Table 4.

Prediction performance of the proposed method versus benchmark techniques.

Technique and outcome class		Precision	Recall	F-measure	AUCa
Temporal MMCBRb
	AHEc	0.20	0.17	0.18	0.50
	HRSd	0.09	0.10	0.10	0.54
	Neither	0.97	0.96	0.96	0.54
Time fusion CNNe
	AHE	0.12	0.33	0.18	0.65
	HRS	0.06	0.38	0.10	0.67
	Neither	0.97	0.81	0.88	0.63
T-LSTMf
	AHE	0.09	0.33	0.14	0.65
	HRS	0.05	0.27	0.09	0.68
	Neither	0.97	0.84	0.90	0.63
RNN-LRg
	AHE	0.21	0.42	0.28	0.82
	HRS	0.08	0.40	0.13	0.64
	Neither	0.98	0.85	0.91	0.66

^aAUC: area under the curve.

^bMMCBR: multiple measurement case-based reasoning.

^cAHE: acute hepatic encephalopathy.

^dHRS: hepatorenal syndrome.

^eCNN: convolutional neural network.

^fT-LSTM: time aware long short-term memory.

^gRNN-LR: recurrent neural network-latent regulator.