A NLP-based semi-automatic identification system for delays in follow-up examinations: an Italian case study on clinical referrals

Table 3 Results of the pipeline on the test set for the temporal information extraction

Metric	Value
Presence/Absence of the temporal indication
Accuracy	0.999
Precision	0.990
Recall	0.973
Correctness of the *NTI*
Accuracy on all referrals	0.998
Accuracy on referrals with any temporal indication	0.953
Accuracy on referrals with a follow-up temporal indication	0.948

Results of the pipeline on the test set, measuring different metrics with respect to both the binary classification problem of presence/absence of the temporal indication and to the accuracy of the extracted NTI

ISSN: 1472-6947