BMC Medical Informatics and Decision Making

Table 4 The utility of the dataset was tested by evaluating a clinical entity recognition system. The precision (P), recall (R), and F₁ were calculated for every entity type using each version of the dataset

From: A pseudonymized corpus of occupational health narratives for clinical entity recognition in Spanish

Entity	Original			Masked			Pseudonymized
Entity	P	R	F₁	P	R	F₁	P	R	F₁
Disease	0.93	0.78	0.85	0.90	0.74	0.81	0.92	0.76	0.83
Body part	0.96	0.98	0.97	0.95	0.98	0.96	0.95	0.98	0.97
Medication	0.96	0.94	0.95	0.93	0.94	0.93	0.96	0.93	0.95

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com