| Id |
Subject |
Object |
Predicate |
Lexical cue |
| T91 |
0-50 |
Sentence |
denotes |
Development and validation of the diagnostic model |
| T92 |
51-346 |
Sentence |
denotes |
To develop an optimal model, we evaluated 3 models by analyzing (i) the clinical features model (C model), (ii) radiological semantic features model (R model), and (iii) the combination of clinical and radiological semantic features model (CR model) by multivariate logistic regression analysis. |
| T93 |
347-476 |
Sentence |
denotes |
The classification performances of the models were evaluated by the area under the receiver operating characteristic (ROC) curve. |
| T94 |
477-569 |
Sentence |
denotes |
The area under the curve (AUC), accuracy, sensitivity, and specificity were also calculated. |
| T95 |
570-771 |
Sentence |
denotes |
A decision curve analysis was conducted to determine the clinical usefulness of the diagnostic model by quantifying the net benefits at different threshold probabilities in the validation dataset [24]. |
| T96 |
772-851 |
Sentence |
denotes |
The development of decision curve was described in the Supplementary Materials. |
| T97 |
852-933 |
Sentence |
denotes |
Figure 2 depicts the flowchart of the proposed analysis pipeline described above. |
| T98 |
934-1138 |
Sentence |
denotes |
We also built a nomogram, which was a quantitative tool to predict the individual probability of infection by COVID-19, based on the multivariate logistic analysis of the CR model with the primary cohort. |
| T99 |
1139-1295 |
Sentence |
denotes |
Depending on the coefficient of the predictive factors in multivariate logistic regression model, all values of each predictive factor were assigned points. |
| T100 |
1296-1375 |
Sentence |
denotes |
A total point was obtained by summing all the points of each predictive factor. |
| T101 |
1376-1486 |
Sentence |
denotes |
The scale also showed the relationship between the total point and the prediction probability in the nomogram. |
| T102 |
1487-1634 |
Sentence |
denotes |
The corresponding calibration curves of the CR model in the primary cohort and validation cohort are shown in the Supplementary Material (Fig. E3). |
| T103 |
1635-1694 |
Sentence |
denotes |
Fig. 2 Workflow of data process and analysis in this study. |
| T104 |
1695-1825 |
Sentence |
denotes |
Radiological semantic features, including qualitative and quantitative imaging features, are extracted from axial lung CT section. |
| T105 |
1826-1918 |
Sentence |
denotes |
The clinical manifestation and laboratory parameters are provided by electronic case system. |
| T106 |
1919-2033 |
Sentence |
denotes |
Statistical analysis is performed for comparing the different features between COVID-19 and non-COVID-19 patients. |
| T107 |
2034-2211 |
Sentence |
denotes |
Univariate analysis, least absolute shrinkage, and selection operator (LASSO) are further performed to determine the COVID-19 risk factors with p < 0.05 in statistical analysis. |
| T108 |
2212-2308 |
Sentence |
denotes |
Three models based on the selected features are established by multivariate logistic regression. |
| T109 |
2309-2451 |
Sentence |
denotes |
These models include radiological mode (R model), clinical model (C model), and the combination of clinical and radiological model (CR model). |
| T110 |
2452-2629 |
Sentence |
denotes |
The performance and clinical benefits of the prediction model are assessed by the area under a receiver operating characteristic (ROC) curve and the decision curve, respectively |
