Loss of Smell and Taste Can Accurately Predict COVID-19 Infection: A Machine-Learning Approach.
Loss of Smell and Taste Can Accurately Predict COVID-19 Infection: A Machine-Learning Approach.
复制标题
DOI：
10.3390/jcm10040570
复制
发表时间：
2021-02-03
影响因子：
3.9
通讯作者：
Sanchez-Gomez S
中科院分区：
文献类型：
--
作者：
Callejon-Leblic MA;Moreno-Luna R;Del Cuvillo A;Reyes-Tejero IM;Garcia-Villaran MA;Santos-Peña M;Maza-Solano JM;Martín-Jimenez DI;Palacios-Garcia JM;Fernandez-Velez C;Gonzalez-Garcia J;Sanchez-Calvo JM;Solanellas-Soler J;Sanchez-Gomez S
COVID-19疫情已在全球广泛蔓延。嗅觉和味觉的丧失已成为COVID-19的主要预测因素。我们研究的目的是开发一个全面的机器学习（ML）建模框架，以评估COVID-19感染中嗅觉和味觉障碍沿着其他症状的预测价值。进行了一项多中心病例对照研究，其中通过实时逆转录聚合酶链反应（RT-PCR）检测的COVID-19疑似病例使用视觉模拟量表（VAS）告知其症状的存在和严重程度。ML算法被应用于收集的数据，通过在训练数据集（75%）和测试数据集（25%）中随机划分患者，使用50倍交叉验证方案预测COVID-19诊断。共纳入777例患者。嗅觉和味觉丧失被发现是COVID-19阳性的更高比值比为6.21和2.42的症状。当使用VAS预测COVID-19诊断时，所应用的ML算法达到了80%的平均准确性，82%的灵敏度和78%的特异性。这项研究得出结论，嗅觉和味觉障碍是准确的预测因子，ML算法构成了COVID-19诊断预测的有用工具。
The COVID-19 outbreak has spread extensively around the world. Loss of smell and taste have emerged as main predictors for COVID-19. The objective of our study is to develop a comprehensive machine learning (ML) modelling framework to assess the predictive value of smell and taste disorders, along with other symptoms, in COVID-19 infection. A multicenter case-control study was performed, in which suspected cases for COVID-19, who were tested by real-time reverse-transcription polymerase chain reaction (RT-PCR), informed about the presence and severity of their symptoms using visual analog scales (VAS). ML algorithms were applied to the collected data to predict a COVID-19 diagnosis using a 50-fold cross-validation scheme by randomly splitting the patients in training (75%) and testing datasets (25%). A total of 777 patients were included. Loss of smell and taste were found to be the symptoms with higher odds ratios of 6.21 and 2.42 for COVID-19 positivity. The ML algorithms applied reached an average accuracy of 80%, a sensitivity of 82%, and a specificity of 78% when using VAS to predict a COVID-19 diagnosis. This study concludes that smell and taste disorders are accurate predictors, with ML algorithms constituting helpful tools for COVID-19 diagnostic prediction.
登录
查看更多内容
影响因子：
3.5
作者：
Barra GB;Santa Rita TH;Mesquita PG;Jácomo RH;Nery LFA
通讯作者：
Nery LFA
影响因子：
--
作者：
Bagheri SH;Asghari A;Farhadi M;Shamshiri AR;Kabir A;Kamrava SK;Jalessi M;Mohebbi A;Alizadeh R;Honarmand AA;Ghalehbaghi B;Salimi A;Dehghani Firouzabadi F
通讯作者：
Dehghani Firouzabadi F
气味和品味变化是19009年大流行和政治决策有效性的早期指标。
影响因子：
16.6
作者：
Pierron D;Pereda-Loth V;Mantel M;Moranges M;Bignon E;Alva O;Kabous J;Heiske M;Pacalon J;David R;Dinnella C;Spinelli S;Monteleone E;Farruggia MC;Cooper KW;Sell EA;Thomas-Danguin T;Bakke AJ;Parma V;Hayes JE;Letellier T;Ferdenzi C;Golebiowski J;Bensafi M
通讯作者：
Bensafi M
影响因子：
6.4
作者：
Roland, Lauren T.;Gurrola, Jose G., II;Chang, Jolie L.
通讯作者：
Chang, Jolie L.
影响因子：
7.8
作者：
Mercante, Giuseppe;Ferreli, Fabio;Spriano, Giuseppe
通讯作者：
Spriano, Giuseppe