Machine learning-based detection of sleep-disordered breathing in hypertrophic cardiomyopathy

Keitaro Akita; Shigetaka Kageyama; Sayumi Suzuki; Kazuto Ohno; Masamitsu Kamakura; Ryuzo Nawada; Chiei Takanaka; Yasushi Wakabayashi; Takahiro Kanda; Kei Tawarahara; Masahiro Mutoh; Masaki Matsunaga; Satoru Suwa; Yasuyo Takeuchi; Hiroki Sakamoto; Hideki Saito; Kazusa Hayashi; Nobuyuki Wakahara; Kyoko Unno; Takenori Ikoma; Ryota Sato; Keisuke Iguchi; Terumori Satoh; Makoto Sano; Kenichiro Suwa; Yoshihisa Naruse; Hayato Ohtani; Masao Saotome; Yuichiro Maekawa; Searching for Atrial Fibrillation and Early Recruitment of Heart Failure in HCM (SAFER-HCM) Registry Investigators

doi:10.1136/heartjnl-2023-323856

Machine learning-based detection of sleep-disordered breathing in hypertrophic cardiomyopathy

Heart. 2024 Apr 8:heartjnl-2023-323856. doi: 10.1136/heartjnl-2023-323856. Online ahead of print.

Authors

Keitaro Akita¹, Shigetaka Kageyama², Sayumi Suzuki¹, Kazuto Ohno¹, Masamitsu Kamakura², Ryuzo Nawada², Chiei Takanaka³, Yasushi Wakabayashi⁴, Takahiro Kanda⁵, Kei Tawarahara⁵, Masahiro Mutoh⁶, Masaki Matsunaga⁷, Satoru Suwa⁸, Yasuyo Takeuchi⁹, Hiroki Sakamoto⁹, Hideki Saito¹⁰, Kazusa Hayashi¹¹, Nobuyuki Wakahara¹², Kyoko Unno¹, Takenori Ikoma¹, Ryota Sato¹, Keisuke Iguchi¹, Terumori Satoh¹, Makoto Sano¹, Kenichiro Suwa¹, Yoshihisa Naruse¹, Hayato Ohtani¹, Masao Saotome¹, Yuichiro Maekawa¹³; Searching for Atrial Fibrillation and Early Recruitment of Heart Failure in HCM (SAFER-HCM) Registry Investigators

Affiliations

¹ Division of Cardiology, Internal Medicine III, Hamamatsu University School of Medicine, Hamamatsu, Shizuoka, Japan.
² Department of Cardiology, Shizuoka City Shizuoka Hospital, Shizuoka, Japan.
³ Takanaka Clinic, Hamamatsu, Shizuoka, Japan.
⁴ Department of Cardiology, Seirei Mikatahara Hospital, Hamamatsu, Shizuoka, Japan.
⁵ Department of Cardiology, Hamamatsu Red Cross Hospital, Hamamatsu, Shizuoka, Japan.
⁶ Department of Cardiology, Hamamatsu Medical Center, Hamamatsu, Shizuoka, Japan.
⁷ Department of Cardiology, Iwata City Hospital, Iwata, Shizuoka, Japan.
⁸ Department of Cardiovascular Medicine, Juntendo University Shizuoka Hospital, Izunokuni, Shizuoka, Japan.
⁹ Department of Cardiology, Shizuoka General Hospital, Shizuoka, Japan.
¹⁰ Department of Cardiology, Seirei Hamamatsu General Hospital, Hamamatsu, Shizuoka, Japan.
¹¹ Department of Internal Medicine, JA Shizuoka Kohseiren Enshu Hospital, Hamamatsu, Shizuoka, Japan.
¹² Department of Cardiology, Fujinomiya City General Hospital, Fujinomiya, Shizuoka, Japan.
¹³ Division of Cardiology, Internal Medicine III, Hamamatsu University School of Medicine, Hamamatsu, Shizuoka, Japan ymaekawa@hama-med.ac.jp.

PMID: 38589224
DOI: 10.1136/heartjnl-2023-323856

Abstract

Background: Hypertrophic cardiomyopathy (HCM) is often concomitant with sleep-disordered breathing (SDB), which can cause adverse cardiovascular events. Although an appropriate approach to SDB prevents cardiac remodelling, detection of concomitant SDB in patients with HCM remains suboptimal. Thus, we aimed to develop a machine learning-based discriminant model for SDB in HCM.

Methods: In the present multicentre study, we consecutively registered patients with HCM and performed nocturnal oximetry. The outcome was a high Oxygen Desaturation Index (ODI), defined as 3% ODI >10, which significantly correlated with the presence of moderate or severe SDB. We randomly divided the whole participants into a training set (80%) and a test set (20%). With data from the training set, we developed a random forest discriminant model for high ODI based on clinical parameters. We tested the ability of the discriminant model on the test set and compared it with a previous logistic regression model for distinguishing SDB in patients with HCM.

Results: Among 369 patients with HCM, 228 (61.8%) had high ODI. In the test set, the area under the receiver operating characteristic curve of the discriminant model was 0.86 (95% CI 0.77 to 0.94). The sensitivity was 0.91 (95% CI 0.79 to 0.98) and specificity was 0.68 (95% CI 0.48 to 0.84). When the test set was divided into low-probability and high-probability groups, the high-probability group had a higher prevalence of high ODI than the low-probability group (82.4% vs 17.4%, OR 20.9 (95% CI 5.3 to 105.8), Fisher's exact test p<0.001). The discriminant model significantly outperformed the previous logistic regression model (DeLong test p=0.03).

Conclusions: Our study serves as the first to develop a machine learning-based discriminant model for the concomitance of SDB in patients with HCM. The discriminant model may facilitate cost-effective screening tests and treatments for SDB in the population with HCM.

Keywords: Cardiomyopathy, Hypertrophic.