Table 3.
Studies using AI to diagnose renal cancer.
| Study | Application of the Study | Type of Study | Size of the Sample Used | Features Used for Training | Algorithms Used | Accuracy, % | Sensitivity, % | Specificity, % | AUC |
|---|---|---|---|---|---|---|---|---|---|
| Zheng et al., 2016 [18] | Forecast the presence of the disease in the earlier stages | Retrospective | 126 patients (68 healthy participants and 48 renal cell cancer (RCC) patients) | Serum metabolome biomarker cluster | ANN: healthy participants | 91.3 | - | - | - |
| ANN: RCC | 94.7 | - | - | - | |||||
| Haifler et al., 2018 [19] | Discriminate between normal and malignant renal tissue | Prospective | 6 clear-cell RCC specimens; 6 normal kidney tissue specimens | Short-wave infrared Raman spectroscopy | SMLR | 92.5 | 95.8 | 88.8 | 0.94 |
Sparse Multinomial Logistic Regression (SMLR).