Frontiers in Psychiatry (Jun 2023)
Comprehensive evaluation of machine learning algorithms for predicting sleep–wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability
- Xue Li,
- Chiaki Ono,
- Noriko Warita,
- Tomoka Shoji,
- Tomoka Shoji,
- Takashi Nakagawa,
- Takashi Nakagawa,
- Hitomi Usukura,
- Zhiqian Yu,
- Yuta Takahashi,
- Kei Ichiji,
- Norihiro Sugita,
- Natsuko Kobayashi,
- Saya Kikuchi,
- Ryoko Kimura,
- Yumiko Hamaie,
- Yumiko Hamaie,
- Mizuki Hino,
- Yasuto Kunii,
- Yasuto Kunii,
- Keiko Murakami,
- Mami Ishikuro,
- Taku Obara,
- Tomohiro Nakamura,
- Fuji Nagami,
- Takako Takai,
- Soichi Ogishima,
- Junichi Sugawara,
- Tetsuro Hoshiai,
- Masatoshi Saito,
- Gen Tamiya,
- Nobuo Fuse,
- Susumu Fujii,
- Masaharu Nakayama,
- Shinichi Kuriyama,
- Shinichi Kuriyama,
- Masayuki Yamamoto,
- Masayuki Yamamoto,
- Nobuo Yaegashi,
- Nobuo Yaegashi,
- Noriyasu Homma,
- Hiroaki Tomita,
- Hiroaki Tomita,
- Hiroaki Tomita,
- Hiroaki Tomita
Affiliations
- Xue Li
- Department of Psychiatry, Tohoku University Graduate School of Medicine, Sendai, Japan
- Chiaki Ono
- Department of Psychiatry, Tohoku University Hospital, Sendai, Japan
- Noriko Warita
- Department of Preventive Medicine and Epidemiology, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Tomoka Shoji
- Department of Psychiatry, Tohoku University Graduate School of Medicine, Sendai, Japan
- Tomoka Shoji
- Department of Preventive Medicine and Epidemiology, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Takashi Nakagawa
- Department of Psychiatry, Tohoku University Graduate School of Medicine, Sendai, Japan
- Takashi Nakagawa
- Department of Psychiatry, Tohoku University Hospital, Sendai, Japan
- Hitomi Usukura
- Department of Disaster Psychiatry, International Research Institute of Disaster Sciences, Tohoku University, Sendai, Japan
- Zhiqian Yu
- Department of Disaster Psychiatry, International Research Institute of Disaster Sciences, Tohoku University, Sendai, Japan
- Yuta Takahashi
- Department of Psychiatry, Tohoku University Hospital, Sendai, Japan
- Kei Ichiji
- Department of Radiological Imaging and Informatics, Tohoku University Graduate School of Medicine, Sendai, Japan
- Norihiro Sugita
- Department of Management Science and Technology, Graduate School of Engineering, Tohoku University, Sendai, Japan
- Natsuko Kobayashi
- Department of Psychiatry, Tohoku University Hospital, Sendai, Japan
- Saya Kikuchi
- Department of Psychiatry, Tohoku University Hospital, Sendai, Japan
- Ryoko Kimura
- Department of Psychiatry, Tohoku University Graduate School of Medicine, Sendai, Japan
- Yumiko Hamaie
- Department of Psychiatry, Tohoku University Hospital, Sendai, Japan
- Yumiko Hamaie
- Department of Disaster Psychiatry, International Research Institute of Disaster Sciences, Tohoku University, Sendai, Japan
- Mizuki Hino
- Department of Disaster Psychiatry, International Research Institute of Disaster Sciences, Tohoku University, Sendai, Japan
- Yasuto Kunii
- Department of Psychiatry, Tohoku University Hospital, Sendai, Japan
- Yasuto Kunii
- Department of Disaster Psychiatry, International Research Institute of Disaster Sciences, Tohoku University, Sendai, Japan
- Keiko Murakami
- Department of Preventive Medicine and Epidemiology, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Mami Ishikuro
- Department of Preventive Medicine and Epidemiology, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Taku Obara
- Department of Preventive Medicine and Epidemiology, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Tomohiro Nakamura
- Department of Health Record Informatics, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Fuji Nagami
- Department of Public Relations and Planning, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Takako Takai
- Department of Health Record Informatics, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Soichi Ogishima
- Department of Health Record Informatics, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Junichi Sugawara
- Department of Community Medical Supports, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Tetsuro Hoshiai
- 0Department of Obstetrics, Tohoku University Graduate School of Medicine, Sendai, Japan
- Masatoshi Saito
- 0Department of Obstetrics, Tohoku University Graduate School of Medicine, Sendai, Japan
- Gen Tamiya
- 1Department of Integrative Genomics, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Nobuo Fuse
- 1Department of Integrative Genomics, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Susumu Fujii
- 2Department of Disaster Medical Informatics, International Research Institute of Disaster Sciences, Tohoku University, Sendai, Japan
- Masaharu Nakayama
- 2Department of Disaster Medical Informatics, International Research Institute of Disaster Sciences, Tohoku University, Sendai, Japan
- Shinichi Kuriyama
- Department of Preventive Medicine and Epidemiology, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Shinichi Kuriyama
- 3Department of Disaster Public Health, International Research Institute of Disaster Sciences, Tohoku University, Sendai, Japan
- Masayuki Yamamoto
- Department of Management Science and Technology, Graduate School of Engineering, Tohoku University, Sendai, Japan
- Masayuki Yamamoto
- 1Department of Integrative Genomics, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Nobuo Yaegashi
- Department of Public Relations and Planning, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Nobuo Yaegashi
- 0Department of Obstetrics, Tohoku University Graduate School of Medicine, Sendai, Japan
- Noriyasu Homma
- Department of Radiological Imaging and Informatics, Tohoku University Graduate School of Medicine, Sendai, Japan
- Hiroaki Tomita
- Department of Psychiatry, Tohoku University Graduate School of Medicine, Sendai, Japan
- Hiroaki Tomita
- Department of Psychiatry, Tohoku University Hospital, Sendai, Japan
- Hiroaki Tomita
- Department of Preventive Medicine and Epidemiology, Tohoku University Tohoku Medical Megabank Organization, Sendai, Japan
- Hiroaki Tomita
- Department of Disaster Psychiatry, International Research Institute of Disaster Sciences, Tohoku University, Sendai, Japan
- DOI
- https://doi.org/10.3389/fpsyt.2023.1104222
- Journal volume & issue
-
Vol. 14
Abstract
IntroductionPerinatal women tend to have difficulties with sleep along with autonomic characteristics. This study aimed to identify a machine learning algorithm capable of achieving high accuracy in predicting sleep–wake conditions and differentiating between the wake conditions before and after sleep during pregnancy based on heart rate variability (HRV).MethodsNine HRV indicators (features) and sleep–wake conditions of 154 pregnant women were measured for 1 week, from the 23rd to the 32nd weeks of pregnancy. Ten machine learning and three deep learning methods were applied to predict three types of sleep–wake conditions (wake, shallow sleep, and deep sleep). In addition, the prediction of four conditions, in which the wake conditions before and after sleep were differentiated—shallow sleep, deep sleep, and the two types of wake conditions—was also tested.Results and DiscussionIn the test for predicting three types of sleep–wake conditions, most of the algorithms, except for Naïve Bayes, showed higher areas under the curve (AUCs; 0.82–0.88) and accuracy (0.78–0.81). The test using four types of sleep–wake conditions with differentiation between the wake conditions before and after sleep also resulted in successful prediction by the gated recurrent unit with the highest AUC (0.86) and accuracy (0.79). Among the nine features, seven made major contributions to predicting sleep–wake conditions. Among the seven features, “the number of interval differences of successive RR intervals greater than 50 ms (NN50)” and “the proportion dividing NN50 by the total number of RR intervals (pNN50)” were useful to predict sleep–wake conditions unique to pregnancy. These findings suggest alterations in the vagal tone system specific to pregnancy.
Keywords