Abstract
Introduction: Chronic kidney disease (CKD) is a significant concern following renal tumor surgery, impacting long-term renal function and patient outcomes. This study investigated the potential of computed tomography (CT)-based radiomics as a quantitative imaging approach to predict postoperative CKD in kidney tumor patients. Methods: We included adult patients with renal tumor surgery treated at our center between 2012 and 2022. Preoperative retrospective CT-imaging data were analyzed, and radiomic features were extracted from tumor lesions and renal parenchyma. Machine learning models were trained to predict postoperative new-onset CKD based on clinical information and radiomics. Model performance was assessed using five-fold cross-validation on the training set (n = 65) and on a separate test set (n = 17). Model performance was primarily evaluated using the receiver operating characteristic curve, with the area under the curve (AUC) serving as the principal summary metric. Results: The study cohort comprised n = 82 patients, of whom n = 25 (30%) developed postoperative new-onset CKD. The best models achieved a mean validation AUC of 0.74 [95% CI: 0.60–0.86] for solely radiomics, 0.83 [0.73–0.93] with clinical information only, and 0.80 [0.67–0.91] on radiomics and clinical parameters, respectively (p > 0.05). For the test dataset, AUCs were 0.62 [95% CI: 0.29–0.92], 0.77 [0.50–0.98], and 0.80 [0.52–1.00], respectively (p > 0.05). Conclusion: Preoperative CT-based radiomic features in combination with clinical information can serve as a noninvasive predictor of postoperative CKD in renal tumor patients undergoing surgical resection. While prospective and external validation is needed, this approach facilitated clinical decision-making and enabled personalized treatment strategies in patients with renal tumors.
Plain Language Summary
Patients who have surgery to remove a kidney tumor can sometimes develop chronic kidney disease (CKD) afterward. CKD means that the kidneys cannot clean the blood as well as they should. It is usually identified when a person’s “estimated glomerular filtration rate” – a common measure of kidney function – drops below a certain level. Being able to predict who is at risk before surgery could help doctors choose the safest treatment plan. In this study, we examined whether information from routine pre-surgery computed tomography scans could help predict which patients may develop CKD after their operation. We used a method called “radiomics,” which means turning medical images into numerical data that describe patterns and structures not easily seen by the human eye. We combined this imaging information with patients’ clinical data, such as age, kidney function before surgery, and other health conditions. We analyzed records from 82 adults who had surgery for a kidney tumor. Of these patients, about 30% developed CKD after their procedure. We built computer-based prediction models using different sets of information: radiomics alone, clinical data alone, and both together. We then tested how well these models could identify patients at higher risk. The results showed that clinical information together with radiomics improved the prediction of CKD compared to clinical data alone. Overall, the study suggests that combining medical imaging and clinical information may help support decision-making before kidney tumor surgery. More research with larger groups of patients is needed to confirm these findings.
