1
|
Rahadian RE, Okada Y, Shahidah N, Hong D, Ng YY, Chia MY, Gan HN, Leong BS, Mao DR, Ng WM, Doctor NE, Ong MEH. Machine learning prediction of refractory ventricular fibrillation in out-of-hospital cardiac arrest using features available to EMS. Resusc Plus 2024; 18:100606. [PMID: 38533482 PMCID: PMC10963854 DOI: 10.1016/j.resplu.2024.100606] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 02/22/2024] [Accepted: 03/04/2024] [Indexed: 03/28/2024] Open
Abstract
Background Shock-refractory ventricular fibrillation (VF) or ventricular tachycardia (VT) is a treatment challenge in out-of-hospital cardiac arrest (OHCA). This study aimed to develop and validate machine learning models that could be implemented by emergency medical services (EMS) to predict refractory VF/VT in OHCA patients. Methods This was a retrospective study examining adult non-traumatic OHCA patients brought into the emergency department by Singapore EMS from the Pan-Asian Resuscitation Outcomes Study (PAROS) registry. Data from April 2010 to March 2020 were extracted for this study. Refractory VF/VT was defined as VF/VT persisting or recurring after at least one shock. Features were selected based on expert clinical opinion and availability to dispatch prior to arrival at scene. Multivariable logistic regression (MVR), LASSO and random forest (RF) models were investigated. Model performance was evaluated using receiver operator characteristic (ROC) area under curve (AUC) analysis and calibration plots. Results 20,713 patients were included in this study, of which 860 (4.1%) fulfilled the criteria for refractory VF/VT. All models performed comparably and were moderately well-calibrated. ROC-AUC were 0.732 (95% CI, 0.695 - 0.769) for MVR, 0.738 (95% CI, 0.701 - 0.774) for LASSO, and 0.731 (95% CI, 0.690 - 0.773) for RF. The shared important predictors across all models included male gender and public location. Conclusion The machine learning models developed have potential clinical utility to improve outcomes in cases of refractory VF/VT OHCA. Prediction of refractory VF/VT prior to arrival at patient's side may allow for increased options for intervention both by EMS and tertiary care centres.
Collapse
Affiliation(s)
| | - Yohei Okada
- Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
- Department of Preventive Services, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Nur Shahidah
- Department of Emergency Medicine, Singapore General Hospital, Singapore, Singapore
- Pre-hospital and Emergency Research Centre, Duke-NUS Medical School, Singapore
| | - Dehan Hong
- Emergency Medical Services Department, Singapore Civil Defence Force, Singapore
| | - Yih Yng Ng
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore
- Department of Preventive and Population Medicine, Tan Tock Seng Hospital, Singapore, Singapore
| | | | - Han Nee Gan
- Accident & Emergency, Changi General Hospital, Singapore, Singapore
| | - Benjamin S.H. Leong
- Emergency Medicine Department, National University Hospital, Singapore, Singapore
| | - Desmond R. Mao
- Department of Acute and Emergency Care, Khoo Teck Puat Hospital, Singapore, Singapore
| | - Wei Ming Ng
- Emergency Medicine Department, Ng Teng Fong General Hospital, Singapore, Singapore
| | | | - Marcus Eng Hock Ong
- Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
- Department of Emergency Medicine, Singapore General Hospital, Singapore, Singapore
| |
Collapse
|
2
|
Drumheller BC, Tam J, Schatz KW, Doshi AA. Use of resuscitative endovascular balloon occlusion of the aorta (REBOA) and ultrasound-guided left stellate ganglion block to rescue out of hospital cardiac arrest due to refractory ventricular fibrillation: A case report. Resusc Plus 2024; 17:100524. [PMID: 38162991 PMCID: PMC10755478 DOI: 10.1016/j.resplu.2023.100524] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Revised: 11/20/2023] [Accepted: 11/23/2023] [Indexed: 01/03/2024] Open
Abstract
Out of hospital cardiac arrest from shockable rhythms that is refractory to standard treatment is a unique challenge. Such patients can achieve neurological recovery even with long low-flow times if perfusion can somehow be restored to the heart and brain. Extracorporeal cardiopulmonary resuscitation is an effective treatment for refractory cardiac arrest if applied early and accurately, but often cannot be directly implemented by frontline providers and has strict inclusion/exclusion criteria. We present the case of a novel treatment strategy for out of hospital cardiac arrest due to refractory ventricular fibrillation utilizing Resuscitative Endovascular Balloon Occlusion of the Aorta-assisted cardiopulmonary resuscitation and intra-arrest left stellate ganglion blockade to achieve return of spontaneous circulation and eventual good neurological outcome after 101 minutes of downtime.
Collapse
Affiliation(s)
- Byron C. Drumheller
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
| | - Jonathan Tam
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
- Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
| | - Kimberly W. Schatz
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
| | - Ankur A. Doshi
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA
| |
Collapse
|
3
|
Chang H, Kim JW, Jung W, Heo S, Lee SU, Kim T, Hwang SY, Do Shin S, Cha WC. Machine learning pre-hospital real-time cardiac arrest outcome prediction (PReCAP) using time-adaptive cohort model based on the Pan-Asian Resuscitation Outcome Study. Sci Rep 2023; 13:20344. [PMID: 37990066 PMCID: PMC10663550 DOI: 10.1038/s41598-023-45767-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2023] [Accepted: 10/23/2023] [Indexed: 11/23/2023] Open
Abstract
To save time during transport, where resuscitation quality can degrade in a moving ambulance, it would be prudent to continue the resuscitation on scene if there is a high likelihood of ROSC occurring at the scene. We developed the pre-hospital real-time cardiac arrest outcome prediction (PReCAP) model to predict ROSC at the scene using prehospital input variables with time-adaptive cohort. The patient survival at discharge from the emergency department (ED), the 30-day survival rate, and the final Cerebral Performance Category (CPC) were secondary prediction outcomes in this study. The Pan-Asian Resuscitation Outcome Study (PAROS) database, which includes out-of-hospital cardiac arrest (OHCA) patients transferred by emergency medical service in Asia between 2009 and 2018, was utilized for this study. From the variables available in the PAROS database, we selected relevant variables to predict OHCA outcomes. Light gradient-boosting machine (LightGBM) was used to build the PReCAP model. Between 2009 and 2018, 157,654 patients in the PAROS database were enrolled in our study. In terms of prediction of ROSC on scene, the PReCAP had an AUROC score between 0.85 and 0.87. The PReCAP had an AUROC score between 0.91 and 0.93 for predicting survived to discharge from ED, and an AUROC score between 0.80 and 0.86 for predicting the 30-day survival. The PReCAP predicted CPC with an AUROC score ranging from 0.84 to 0.91. The feature importance differed with time in the PReCAP model prediction of ROSC on scene. Using the PAROS database, PReCAP predicted ROSC on scene, survival to discharge from ED, 30-day survival, and CPC for each minute with an AUROC score ranging from 0.8 to 0.93. As this model used a multi-national database, it might be applicable for a variety of environments and populations.
Collapse
Affiliation(s)
- Hansol Chang
- Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 115 Irwon-ro Gangnam-gu, Seoul, 06355, Republic of Korea
- Department of Digital Health, Samsung Advanced Institute for Health Science & Technology (SAIHST), Sungkyunkwan University, 115 Irwon-ro Gangnam-gu, Seoul, 06355, Republic of Korea
| | - Ji Woong Kim
- LG UPLUS, 71, Magokjungang 8-ro, Gangseo-gu, Seoul, 07795, Republic of Korea
| | - Weon Jung
- Smart Health Lab, Research Institute of Future Medicine, Samsung Medical Center, 81 Irwon-ro Gangnam-gu, Seoul, 06351, Korea
| | - Sejin Heo
- Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 115 Irwon-ro Gangnam-gu, Seoul, 06355, Republic of Korea
| | - Se Uk Lee
- Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 115 Irwon-ro Gangnam-gu, Seoul, 06355, Republic of Korea
| | - Taerim Kim
- Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 115 Irwon-ro Gangnam-gu, Seoul, 06355, Republic of Korea
| | - Sung Yeon Hwang
- Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 115 Irwon-ro Gangnam-gu, Seoul, 06355, Republic of Korea
| | - Sang Do Shin
- Department of Emergency Medicine, Seoul National University Hospital, Seoul, Korea
| | - Won Chul Cha
- Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 115 Irwon-ro Gangnam-gu, Seoul, 06355, Republic of Korea.
- Department of Digital Health, Samsung Advanced Institute for Health Science & Technology (SAIHST), Sungkyunkwan University, 115 Irwon-ro Gangnam-gu, Seoul, 06355, Republic of Korea.
- Digital Innovation, Samsung Medical Center, 81 Irwon-ro Gangnam-gu, Seoul, 06351, Republic of Korea.
- Department of Emergency Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea.
| |
Collapse
|
4
|
Lupton JR, Neth MR, Sahni R, Jui J, Wittwer L, Newgard CD, Daya MR. Survival by time-to-administration of amiodarone, lidocaine, or placebo in shock-refractory out-of-hospital cardiac arrest. Acad Emerg Med 2023; 30:906-917. [PMID: 36869657 DOI: 10.1111/acem.14716] [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: 12/08/2022] [Revised: 02/24/2023] [Accepted: 03/01/2023] [Indexed: 03/05/2023]
Abstract
BACKGROUND Amiodarone and lidocaine have not been shown to have a clear survival benefit compared to placebo for out-of-hospital cardiac arrest (OHCA). However, randomized trials may have been impacted by delayed administration of the study drugs. We sought to evaluate how timing from emergency medical services (EMS) arrival on scene to drug administration affects the efficacy of amiodarone and lidocaine compared to placebo. METHOD This is a secondary analysis of the 10-site, 55-EMS-agency double-blind randomized controlled amiodarone, lidocaine, or placebo in OHCA study. We included patients with initial shockable rhythms who received the study drugs of amiodarone, lidocaine, or placebo before achieving return of spontaneous circulation. We performed logistic regression analyses evaluating survival to hospital discharge and secondary outcomes of survival to admission and functional survival (modified Rankin scale score ≤ 3). We evaluated the samples stratified by early (<8 min) and late administration groups (≥8 min). We compared outcomes for amiodarone and lidocaine compared to placebo and adjust for potential confounders. RESULTS There were 2802 patients meeting inclusion criteria, with 879 (31.4%) in the early (<8 min) and 1923 (68.6%) in the late (≥8 min) groups. In the early group, patients receiving amiodarone, compared to placebo, had significantly higher survival to admission (62.0% vs. 48.5%, p = 0.001; adjusted OR [95% CI] 1.76 [1.24-2.50]), survival to discharge (37.1% vs. 28.0%, p = 0.021; 1.56 [1.07-2.29]), and functional survival (31.6% vs. 23.3%, p = 0.029; 1.55 [1.04-2.32]). There were no significant differences with early lidocaine compared to early placebo (p > 0.05). Patients in the late group who received amiodarone or lidocaine had no significant differences in outcomes at discharge compared to placebo (p > 0.05). CONCLUSIONS The early administration of amiodarone, particularly within 8 min, is associated with greater survival to admission, survival to discharge, and functional survival compared to placebo in patients with an initial shockable rhythm.
Collapse
Affiliation(s)
- Joshua R Lupton
- Department of Emergency Medicine, Oregon Health & Science University, Portland, Oregon, USA
| | - Matthew R Neth
- Department of Emergency Medicine, Oregon Health & Science University, Portland, Oregon, USA
| | - Ritu Sahni
- Department of Emergency Medicine, Oregon Health & Science University, Portland, Oregon, USA
| | - Jonathan Jui
- Department of Emergency Medicine, Oregon Health & Science University, Portland, Oregon, USA
| | - Lynn Wittwer
- Department of Emergency Medicine, Oregon Health & Science University, Portland, Oregon, USA
| | - Craig D Newgard
- Department of Emergency Medicine, Oregon Health & Science University, Portland, Oregon, USA
| | - Mohamud R Daya
- Department of Emergency Medicine, Oregon Health & Science University, Portland, Oregon, USA
| |
Collapse
|
5
|
Coult J, Yang BY, Kwok H, Kutz JN, Boyle PM, Blackwood J, Rea TD, Kudenchuk PJ. Prediction of Shock-Refractory Ventricular Fibrillation During Resuscitation of Out-of-Hospital Cardiac Arrest. Circulation 2023; 148:327-335. [PMID: 37264936 DOI: 10.1161/circulationaha.122.063651] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/14/2022] [Accepted: 05/08/2023] [Indexed: 06/03/2023]
Abstract
BACKGROUND Out-of-hospital cardiac arrest due to shock-refractory ventricular fibrillation (VF) is associated with relatively poor survival. The ability to predict refractory VF (requiring ≥3 shocks) in advance of repeated shock failure could enable preemptive targeted interventions aimed at improving outcome, such as earlier administration of antiarrhythmics, reconsideration of epinephrine use or dosage, changes in shock delivery strategy, or expedited invasive treatments. METHODS We conducted a cohort study of VF out-of-hospital cardiac arrest to develop an ECG-based algorithm to predict patients with refractory VF. Patients with available defibrillator recordings were randomized 80%/20% into training/test groups. A random forest classifier applied to 3-s ECG segments immediately before and 1 minute after the initial shock during cardiopulmonary resuscitation was used to predict the need for ≥3 shocks based on singular value decompositions of ECG wavelet transforms. Performance was quantified by area under the receiver operating characteristic curve. RESULTS Of 1376 patients with VF out-of-hospital cardiac arrest, 311 (23%) were female, 864 (63%) experienced refractory VF, and 591 (43%) achieved functional neurological survival. Total shock count was associated with decreasing likelihood of functional neurological survival, with a relative risk of 0.95 (95% CI, 0.93-0.97) for each successive shock (P<0.001). In the 275 test patients, the area under the receiver operating characteristic curve for predicting refractory VF was 0.85 (95% CI, 0.79-0.89), with specificity of 91%, sensitivity of 63%, and a positive likelihood ratio of 6.7. CONCLUSIONS A machine learning algorithm using ECGs surrounding the initial shock predicts patients likely to experience refractory VF, and could enable rescuers to preemptively target interventions to potentially improve resuscitation outcome.
Collapse
Affiliation(s)
- Jason Coult
- Department of Medicine (J.C., T.D.R.), University of Washington, Seattle
| | - Betty Y Yang
- Department of Emergency Medicine, University of Texas Southwestern Medical Center, Dallas (B.Y.Y.)
| | - Heemun Kwok
- Department of Applied Mathematics (J.N.K.), University of Washington, Seattle
| | - J Nathan Kutz
- Department of Applied Mathematics (J.N.K.), University of Washington, Seattle
| | - Patrick M Boyle
- Department of Bioengineering (P.M.B.), University of Washington, Seattle
- Institute for Stem Cell and Regenerative Medicine (P.M.B.), University of Washington, Seattle
- Center for Cardiovascular Biology (P.M.B.), University of Washington, Seattle
| | - Jennifer Blackwood
- Emergency Medical Services Division, Public Health - Seattle & King County, Seattle, WA (J.B., T.D.R.)
| | - Thomas D Rea
- Department of Medicine (J.C., T.D.R.), University of Washington, Seattle
- Emergency Medical Services Division, Public Health - Seattle & King County, Seattle, WA (J.B., T.D.R.)
| | | |
Collapse
|
6
|
Perry E, Nehme E, Stub D, Anderson D, Nehme Z. The impact of time to amiodarone administration on survival from out-of-hospital cardiac arrest. Resusc Plus 2023; 14:100405. [PMID: 37303855 PMCID: PMC10250159 DOI: 10.1016/j.resplu.2023.100405] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Revised: 05/20/2023] [Accepted: 05/22/2023] [Indexed: 06/13/2023] Open
Abstract
Aim To examine the impact of time to amiodarone administration on survival from shock-refractory Ventricular Fibrillation/pulseless Ventricular Tachycardia (VF/pVT) following out-of-hospital cardiac arrest (OHCA). Methods A retrospective cohort study of adult (≥16 years) OHCA patients in shock-refractory VF/pVT (after 3 consecutive defibrillation attempts) of medical aetiology who arrested between January 2010 and December 2019. Time-dependent propensity score matching was used to sequentially match patients who received amiodarone at any given minute of resuscitation with patients eligible to receive amiodarone during the same minute. Log-binomial regression models were used to assess the association between time of amiodarone administration (by quartiles of time-to-matching) and survival outcomes. Results A total of 2,026 patients were included, 1,393 (68.8%) of whom received amiodarone with a median (interquartile range) time to administration of 22.0 (18.0-27.0) minutes. Propensity score matching yielded 1,360 matched pairs. Amiodarone administration within 28 minutes of the emergency call was associated with a higher likelihood of return of spontaneous circulation (ROSC) (≤18minutes: RR = 1.03 (95%CI 1.02, 1.04); 19-22minutes: RR = 1.02 (95%CI 1.01, 1.03); 23-27minutes: RR = 1.01 (95%CI 1.00, 1.02)) and event survival (pulse on hospital arrival) (≤18 minutes: RR = 1.05 (95%CI 1.03, 1.07); 19-22 minutes: RR = 1.03 (95%CI 1.01, 1.05); 23-27 minutes: RR = 1.02 (95%CI 1.00, 1.03). Amiodarone administration within 23 minutes of the emergency call was associated with a higher likelihood of survival to hospital discharge (≤18minutes: RR = 1.17 (95%CI 1.09, 1.24; 19-22 minutes: RR = 1.10 (95%CI 1.04, 1.17). Conclusion Amiodarone administered within 23 minutes of the emergency call is associated with improved survival outcomes in shock-refractory VF/pVT, although prospective trials are required to confirm these findings.
Collapse
Affiliation(s)
- Elizabeth Perry
- Centre for Research and Evaluation, Ambulance Victoria, Doncaster, Victoria, Australia
- Department of Paramedicine, Monash University, Frankston, Victoria, Australia
| | - Emily Nehme
- Centre for Research and Evaluation, Ambulance Victoria, Doncaster, Victoria, Australia
- School of Public Health and Preventive Medicine, Monash University, Prahran, Victoria, Australia
| | - Dion Stub
- Centre for Research and Evaluation, Ambulance Victoria, Doncaster, Victoria, Australia
- School of Public Health and Preventive Medicine, Monash University, Prahran, Victoria, Australia
- Alfred Health, Prahran, Victoria, Australia
| | - David Anderson
- Centre for Research and Evaluation, Ambulance Victoria, Doncaster, Victoria, Australia
- Department of Paramedicine, Monash University, Frankston, Victoria, Australia
- School of Public Health and Preventive Medicine, Monash University, Prahran, Victoria, Australia
- Alfred Health, Prahran, Victoria, Australia
| | - Ziad Nehme
- Centre for Research and Evaluation, Ambulance Victoria, Doncaster, Victoria, Australia
- Department of Paramedicine, Monash University, Frankston, Victoria, Australia
- School of Public Health and Preventive Medicine, Monash University, Prahran, Victoria, Australia
| |
Collapse
|