Your browser doesn't support javascript.
loading
Predictive Model of Risk Factors of High Flow Nasal Cannula Using Machine Learning in COVID-19
Nobuaki Matsunaga; Keisuke Kamata; Yusuke Asai; Shinya Tsuzuki; Yasuaki Sakamoto; Shinpei Ijichi; Takayuki Akiyama; Jiefu Yu; Gen Yamada; Mari Terada; Setsuko Suzuki; Kumiko Suzuki; Sho Saito; Kayoko Hayakawa; Norio Ohmagari.
Afiliação
  • Nobuaki Matsunaga; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Keisuke Kamata; DataRobot Inc.
  • Yusuke Asai; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Shinya Tsuzuki; National Center for Global Health and Medicine
  • Yasuaki Sakamoto; DataRobot Inc.
  • Shinpei Ijichi; DataRobot Inc.
  • Takayuki Akiyama; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Jiefu Yu; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Gen Yamada; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Mari Terada; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Setsuko Suzuki; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Kumiko Suzuki; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Sho Saito; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Kayoko Hayakawa; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
  • Norio Ohmagari; National Center for Global Health and Medicine: Kokuritsu Kenkyu Kaihatsu Hojin Kokuritsu Kokusai Iryo Kenkyu Center
Preprint em Inglês | medRxiv | ID: ppmedrxiv-22271673
ABSTRACT
BackgroundWith the rapid increase in the number of COVID-19 patients in Japan, the number of patients receiving oxygen at home has also increased rapidly, and some of these patients have died. An efficient approach to identify high-risk patients with slowly progressing and rapidly worsening COVID-19, and to avoid missing the timing of therapeutic intervention will improve patient prognosis and prevent medical complications. MethodsPatients admitted to medical institutions in Japan from November 14, 2020 to April 11, 2021 and registered in the COVID-19 Registry Japan were included. Risk factors for patients with High Flow Nasal Cannula invasive respiratory management or higher were comprehensively explored using machine learning. Age-specific cohorts were created, and severity prediction was performed for the patient surge period and normal times, respectively. ResultsWe were able to obtain a model that was able to predict severe disease with a sensitivity of 57% when the specificity was set at 90% for those aged 40-59 years, and with a specificity of 50% and 43% when the sensitivity was set at 90% for those aged 60-79 years and 80 years and older, respectively. We were able to identify lactate dehydrogenase level (LDH) as an important factor in predicting the severity of illness in all age groups. DiscussionUsing machine learning, we were able to identify risk factors with high accuracy, and predict the severity of the disease. Using machine learning, we were able to identify risk factors with high accuracy, and predict the severity of the disease. We plan to develop a tool that will be useful in determining the indications for hospitalisation for patients undergoing home care and early hospitalisation.
Licença
cc_by_nc
Texto completo: Disponível Coleções: Preprints Base de dados: medRxiv Tipo de estudo: Cohort_studies / Experimental_studies / Estudo observacional / Estudo prognóstico / Rct Idioma: Inglês Ano de publicação: 2022 Tipo de documento: Preprint
Texto completo: Disponível Coleções: Preprints Base de dados: medRxiv Tipo de estudo: Cohort_studies / Experimental_studies / Estudo observacional / Estudo prognóstico / Rct Idioma: Inglês Ano de publicação: 2022 Tipo de documento: Preprint
...