A deep learning approach for classifying and predicting children's nutritional status in Ethiopia using LSTM-FC neural networks

Table 1 Performance metrics of LSTM-FC model across different time-based data splits

Train set	Test set	Sensitivity	Specificity	Precision	F1	AUC (95% CI)	Accuracy (95% CI)
2002 and 2006	2009	0.72	0.68	0.7	0.71	0.74 (0.70–0.78)	0.69 (0.65–0.73)
2002, 2006, and 2009	20,013	0.78	0.75	0.76	0.77	0.80 (0.76–0.84)	0.77 (0.73–0.81)
2002, 2006, 2009, and 2013	2016	0.85	0.84	0.83	0.84	0.90 (0.87–0.93)	0.83 (0.79–0.87)
2006 and 2009	20,013	0.75	0.72	0.74	0.74	0.78 (0.74–0.82)	0.73 (0.69–0.77)
2009 and 2013	2016	0.81	0.79	0.8	0.8	0.84 (0.80–0.88)	0.82 (0.78–0.86)

ISSN: 1756-0381