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

Abstract

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

Mapping publications using the Japan Trauma Data Bank: Scoping review of the international literature

“…18 Research teams should carefully choose the statistical methods for analysis depending on their research objectives. Although we found only two articles using machine learning methods, data science can have a significant impact on research [19][20][21] Clinicians also need to have a deeper understanding of it and collaboration between clinicians, statisticians, and data scientists may be crucial for effective data analysis. 22 Publications using the JTDB were seen in a variety of internationally recognized journals.…”

Application of the TiPS65 score for out-of-hospital cardiac arrest patients with initial non-shockable rhythm treated with ECPR

“…Generally, the causes of OHCA with non-shockable rhythm are diverse such as cardiogenic, respiratory causes, sepsis, subarachnoid hemorrhage, electrolyte abnormality and etc. 17 , 18 , 19 , 20 , 21 Despite the application of ECPR and appropriate treatment for the underlying cause, some patients with non-shockable rhythm do not achieve good neurological function. This is because the primary cause of cardiac arrest itself can severely injure the brain, leading to poor neurological outcomes despite intervention.…”

“…This is because the primary cause of cardiac arrest itself can severely injure the brain, leading to poor neurological outcomes despite intervention. 17 , 18 , 19 , 20 , 21 For example, in patients with cardiac arrest because of hypoxia due to respiratory failure or a massive intracranial hemorrhage, the brain is likely to be severely injured when ECPR started. 8 , 22 Indeed, survival was better in patients with scores 3 or 4, but neurological outcomes were similar to the other groups.…”

Overview and future prospects of out-of-hospital cardiac arrest registries in Japan

“… 30 One study obtained in-hospital data from 15 tertiary critical care medical centres (CCMCs) and one non-CCMC community hospital with an emergency department all located in Osaka Prefecture in Japan. 31 , 32 Osaka Prefecture is an urban region with an area of 1905 km 2 and a residential population of approximately 8.8 million in 2015. In Osaka Prefecture, 7500 OHCAs occur annually, and approximately 25% of patients with OHCA (approximately ≥ 2000 cases) were registered every year from 2012 to 2021.…”