1
|
Bomrah S, Uddin M, Upadhyay U, Komorowski M, Priya J, Dhar E, Hsu SC, Syed-Abdul S. A scoping review of machine learning for sepsis prediction- feature engineering strategies and model performance: a step towards explainability. Crit Care 2024; 28:180. [PMID: 38802973 PMCID: PMC11131234 DOI: 10.1186/s13054-024-04948-6] [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: 02/26/2024] [Accepted: 05/10/2024] [Indexed: 05/29/2024] Open
Abstract
BACKGROUND Sepsis, an acute and potentially fatal systemic response to infection, significantly impacts global health by affecting millions annually. Prompt identification of sepsis is vital, as treatment delays lead to increased fatalities through progressive organ dysfunction. While recent studies have delved into leveraging Machine Learning (ML) for predicting sepsis, focusing on aspects such as prognosis, diagnosis, and clinical application, there remains a notable deficiency in the discourse regarding feature engineering. Specifically, the role of feature selection and extraction in enhancing model accuracy has been underexplored. OBJECTIVES This scoping review aims to fulfill two primary objectives: To identify pivotal features for predicting sepsis across a variety of ML models, providing valuable insights for future model development, and To assess model efficacy through performance metrics including AUROC, sensitivity, and specificity. RESULTS The analysis included 29 studies across diverse clinical settings such as Intensive Care Units (ICU), Emergency Departments, and others, encompassing 1,147,202 patients. The review highlighted the diversity in prediction strategies and timeframes. It was found that feature extraction techniques notably outperformed others in terms of sensitivity and AUROC values, thus indicating their critical role in improving sepsis prediction models. CONCLUSION Key dynamic indicators, including vital signs and critical laboratory values, are instrumental in the early detection of sepsis. Applying feature selection methods significantly boosts model precision, with models like Random Forest and XG Boost showing promising results. Furthermore, Deep Learning models (DL) reveal unique insights, spotlighting the pivotal role of feature engineering in sepsis prediction, which could greatly benefit clinical practice.
Collapse
Affiliation(s)
- Sherali Bomrah
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, No. 291, Zhongzheng Rd, Zhonghe District, New Taipei City, 235, Taiwan
- International Center for Health Information Technology, College of Medical Science and Technology, Taipei Medical University, Taipei, 235, Taiwan
- College of Medicine, Taipei Medical University, Taipei, 110, Taiwan
| | - Mohy Uddin
- Research Quality Management Section, King Abdullah International Medical Research Center, King Saud Bin Abdulaziz University for Health Sciences, Ministry of National Guard-Health Affairs, 11426, Riyadh, Saudi Arabia
| | - Umashankar Upadhyay
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, No. 291, Zhongzheng Rd, Zhonghe District, New Taipei City, 235, Taiwan
- International Center for Health Information Technology, College of Medical Science and Technology, Taipei Medical University, Taipei, 235, Taiwan
- School of Biotechnology and Applied Sciences, Shoolini University of Biotechnology and Management Sciences, Solan, 173229, India
| | - Matthieu Komorowski
- Faculty of Medicine, Department of Surgery and Cancer, Imperial College of London, South Kensington Campus, London, UK
| | - Jyoti Priya
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, No. 291, Zhongzheng Rd, Zhonghe District, New Taipei City, 235, Taiwan
- International Center for Health Information Technology, College of Medical Science and Technology, Taipei Medical University, Taipei, 235, Taiwan
| | - Eshita Dhar
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, No. 291, Zhongzheng Rd, Zhonghe District, New Taipei City, 235, Taiwan
- International Center for Health Information Technology, College of Medical Science and Technology, Taipei Medical University, Taipei, 235, Taiwan
| | - Shih-Chang Hsu
- Department of Emergency, School of Medicine, College of Medicine, Taipei Medical University, Taipei, 106, Taiwan
- Emergency Department, Wan Fang Hospital, Taipei Medical University, Taipei, 116, Taiwan
| | - Shabbir Syed-Abdul
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, No. 291, Zhongzheng Rd, Zhonghe District, New Taipei City, 235, Taiwan.
- International Center for Health Information Technology, College of Medical Science and Technology, Taipei Medical University, Taipei, 235, Taiwan.
- School of Gerontology and Long-Term Care, College of Nursing, Taipei Medical University, Taipei, Taiwan.
| |
Collapse
|
2
|
Yoon SJ, Kim D, Park SH, Han JH, Lim J, Shin JE, Eun HS, Lee SM, Park MS. Prediction of Postnatal Growth Failure in Very Low Birth Weight Infants Using a Machine Learning Model. Diagnostics (Basel) 2023; 13:3627. [PMID: 38132211 PMCID: PMC10743090 DOI: 10.3390/diagnostics13243627] [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: 10/31/2023] [Revised: 12/04/2023] [Accepted: 12/06/2023] [Indexed: 12/23/2023] Open
Abstract
Accurate prediction of postnatal growth failure (PGF) can be beneficial for early intervention and prevention. We aimed to develop a machine learning model to predict PGF at discharge among very low birth weight (VLBW) infants using extreme gradient boosting. A total of 729 VLBW infants, born between 2013 and 2017 in four hospitals, were included. PGF was defined as a decrease in z-score between birth and discharge that was greater than 1.28. Feature selection and addition were performed to improve the accuracy of prediction at four different time points, including 0, 7, 14, and 28 days after birth. A total of 12 features with high contribution at all time points by feature importance were decided upon, and good performance was shown as an area under the receiver operating characteristic curve (AUROC) of 0.78 at 7 days. After adding weight change to the 12 features-which included sex, gestational age, birth weight, small for gestational age, maternal hypertension, respiratory distress syndrome, duration of invasive ventilation, duration of non-invasive ventilation, patent ductus arteriosus, sepsis, use of parenteral nutrition, and reach at full enteral nutrition-the AUROC at 7 days after birth was shown as 0.84. Our prediction model for PGF performed well at early detection. Its potential clinical application as a supplemental tool could be helpful for reducing PGF and improving child health.
Collapse
Affiliation(s)
- So Jin Yoon
- Department of Pediatrics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea; (S.J.Y.)
| | - Donghyun Kim
- Department of Advanced General Dentistry, Yonsei University College of Dentistry, Seoul 03722, Republic of Korea
- InVisionLab Inc., Seoul 05854, Republic of Korea
| | - Sook Hyun Park
- Department of Pediatrics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea; (S.J.Y.)
| | - Jung Ho Han
- Department of Pediatrics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea; (S.J.Y.)
| | - Joohee Lim
- Department of Pediatrics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea; (S.J.Y.)
| | - Jeong Eun Shin
- Department of Pediatrics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea; (S.J.Y.)
| | - Ho Seon Eun
- Department of Pediatrics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea; (S.J.Y.)
| | - Soon Min Lee
- Department of Pediatrics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea; (S.J.Y.)
| | - Min Soo Park
- Department of Pediatrics, Yonsei University College of Medicine, Seoul 03722, Republic of Korea; (S.J.Y.)
| |
Collapse
|
3
|
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
|
4
|
Strickler EAT, Thomas J, Thomas JP, Benjamin B, Shamsuddin R. Exploring a global interpretation mechanism for deep learning networks when predicting sepsis. Sci Rep 2023; 13:3067. [PMID: 36810645 PMCID: PMC9945464 DOI: 10.1038/s41598-023-30091-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2022] [Accepted: 02/15/2023] [Indexed: 02/24/2023] Open
Abstract
The purpose of this study is to identify additional clinical features for sepsis detection through the use of a novel mechanism for interpreting black-box machine learning models trained and to provide a suitable evaluation for the mechanism. We use the publicly available dataset from the 2019 PhysioNet Challenge. It has around 40,000 Intensive Care Unit (ICU) patients with 40 physiological variables. Using Long Short-Term Memory (LSTM) as the representative black-box machine learning model, we adapted the Multi-set Classifier to globally interpret the black-box model for concepts it learned about sepsis. To identify relevant features, the result is compared against: (i) features used by a computational sepsis expert, (ii) clinical features from clinical collaborators, (iii) academic features from literature, and (iv) significant features from statistical hypothesis testing. Random Forest was found to be the computational sepsis expert because it had high accuracies for solving both the detection and early detection, and a high degree of overlap with clinical and literature features. Using the proposed interpretation mechanism and the dataset, we identified 17 features that the LSTM used for sepsis classification, 11 of which overlaps with the top 20 features from the Random Forest model, 10 with academic features and 5 with clinical features. Clinical opinion suggests, 3 LSTM features have strong correlation with some clinical features that were not identified by the mechanism. We also found that age, chloride ion concentration, pH and oxygen saturation should be investigated further for connection with developing sepsis. Interpretation mechanisms can bolster the incorporation of state-of-the-art machine learning models into clinical decision support systems, and might help clinicians to address the issue of early sepsis detection. The promising results from this study warrants further investigation into creation of new and improvement of existing interpretation mechanisms for black-box models, and into clinical features that are currently not used in clinical assessment of sepsis.
Collapse
Affiliation(s)
- Ethan A T Strickler
- Physics and Mathematics, East Central University, PO Box 385, Ada, OK, 74820, USA
| | - Joshua Thomas
- Department of Internal Medicine, Rush University Medical Center, 1700 W Van Buren St, 5th Floor, Chicago, IL, 60612, USA
| | - Johnson P Thomas
- Oklahoma State University, 201 Math and Science Building, Stillwater, OK, 74078, USA
| | - Bruce Benjamin
- School of Biomedical Sciences, Center for Health Sciences, 1111 W. 17th st., Tulsa, OK, 74107, USA
| | - Rittika Shamsuddin
- Oklahoma State University, 212 Math and Science Building, Stillwater, OK, 74078, USA.
| |
Collapse
|
5
|
Chen Q, Li R, Lin C, Lai C, Huang Y, Lu W, Li L. SEPRES: Intensive Care Unit Clinical Data Integration System to Predict Sepsis. Appl Clin Inform 2023; 14:65-75. [PMID: 36452980 PMCID: PMC9876660 DOI: 10.1055/a-1990-3037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2022] [Accepted: 11/28/2022] [Indexed: 12/05/2022] Open
Abstract
BACKGROUND The lack of information interoperability between different devices and systems in the intensive care unit (ICU) hinders further utilization of data, especially for early warning of specific diseases in the ICU. OBJECTIVES We aimed to establish a data integration system. Based on this system, the sepsis prediction module was added to compose the Sepsis PREdiction System (SEPRES), where real-time early warning of sepsis can be implemented at the bedside in the ICU. METHODS Data are collected from bedside devices through the integration hub and uploaded to the integration system through the local area network. The data integration system was designed to integrate vital signs data, laboratory data, ventilator data, demographic data, pharmacy data, nursing data, etc. from multiple medical devices and systems. It integrates, standardizes, and stores information, making the real-time inference of the early warning module possible. The built-in sepsis early warning module can detect the onset of sepsis within 5 hours preceding at most. RESULTS Our data integration system has already been deployed in Ruijin Hospital, confirming the feasibility of our system. CONCLUSION We highlight that SEPRES has the potential to improve ICU management by helping medical practitioners identify at-sepsis-risk patients and prepare for timely diagnosis and intervention.
Collapse
Affiliation(s)
- Qiyu Chen
- Division of Applied Mathematics, Fudan University, Shanghai, China
| | - Ranran Li
- Department of Critical Care Medicine, Shanghai Jiaotong University School of Medicine, Ruijin Hospital, Shanghai, China
| | - ChihChe Lin
- Department of Intelligent Medical Products, Shanghai Electric Group Co., Ltd. Central Academe, Shanghai, China
| | - Chiming Lai
- Department of Intelligent Medical Products, Shanghai Electric Group Co., Ltd. Central Academe, Shanghai, China
| | - Yaling Huang
- Department of Intelligent Medical Products, Shanghai Electric Group Co., Ltd. Central Academe, Shanghai, China
| | - Wenlian Lu
- Division of Applied Mathematics, Fudan University, Shanghai, China
| | - Lei Li
- Department of Critical Care Medicine, Shanghai Jiaotong University School of Medicine, Ruijin Hospital, Shanghai, China
| |
Collapse
|
6
|
Chen Q, Li R, Lin C, Lai C, Chen D, Qu H, Huang Y, Lu W, Tang Y, Li L. Transferability and interpretability of the sepsis prediction models in the intensive care unit. BMC Med Inform Decis Mak 2022; 22:343. [PMID: 36581881 PMCID: PMC9798724 DOI: 10.1186/s12911-022-02090-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2022] [Accepted: 12/16/2022] [Indexed: 12/31/2022] Open
Abstract
BACKGROUND We aimed to develop an early warning system for real-time sepsis prediction in the ICU by machine learning methods, with tools for interpretative analysis of the predictions. In particular, we focus on the deployment of the system in a target medical center with small historical samples. METHODS Light Gradient Boosting Machine (LightGBM) and multilayer perceptron (MLP) were trained on Medical Information Mart for Intensive Care (MIMIC-III) dataset and then finetuned on the private Historical Database of local Ruijin Hospital (HDRJH) using transfer learning technique. The Shapley Additive Explanations (SHAP) analysis was employed to characterize the feature importance in the prediction inference. Ultimately, the performance of the sepsis prediction system was further evaluated in the real-world study in the ICU of the target Ruijin Hospital. RESULTS The datasets comprised 6891 patients from MIMIC-III, 453 from HDRJH, and 67 from Ruijin real-world data. The area under the receiver operating characteristic curves (AUCs) for LightGBM and MLP models derived from MIMIC-III were 0.98 - 0.98 and 0.95 - 0.96 respectively on MIMIC-III dataset, and, in comparison, 0.82 - 0.86 and 0.84 - 0.87 respectively on HDRJH, from 1 to 5 h preceding. After transfer learning and ensemble learning, the AUCs of the final ensemble model were enhanced to 0.94 - 0.94 on HDRJH and to 0.86 - 0.9 in the real-world study in the ICU of the target Ruijin Hospital. In addition, the SHAP analysis illustrated the importance of age, antibiotics, net balance, and ventilation for sepsis prediction, making the model interpretable. CONCLUSIONS Our machine learning model allows accurate real-time prediction of sepsis within 5-h preceding. Transfer learning can effectively improve the feasibility to deploy the prediction model in the target cohort, and ameliorate the model performance for external validation. SHAP analysis indicates that the role of antibiotic usage and fluid management needs further investigation. We argue that our system and methodology have the potential to improve ICU management by helping medical practitioners identify at-sepsis-risk patients and prepare for timely diagnosis and intervention. TRIAL REGISTRATION NCT05088850 (retrospectively registered).
Collapse
Affiliation(s)
- Qiyu Chen
- grid.8547.e0000 0001 0125 2443Department of Applied Mathematics, School of Mathematical Sciences, Fudan University, Shanghai, 200433 China
| | - Ranran Li
- grid.16821.3c0000 0004 0368 8293Department of Critical Care Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025 China
| | - ChihChe Lin
- grid.495525.a0000 0004 0552 4356Shanghai Electric Group Co., Ltd., Central Academe, Shanghai, China
| | - Chiming Lai
- grid.495525.a0000 0004 0552 4356Shanghai Electric Group Co., Ltd., Central Academe, Shanghai, China
| | - Dechang Chen
- grid.16821.3c0000 0004 0368 8293Department of Critical Care Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025 China
| | - Hongping Qu
- grid.16821.3c0000 0004 0368 8293Department of Critical Care Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025 China
| | - Yaling Huang
- grid.495525.a0000 0004 0552 4356Shanghai Electric Group Co., Ltd., Central Academe, Shanghai, China
| | - Wenlian Lu
- grid.8547.e0000 0001 0125 2443Department of Applied Mathematics, School of Mathematical Sciences, Fudan University, Shanghai, 200433 China
| | - Yaoqing Tang
- grid.16821.3c0000 0004 0368 8293Department of Critical Care Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025 China
| | - Lei Li
- grid.16821.3c0000 0004 0368 8293Department of Critical Care Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025 China
| |
Collapse
|
7
|
Sadasivuni S, Bhanushali SP, Banerjee I, Sanyal A. In-sensor neural network for high energy efficiency analog-to-information conversion. Sci Rep 2022; 12:18253. [PMID: 36309584 PMCID: PMC9617885 DOI: 10.1038/s41598-022-23100-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Accepted: 10/25/2022] [Indexed: 12/31/2022] Open
Abstract
This work presents an on-chip analog-to-information conversion technique that utilizes analog hyper-dimensional computing based on reservoir-computing paradigm to process electrocardiograph (ECG) signals locally in-sensor and reduce radio frequency transmission by more than three orders-of-magnitude. Instead of transmitting the naturally sparse ECG signal or extracted features, the on-chip analog-to-information converter analyzes the ECG signal through a nonlinear reservoir kernel followed by an artificial neural network, and transmits the prediction results. The proposed technique is demonstrated for detection of sepsis onset and achieves state-of-the-art accuracy and energy efficiency while reducing sensor power by [Formula: see text] with test-chips prototyped in 65 nm CMOS.
Collapse
Affiliation(s)
- Sudarsan Sadasivuni
- grid.273335.30000 0004 1936 9887Electrical Engineering, University at Buffalo, Buffalo, 14260 USA
| | - Sumukh Prashant Bhanushali
- grid.215654.10000 0001 2151 2636School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, 85287 USA
| | - Imon Banerjee
- grid.470142.40000 0004 0443 9766Mayo Clinic, Phoenix, 85054 USA
| | - Arindam Sanyal
- grid.215654.10000 0001 2151 2636School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, 85287 USA
| |
Collapse
|