1
|
Kiss B, Nagy R, Kói T, Harnos A, Édes IF, Ábrahám P, Mészáros H, Hegyi P, Zima E. Prediction performance of scoring systems after out-of-hospital cardiac arrest: A systematic review and meta-analysis. PLoS One 2024; 19:e0293704. [PMID: 38300929 PMCID: PMC10833585 DOI: 10.1371/journal.pone.0293704] [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] [Received: 06/02/2023] [Accepted: 10/17/2023] [Indexed: 02/03/2024] Open
Abstract
INTRODUCTION Ongoing changes in post resuscitation medicine and society create a range of ethical challenges for clinicians. Withdrawal of life-sustaining treatment is a very sensitive, complex decision to be made by the treatment team and the relatives together. According to the guidelines, prognostication after cardiopulmonary resuscitation should be based on a combination of clinical examination, biomarkers, imaging, and electrophysiological testing. Several prognostic scores exist to predict neurological and mortality outcome in post-cardiac arrest patients. We aimed to perform a meta-analysis and systematic review of current scoring systems used after out-of-hospital cardiac arrest (OHCA). MATERIALS AND METHODS Our systematic search was conducted in four databases: Medline, Embase, Central and Scopus on 24th April 2023. The patient population consisted of successfully resuscitated adult patients after OHCA. We included all prognostic scoring systems in our analysis suitable to estimate neurologic function as the primary outcome and mortality as the secondary outcome. For each score and outcome, we collected the AUC (area under curve) values and their CIs (confidence iterval) and performed a random-effects meta-analysis to obtain pooled AUC estimates with 95% CI. To visualize the trade-off between sensitivity and specificity achieved using different thresholds, we created the Summary Receiver Operating Characteristic (SROC) curves. RESULTS 24,479 records were identified, 51 of which met the selection criteria and were included in the qualitative analysis. Of these, 24 studies were included in the quantitative synthesis. The performance of CAHP (Cardiac Arrest Hospital Prognosis) (0.876 [0.853-0.898]) and OHCA (0.840 [0.824-0.856]) was good to predict neurological outcome at hospital discharge, and TTM (Targeted Temperature Management) (0.880 [0.844-0.916]), CAHP (0.843 [0.771-0.915]) and OHCA (0.811 [0.759-0.863]) scores predicted good the 6-month neurological outcome. We were able to confirm the superiority of the CAHP score especially in the high specificity range based on our sensitivity and specificity analysis. CONCLUSION Based on our results CAHP is the most accurate scoring system for predicting the neurological outcome at hospital discharge and is a bit less accurate than TTM score for the 6-month outcome. We recommend the use of the CAHP scoring system in everyday clinical practice not only because of its accuracy and the best performance concerning specificity but also because of the rapid and easy availability of the necessary clinical data for the calculation.
Collapse
Affiliation(s)
- Boldizsár Kiss
- Heart and Vascular Centre, Semmelweis University, Budapest, Hungary
- Centre for Translational Medicine, Semmelweis University, Budapest, Hungary
| | - Rita Nagy
- Centre for Translational Medicine, Semmelweis University, Budapest, Hungary
- Heim Pál National Pediatric Insitute, Budapest, Hungary
- Institute for Translational Medicine, Medical School, University of Pécs, Pécs, Hungary
| | - Tamás Kói
- Centre for Translational Medicine, Semmelweis University, Budapest, Hungary
- Mathematical Institute, Budapest University of Technology and Economics, Budapest, Hungary
| | - Andrea Harnos
- Centre for Translational Medicine, Semmelweis University, Budapest, Hungary
- Department of Biostatistics, University of Veterinary Medicine, Budapest, Hungary
| | | | - Pál Ábrahám
- Heart and Vascular Centre, Semmelweis University, Budapest, Hungary
| | - Henriette Mészáros
- Heart and Vascular Centre, Semmelweis University, Budapest, Hungary
- Centre for Translational Medicine, Semmelweis University, Budapest, Hungary
| | - Péter Hegyi
- Centre for Translational Medicine, Semmelweis University, Budapest, Hungary
- Institute for Translational Medicine, Medical School, University of Pécs, Pécs, Hungary
- Institute for Pancreatic Diseases, Semmelweis University, Budapest, Hungary
| | - Endre Zima
- Heart and Vascular Centre, Semmelweis University, Budapest, Hungary
| |
Collapse
|
2
|
Chou SY, Bamodu OA, Chiu WT, Hong CT, Chan L, Chung CC. Artificial neural network-boosted Cardiac Arrest Survival Post-Resuscitation In-hospital (CASPRI) score accurately predicts outcome in cardiac arrest patients treated with targeted temperature management. Sci Rep 2022; 12:7254. [PMID: 35508580 PMCID: PMC9068683 DOI: 10.1038/s41598-022-11201-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2021] [Accepted: 04/14/2022] [Indexed: 01/04/2023] Open
Abstract
Existing prognostic models to predict the neurological recovery in patients with cardiac arrest receiving targeted temperature management (TTM) either exhibit moderate accuracy or are too complicated for clinical application. This necessitates the development of a simple and generalizable prediction model to inform clinical decision-making for patients receiving TTM. The present study explores the predictive validity of the Cardiac Arrest Survival Post-resuscitation In-hospital (CASPRI) score in cardiac arrest patients receiving TTM, regardless of cardiac event location, and uses artificial neural network (ANN) algorithms to boost the prediction performance. This retrospective observational study evaluated the prognostic relevance of the CASPRI score and applied ANN to develop outcome prediction models in a cohort of 570 patients with cardiac arrest and treated with TTM between 2014 and 2019 in a nationwide multicenter registry in Taiwan. In univariate logistic regression analysis, the CASPRI score was significantly associated with neurological outcome, with the area under the receiver operating characteristics curve (AUC) of 0.811. The generated ANN model, based on 10 items of the CASPRI score, achieved a training AUC of 0.976 and validation AUC of 0.921, with the accuracy, precision, sensitivity, and specificity of 89.2%, 91.6%, 87.6%, and 91.2%, respectively, for the validation set. CASPRI score has prognostic relevance in patients who received TTM after cardiac arrest. The generated ANN-boosted, CASPRI-based model exhibited good performance for predicting TTM neurological outcome, thus, we propose its clinical application to improve outcome prediction, facilitate decision-making, and formulate individualized therapeutic plans for patients receiving TTM.
Collapse
Affiliation(s)
- Szu-Yi Chou
- Graduate Institute of Neural Regenerative Medicine, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan, ROC.,Ph.D. Program for Neural Regenerative Medicine, College of Medical Science and Technology, Taipei Medical University and National Health Research Institutes, Taipei, Taiwan, ROC
| | - Oluwaseun Adebayo Bamodu
- Department of Medical Research & Education, Shuang Ho Hospital, Taipei Medical University, New Taipei City, 235, Taiwan, ROC.,Department of Urology, Shuang Ho Hospital, Taipei Medical University, New Taipei City, 235, Taiwan, ROC.,Department of Hematology & Oncology, Shuang Ho Hospital, Taipei Medical University, New Taipei City, 235, Taiwan, ROC
| | - Wei-Ting Chiu
- Department of Neurology, Shuang Ho Hospital, Taipei Medical University, 291, Zhongzheng Road, Zhonghe District, New Taipei City, 235, Taiwan, ROC.,Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taipei City, 110, Taiwan, ROC.,Division of Critical Care Medicine, Department of Emergency and Critical Care Medicine, Taipei Medical University-Shuang Ho Hospital, New Taipei City, 235, Taiwan, ROC
| | - Chien-Tai Hong
- Department of Neurology, Shuang Ho Hospital, Taipei Medical University, 291, Zhongzheng Road, Zhonghe District, New Taipei City, 235, Taiwan, ROC.,Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taipei City, 110, Taiwan, ROC
| | - Lung Chan
- Department of Neurology, Shuang Ho Hospital, Taipei Medical University, 291, Zhongzheng Road, Zhonghe District, New Taipei City, 235, Taiwan, ROC. .,Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taipei City, 110, Taiwan, ROC.
| | - Chen-Chih Chung
- Department of Neurology, Shuang Ho Hospital, Taipei Medical University, 291, Zhongzheng Road, Zhonghe District, New Taipei City, 235, Taiwan, ROC. .,Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taipei City, 110, Taiwan, ROC. .,Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei City, 110, Taiwan, ROC.
| |
Collapse
|
3
|
Chiu WT, Chung CC, Huang CH, Chien YS, Hsu CH, Wu CH, Wang CH, Chiu HW, Chan L. Predicting the survivals and favorable neurologic outcomes after targeted temperature management by artificial neural networks. J Formos Med Assoc 2021; 121:490-499. [PMID: 34330620 DOI: 10.1016/j.jfma.2021.07.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2020] [Revised: 05/12/2021] [Accepted: 07/05/2021] [Indexed: 10/20/2022] Open
Abstract
BACKGROUND To identify the outcome-associated predictors and develop predictive models for patients receiving targeted temperature management (TTM) by artificial neural network (ANN). METHODS The derived cohort consisted of 580 patients with cardiac arrest and ROSC treated with TTM between January 2014 and August 2019. We evaluated the predictive value of parameters associated with survival and favorable neurologic outcome. ANN were applied for developing outcome prediction models. The generalizability of the models was assessed through 5-fold cross-validation. The performance of the models was assessed according to the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS The parameters associated with survival were age, duration of cardiopulmonary resuscitation, history of diabetes mellitus (DM), heart failure, end-stage renal disease (ESRD), systolic blood pressure (BP), diastolic BP, body temperature, motor response after ROSC, emergent coronary angiography or percutaneous coronary intervention (PCI), and the cooling methods. The parameters associated with the favorable neurologic outcomes were age, sex, DM, chronic obstructive pulmonary disease, ESRD, stroke, pre-arrest cerebral-performance category, BP, body temperature, motor response after ROSC, emergent coronary angiography or PCI, and cooling methods. After adequate training, ANN Model 1 to predict survival achieved an AUC of 0.80. Accuracy, sensitivity, and specificity were 75.9%, 71.6%, and 79.3%, respectively. ANN Model 4 to predict the favorable neurologic outcome achieved an AUC of 0.87, with accuracy, sensitivity, and specificity of 86.7%, 77.7%, and 88.0%, respectively. CONCLUSIONS The ANN-based models achieved good performance to predict the survival and favorable neurologic outcomes after TTM. The models proposed have clinical value to assist in decision-making.
Collapse
Affiliation(s)
- Wei-Ting Chiu
- Department of Neurology, Shuang Ho Hospital, Taipei Medical University, Taiwan; Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taiwan; Taipei Neuroscience Institute, Taipei Medical University, Taiwan; Division of Critical Care Medicine, Department of Emergency and Critical Care Medicine, Shuang Ho Hospital, Taipei Medical University, Taipei, Taiwan
| | - Chen-Chih Chung
- Department of Neurology, Shuang Ho Hospital, Taipei Medical University, Taiwan; Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taiwan; Taipei Neuroscience Institute, Taipei Medical University, Taiwan; Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan
| | - Chien-Hua Huang
- Department of Emergency Medicine, National Taiwan University Medical College and Hospital, Taipei, Taiwan; Cardiovascular Division, Department of Internal Medicine, National Taiwan University College of Medicine and Hospital, Taiwan
| | - Yu-San Chien
- Department of Critical Care Medicine, MacKay Memorial Hospital, Taipei Branch, Taiwan
| | - Chih-Hsin Hsu
- Division of Cardiology, Department of Internal Medicine, National Cheng Kung University Hospital Dou Liou Branch, College of Medicine, National Cheng Kung University, Taiwan
| | - Cheng-Hsueh Wu
- Department of Critical Care Medicine, Taipei Veterans General Hospital, National Yang-Ming University, Taipei, Taiwan
| | - Chen-Hsu Wang
- Attending Physician, Coronary Care Unit, Cardiovascular Center, Cathay General Hospital, Taipei, Taiwan
| | - Hung-Wen Chiu
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan; Clinical Big Data Research Center, Taipei Medical University Hospital, Taiwan
| | - Lung Chan
- Department of Neurology, Shuang Ho Hospital, Taipei Medical University, Taiwan; Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taiwan; Taipei Neuroscience Institute, Taipei Medical University, Taiwan.
| |
Collapse
|