- 著者
- Yuki Kataoka Tomohisa Baba Tatsuyoshi Ikenoue Yoshinori Matsuoka Junichi Matsumoto Junji Kumasawa Kentaro Tochitani Hiraku Funakoshi Tomohiro Hosoda Aiko Kugimiya Michinori Shirano Fumiko Hamabe Sachiyo Iwata Yoshiro Kitamura Tsubasa Goto Tomohiro Handa Shoji Kido Shingo Fukuma Noriyuki Tomiyama Toyohiro Hirai Takashi Ogura Japan COVID-19 AI team
- 出版者
- Society for Clinical Epidemiology
- 雑誌
- Annals of Clinical Epidemiology (ISSN:24344338)
- 巻号頁・発行日
- pp.22014, (Released:2022-07-08)
- 被引用文献数
- 2
Background: We aimed to develop and externally validate a novel machine learning model that can classify CT image findings as positive or negative for SARS-CoV-2 reverse transcription polymerase chain reaction (RT-PCR).Methods: We used 2,928 images from a wide variety of case-control type data sources for the development and internal validation of the machine learning model. A total of 633 COVID-19 cases and 2,295 non-COVID-19 cases were included in the study. We randomly divided cases into training and tuning sets at a ratio of 8:2. For external validation, we used 893 images from 740 consecutive patients at 11 acute care hospitals suspected of having COVID-19 at the time of diagnosis. The dataset included 343 COVID-19 patients. The reference standard was RT-PCR.Results: In external validation, the sensitivity and specificity of the model were 0.869 and 0.432, at the low-level cutoff, 0.724 and 0.721, at the high-level cutoff. Area under the receiver operating characteristic was 0.76.Conclusions: Our machine learning model exhibited a high sensitivity in external validation datasets and may assist physicians to rule out COVID-19 diagnosis in a timely manner at emergency departments. Further studies are warranted to improve model specificity.
- 著者
- Masashi Yamanouchi Yuki Uehara Hirohide Yokokawa Tomohiro Hosoda Yukiko Watanabe Takayoshi Shiga Akihiro Inui Yukiko Otsuki Kazutoshi Fujibayashi Hiroshi Isonuma Toshio Naito
- 出版者
- 一般社団法人 日本内科学会
- 雑誌
- Internal Medicine (ISSN:09182918)
- 巻号頁・発行日
- vol.53, no.21, pp.2471-2475, 2014 (Released:2014-11-01)
- 参考文献数
- 26
- 被引用文献数
- 4 24
Objective The causes of fever of unknown origin (FUO) vary depending on the region and time period. We herein present a study of patients with classic FUO where we investigated differences based on patient background factors, such as age and causative diseases, and changes that have occurred over time. Methods We extracted and analyzed data from the medical records of 256 patients ≥18 years old who met the criteria for classic FUO and were hospitalized between August, 1994 and December, 2012. Results The median age of the patients was 55 years (range: 18-94 years). The cause of FUO was infection in 27.7% of the patients (n=71), non-infectious inflammatory disease (NIID) in 18.4% (47), malignancy in 10.2% (26), other in 14.8% (38), and unknown in 28.9% (74). The most common single cause was human immunodeficiency virus (HIV)/acquired immunodeficiency syndrome (AIDS) (n=17). NIID and malignancy were more common in patients ≥65 years old than in patients <65 years old. During 2004-2012, compared to 1994-2003, infections and "other" causes were decreased, whereas NIID, malignancy, and unknown causes were increased. Conclusion FUO associated with HIV/AIDS is increasing in Japan. In addition, as in previous studies in Japan and overseas, our study showed that the number of patients in whom the cause of FUO remains unknown is increasing and exceeds 20% of all cases. The present study identified diseases that should be considered in the differential diagnosis of FUO, providing useful information for the future diagnosis and treatment of FUO.