BMC Medical Informatics and Decision Making

Table 2 Predictive performance of models using pre-assigned (P) or learned (L) weights in the weighted aggregation (WA) strategy

From: Learning temporal weights of clinical events using variable importance

	Accuracy			AUC			AUPRC
ADE	PWA	LWA		PWA	LWA		PWA	LWA
D611	76.46	76.68		0.882	0.882		0.956	0.954
D642	97.79	97.79		0.973	0.965		0.750	0.688
D695	76.28	76.69		0.863	0.872		0.771	0.768
E273	81.77	81.78		0.681	0.669		0.309	0.323
G620	91.64	91.64		0.809	0.803		0.316	0.326
I952	91.71	91.71		0.583	0.564		0.110	0.107
L270	73.07	72.12		0.847	0.841		0.807	0.793
L271	84.18	84.18		0.774	0.735		0.386	0.342
M804	95.17	95.17		0.652	0.615		0.098	0.075
M814	98.71	98.71		0.732	0.740		0.040	0.050
O355	72.24	71.55		0.978	0.980		0.934	0.942
R502	99.16	99.16		0.800	0.776		0.218	0.168
T782	94.81	94.81		0.712	0.700		0.156	0.152
T783	83.33	83.33		0.749	0.758		0.362	0.363
T784	66.15	66.15		0.734	0.741		0.809	0.811
T801	90.35	90.35		0.891	0.892		0.493	0.458
T808	77.93	77.72		0.882	0.879		0.958	0.958
T886	94.95	94.95		0.689	0.692		0.117	0.109
T887	61.35	60.97		0.751	0.752		0.776	0.773
Average	84.58	84.50		0.788	0.782		0.493	0.482
p-value	0.2936			0.1564			0.08743

Bold indicates winning

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com