Predicting the Disease Outcome in COVID-19 Positive Patients Through Machine Learning: A Retrospective Cohort Study With Brazilian Data

被引:26
作者
Hojo De Souza, Fernanda Sumika [1 ]
Hojo-Souza, Natalia Satchiko [2 ]
Dos Santos, Edimilson Batista [1 ]
Da Silva, Cristiano Maciel [3 ]
Guidoni, Daniel Ludovico [1 ]
机构
[1] Univ Fed Sao Joao del Rei, Dept Comp Sci, Sao Joao Del Rei, Brazil
[2] Oswaldo Cruz Fdn Minas, Lab Immunopathol, Belo Horizonte, MG, Brazil
[3] Univ Fed Sao Joao del Rei, Dept Technol, Ouro Branco, Brazil
来源
FRONTIERS IN ARTIFICIAL INTELLIGENCE | 2021年 / 4卷
关键词
COVID-19; prediction model; disease outcome; machine learning; Brazil;
D O I
10.3389/frai.2021.579931
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The first officially registered case of COVID-19 in Brazil was on February 26, 2020. Since then, the situation has worsened with more than 672, 000 confirmed cases and at least 36, 000 reported deaths by June 2020. Accurate diagnosis of patients with COVID-19 is extremely important to offer adequate treatment, and avoid overloading the healthcare system. Characteristics of patients such as age, comorbidities and varied clinical symptoms can help in classifying the level of infection severity, predict the disease outcome and the need for hospitalization. Here, we present a study to predict a poor prognosis in positive COVID-19 patients and possible outcomes using machine learning. The study dataset comprises information of 8, 443 patients concerning closed cases due to cure or death. Our experimental results show the disease outcome can be predicted with a Receiver Operating Characteristic AUC of 0.92, Sensitivity of 0.88 and Specificity of 0.82 for the best prediction model. This is a preliminary retrospective study which can be improved with the inclusion of further data. Conclusion: Machine learning techniques fed with demographic and clinical data along with comorbidities of the patients can assist in the prognostic prediction and physician decision-making, allowing a faster response and contributing to the non-overload of healthcare systems.
引用
收藏
页数:13
相关论文
共 37 条
[1]   Artificial intelligence and machine learning to fight COVID-19 [J].
Alimadadi, Ahmad ;
Aryal, Sachin ;
Manandhar, Ishan ;
Munroe, Patricia B. ;
Joe, Bina ;
Cheng, Xi .
PHYSIOLOGICAL GENOMICS, 2020, 52 (04) :200-202
[2]  
[Anonymous], 1973, Pattern Classification and Scene Analysis
[3]  
Bishop C.M., 2006, Pattern Recognition and Machine Learning, DOI DOI 10.1007/978-0-387-45528-0
[4]  
Brazilian Institute of Geography and Statistics, 2020, I BRAS GEOGR EST IBG
[5]  
Bruce P., 2017, PRACTICAL STAT DATA
[6]   COVID-19 in Latin America [J].
Burki, Talha .
LANCET INFECTIOUS DISEASES, 2020, 20 (05) :547-548
[7]  
Chen Y., 2020, Technical report
[8]  
de Souza F S., 2020, Frontiers in Artificial Intelligence, DOI DOI 10.1101/2020.06.26.20140764
[9]   Bayesian network classifiers [J].
Friedman, N ;
Geiger, D ;
Goldszmidt, M .
MACHINE LEARNING, 1997, 29 (2-3) :131-163
[10]   Clinical characteristics of coronavirus disease 2019 (COVID-19) in China: A systematic review and meta-analysis [J].
Fu, Leiwen ;
Wang, Bingyi ;
Yuan, Tanwei ;
Chen, Xiaoting ;
Ao, Yunlong ;
Fitzpatrick, Thomas ;
Li, Peiyang ;
Zhou, Yiguo ;
Lin, Yi-fan ;
Duan, Qibin ;
Luo, Ganfeng ;
Fan, Song ;
Lu, Yong ;
Feng, Anping ;
Zhan, Yuewei ;
Liang, Bowen ;
Cai, Weiping ;
Zhang, Lin ;
Du, Xiangjun ;
Li, Linghua ;
Shu, Yuelong ;
Zou, Huachun .
JOURNAL OF INFECTION, 2020, 80 (06) :656-665