Skip to main content

Table 3 Comparison of performance metrics for the HEA BioBERT architecture at 80% and 100% coverage. Coverage refers to the percent of articles the model makes a prediction for (as opposed to abstaining from making a prediction when the model has a confidence below the Threshold). The Precision, Recall, and Accuracy scores reflect the accuracy of the model on the resulting 80% of predicted articles

From: AutoDiscern: rating the quality of online health information with hierarchical encoder attention-based neural networks

Question

Coverage

Threshold

Precision

Recall

Accuracy

Q4: References

80%

0.79

0.87

0.79

87%

Q5: Date

80%

0.79

0.87

0.88

87%

Q9: How Treatment Works

80%

0.81

0.84

0.71

82%

Q10: Treatment Benefits

80%

0.70

0.66

0.55

83%

Q11: Treatment Risks

80%

0.86

0.90

0.90

91%

Q4: References

100%

0.50

0.83

0.80

84%

Q5: Date

100%

0.50

0.83

0.83

83%

Q9: How Treatment Works

100%

0.50

0.77

0.72

78%

Q10: Treatment Benefits

100%

0.50

0.57

0.54

77%

Q11: Treatment Risks

100%

0.50

0.81

0.81

81%