Predicting coronavirus disease 2019 severity using explainable artificial intelligence techniques
Abstract Predictive models for determining coronavirus disease 2019 (COVID-19) severity have been established; however, the complexity of the interactions among factors limits the use of conventional statistical methods. This study aimed to establish a simple and accurate predictive model for COVID-...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-85733-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850095063584997376 |
|---|---|
| author | Takuya Ozawa Shotaro Chubachi Ho Namkoong Shota Nemoto Ryo Ikegami Takanori Asakura Hiromu Tanaka Ho Lee Takahiro Fukushima Shuhei Azekawa Shiro Otake Kensuke Nakagawara Mayuko Watase Katsunori Masaki Hirofumi Kamata Norihiro Harada Tetsuya Ueda Soichiro Ueda Takashi Ishiguro Ken Arimura Fukuki Saito Takashi Yoshiyama Yasushi Nakano Yoshikazu Muto Yusuke Suzuki Ryuya Edahiro Koji Murakami Yasunori Sato Yukinori Okada Ryuji Koike Makoto Ishii Naoki Hasegawa Yuko Kitagawa Katsushi Tokunaga Akinori Kimura Satoru Miyano Seishi Ogawa Takanori Kanai Koichi Fukunaga Seiya Imoto |
| author_facet | Takuya Ozawa Shotaro Chubachi Ho Namkoong Shota Nemoto Ryo Ikegami Takanori Asakura Hiromu Tanaka Ho Lee Takahiro Fukushima Shuhei Azekawa Shiro Otake Kensuke Nakagawara Mayuko Watase Katsunori Masaki Hirofumi Kamata Norihiro Harada Tetsuya Ueda Soichiro Ueda Takashi Ishiguro Ken Arimura Fukuki Saito Takashi Yoshiyama Yasushi Nakano Yoshikazu Muto Yusuke Suzuki Ryuya Edahiro Koji Murakami Yasunori Sato Yukinori Okada Ryuji Koike Makoto Ishii Naoki Hasegawa Yuko Kitagawa Katsushi Tokunaga Akinori Kimura Satoru Miyano Seishi Ogawa Takanori Kanai Koichi Fukunaga Seiya Imoto |
| author_sort | Takuya Ozawa |
| collection | DOAJ |
| description | Abstract Predictive models for determining coronavirus disease 2019 (COVID-19) severity have been established; however, the complexity of the interactions among factors limits the use of conventional statistical methods. This study aimed to establish a simple and accurate predictive model for COVID-19 severity using an explainable machine learning approach. A total of 3,301 patients ≥ 18 years diagnosed with COVID-19 between February 2020 and October 2022 were included. The discovery cohort comprised patients whose disease onset fell before October 1, 2020 (N = 1,023), and the validation cohort comprised the remaining patients (N = 2,278). Pointwise linear and logistic regression models were used to extract 41 features. Reinforcement learning was used to generate a simple model with high predictive accuracy. The primary evaluation was the area under the receiver operating characteristic curve (AUC). The predictive model achieved an AUC of ≥ 0.905 using four features: serum albumin levels, lactate dehydrogenase levels, age, and neutrophil count. The highest AUC value was 0.906 (sensitivity, 0.842; specificity, 0.811) in the discovery cohort and 0.861 (sensitivity, 0.804; specificity, 0.675) in the validation cohort. Simple and well-structured predictive models were established, which may aid in patient management and the selection of therapeutic interventions. |
| format | Article |
| id | doaj-art-0ae5a302831c4d9d98e47711fc9732cd |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-0ae5a302831c4d9d98e47711fc9732cd2025-08-20T02:41:31ZengNature PortfolioScientific Reports2045-23222025-03-0115111210.1038/s41598-025-85733-5Predicting coronavirus disease 2019 severity using explainable artificial intelligence techniquesTakuya Ozawa0Shotaro Chubachi1Ho Namkoong2Shota Nemoto3Ryo Ikegami4Takanori Asakura5Hiromu Tanaka6Ho Lee7Takahiro Fukushima8Shuhei Azekawa9Shiro Otake10Kensuke Nakagawara11Mayuko Watase12Katsunori Masaki13Hirofumi Kamata14Norihiro Harada15Tetsuya Ueda16Soichiro Ueda17Takashi Ishiguro18Ken Arimura19Fukuki Saito20Takashi Yoshiyama21Yasushi Nakano22Yoshikazu Muto23Yusuke Suzuki24Ryuya Edahiro25Koji Murakami26Yasunori Sato27Yukinori Okada28Ryuji Koike29Makoto Ishii30Naoki Hasegawa31Yuko Kitagawa32Katsushi Tokunaga33Akinori Kimura34Satoru Miyano35Seishi Ogawa36Takanori Kanai37Koichi Fukunaga38Seiya Imoto39Division of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDepartment of Infectious Diseases, Keio University School of MedicineIndustrial and Digital Business Unit, Hitachi, LtdIndustrial and Digital Business Unit, Hitachi, LtdDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDepartment of Respiratory Medicine, Faculty of Medicine, Graduate School of Medicine, Juntendo UniversityDepartment of Respiratory Medicine, Osaka Saiseikai Nakatsu HospitalJCHO (Japan Community Health Care Organization, Internal Medicine, Saitama Medical CenterDepartment of Respiratory Medicine, Saitama Cardiovascular and Respiratory CenterDepartment of Respiratory Medicine, Tokyo Women’s Medical UniversityDepartment of Emergency and Critical Care Medicine, Kansai Medical University General Medical CenterRespiratory Disease Center, Fukujuji HospitalDepartment of Internal Medicine, Kawasaki Municipal Ida HospitalDepartment of Infectious Diseases, Tosei General HospitalDepartment of Clinical Medicine (Laboratory of Bioregulatory Medicine), Kitasato University School of PharmacyDepartment of Statistical Genetics, Osaka University Graduate School of MedicineDepartment of Respiratory Medicine, Tohoku University Graduate School of MedicineBiostatistics Unit, Clinical and Translational Research Center, Keio University HospitalDepartment of Statistical Genetics, Osaka University Graduate School of MedicineHealth Science Research and Development Center, Tokyo Medical and Dental UniversityDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDepartment of Infectious Diseases, Keio University School of MedicineDepartment of Surgery, Keio University School of MedicineGenome Medical Science Project (Toyama), National Center for Global Health and MedicineInstitute of Research, Tokyo Medical and Dental UniversityM&D Data Science Center, Tokyo Medical and Dental UniversityDepartment of Pathology and Tumor Biology, Kyoto UniversityDivision of Gastroenterology and Hepatology, Department of Medicine, Keio University School of MedicineDivision of Pulmonary Medicine, Department of Internal Medicine, Keio University School of MedicineDivision of Health Medical Intelligence, Human Genome Center, the Institute of Medical Science, the University of TokyoAbstract Predictive models for determining coronavirus disease 2019 (COVID-19) severity have been established; however, the complexity of the interactions among factors limits the use of conventional statistical methods. This study aimed to establish a simple and accurate predictive model for COVID-19 severity using an explainable machine learning approach. A total of 3,301 patients ≥ 18 years diagnosed with COVID-19 between February 2020 and October 2022 were included. The discovery cohort comprised patients whose disease onset fell before October 1, 2020 (N = 1,023), and the validation cohort comprised the remaining patients (N = 2,278). Pointwise linear and logistic regression models were used to extract 41 features. Reinforcement learning was used to generate a simple model with high predictive accuracy. The primary evaluation was the area under the receiver operating characteristic curve (AUC). The predictive model achieved an AUC of ≥ 0.905 using four features: serum albumin levels, lactate dehydrogenase levels, age, and neutrophil count. The highest AUC value was 0.906 (sensitivity, 0.842; specificity, 0.811) in the discovery cohort and 0.861 (sensitivity, 0.804; specificity, 0.675) in the validation cohort. Simple and well-structured predictive models were established, which may aid in patient management and the selection of therapeutic interventions.https://doi.org/10.1038/s41598-025-85733-5COVID-19Machine learningArtificial intelligence |
| spellingShingle | Takuya Ozawa Shotaro Chubachi Ho Namkoong Shota Nemoto Ryo Ikegami Takanori Asakura Hiromu Tanaka Ho Lee Takahiro Fukushima Shuhei Azekawa Shiro Otake Kensuke Nakagawara Mayuko Watase Katsunori Masaki Hirofumi Kamata Norihiro Harada Tetsuya Ueda Soichiro Ueda Takashi Ishiguro Ken Arimura Fukuki Saito Takashi Yoshiyama Yasushi Nakano Yoshikazu Muto Yusuke Suzuki Ryuya Edahiro Koji Murakami Yasunori Sato Yukinori Okada Ryuji Koike Makoto Ishii Naoki Hasegawa Yuko Kitagawa Katsushi Tokunaga Akinori Kimura Satoru Miyano Seishi Ogawa Takanori Kanai Koichi Fukunaga Seiya Imoto Predicting coronavirus disease 2019 severity using explainable artificial intelligence techniques Scientific Reports COVID-19 Machine learning Artificial intelligence |
| title | Predicting coronavirus disease 2019 severity using explainable artificial intelligence techniques |
| title_full | Predicting coronavirus disease 2019 severity using explainable artificial intelligence techniques |
| title_fullStr | Predicting coronavirus disease 2019 severity using explainable artificial intelligence techniques |
| title_full_unstemmed | Predicting coronavirus disease 2019 severity using explainable artificial intelligence techniques |
| title_short | Predicting coronavirus disease 2019 severity using explainable artificial intelligence techniques |
| title_sort | predicting coronavirus disease 2019 severity using explainable artificial intelligence techniques |
| topic | COVID-19 Machine learning Artificial intelligence |
| url | https://doi.org/10.1038/s41598-025-85733-5 |
| work_keys_str_mv | AT takuyaozawa predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT shotarochubachi predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT honamkoong predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT shotanemoto predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT ryoikegami predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT takanoriasakura predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT hiromutanaka predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT holee predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT takahirofukushima predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT shuheiazekawa predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT shirootake predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT kensukenakagawara predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT mayukowatase predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT katsunorimasaki predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT hirofumikamata predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT norihiroharada predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT tetsuyaueda predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT soichiroueda predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT takashiishiguro predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT kenarimura predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT fukukisaito predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT takashiyoshiyama predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT yasushinakano predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT yoshikazumuto predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT yusukesuzuki predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT ryuyaedahiro predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT kojimurakami predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT yasunorisato predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT yukinoriokada predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT ryujikoike predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT makotoishii predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT naokihasegawa predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT yukokitagawa predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT katsushitokunaga predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT akinorikimura predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT satorumiyano predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT seishiogawa predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT takanorikanai predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT koichifukunaga predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques AT seiyaimoto predictingcoronavirusdisease2019severityusingexplainableartificialintelligencetechniques |