Assessing risk factors for malnutrition among women in Bangladesh and forecasting malnutrition using machine learning approaches

Table 5 Compare the performance of machine learning algorithms across six protocols for malnutrition of women

k	Ac	Kappa	\(F_1\)	SE	SP	PPV	NPV
Naïve Bayes
2	0.590	0.151	0.668	0.751	0.395	0.601	0.568
3	0.592	0.154	0.669	0.754	0.397	0.602	0.571
5	0.593	0.157	0.669	0.751	0.401	0.604	0.572
7	0.594	0.158	0.670	0.753	0.401	0.604	0.573
10	0.593	0.156	0.670	0.753	0.399	0.603	0.571
11	0.593	0.156	0.670	0.752	0.400	0.603	0.571
Classification and Regression Tree
2	0.594	0.146	0.689	0.821	0.319	0.594	0.596
3	0.595	0.149	0.688	0.814	0.329	0.595	0.593
5	0.594	0.147	0.688	0.814	0.328	0.595	0.592
7	0.593	0.147	0.685	0.806	0.335	0.595	0.588
10	0.594	0.149	0.683	0.798	0.346	0.597	0.585
11	0.593	0.147	0.685	0.806	0.335	0.595	0.588
C5.0
2	0.599	0.159	0.689	0.809	0.344	0.599	0.598
3	0.601	0.168	0.681	0.778	0.386	0.606	0.589
5	0.597	0.160	0.681	0.785	0.369	0.602	0.587
7	0.599	0.164	0.683	0.787	0.371	0.603	0.590
10	0.599	0.164	0.681	0.781	0.378	0.604	0.588
11	0.600	0.163	0.686	0.797	0.360	0.602	0.594
Logistic Regression
2	0.598	0.164	0.677	0.769	0.391	0.605	0.582
3	0.597	0.162	0.677	0.769	0.389	0.604	0.581
5	0.599	0.166	0.679	0.773	0.388	0.605	0.585
7	0.600	0.168	0.680	0.774	0.389	0.606	0.586
10	0.598	0.163	0.678	0.771	0.387	0.604	0.583
11	0.599	0.166	0.679	0.774	0.387	0.605	0.585
Random Forest
2	0.597	0.153	0.690	0.817	0.330	0.597	0.598
3	0.596	0.149	0.691	0.826	0.317	0.595	0.600
5	0.599	0.157	0.694	0.827	0.323	0.597	0.606
7	0.599	0.157	0.691	0.820	0.332	0.598	0.602
10	0.600	0.157	0.693	0.826	0.325	0.597	0.606
11	0.599	0.156	0.693	0.824	0.326	0.597	0.604
Gradient Boosting Machine
2	0.602	0.168	0.686	0.793	0.369	0.604	0.596
3	0.600	0.165	0.685	0.794	0.365	0.603	0.594
5	0.603	0.169	0.689	0.803	0.360	0.603	0.601
7	0.603	0.168	0.690	0.807	0.355	0.603	0.603
10	0.604	0.171	0.692	0.811	0.354	0.603	0.607
11	0.602	0.166	0.690	0.809	0.351	0.602	0.602

ISSN: 2055-0928