1
|
Park S, Perumalsamy H, Gerelkhuu Z, Sunderraj S, Lee Y, Yoon TH. Phenotypic Landscape of Immune Cells in Sepsis: Insights from High-Dimensional Mass Cytometry. ACS Infect Dis 2024. [PMID: 38850242 DOI: 10.1021/acsinfecdis.4c00066] [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: 06/10/2024]
Abstract
Understanding the sepsis-induced immunological response can be facilitated by identifying phenotypic changes in immune cells at the single-cell level. Mass cytometry, a novel multiparametric single-cell analysis technique, offers considerable benefits in characterizing sepsis-induced phenotypic changes in peripheral blood mononuclear cells. Here, we analyzed peripheral blood mononuclear cells from 20 sepsis patients and 10 healthy donors using mass cytometry and employing 23 markers. Both manual gating and automated clustering approaches (PhenoGraph) were used for cell identification, complemented by uniform manifold approximation and projection (UMAP) for dimensionality reduction and visualization. Our study revealed that patients with sepsis exhibited a unique immune cell profile, marked by an increased presence of monocytes, B cells, and dendritic cells, alongside a reduction in natural killer (NK) cells and CD4/CD8 T cells. Notably, significant changes in the distributions of monocytes and B and CD4 T cells were observed. Clustering with PhenoGraph unveiled the subsets of each cell type and identified elevated CCR6 expression in sepsis patients' monocyte subset (PG#5), while further PhenoGraph clustering on manually gated T and B cells discovered sepsis-specific CD4 T cell subsets (CCR4low CD20low CD38low) and B cell subsets (HLA-DRlow CCR7low CCR6high), which could potentially serve as novel diagnostic markers for sepsis.
Collapse
Affiliation(s)
- Sehee Park
- Department of Chemistry, College of Natural Sciences, Hanyang University, Seoul 04763, Republic of Korea
| | - Haribalan Perumalsamy
- Institute of Next Generation Material Design, Hanyang University, Seoul 04763, Republic of Korea
| | - Zayakhuu Gerelkhuu
- Institute of Next Generation Material Design, Hanyang University, Seoul 04763, Republic of Korea
| | - Sneha Sunderraj
- Department of Medical and Digital Engineering, College of Engineering, Hanyang University, Seoul 04763, Republic of Korea
| | - Yangsoon Lee
- Department of Laboratory Medicine, College of Medicine, Hanyang University, Seoul 04763, Republic of Korea
| | - Tae Hyun Yoon
- Department of Chemistry, College of Natural Sciences, Hanyang University, Seoul 04763, Republic of Korea
- Institute of Next Generation Material Design, Hanyang University, Seoul 04763, Republic of Korea
- Department of Medical and Digital Engineering, College of Engineering, Hanyang University, Seoul 04763, Republic of Korea
- Yoon Idea Lab Co., Ltd., Seoul 04763, Republic of Korea
| |
Collapse
|
2
|
Steinbach D, Ahrens PC, Schmidt M, Federbusch M, Heuft L, Lübbert C, Nauck M, Gründling M, Isermann B, Gibb S, Kaiser T. Applying Machine Learning to Blood Count Data Predicts Sepsis with ICU Admission. Clin Chem 2024; 70:506-515. [PMID: 38431275 DOI: 10.1093/clinchem/hvae001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2023] [Accepted: 11/16/2023] [Indexed: 03/05/2024]
Abstract
BACKGROUND Timely diagnosis is crucial for sepsis treatment. Current machine learning (ML) models suffer from high complexity and limited applicability. We therefore created an ML model using only complete blood count (CBC) diagnostics. METHODS We collected non-intensive care unit (non-ICU) data from a German tertiary care centre (January 2014 to December 2021). Using patient age, sex, and CBC parameters (haemoglobin, platelets, mean corpuscular volume, white and red blood cells), we trained a boosted random forest, which predicts sepsis with ICU admission. Two external validations were conducted using data from another German tertiary care centre and the Medical Information Mart for Intensive Care IV database (MIMIC-IV). Using the subset of laboratory orders also including procalcitonin (PCT), an analogous model was trained with PCT as an additional feature. RESULTS After exclusion, 1 381 358 laboratory requests (2016 from sepsis cases) were available. The CBC model shows an area under the receiver operating characteristic (AUROC) of 0.872 (95% CI, 0.857-0.887). External validations show AUROCs of 0.805 (95% CI, 0.787-0.824) for University Medicine Greifswald and 0.845 (95% CI, 0.837-0.852) for MIMIC-IV. The model including PCT revealed a significantly higher AUROC (0.857; 95% CI, 0.836-0.877) than PCT alone (0.790; 95% CI, 0.759-0.821; P < 0.001). CONCLUSIONS Our results demonstrate that routine CBC results could significantly improve diagnosis of sepsis when combined with ML. The CBC model can facilitate early sepsis prediction in non-ICU patients with high robustness in external validations. Its implementation in clinical decision support systems has strong potential to provide an essential time advantage and increase patient safety.
Collapse
Affiliation(s)
- Daniel Steinbach
- University Institute for Laboratory Medicine, OWL University Hospital of Bielefeld University, Detmold, Germany
| | - Paul C Ahrens
- University Institute for Laboratory Medicine, OWL University Hospital of Bielefeld University, Detmold, Germany
| | - Maria Schmidt
- University Institute for Laboratory Medicine, OWL University Hospital of Bielefeld University, Detmold, Germany
| | - Martin Federbusch
- University Institute for Laboratory Medicine, OWL University Hospital of Bielefeld University, Detmold, Germany
| | - Lara Heuft
- Institute of Human Genetics, Leipzig University Hospital, Leipzig, Germany
| | - Christoph Lübbert
- Department of Infectious Diseases/Tropical Medicine, Nephrology and Rheumatology, Hospital St. Georg, Leipzig, Germany
- Division of Infectious Diseases and Tropical Medicine, Department of Medicine I, Interdisciplinary Center for Infectious Diseases, Leipzig University Hospital, Leipzig, Germany
| | - Matthias Nauck
- Institute of Clinical Chemistry and Laboratory Medicine, University Medicine Greifswald, Greifswald, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Greifswald, University Medicine Greifswald, Greifswald, Germany
| | - Matthias Gründling
- Anesthesiology and Intensive Care Medicine, University Medicine Greifswald, Greifswald, Germany
| | - Berend Isermann
- University Institute for Laboratory Medicine, OWL University Hospital of Bielefeld University, Detmold, Germany
| | - Sebastian Gibb
- University Institute for Laboratory Medicine, OWL University Hospital of Bielefeld University, Detmold, Germany
- Anesthesiology and Intensive Care Medicine, University Medicine Greifswald, Greifswald, Germany
| | - Thorsten Kaiser
- University Institute for Laboratory Medicine, OWL University Hospital of Bielefeld University, Detmold, Germany
| |
Collapse
|
3
|
Yang HS. Machine Learning for Sepsis Prediction: Prospects and Challenges. Clin Chem 2024; 70:465-467. [PMID: 38431277 DOI: 10.1093/clinchem/hvae006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2023] [Accepted: 01/11/2024] [Indexed: 03/05/2024]
Affiliation(s)
- He S Yang
- Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, NY, 10065, United States
| |
Collapse
|
4
|
Agnello L, Vidali M, Padoan A, Lucis R, Mancini A, Guerranti R, Plebani M, Ciaccio M, Carobene A. Machine learning algorithms in sepsis. Clin Chim Acta 2024; 553:117738. [PMID: 38158005 DOI: 10.1016/j.cca.2023.117738] [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: 11/20/2023] [Revised: 12/20/2023] [Accepted: 12/20/2023] [Indexed: 01/03/2024]
Abstract
Sepsis remains a significant global health challenge due to its high mortality and morbidity, compounded by the difficulty of early detection given its variable clinical manifestations. The integration of machine learning (ML) into laboratory medicine for timely sepsis identification and outcome forecasting is an emerging field of interest. This comprehensive review assesses the current body of research on ML applications for sepsis within the realm of laboratory diagnostics, detailing both their strengths and shortcomings. An extensive literature search was performed by two independent investigators across PubMed and Scopus databases, employing the keywords "Sepsis," "Machine Learning," and "Laboratory" without publication date limitations, culminating in January 2023. Each selected study was meticulously evaluated for various aspects, including its design, intent (diagnostic or prognostic), clinical environment, demographics, sepsis criteria, data gathering period, and the scope and nature of features, in addition to the ML methodologies and their validation procedures. Out of 135 articles reviewed, 39 fulfilled the criteria for inclusion. Among these, the majority (30 studies) were focused on devising ML algorithms for diagnosis, fewer (8 studies) on prognosis, and one study addressed both aspects. The dissemination of these studies across an array of journals reflects the interdisciplinary engagement in the development of ML algorithms for sepsis. This analysis highlights the promising role of ML in the early diagnosis of sepsis while drawing attention to the need for uniformity in validating models and defining features, crucial steps for ensuring the reliability and practicality of ML in clinical setting.
Collapse
Affiliation(s)
- Luisa Agnello
- Institute of Clinical Biochemistry, Clinical Molecular Medicine and Clinical Laboratory Medicine, Department of Biomedicine, Neurosciences and Advanced Diagnostics, University of Palermo, Palermo, Italy
| | - Matteo Vidali
- Clinical Pathology Unit, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milano, Italy
| | - Andrea Padoan
- Department of Medicine-DIMED, University of Padova, Padova, Italy; Laboratory Medicine Unit, University-Hospital of Padova, Padova, Italy; QI.LAB.MED., Spin-off of the University of Padova, Padova, Italy
| | - Riccardo Lucis
- Department of Medicine (DAME), University of Udine, 33100, Udine, Italy; Microbiology and Virology Unit, Department of Laboratory Medicine, Azienda Sanitaria Friuli Occidentale (ASFO), Santa Maria degli Angeli Hospital, 33170, Pordenone, Italy
| | - Alessio Mancini
- School of Biosciences and Veterinary Medicine, University of Camerino, Camerino, Italy; Operative Unit of Clinical Pathology, AST2 Ancona, Senigallia, Italy
| | - Roberto Guerranti
- Department of Medical Biotechnologies, University of Siena, Siena, Italy; Clinical Pathology Unit, Innovation, Experimentation and Clinical and Translational Research Department, University Hospital of Siena, Siena, Italy
| | - Mario Plebani
- Department of Medicine-DIMED, University of Padova, Padova, Italy; Laboratory Medicine Unit, University-Hospital of Padova, Padova, Italy; QI.LAB.MED., Spin-off of the University of Padova, Padova, Italy; Clinical Biochemistry and Clinical Molecular Biology, School of Medicine, University of Padova, Padova, Italy
| | - Marcello Ciaccio
- Institute of Clinical Biochemistry, Clinical Molecular Medicine and Clinical Laboratory Medicine, Department of Biomedicine, Neurosciences and Advanced Diagnostics, University of Palermo, Palermo, Italy; Department of Laboratory Medicine, University Hospital "P. Giaccone", Palermo, Italy.
| | - Anna Carobene
- IRCCS San Raffaele Scientific Institute, Milan, Italy
| |
Collapse
|
5
|
Dou Y, Li W, Nan Y, Zhang Y, Peng S. Feature augmentation and semi-supervised conditional transfer learning for early detection of sepsis. Comput Biol Med 2023; 165:107418. [PMID: 37716243 DOI: 10.1016/j.compbiomed.2023.107418] [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: 06/07/2023] [Revised: 07/25/2023] [Accepted: 08/28/2023] [Indexed: 09/18/2023]
Abstract
Early detection of Sepsis is crucial for improving patient outcomes, as it is a significant public health concern that results in substantial morbidity and mortality. However, despite the widespread use of the Sequential Organ Failure Assessment (SOFA) in clinical settings to identify sepsis, obtaining sufficient physiological data before onset remains challenging, limiting early detection of sepsis. To address this challenge, we propose an interpretable machine learning model, ITFG (Interpretable Tree-based Feature Generation), that leverages potential correlations between features based on existing knowledge to identify sepsis within six hours of onset using valuable and continuous physiological measures. Furthermore, we introduce a Semi-supervised Attention-based Conditional Transfer Learning (SAC-TL) framework to enhance the model's generality and enable it to be used for early warning of sepsis in the target domain with less information from the source domain. Our proposed approaches effectively address the problem of systematic feature sparsity and missing data, while also being practical for different degrees of generalizability. We evaluated our proposed approaches on open datasets, MIMIC and PhysioNet, obtaining AUC of 97.98% and 86.21%, respectively, demonstrating their effectiveness in different data environments and achieving the best early detection results.
Collapse
Affiliation(s)
- Yutao Dou
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China; Centre for Distributed and High Performance Computing, School of Computer Science, The University of Sydney, Darlington, NSW, 2008, Australia.
| | - Wei Li
- Centre for Distributed and High Performance Computing, School of Computer Science, The University of Sydney, Darlington, NSW, 2008, Australia
| | - Yucen Nan
- Centre for Distributed and High Performance Computing, School of Computer Science, The University of Sydney, Darlington, NSW, 2008, Australia
| | - Yidi Zhang
- State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Beijing, China
| | - Shaoliang Peng
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China.
| |
Collapse
|
6
|
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
|
7
|
Moreno-Torres V, Royuela A, Múñez E, Ortega A, Gutierrez Á, Mills P, Ramos-Martínez A. Better prognostic ability of NEWS2, SOFA and SAPS-II in septic patients. Med Clin (Barc) 2022; 159:224-229. [PMID: 34949450 DOI: 10.1016/j.medcli.2021.10.021] [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: 08/16/2021] [Revised: 10/26/2021] [Accepted: 10/28/2021] [Indexed: 12/30/2022]
Abstract
BACKGROUND AND OBJECTIVES To compare the ability of qSOFA, NEWS2, SOFA, LODS, SIRS, APACHE-II and SAPS-II scores. MATERIAL AND METHODS Analysis of in-hospital mortality of 203 patients admitted to the ICU because of sepsis. The scores were compared according to their application. Discrimination was evaluated with AUC-ROC curve and performance with the Akaike's (AIC) and Bayesian information criterion (BIC). RESULTS In-hospital mortality was 31.53%. NEWS2 showed better mortality discrimination ability and better performance considering the AIC/BIC criterion for mortality tan qSOFA (AUC-ROC=.615 and .536; P=.039). SOFA presented higher performance and AUC-ROC tan LODS (.776 vs .693; P=.01) and both showed higher discrimination ability than SIRS (AUC-ROC=.521; P<.003). Finally, SAPS-II was able to predict mortality with better performance than APACHE-II and presented higher discrimination capacity but without statistical significance compared (AUROC=.738 for SAPS-II and AUROC=.673 for APACHE-II; P=.08). CONCLUSION NEWS2 is a better predictor of mortality than qSOFA and its implementation for the early recognition of the septic patient or the patient with higher risk in the emergency and hospitalization wards should be addressed. In addition, given that SOFA and SAPS-II showed better performance and are simpler than LODS and APACHE-II, respectively, both should be considered the scores of choice in this setting.
Collapse
Affiliation(s)
- Víctor Moreno-Torres
- Servicio de Medicina Interna, Hospital Universitario Puerta de Hierro-Majadahonda, Majadahonda, Madrid, España.
| | - Ana Royuela
- Unidad de Bioestadística Clínica, Instituto de Investigación Sanitaria Puerta de Hierro Segovia de Arana, Majadahonda, Madrid, España; Consorcio de Investigación Biomédica en Red de Epidemiología y Salud Pública (CIBERESP), Madrid, España
| | - Elena Múñez
- Servicio de Medicina Interna, Hospital Universitario Puerta de Hierro-Majadahonda, Majadahonda, Madrid, España
| | - Alfonso Ortega
- Unidad de Cuidados Intensivos, Hospital Universitario Puerta de Hierro-Majadahonda, Majadahonda, Madrid, España
| | - Ángela Gutierrez
- Servicio de Medicina Interna, Hospital Universitario Puerta de Hierro-Majadahonda, Majadahonda, Madrid, España
| | - Patricia Mills
- Servicio de Medicina Interna, Hospital Universitario Puerta de Hierro-Majadahonda, Majadahonda, Madrid, España
| | - Antonio Ramos-Martínez
- Servicio de Medicina Interna, Hospital Universitario Puerta de Hierro-Majadahonda, Majadahonda, Madrid, España
| |
Collapse
|
8
|
Guo Z, Guo B, Wang S, Zhang H, Zhang W, Qin B, Shao H. Impact of satellite blood culture on early diagnosis of sepsis. JOURNAL OF INTENSIVE MEDICINE 2021; 2:56-60. [PMID: 36789234 PMCID: PMC9924021 DOI: 10.1016/j.jointm.2021.11.003] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/03/2021] [Revised: 10/28/2021] [Accepted: 11/17/2021] [Indexed: 12/29/2022]
Abstract
Background The aim of this study was to assess whether satellite blood culture (SBC) can improve turnaround times, antibiotic switching, and patient prognosis, relative to laboratory blood culture (LBC). . Methods Patients with sepsis treated in the intensive care units (ICUs) of Henan Provincial People's Hospital from February 5, 2018 to January 19, 2019 who met the inclusion criteria were recruited to the study and divided into the SBC group and LBC group according to different blood culture methods. Patient demographics, blood culture, antibiotic adjustment, and prognosis data were collected and compared between the two groups. . Results A total of 204 blood culture sets from 52 ICU patients, including 100 from the medical microbiology LBC group and 104 from the SBC group, were analyzed in this study. There was no significant difference in the positive rates between the two groups. Time from specimen collection to incubation was significantly shorter in the SBC group than that in the LBC group (1.65 h vs. 3.51 h, z=-4.09, P<0.001). The median time from specimen collection to notification of blood culture positivity was 24.83 h in the SBC group and 27.83 h in the LBC group. Median times from adjustment of antibiotics according to the first report were 26.05 h and 51.71 h in the SBC and LBC groups, respectively, while those according to the final report were 97.17 h and 111.45 h, respectively. Median ICU lengths of stay were 15.00 days and 17.00 days in the SBC and LBC groups, respectively, and median ICU lengths of stay were 18.00 days and 23.50 days, respectively. Mean hospitalization costs were 157.99 and 186.73 thousand yuan in the SBC and LBC groups, respectively. . Conclusion SBC can significantly reduce blood culture turnaround times; however, there were no significant differences between the two blood culture methods in initial reporting of positive cultures, time to adjustment of antibiotic therapy, or medical costs, despite a trend toward improvement.
Collapse
Affiliation(s)
- Ziqi Guo
- Department of Critical Care Medicine, Henan University People's Hospital, Zhengzhou, Henan 455000, China,Department of Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000,China,Henan Key Laboratory for Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000, China
| | - Bo Guo
- Department of Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000,China,Henan Key Laboratory for Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000, China,Department of Critical Care Medicine, Zhengzhou University People's Hospital, Zhengzhou, Henan 455000, China
| | - Shanmei Wang
- Department of Microbiology Laboratory, Henan Provincial People's Hospital, Zhengzhou, Henan 455000, China
| | - Huifeng Zhang
- Department of Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000,China,Henan Key Laboratory for Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000, China,Department of Critical Care Medicine, Zhengzhou University People's Hospital, Zhengzhou, Henan 455000, China
| | - Wenxiao Zhang
- Department of Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000,China,Henan Key Laboratory for Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000, China,Department of Critical Care Medicine, Zhengzhou University People's Hospital, Zhengzhou, Henan 455000, China
| | - Bingyu Qin
- Department of Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000,China,Henan Key Laboratory for Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000, China,Department of Critical Care Medicine, Zhengzhou University People's Hospital, Zhengzhou, Henan 455000, China
| | - Huanzhang Shao
- Department of Critical Care Medicine, Henan University People's Hospital, Zhengzhou, Henan 455000, China,Department of Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000,China,Henan Key Laboratory for Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000, China,Department of Critical Care Medicine, Zhengzhou University People's Hospital, Zhengzhou, Henan 455000, China,Corresponding author: Huanzhang Shao, Department of Critical Care Medicine, Henan Provincial People's Hospital, Zhengzhou, Henan 455000, China.
| |
Collapse
|
9
|
Kuo YY, Huang ST, Chiu HW. Applying artificial neural network for early detection of sepsis with intentionally preserved highly missing real-world data for simulating clinical situation. BMC Med Inform Decis Mak 2021; 21:290. [PMID: 34686163 PMCID: PMC8539833 DOI: 10.1186/s12911-021-01653-0] [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: 07/02/2021] [Accepted: 10/12/2021] [Indexed: 12/12/2022] Open
Abstract
Purpose Some predictive systems using machine learning models have been developed to predict sepsis; however, they were mostly built with a low percent of missing values, which does not correspond with the actual clinical situation. In this study, we developed a machine learning model with a high rate of missing and erroneous data to enable prediction under missing, noisy, and erroneous inputs, as in the actual clinical situation. Materials and methods The proposed artificial neural network model was implemented using the MATLAB ANN toolbox, based on stochastic gradient descent. The dataset was collected over the past decade with approval from the appropriate institutional review boards, and the sepsis status was identified and labeled using Sepsis-3 clinical criteria. The imputation method was built by last observation carried forward and mean value, aimed to simulate clinical situation. Results The mean area under the receiver operating characteristic (ROC) curve (AUC) of classifying sepsis and nonsepsis patients was 0.82 and 0.786 at 0 h and 40 h prior to onset, respectively. The highest model performance was found for one-hourly data, demonstrating that our ANN model can perform adequately with limited hourly data provided. Conclusions Our model has the moderate ability to predict sepsis up to 40 h in advance under simulated clinical situation with real-world data.
Collapse
Affiliation(s)
- Yao-Yi Kuo
- School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan
| | - Shu-Tien Huang
- Department of Emergency Medicine, Mackay Memorial Hospital, Taipei, Taiwan
| | - Hung-Wen Chiu
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.
| |
Collapse
|
10
|
Giacobbe DR, Signori A, Del Puente F, Mora S, Carmisciano L, Briano F, Vena A, Ball L, Robba C, Pelosi P, Giacomini M, Bassetti M. Early Detection of Sepsis With Machine Learning Techniques: A Brief Clinical Perspective. Front Med (Lausanne) 2021; 8:617486. [PMID: 33644097 PMCID: PMC7906970 DOI: 10.3389/fmed.2021.617486] [Citation(s) in RCA: 25] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2020] [Accepted: 01/19/2021] [Indexed: 12/15/2022] Open
Abstract
Sepsis is a major cause of death worldwide. Over the past years, prediction of clinically relevant events through machine learning models has gained particular attention. In the present perspective, we provide a brief, clinician-oriented vision on the following relevant aspects concerning the use of machine learning predictive models for the early detection of sepsis in the daily practice: (i) the controversy of sepsis definition and its influence on the development of prediction models; (ii) the choice and availability of input features; (iii) the measure of the model performance, the output, and their usefulness in the clinical practice. The increasing involvement of artificial intelligence and machine learning in health care cannot be disregarded, despite important pitfalls that should be always carefully taken into consideration. In the long run, a rigorous multidisciplinary approach to enrich our understanding in the application of machine learning techniques for the early recognition of sepsis may show potential to augment medical decision-making when facing this heterogeneous and complex syndrome.
Collapse
Affiliation(s)
- Daniele Roberto Giacobbe
- Infectious Diseases Unit, San Martino Policlinico Hospital – IRCCS for Oncology and Neurosciences, Genoa, Italy
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| | - Alessio Signori
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| | - Filippo Del Puente
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| | - Sara Mora
- Department of Informatics Bioengineering, Robotics, and Systems Engineering (DIBRIS), University of Genoa, Genoa, Italy
| | - Luca Carmisciano
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| | - Federica Briano
- Infectious Diseases Unit, San Martino Policlinico Hospital – IRCCS for Oncology and Neurosciences, Genoa, Italy
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| | - Antonio Vena
- Infectious Diseases Unit, San Martino Policlinico Hospital – IRCCS for Oncology and Neurosciences, Genoa, Italy
| | - Lorenzo Ball
- Anaesthesia and Intensive Care, San Martino Policlinico Hospital – IRCCS for Oncology and Neurosciences, Genoa, Italy
- Department of Surgical Sciences and Integrated Diagnostics (DISC), University of Genoa, Genoa, Italy
| | - Chiara Robba
- Anaesthesia and Intensive Care, San Martino Policlinico Hospital – IRCCS for Oncology and Neurosciences, Genoa, Italy
- Department of Surgical Sciences and Integrated Diagnostics (DISC), University of Genoa, Genoa, Italy
| | - Paolo Pelosi
- Anaesthesia and Intensive Care, San Martino Policlinico Hospital – IRCCS for Oncology and Neurosciences, Genoa, Italy
- Department of Surgical Sciences and Integrated Diagnostics (DISC), University of Genoa, Genoa, Italy
| | - Mauro Giacomini
- Department of Informatics Bioengineering, Robotics, and Systems Engineering (DIBRIS), University of Genoa, Genoa, Italy
| | - Matteo Bassetti
- Infectious Diseases Unit, San Martino Policlinico Hospital – IRCCS for Oncology and Neurosciences, Genoa, Italy
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| |
Collapse
|
11
|
Chicco D, Jurman G. Survival prediction of patients with sepsis from age, sex, and septic episode number alone. Sci Rep 2020; 10:17156. [PMID: 33051513 PMCID: PMC7555553 DOI: 10.1038/s41598-020-73558-3] [Citation(s) in RCA: 18] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2020] [Accepted: 09/15/2020] [Indexed: 12/14/2022] Open
Abstract
Sepsis is a life-threatening condition caused by an exaggerated reaction of the body to an infection, that leads to organ failure or even death. Since sepsis can kill a patient even in just one hour, survival prediction is an urgent priority among the medical community: even if laboratory tests and hospital analyses can provide insightful information about the patient, in fact, they might not come in time to allow medical doctors to recognize an immediate death risk and treat it properly. In this context, machine learning can be useful to predict survival of patients within minutes, especially when applied to few medical features easily retrievable. In this study, we show that it is possible to achieve this goal by applying computational intelligence algorithms to three features of patients with sepsis, recorded at hospital admission: sex, age, and septic episode number. We applied several data mining methods to a cohort of 110,204 admissions of patients, and obtained high prediction scores both on this complete dataset (top precision-recall area under the curve PR AUC = 0.966) and on its subset related to the recent Sepsis-3 definition (top PR AUC = 0.860). Additionally, we tested our models on an external validation cohort of 137 patients, and achieved good results in this case too (top PR AUC = 0.863), confirming the generalizability of our approach. Our results can have a huge impact on clinical settings, allowing physicians to forecast the survival of patients by sex, age, and septic episode number alone.
Collapse
|