sequential Organ Failure Assessment (SOFA) and Quick SOFA (qSOFA) scoring systems at the time of sepsis onset.
Collapse
|
20
|
Singh YV, Singh P, Khan S, Singh RS. A Machine Learning Model for Early Prediction and Detection of Sepsis in Intensive Care Unit Patients. JOURNAL OF HEALTHCARE ENGINEERING 2022; 2022:9263391. [PMID: 35378945 PMCID: PMC8976655 DOI: 10.1155/2022/9263391] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Revised: 03/01/2022] [Accepted: 03/09/2022] [Indexed: 12/17/2022]
Abstract
In today's scenario, sepsis is impacting millions of patients in the intensive care unit due to the fact that the mortality rate is increased exponentially and has become a major challenge in the field of healthcare. Such peoples require determinant care which increases the cost of the treatment by using a large number of resources because of the nonavailability of the resources. The treatment of sepsis is available in the early state, but treatment is not started at the right time, and then it converts to the advanced level of sepsis and increases the fatalities. Thus, an intensive analysis is required to detect and identify sepsis at the early stage. There are some models available that work based on the manual score and based on only the biomark features, but these are not fully automated. Some machine learning-based models are also available, which can reduce the mortality rate, but accuracy is not up to date. This paper proposes a machine learning model for early detecting and predicting sepsis in intensive care unit patients. Various models, random forest (RF), linear regression (LR), support vector machine (SVM), naive Bayes (NB), ensemble (of SVM, RF, NB, and LR), XGBoost, and proposed ensemble (of SVM, RF, NB, LR, and XGBoost), are simulated by using the collected data from intensive care unit patient's database that is based on the clinical laboratory values and vital signs. The performance of the models is evaluated by considering the same datasets. The balanced accuracy of RF, LR, SVM, NB, ensemble (of SVM, RF, NB, and LR), XGBoost, and proposed ensemble (of SVM, RF, NB, LR, and XGBoost) is 0.90, 0.73, 0.93, 0.74, 0.94, 0.95, and 0.96, respectively. It is also evident from the experimental results that the proposed ensemble model performs well as compared to the other models.
Collapse
Affiliation(s)
- Yash Veer Singh
- Department of Information Technology, ABES Engineering College, Ghaziabad (UP) 201009, India
| | - Pushpendra Singh
- Department of Information Technology, Raj Kumar Goel Institute of Technology, Ghaziabad (UP) 101003, India
| | - Shadab Khan
- Department of Computer Science & Engineering, Sunder Deep Engineering College, Ghaziabad (UP) 201002, India
| | - Ram Sewak Singh
- Department of Electronics and Communication,School of Electrical Engineering and Computing, Adama Science and Technology University, Adama, Ethiopia
| |
Collapse
|
21
|
Sepsis prediction in intensive care unit based on genetic feature optimization and stacked deep ensemble learning. Neural Comput Appl 2022. [DOI: 10.1007/s00521-021-06631-1] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
|
22
|
Kim JK, Ahn W, Park S, Lee SH, Kim L. Early Prediction of Sepsis Onset Using Neural Architecture Search Based on Genetic Algorithms. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:ijerph19042349. [PMID: 35206537 PMCID: PMC8872017 DOI: 10.3390/ijerph19042349] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Revised: 02/13/2022] [Accepted: 02/14/2022] [Indexed: 12/14/2022]
Abstract
Sepsis is a life-threatening condition with a high mortality rate. Early prediction and treatment are the most effective strategies for increasing survival rates. This paper proposes a neural architecture search (NAS) model to predict the onset of sepsis with a low computational cost and high search performance by applying a genetic algorithm (GA). The proposed model shares the weights of all possible connection nodes internally within the neural network. Externally, the search cost is reduced through the weight-sharing effect between the genotypes of the GA. A predictive analysis was performed using the Medical Information Mart for Intensive Care III (MIMIC-III), a medical time-series dataset, with the primary objective of predicting sepsis onset 3 h before occurrence. In addition, experiments were conducted under various prediction times (0-12 h) for comparison. The proposed model exhibited an area under the receiver operating characteristic curve (AUROC) score of 0.94 (95% CI: 0.92-0.96) for 3 h, which is 0.31-0.26 higher than the scores obtained using the Sequential Organ Failure Assessment (SOFA), quick SOFA (qSOFA), and Simplified Acute Physiology Score (SAPS) II scoring systems. Furthermore, the proposed model exhibited a 12% improvement in the AUROC value over a simple model based on the long short-term memory neural network. Additionally, it is not only optimally searchable for sepsis onset prediction, but also outperforms conventional models that use similar predictive purposes and datasets. Notably, it is sufficiently robust to shape changes in the input data and has less structural dependence.
Collapse
Affiliation(s)
- Jae Kwan Kim
- Center for Bionics, Korea Institute of Science and Technology, Seoul 02792, Korea
- School of Mechanical Engineering, Yonsei University, Seoul 03722, Korea
| | - Wonbin Ahn
- Applied AI Research Lab, LG AI Research, Seoul 07796, Korea
| | - Sangin Park
- Center for Bionics, Korea Institute of Science and Technology, Seoul 02792, Korea
| | - Soo-Hong Lee
- School of Mechanical Engineering, Yonsei University, Seoul 03722, Korea
| | - Laehyun Kim
- Center for Bionics, Korea Institute of Science and Technology, Seoul 02792, Korea
- Department of HY-KIST Bio-Convergence, Hanyang University, Seoul 04763, Korea
| |
Collapse
|
23
|
Shashikumar SP, Wardi G, Paul P, Carlile M, Brenner LN, Hibbert KA, North CM, Mukerji SS, Robbins GK, Shao YP, Westover MB, Nemati S, Malhotra A. Development and Prospective Validation of a Deep Learning Algorithm for Predicting Need for Mechanical Ventilation. Chest 2021; 159:2264-2273. [PMID: 33345948 PMCID: PMC8027289 DOI: 10.1016/j.chest.2020.12.009] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2020] [Revised: 11/19/2020] [Accepted: 12/04/2020] [Indexed: 01/17/2023] Open
Abstract
BACKGROUND Objective and early identification of hospitalized patients, and particularly those with novel coronavirus disease 2019 (COVID-19), who may require mechanical ventilation (MV) may aid in delivering timely treatment. RESEARCH QUESTION Can a transparent deep learning (DL) model predict the need for MV in hospitalized patients and those with COVID-19 up to 24 h in advance? STUDY DESIGN AND METHODS We trained and externally validated a transparent DL algorithm to predict the future need for MV in hospitalized patients, including those with COVID-19, using commonly available data in electronic health records. Additionally, commonly used clinical criteria (heart rate, oxygen saturation, respiratory rate, Fio2, and pH) were used to assess future need for MV. Performance of the algorithm was evaluated using the area under receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value. RESULTS We obtained data from more than 30,000 ICU patients (including more than 700 patients with COVID-19) from two academic medical centers. The performance of the model with a 24-h prediction horizon at the development and validation sites was comparable (AUC, 0.895 vs 0.882, respectively), providing significant improvement over traditional clinical criteria (P < .001). Prospective validation of the algorithm among patients with COVID-19 yielded AUCs in the range of 0.918 to 0.943. INTERPRETATION A transparent deep learning algorithm improves on traditional clinical criteria to predict the need for MV in hospitalized patients, including in those with COVID-19. Such an algorithm may help clinicians to optimize timing of tracheal intubation, to allocate resources and staff better, and to improve patient care.
Collapse
Affiliation(s)
| | - Gabriel Wardi
- Department of Emergency Medicine, University of California, San Diego, La Jolla, CA; Division of Pulmonary, Critical Care, and Sleep Medicine, University of California, San Diego, La Jolla, CA
| | - Paulina Paul
- Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA
| | - Morgan Carlile
- Department of Emergency Medicine, University of California, San Diego, La Jolla, CA
| | - Laura N Brenner
- Division of Pulmonary and Critical Care Medicine, Massachusetts General Hospital, Boston, MA
| | - Kathryn A Hibbert
- Division of Pulmonary and Critical Care Medicine, Massachusetts General Hospital, Boston, MA
| | - Crystal M North
- Division of Pulmonary and Critical Care Medicine, Massachusetts General Hospital, Boston, MA
| | | | - Gregory K Robbins
- Division of Infectious Diseases, Massachusetts General Hospital, Boston, MA
| | - Yu-Ping Shao
- Department of Neurology, Massachusetts General Hospital, Boston, MA
| | | | - Shamim Nemati
- Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA
| | - Atul Malhotra
- Division of Pulmonary, Critical Care, and Sleep Medicine, University of California, San Diego, La Jolla, CA.
| |
Collapse
|
24
|
Tavolara TE, Niazi MKK, Gower AC, Ginese M, Beamer G, Gurcan MN. Deep learning predicts gene expression as an intermediate data modality to identify susceptibility patterns in Mycobacterium tuberculosis infected Diversity Outbred mice. EBioMedicine 2021; 67:103388. [PMID: 34000621 PMCID: PMC8138606 DOI: 10.1016/j.ebiom.2021.103388] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2021] [Revised: 04/22/2021] [Accepted: 04/23/2021] [Indexed: 12/14/2022] Open
Abstract
BACKGROUND Machine learning sustains successful application to many diagnostic and prognostic problems in computational histopathology. Yet, few efforts have been made to model gene expression from histopathology. This study proposes a methodology which predicts selected gene expression values (microarray) from haematoxylin and eosin whole-slide images as an intermediate data modality to identify fulminant-like pulmonary tuberculosis ('supersusceptible') in an experimentally infected cohort of Diversity Outbred mice (n=77). METHODS Gradient-boosted trees were utilized as a novel feature selector to identify gene transcripts predictive of fulminant-like pulmonary tuberculosis. A novel attention-based multiple instance learning model for regression was used to predict selected genes' expression from whole-slide images. Gene expression predictions were shown to be sufficiently replicated to identify supersusceptible mice using gradient-boosted trees trained on ground truth gene expression data. FINDINGS The model was accurate, showing high positive correlations with ground truth gene expression on both cross-validation (n = 77, 0.63 ≤ ρ ≤ 0.84) and external testing sets (n = 33, 0.65 ≤ ρ ≤ 0.84). The sensitivity and specificity for gene expression predictions to identify supersusceptible mice (n=77) were 0.88 and 0.95, respectively, and for an external set of mice (n=33) 0.88 and 0.93, respectively. IMPLICATIONS Our methodology maps histopathology to gene expression with sufficient accuracy to predict a clinical outcome. The proposed methodology exemplifies a computational template for gene expression panels, in which relatively inexpensive and widely available tissue histopathology may be mapped to specific genes' expression to serve as a diagnostic or prognostic tool. FUNDING National Institutes of Health and American Lung Association.
Collapse
Affiliation(s)
- Thomas E Tavolara
- Center for Biomedical Informatics, Wake Forest School of Medicine, 486 Patterson Avenue, Winston-Salem, NC 27101, United States
| | - M K K Niazi
- Center for Biomedical Informatics, Wake Forest School of Medicine, 486 Patterson Avenue, Winston-Salem, NC 27101, United States.
| | - Adam C Gower
- Department of Medicine, Boston University School of Medicine, 72 E. Concord St Evans Building, Boston, MA 02118, United States
| | - Melanie Ginese
- Department of Infectious Disease and Global Health, Tufts University Cummings School of Veterinary Medicine, 200 Westboro Rd., North Grafton, MA 01536, United States
| | - Gillian Beamer
- Department of Infectious Disease and Global Health, Tufts University Cummings School of Veterinary Medicine, 200 Westboro Rd., North Grafton, MA 01536, United States
| | - Metin N Gurcan
- Center for Biomedical Informatics, Wake Forest School of Medicine, 486 Patterson Avenue, Winston-Salem, NC 27101, United States
| |
Collapse
|