ABSTRACT
Objectives: The whole picture of the disturbance in endoscopy performance caused by the coronavirus disease 2019 (COVID-19) pandemic in Japan remains to be clarified. Therefore, the Japan Gastroenterological Endoscopy Society-Tohoku conducted this questionnaire survey in Tohoku region of Japan. Methods: A questionnaire on the number of diagnostic endoscopy procedures and resulting diagnosed cancers in 2019 and 2020 was sent to all guidance/guidance cooperation hospitals in the Japan Gastroenterological Endoscopy Society who worked in the Tohoku region. The percentage change was calculated by comparing the numbers in 2020 with those in 2019 (the pre-COVID-19 period). Results: Among the applicable 89 guidance/guidance cooperation hospitals, 83 (94%) returned the questionnaire. The number of endoscopy procedures promptly decreased to the nadir in April and May 2020 (during the first state of emergency in Japan);however, it recovered relatively quickly, within a few months after the state of emergency was lifted. Consequently, the annual reduction in the number of endoscopy procedures in 2020 (in comparison to 2019) was 10.1% for esophagogastroduodenoscopy and 7.9% for colonoscopy. The reduction in the number of diagnostic endoscopy procedures led to a 5.5% reduction in esophagogastric cancer and 2.7% in colorectal cancer. Conclusions: This is the most comprehensive survey on the impact of the COVID-19 pandemic on the performance of endoscopy and the resulting diagnosis of cancer in Japan. Understanding the magnitude of the decline in endoscopic examinations and cancer detection due to the pandemic is critical to understanding how many people will ultimately be affected and establishing a strategy for providing endoscopy during national emergencies. Copyright © 2023 The Authors. DEN Open published by John Wiley & Sons Australia, Ltd on behalf of Japan Gastroenterological Endoscopy Society.
ABSTRACT
The COVID-19 outbreak was announced as a global pandemic by the World Health Organisation in March 2020 and has affected a growing number of people in the past few weeks. In this context, advanced artificial intelligence techniques are brought to the fore in responding to fight against and reduce the impact of this global health crisis. In this study, we focus on developing some potential use-cases of intelligent speech analysis for COVID-19 diagnosed patients. In particular, by analysing speech recordings from these patients, we construct audio-only-based models to automatically categorise the health state of patients from four aspects, including the severity of illness, sleep quality, fatigue, and anxiety. For this purpose, two established acoustic feature sets and support vector machines are utilised. Our experiments show that an average accuracy of.69 obtained estimating the severity of illness, which is derived from the number of days in hospitalisation. We hope that this study can foster an extremely fast, low-cost, and convenient way to automatically detect the COVID-19 disease. © 2020 ISCA