Skip to main content
Fig. 3 | Cardiovascular Diabetology

Fig. 3

From: Machine-learning to stratify diabetic patients using novel cardiac biomarkers and integrative genomics

Fig. 3

Feature importance of mitochondrial DNA SNPs from patients. a The most important predictive parameters using binary classification with HbA1c, the absolute value of a feature being high (red) or low (blue) depicting diabetic (right-side) or non-diabetic (left-side) status. b The most important predictive parameters using binary classification without HbA1c, the absolute value of a feature being high (red) or low (blue) depicting diabetic (right-side) or non-diabetic (left-side) status. c Frequency of mitochondrial DNA SNPs by nucleotide converted in ND and T2DM patients; increasing frequency of SNPs occurring in the patient population are depicted by movement closer to the mitochondrial DNA strand. d SHAP binary depiction with HbA1c of the interaction between SNP16126 and HbA1c. e SHAP binary depiction without HbA1c of the interaction between SNP7028 and SNP73. SHAP values > 0.0 are diabetic (T2DM), SHAP values < 0.0 are non-diabetic (ND), SHAP values = 0 are either ND or T2DM without influence on the model. ND: non-diabetic; T2DM: type 2 diabetic; HbA1c: glycated hemoglobin; binary: no diabetes and diabetes; multiple: no diabetes, prediabetes, and type 2 diabetes

Back to article page