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

Yohei Okada; Sho Komukai; Tetsuhisa Kitamura; Takeyuki Kiguchi; Taro Irisawa; Tomoki Yamada; Kazuhisa Yoshiya; Changhwi Park; Tetsuro Nishimura; Takuya Ishibe; Yoshiki Yagi; Masafumi Kishimoto; Toshiya Inoue; Yasuyuki Hayashi; Taku Sogabe; Takaya Morooka; Haruko Sakamoto; Keitaro Suzuki; Fumiko Nakamura; Tasuku Matsuyama; Norihiro Nishioka; Daisuke Kobayashi; Satoshi Matsui; Atsushi Hirayama; Satoshi Yoshimura; Shunsuke Kimata; Takeshi Shimazu; Shigeru Ohtsuru; Taku Iwami; CRITICAL Research Group Investigators

doi:10.1002/ams2.760

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

Acute Med Surg. 2022 May 27;9(1):e760. doi: 10.1002/ams2.760. eCollection 2022 Jan-Dec.

Authors

Yohei Okada^{1

2}, Sho Komukai³, Tetsuhisa Kitamura⁴, Takeyuki Kiguchi⁵, Taro Irisawa⁶, Tomoki Yamada⁷, Kazuhisa Yoshiya⁸, Changhwi Park⁹, Tetsuro Nishimura¹⁰, Takuya Ishibe¹¹, Yoshiki Yagi¹², Masafumi Kishimoto¹³, Toshiya Inoue¹⁴, Yasuyuki Hayashi¹⁵, Taku Sogabe¹⁶, Takaya Morooka¹⁷, Haruko Sakamoto¹⁸, Keitaro Suzuki¹⁹, Fumiko Nakamura²⁰, Tasuku Matsuyama²¹, Norihiro Nishioka¹, Daisuke Kobayashi¹, Satoshi Matsui⁴, Atsushi Hirayama²², Satoshi Yoshimura¹, Shunsuke Kimata¹, Takeshi Shimazu⁶, Shigeru Ohtsuru², Taku Iwami¹; CRITICAL Research Group Investigators

Affiliations

¹ Department of Preventive Services, School of Public Health Kyoto University Kyoto Japan.
² Department of Primary Care and Emergency Medicine, Graduate School of Medicine Kyoto University Kyoto Japan.
³ Division of Biomedical Statistics, Department of Integrated Medicine, Graduate School of Medicine Osaka University Suita Japan.
⁴ Division of Environmental Medicine and Population Sciences, Department of Social and Environmental Medicine, Graduate School of Medicine Osaka University Osaka Japan.
⁵ Critical Care and Trauma Center Osaka General Medical Center Osaka Japan.
⁶ Department of Traumatology and Acute Critical Medicine Osaka University Graduate School of Medicine Suita Japan.
⁷ Emergency and Critical Care Medical Center Osaka Police Hospital Osaka Japan.
⁸ Department of Emergency and Critical Care Medicine Takii Hospital, Kansai Medical University Moriguchi Japan.
⁹ Department of Emergency Medicine Tane General Hospital Osaka Japan.
¹⁰ Department of Critical Care Medicine Osaka City University Osaka Japan.
¹¹ Department of Emergency and Critical Care Medicine Kindai University School of Medicine Osaka-Sayama Japan.
¹² Osaka Mishima Emergency Critical Care Center Takatsuki Japan.
¹³ Osaka Prefectural Nakakawachi Medical Center of Acute Medicine Higashi-Osaka Japan.
¹⁴ Senshu Trauma and Critical Care Center Osaka Japan.
¹⁵ Senri Critical Care Medical Center Saiseikai Senri Hospital Suita Japan.
¹⁶ Traumatology and Critical Care Medical Center National Hospital Organization Osaka National Hospital Osaka Japan.
¹⁷ Emergency and Critical Care Medical Center Osaka City General Hospital Osaka Japan.
¹⁸ Department of Pediatrics Osaka Red Cross Hospital Osaka Japan.
¹⁹ Emergency and Critical Care Medical Center Kishiwada Tokushukai Hospital Osaka Japan.
²⁰ Department of Emergency and Critical Care Medicine Kansai Medical University Hirakata Osaka Japan.
²¹ Department of Emergency Medicine Kyoto Prefectural University of Medicine Kyoto Japan.
²² Public Health, Department of Social and Environmental Medicine Osaka University Graduate School of Medicine Osaka Japan.

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.

Keywords: Asystole; cardiac arrest; clustering; latent class analysis; pulseless electrical activity; subphenotype.