Table 1.

Performance of the algorithm for predicting daily dosage in the validation sample

Models	Prescription type	N	Accuracy (95% CI)	G-means (95% CI)
Non-informativeness prediction (NLP1 model)	Regular prescriptions	982	0.992 (0.986 to 0.998)	0.969 (0.958 to 0.980)
	Titrated prescriptions	18	1.000 (1.000 to 1.000)	1.000 (1.000 to 1.000)
	All prescriptions	1000	0.992 (0.968 to 0.998)	0.973 (0.963 to 0.983)
Dosage prediction (NLP2 model)	Regular prescriptions	852	0.964 (0.951 to 0.976)	0.969 (0.957 to 0.981)
	Titrated prescriptions	18	0.944 (0.839 to 1.000)	0.972 (0.896 to 1.000)
	All prescriptions	870	0.963 (0.951 to 0.976)	0.968 (0.956 to 0.980)
Overall prediction	Regular prescriptions	982	0.968 (0.957 to 0.979)	N/A
	Titrated prescriptions	18	0.944 (0.839 to 1.000)	N/A
	All prescriptions	1000	0.968 (0.957 to 0.979)	N/A

N/A, not available; NLP1, first natural language processing model; NLP2, second natural language processing model.