Dataset Information

Clustering out-of-hospital cardiac arrest patients with non-shockable rhythm by machine learning latent class analysis.

ABSTRACT:

Aim

We aimed to identify subphenotypes among patients with out-of-hospital cardiac arrest (OHCA) with initial non-shockable rhythm by applying machine learning latent class analysis and examining the associations between subphenotypes and neurological outcomes.

Methods

This study was a retrospective analysis within a multi-institutional prospective observational cohort study of OHCA patients in Osaka, Japan (the CRITICAL study). The data of adult OHCA patients with medical causes and initial non-shockable rhythm presenting with OHCA between 2012 and 2016 were included in machine learning latent class analysis models, which identified subphenotypes, and patients who presented in 2017 were included in a dataset validating the subphenotypes. We investigated associations between subphenotypes and 30-day neurological outcomes.

Results

Among the 12,594 patients in the CRITICAL study database, 4,849 were included in the dataset used to classify subphenotypes (median age: 75 years, 60.2% male), and 1,465 were included in the validation dataset (median age: 76 years, 59.0% male). Latent class analysis identified four subphenotypes. Odds ratios and 95% confidence intervals for a favorable 30-day neurological outcome among patients with these subphenotypes, using group 4 for comparison, were as follows; group 1, 0.01 (0.001-0.046); group 2, 0.097 (0.051-0.171); and group 3, 0.175 (0.073-0.358). Associations between subphenotypes and 30-day neurological outcomes were validated using the validation dataset.

Conclusion

We identified four subphenotypes of OHCA patients with initial non-shockable rhythm. These patient subgroups presented with different characteristics associated with 30-day survival and neurological outcomes.

SUBMITTER: Okada Y

PROVIDER: S-EPMC9136939 | biostudies-literature | 2022 Jan-Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Clustering out-of-hospital cardiac arrest patients with non-shockable rhythm by machine learning latent class analysis.

Okada Yohei Y Komukai Sho S Kitamura Tetsuhisa T Kiguchi Takeyuki T Irisawa Taro T Yamada Tomoki T Yoshiya Kazuhisa K Park Changhwi C Nishimura Tetsuro T Ishibe Takuya T Yagi Yoshiki Y Kishimoto Masafumi M Inoue Toshiya T Hayashi Yasuyuki Y Sogabe Taku T Morooka Takaya T Sakamoto Haruko H Suzuki Keitaro K Nakamura Fumiko F Matsuyama Tasuku T Nishioka Norihiro N Kobayashi Daisuke D Matsui Satoshi S Hirayama Atsushi A Yoshimura Satoshi S Kimata Shunsuke S Shimazu Takeshi T Ohtsuru Shigeru S Iwami Taku T

Acute medicine & surgery 20220101 1

<h4>Aim</h4>We aimed to identify subphenotypes among patients with out-of-hospital cardiac arrest (OHCA) with initial non-shockable rhythm by applying machine learning latent class analysis and examining the associations between subphenotypes and neurological outcomes.<h4>Methods</h4>This study was a retrospective analysis within a multi-institutional prospective observational cohort study of OHCA patients in Osaka, Japan (the CRITICAL study). The data of adult OHCA patients with medical causes ...[more]

PMID: 35664809

Similar Datasets

Project description:BackgroundSingapore and Osaka in Japan have comparable population sizes and prehospital management; however, the frequency of ECPR differs greatly for out-of-hospital cardiac arrest (OHCA) patients with initial shockable rhythm. Given this disparity, we hypothesized that the outcomes among the OHCA patients with initial shockable rhythm in Singapore were different from those in Osaka. The aim of this study was to evaluate the outcomes of OHCA patients with initial shockable rhythm in Singapore compared to the expected outcomes derived from Osaka data using machine learning-based prediction models.MethodsThis was a secondary analysis of two OHCA databases: the Singapore PAROS database (SG-PAROS) and the Osaka-CRITICAL database from Osaka, Japan. This study included adult (18-74 years) OHCA patients with initial shockable rhythm. A machine learning-based prediction model was derived and validated using data from the Osaka-CRITICAL database (derivation data 2012-2017, validation data 2018-2019), and applied to the SG-PAROS database (2010-2016 data), to predict the risk-adjusted probability of favorable neurological outcomes. The observed and expected outcomes were compared using the observed-expected ratio (OE ratio) with 95% confidence intervals (CI).ResultsFrom the SG-PAROS database, 1,789 patients were included in the analysis. For OHCA patients who achieved return of spontaneous circulation (ROSC) on hospital arrival, the observed favorable neurological outcome was at the same level as expected (OE ratio: 0.905 [95%CI: 0.784-1.036]). On the other hand, for those who had continued cardiac arrest on hospital arrival, the outcomes were lower than expected (shockable rhythm on hospital arrival, OE ratio: 0.369 [95%CI: 0.258-0.499], and nonshockable rhythm, OE ratio: 0.137 [95%CI: 0.065-0.235]).ConclusionThis observational study found that the outcomes for patients with initial shockable rhythm but who did not obtain ROSC on hospital arrival in Singapore were lower than expected from Osaka. We hypothesize this is mainly due to differences in the use of ECPR.

Project description:Background and importanceBystander cardiopulmonary resuscitation (CPR) and initial shockable rhythm are crucial predictors of survival after out-of-hospital cardiac arrest (OHCA). However, the relationship between dispatcher-assisted CPR (DA-CPR) and initial shockable rhythm is not completely elucidated.ObjectiveTo examine the association of DA-CPR with initial shockable rhythm and outcomes.Design, setting and participantsThis nationwide population-based observational study conducted in Japan included 59 688 patients with witnessed OHCA of cardiac origin after excluding those without bystander CPR. Patients were divided into DA-CPR (n = 42 709) and CPR without dispatcher assistance (unassisted CPR, n = 16 979) groups.Outcome measures and analysisThe primary outcome measure was initial shockable rhythm, and secondary outcome measures were 1-month survival and neurologically intact survival. A Cox proportional hazards model adjusted for collapse-to-first-rhythm-analysis time and multivariable logistic regression models were used after propensity score (PS) matching to compare the incidence of initial shockable rhythm and outcomes, respectively.Main resultsAmong all patients (mean age 76.7 years), the rates of initial shockable rhythm, 1-month survival and neurologically intact survival were 20.8, 10.7 and 7.0%, respectively. The incidence of initial shockable rhythm in the DA-CPR group (20.4%, 3462/16 979) was significantly higher than that in the unassisted CPR group (18.5%, 3133/16 979) after PS matching (P < 0.0001). However, no significant differences were found between the two groups with respect to the incidence of initial shockable rhythm in the Cox proportional hazards model [adjusted hazard ratio of DA-CPR for initial shockable rhythm compared with unassisted CPR, 0.99; 95% confidence interval (CI), 0.97-1.02, P = 0.56]. No significant differences were observed in the survival rates in the two groups after PS matching [10.8% (1833/16 979) vs. 10.3% (1752/16 979), P = 0.16] and neurologically intact survival rates [7.3% (1233/16 979) vs. 6.8% (1161/16 979), P = 0.13]. The multivariable logistic regression model showed no significant differences between the groups with regard to survival (adjusted odds ratio of DA-CPR compared with unassisted CPR: 1.00; 95% CI, 0.89-1.13, P = 0.97) and neurologically intact survival (adjusted odds ratio: 1.12; 95% CI, 0.98-1.29, P = 0.14).ConclusionDA-CPR after OHCA had the same independent association with the likelihood of initial shockable rhythm and 1-month meaningful outcome as unassisted CPR.

Project description:BackgroundThe TiPS65 score is a validated scoring system used to predict neurological outcomes in out-of-hospital cardiac arrest (OHCA) patients with shockable rhythm treated with extracorporeal cardiopulmonary resuscitation (ECPR). This study aimed to assess the predictive performance of the TiPS65 score in OHCA patients with initial non-shockable rhythm treated with ECPR.MethodsThis was a secondary analysis using the JAAM-OHCA registry, a multicenter prospective cohort study. The study included adult OHCA patients with initial non-shockable rhythm who underwent ECPR. The TiPS65 score assigned one point to each of four variables: time to hospital ≤25 minutes, pH value ≥7.0 on initial blood gas assessment, shockable on hospital arrival, and age younger than 65 years. Based on the sum score, the predictive performance for 1-month survival and favorable neurological outcomes, defined as the Cerebral Performance Category 1 or 2, was evaluated.ResultsAmong 57,754 patients in the registry, 370 were included in the analysis. The overall one-month survival and favorable neurological outcome were 11.1% (41/370) and 4.2% (15/370), respectively. The 1-month survival rates based on the TiPS65 score were as follows: 11.2% (12/107) for 0 points, 9.3% (14/150) for 1 point, 10.0% (9/90) for 2 points, and 26.1% (6/23) for ≥3 points. Similarly, the 1-month favorable neurological outcomes were: 5.6% (6/107) for 0 points, 2.7% (4/150) for 1 point, 4.4% (4/90) for 2 points, and 4.3% (1/23) for ≥3 points. The area under the curve was 0.535 (95% CI: 0.437-0.630) for 1-month survival and 0.530 (95% CI: 0.372-0.683) for 1-month neurological outcome.ConclusionThis study demonstrates that the TiPS65 score has limited prognostic performance among OHCA patients with initial non-shockable rhythm treated with ECPR. Further research is warranted to develop a predictive tool specifically focused on OHCA with initial non-shockable rhythm to aid in determining candidates for ECPR.

Project description:ImportanceVentricular fibrillation (VF) or pulseless ventricular tachycardia (pVT) are the most treatable causes of out-of-hospital cardiac arrest (OHCA). Yet, it remains unknown if defibrillator pad position, placement in the anterior-posterior (AP) or anterior-lateral (AL) locations, impacts patient outcomes in VF or pVT OHCA.ObjectiveTo determine the association between initial defibrillator pad placement position and OHCA outcomes for patients presenting with VF or pVT.Design, setting, and participantsThis prospective cohort study included patients with OHCA and VF or pVT treated by a single North American emergency medical services (EMS) agency from July 1, 2019, through June 30, 2023. The study included patients with OHCA treated by a large suburban fire-based EMS agency that covers a population of 550 000. Consecutive patients with an initial EMS-assessed rhythm of VF or pVT receiving EMS defibrillation were included. Pediatric patients (younger than 18 years), interfacility transfers, arrests of obvious traumatic etiology, and patients with preexisting do-not-resuscitate status were excluded.ExposureAP or AL pad placement.Main outcomes and measuresReturn of spontaneous circulation (ROSC) at any time with secondary outcomes of pulses present at emergency department (ED) arrival, survival to hospital admission, survival to hospital discharge, and functional survival at hospital discharge (cerebral performance category score of 2 or less). Measures included adjusted odds ratios (aOR), multivariable logistic regressions, and Fine-Gray competing risks regression.ResultsA total of 255 patients with OHCA were included (median [IQR] age, 66 [55-74] years; 63 females [24.7%]), with initial pad positioning documented as either AP (158 patients [62.0%]; median [IQR] age, 65 [54-74] years; 37 females [23.4%]) or AL (97 patients [38.0%]; median [IQR] age, 66 [57-74] years; 26 females [26.8%]). Patients with AP placement had higher adjusted odds ratio (aOR) of ROSC at any time (aOR, 2.64 [95% CI, 1.50-4.65]), but not significantly different odds of pulses present at ED arrival (1.34 [95% CI, 0.78-2.30]), survival to hospital admission (1.41 [0.82-2.43]), survival to hospital discharge (1.55 [95% CI, 0.83-2.90]), or functional survival at hospital discharge (1.86 [95% CI, 0.98-3.51]). Competing risk analysis found significantly greater cumulative incidence of ROSC among those at risk with initial AP placement compared with AL (subdistribution hazard ratio, 1.81 [95% CI, 1.23-2.67]; P = .003).Conclusions and relevanceIn this cohort study of patients with OHCA and VF or pVT, AP defibrillator pad placement was associated with higher ROSC compared with AL placement.

Project description:ObjectiveTo determine if the Clinical Frailty Scale (CFS) predicts out-of-hospital cardiac arrest (OHCA) outcomes better than age?Design: The analysed data was collected as part of a larger study run by NCEPOD on hospital admissions for OHCA in 2018. Study selection was OHCA in over 16-year-olds with restoration of spontaneous circulation (ROSC) for >20 mins and who were admitted to hospital, or who died in the emergency department. Patients from hospitals in England, Wales and Northern Ireland were identified using standard coding for cardiac arrest. CFS, age and gender were examined against two binary outcomes (non-shockable rhythm and survival).Results304 patients with a known CFS, known original rhythm, and known outcome were included. Younger patients had lower CFSs, as a continuous variable (Pearson correlation coefficient 0.44, p-value < 0.001) and in CFS groupings of 1-3, 4-6, 7-9 (p-value < 0.001). CFSs were higher (p-values < 0.001) for both non-shockable rhythm and death (median CFS was 4 for death and 2 for survivors). Logistic regression analysis of continuous scale CFS showed the association with non-shockable rhythm remained when adjusted for age and sex (odds ratio [95% CI]; age adjustment 1.46 [1.28, 1.68] p-value < 0.001) and remained for survival when adjusted for age alone (odds ratio [95% CI]; 1.60 [1.36, 1.88] p-value < 0.001) and when adjusted for age, sex and initial rhythm combined (1.45 [1.21, 1.73] p-value < 0.001). 3.2% of patients had resuscitation against their advanced-care-directives. 12.9% (23/178) of hospitals had electronic systems which shared advance-care-directives with ambulance services and primary care.ConclusionA higher CFS is a prognostic indicator in adult OHCA independent of age. Frail individuals have a lower likelihood of a shockable rhythm and poorer survival. Sensitive sharing of this information with patients when discussing advance-care-directives may enhance shared decision-making.

Dataset Information

Clustering out-of-hospital cardiac arrest patients with non-shockable rhythm by machine learning latent class analysis.

Aim

Methods

Results

Conclusion

Publications

Clustering out-of-hospital cardiac arrest patients with non-shockable rhythm by machine learning latent class analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets