PMC:7782580 / 23852-27130 JSONTXT

{"project":"LitCovid-PubTator","denotations":[{"id":"185","span":{"begin":758,"end":766},"obj":"Disease"},{"id":"188","span":{"begin":824,"end":832},"obj":"Disease"},{"id":"189","span":{"begin":912,"end":920},"obj":"Disease"},{"id":"195","span":{"begin":2052,"end":2061},"obj":"Disease"},{"id":"196","span":{"begin":2264,"end":2273},"obj":"Disease"},{"id":"197","span":{"begin":2284,"end":2292},"obj":"Disease"},{"id":"198","span":{"begin":2668,"end":2676},"obj":"Disease"},{"id":"199","span":{"begin":2678,"end":2687},"obj":"Disease"}],"attributes":[{"id":"A185","pred":"tao:has_database_id","subj":"185","obj":"MESH:C000657245"},{"id":"A188","pred":"tao:has_database_id","subj":"188","obj":"MESH:C000657245"},{"id":"A189","pred":"tao:has_database_id","subj":"189","obj":"MESH:C000657245"},{"id":"A195","pred":"tao:has_database_id","subj":"195","obj":"MESH:D011014"},{"id":"A196","pred":"tao:has_database_id","subj":"196","obj":"MESH:D011014"},{"id":"A197","pred":"tao:has_database_id","subj":"197","obj":"MESH:C000657245"},{"id":"A198","pred":"tao:has_database_id","subj":"198","obj":"MESH:C000657245"},{"id":"A199","pred":"tao:has_database_id","subj":"199","obj":"MESH:D011014"}],"namespaces":[{"prefix":"Tax","uri":"https://www.ncbi.nlm.nih.gov/taxonomy/"},{"prefix":"MESH","uri":"https://id.nlm.nih.gov/mesh/"},{"prefix":"Gene","uri":"https://www.ncbi.nlm.nih.gov/gene/"},{"prefix":"CVCL","uri":"https://web.expasy.org/cellosaurus/CVCL_"}],"text":"Experiment-D\nThe boxplots of the five evaluation indicators, the F1 score (Fig. 5a, d, g), the kappa coefficient (Fig. 5b, e, h), and the specificity (Fig. 5c, f, i) of experiments A–C are shown in Fig. 5, and the precision and sensitivity are shown in Supplementary Fig. 2. A bootstrapping method40 was used to calculate the empirical distributions, and McNemar’s test41 was used to analyze the differences between the CNNCF and the experts. The p-values of the McNemar’s test (Supplementary Tables 1–3) for the five evaluation indicators were all 1.0, indicating no statistically significant difference between the CNNCF results and the expert evaluations.\nFig. 5 Boxplots of the F1 score, kappa score, and specificity for the CNNCF and expert results for COVID-19 identification.\nNC indicates that the positive case is a COVID-19 case, and the negative case is *Normal. CI indicates that the positive case is COVID-19, and the negative case is influenza. Bootstrapping is used to generate n = 1000 resampled independent validation sets for the XVS and the CTVS. a F1 score for the NC using X-data. b Kappa score for the NC using X-data. c Specificity for the NC using X-data. d F1 score for the NC using CT-data. e Kappa score for the NC using CT-data. f Specificity for the NC using CT-data. g F1 score for the CI using CT-data. h Kappa score for the CI using CT-data. i Specificity for the CI using CT-data.\nWe also conducted extra experiments with both configurations of the same data source and different data sources: the descriptions and graph charts can be found in the Supplementary Experiments and Tables (Supplementary Tables 4–19 and Supplementary Figs. 3–18). The data used in experiments E–G were CTHVS and the data were all from the Youan hospital. The data used in experiments H–K were XHVS and the data were all from the Youan hospital. The data used in experiments L–N were XPVS and CTPVS. The data used in the experiment L was from the same data set RSNA, while the data used in experiment M was from different data sets where the pneumonia cases were from the ICNP, and the normal cases were from LUNA16. The data used in the experiments O–R, from the four public data sets and one hospital (Youan hospital) data set (including normal cases, pneumonia cases and COVID-19 cases), were XMVS and CTMVS. In all the experiments (experiments A–R), the CNNCF achieved good performance. Notably, in order to obtain a more comprehensive evaluation of the CNNCF while further improving the usability in clinical practice, experiment-R was performed. In the experiment-R, the CNNCF was used to distinguish three types of cases simultaneously (Including the COVID-19, pneumonia, and normal cases) on both the XMVS and CTMVS. Good performances were obtained on the XMVS, with the best score of F1 score of 91.89%, kappa score of 89.74%, specificity of 97.14%, sensitivity of 94.44%, and a precision of 89.47%, respectively. Excellent performances were obtained on the CTMVS, with the best score of the five evaluation indicators were all 100.00%. The ROC score and PRC score in the experiment-R were also satisfactory which were shown in Supplementary Fig. 18. The results of the experiment-R further demonstrated the effectiveness and robustness of the proposed CNNCF."}

{"project":"LitCovid-PD-HP","denotations":[{"id":"T13","span":{"begin":2052,"end":2061},"obj":"Phenotype"},{"id":"T14","span":{"begin":2264,"end":2273},"obj":"Phenotype"},{"id":"T15","span":{"begin":2678,"end":2687},"obj":"Phenotype"}],"attributes":[{"id":"A13","pred":"hp_id","subj":"T13","obj":"http://purl.obolibrary.org/obo/HP_0002090"},{"id":"A14","pred":"hp_id","subj":"T14","obj":"http://purl.obolibrary.org/obo/HP_0002090"},{"id":"A15","pred":"hp_id","subj":"T15","obj":"http://purl.obolibrary.org/obo/HP_0002090"}],"text":"Experiment-D\nThe boxplots of the five evaluation indicators, the F1 score (Fig. 5a, d, g), the kappa coefficient (Fig. 5b, e, h), and the specificity (Fig. 5c, f, i) of experiments A–C are shown in Fig. 5, and the precision and sensitivity are shown in Supplementary Fig. 2. A bootstrapping method40 was used to calculate the empirical distributions, and McNemar’s test41 was used to analyze the differences between the CNNCF and the experts. The p-values of the McNemar’s test (Supplementary Tables 1–3) for the five evaluation indicators were all 1.0, indicating no statistically significant difference between the CNNCF results and the expert evaluations.\nFig. 5 Boxplots of the F1 score, kappa score, and specificity for the CNNCF and expert results for COVID-19 identification.\nNC indicates that the positive case is a COVID-19 case, and the negative case is *Normal. CI indicates that the positive case is COVID-19, and the negative case is influenza. Bootstrapping is used to generate n = 1000 resampled independent validation sets for the XVS and the CTVS. a F1 score for the NC using X-data. b Kappa score for the NC using X-data. c Specificity for the NC using X-data. d F1 score for the NC using CT-data. e Kappa score for the NC using CT-data. f Specificity for the NC using CT-data. g F1 score for the CI using CT-data. h Kappa score for the CI using CT-data. i Specificity for the CI using CT-data.\nWe also conducted extra experiments with both configurations of the same data source and different data sources: the descriptions and graph charts can be found in the Supplementary Experiments and Tables (Supplementary Tables 4–19 and Supplementary Figs. 3–18). The data used in experiments E–G were CTHVS and the data were all from the Youan hospital. The data used in experiments H–K were XHVS and the data were all from the Youan hospital. The data used in experiments L–N were XPVS and CTPVS. The data used in the experiment L was from the same data set RSNA, while the data used in experiment M was from different data sets where the pneumonia cases were from the ICNP, and the normal cases were from LUNA16. The data used in the experiments O–R, from the four public data sets and one hospital (Youan hospital) data set (including normal cases, pneumonia cases and COVID-19 cases), were XMVS and CTMVS. In all the experiments (experiments A–R), the CNNCF achieved good performance. Notably, in order to obtain a more comprehensive evaluation of the CNNCF while further improving the usability in clinical practice, experiment-R was performed. In the experiment-R, the CNNCF was used to distinguish three types of cases simultaneously (Including the COVID-19, pneumonia, and normal cases) on both the XMVS and CTMVS. Good performances were obtained on the XMVS, with the best score of F1 score of 91.89%, kappa score of 89.74%, specificity of 97.14%, sensitivity of 94.44%, and a precision of 89.47%, respectively. Excellent performances were obtained on the CTMVS, with the best score of the five evaluation indicators were all 100.00%. The ROC score and PRC score in the experiment-R were also satisfactory which were shown in Supplementary Fig. 18. The results of the experiment-R further demonstrated the effectiveness and robustness of the proposed CNNCF."}

{"project":"LitCovid-sentences","denotations":[{"id":"T186","span":{"begin":0,"end":12},"obj":"Sentence"},{"id":"T187","span":{"begin":13,"end":274},"obj":"Sentence"},{"id":"T188","span":{"begin":275,"end":442},"obj":"Sentence"},{"id":"T189","span":{"begin":443,"end":658},"obj":"Sentence"},{"id":"T190","span":{"begin":659,"end":782},"obj":"Sentence"},{"id":"T191","span":{"begin":783,"end":872},"obj":"Sentence"},{"id":"T192","span":{"begin":873,"end":957},"obj":"Sentence"},{"id":"T193","span":{"begin":958,"end":1412},"obj":"Sentence"},{"id":"T194","span":{"begin":1413,"end":1674},"obj":"Sentence"},{"id":"T195","span":{"begin":1675,"end":1765},"obj":"Sentence"},{"id":"T196","span":{"begin":1766,"end":1855},"obj":"Sentence"},{"id":"T197","span":{"begin":1856,"end":1909},"obj":"Sentence"},{"id":"T198","span":{"begin":1910,"end":2126},"obj":"Sentence"},{"id":"T199","span":{"begin":2127,"end":2321},"obj":"Sentence"},{"id":"T200","span":{"begin":2322,"end":2400},"obj":"Sentence"},{"id":"T201","span":{"begin":2401,"end":2561},"obj":"Sentence"},{"id":"T202","span":{"begin":2562,"end":2734},"obj":"Sentence"},{"id":"T203","span":{"begin":2735,"end":2932},"obj":"Sentence"},{"id":"T204","span":{"begin":2933,"end":3055},"obj":"Sentence"},{"id":"T205","span":{"begin":3056,"end":3169},"obj":"Sentence"},{"id":"T206","span":{"begin":3170,"end":3278},"obj":"Sentence"}],"namespaces":[{"prefix":"_base","uri":"http://pubannotation.org/ontology/tao.owl#"}],"text":"Experiment-D\nThe boxplots of the five evaluation indicators, the F1 score (Fig. 5a, d, g), the kappa coefficient (Fig. 5b, e, h), and the specificity (Fig. 5c, f, i) of experiments A–C are shown in Fig. 5, and the precision and sensitivity are shown in Supplementary Fig. 2. A bootstrapping method40 was used to calculate the empirical distributions, and McNemar’s test41 was used to analyze the differences between the CNNCF and the experts. The p-values of the McNemar’s test (Supplementary Tables 1–3) for the five evaluation indicators were all 1.0, indicating no statistically significant difference between the CNNCF results and the expert evaluations.\nFig. 5 Boxplots of the F1 score, kappa score, and specificity for the CNNCF and expert results for COVID-19 identification.\nNC indicates that the positive case is a COVID-19 case, and the negative case is *Normal. CI indicates that the positive case is COVID-19, and the negative case is influenza. Bootstrapping is used to generate n = 1000 resampled independent validation sets for the XVS and the CTVS. a F1 score for the NC using X-data. b Kappa score for the NC using X-data. c Specificity for the NC using X-data. d F1 score for the NC using CT-data. e Kappa score for the NC using CT-data. f Specificity for the NC using CT-data. g F1 score for the CI using CT-data. h Kappa score for the CI using CT-data. i Specificity for the CI using CT-data.\nWe also conducted extra experiments with both configurations of the same data source and different data sources: the descriptions and graph charts can be found in the Supplementary Experiments and Tables (Supplementary Tables 4–19 and Supplementary Figs. 3–18). The data used in experiments E–G were CTHVS and the data were all from the Youan hospital. The data used in experiments H–K were XHVS and the data were all from the Youan hospital. The data used in experiments L–N were XPVS and CTPVS. The data used in the experiment L was from the same data set RSNA, while the data used in experiment M was from different data sets where the pneumonia cases were from the ICNP, and the normal cases were from LUNA16. The data used in the experiments O–R, from the four public data sets and one hospital (Youan hospital) data set (including normal cases, pneumonia cases and COVID-19 cases), were XMVS and CTMVS. In all the experiments (experiments A–R), the CNNCF achieved good performance. Notably, in order to obtain a more comprehensive evaluation of the CNNCF while further improving the usability in clinical practice, experiment-R was performed. In the experiment-R, the CNNCF was used to distinguish three types of cases simultaneously (Including the COVID-19, pneumonia, and normal cases) on both the XMVS and CTMVS. Good performances were obtained on the XMVS, with the best score of F1 score of 91.89%, kappa score of 89.74%, specificity of 97.14%, sensitivity of 94.44%, and a precision of 89.47%, respectively. Excellent performances were obtained on the CTMVS, with the best score of the five evaluation indicators were all 100.00%. The ROC score and PRC score in the experiment-R were also satisfactory which were shown in Supplementary Fig. 18. The results of the experiment-R further demonstrated the effectiveness and robustness of the proposed CNNCF."}