Table 4.

Comparison of recent works of predictive models for diabetic kidney disease or diabetic nephropathy.

Source	Dataset	Model	Complication	Accuracy (%)
Sobrinho et al., 2020 [20]	114 instances and 8 attributes	J48 decision tree	DKD	95
Senan et al., 2021 [19]	400 instances and 24 attributes	Recursive feature elimination to choose attributes followed by random forest classification	DKD	100
Almansour et al., 2019 [21]	400 instances and 24 attributes	Artificial neural network	CKD	99.7
Khanam and foo, 2021 [22]	768 instances and 9 attributes	Neural network	Diabetes	88.6
Our study	410 instances and 18 attributes	IBK and random tree	DKD	93.6585