Prediction of Postoperative Creatinine Levels by Artificial Intelligence after Partial Nephrectomy.

Background and Objectives: Multiple factors are associated with postoperative functional outcomes, such as acute kidney injury (AKI), following partial nephrectomy (PN). The pre-, peri-, and postoperative factors are heavily intertwined and change dynamically, making it difficult to predict postoperative renal function. Therefore, we aimed to build an artificial intelligence (AI) model that utilizes perioperative factors to predict residual renal function and incidence of AKI following PN. Methods and Materials: This retrospective study included 785 patients (training set 706, test set 79) from six tertiary referral centers who underwent open or robotic PN. Forty-four perioperative features were used as inputs to train the AI prediction model. XG-Boost and genetic algorithms were used for the final model selection and to determine feature importance. The primary outcome measure was immediate postoperative serum creatinine (Cr) level. The secondary outcome was the incidence of AKI (estimated glomerular filtration rate (eGFR) < 60 mL/h). The average difference between the true and predicted serum Cr levels was considered the mean absolute error (MAE) and was used as a model evaluation parameter. Results: An AI model for predicting immediate postoperative serum Cr levels was selected from 2000 candidates by providing the lowest MAE (0.03 mg/dL). The model-predicted immediate postoperative serum Cr levels correlated closely with the measured values (R2 = 0.9669). The sensitivity and specificity of the model for predicting AKI were 85.5% and 99.7% in the training set, and 100.0% and 100.0% in the test set, respectively. The limitations of this study included its retrospective design. Conclusions: Our AI model successfully predicted accurate serum Cr levels and the likelihood of AKI. The accuracy of our model suggests that personalized guidelines to optimize multidisciplinary plans involving pre- and postoperative care need to be developed.

Treatment of depression and effect of antidepression treatment on nutritional status in chronic hemodialysis patients.

BACKGROUND: Depression, which is the most common psychological complication in patients with end-stage renal disease (ESRD), has an impact on the clinical outcome and is associated with malnutrition in chronic hemodialysis patients. This study evaluated the effect of antidepression treatment on nutritional status in depressed chronic hemodialysis patients. METHODS: Sixty-two ESRD patients who underwent dialysis for more than 6 months were interviewed and completed a Beck Depression Inventory assessment. Thirty-four patients who had scores greater than 18 on the Beck Depression Inventory score and met Diagnostic and Statistical Manual of Mental Disorders, 4th Edition criteria for major depressive disorder were selected to receive paroxetine 10 mg/day and psychotherapy for 8 weeks. The remaining 28 patients were assigned to the control group. Change in the severity of depressive symptoms was ascertained by administering the Hamilton Depression Rating Scale. Nutritional status was evaluated by normalized protein catabolic rate, serum albumin and blood urea nitrogen level. RESULTS: All patients successfully completed 8 weeks of antidepression treatment. Antidepression treatment decreased the severity of depressive symptoms (Hamilton Depression Rating Scale score: 16.6 +/- 7.0 versus 15.1 +/- 6.6, P < 0.01) and increased normalized protein catabolic rate (1.04 +/- 0.24 versus 1.17 +/- 0.29 g/kg/day, P < 0.05), serum albumin (37.3 +/- 2.0 versus 38.7 +/- 3.2 g/l, P < 0.005), and prehemodialysis blood urea nitrogen level (24.3 +/- 5.6 versus 30.2 +/- 7.9 mmol/L, P < 0.001). In the control group, no change was noted during the study period. CONCLUSION: This study suggests that antidepressant medication with supportive psychotherapy can successfully treat depression and improve nutritional status in chronic hemodialysis patients with depression.

Association of depression with malnutrition in chronic hemodialysis patients.

BACKGROUND: Depression is the most common psychological complication and may increase mortality in chronic hemodialysis patients. Because depression could be associated with poor oral intake and activation of proinflammatory cytokines that could further increase mortality by malnutrition, we investigated the relation between depression and nutritional status in chronic hemodialysis patients. METHODS: Sixty-two Korean patients completed the Beck Depression Inventory (BDI) questionnaire, and the diagnosis of depression was confirmed by Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition (DSM-IV) criteria for major depressive disorder. Nutritional status was evaluated using serum albumin level, normalized protein catabolic rate, subjective global assessment (SGA), and anthropometric measurement. RESULTS: Mean BDI score was 22.7 +/- 11.4, and 35 patients (56.5%) had a BDI score greater than 21, which is the suggested cutoff score for the diagnosis of depression for the Korean population. Of 40 patients who had a score higher than 18 on the BDI, 34 patients met DSM-IV criteria for major depressive disorder. BDI score correlated negatively with a variety of nutritional parameters: serum albumin level (r = -0.47; P < 0.001), normalized protein catabolic rate (r = -0.32; P < 0.05), SGA (r = -0.47; P < 0.01), triceps skinfold thickness (r = -0.40; P < 0.05), midarm muscle circumference (r = -0.57; P < 0.01), and body mass index (r = -0.28; P < 0.05). Multiple regression analysis also identified BDI score as an independent determinant for all kinds of nutritional parameters. CONCLUSION: In patients on chronic hemodialysis therapy, depression is related closely to nutritional status and could be an independent risk factor for malnutrition.

KLOTHO gene polymorphism is associated with coronary artery stenosis but not with coronary calcification in a Korean population.

Experimental studies have demonstrated KLOTHO gene polymorphism might be associated with vascular atherosclerosis and calcification. However, the impact of this genetic variant on human coronary arteries still remains to be elucidated. We investigated the effect of a KLOTHO gene variant on coronary artery stenosis and calcification. Four hundred and thirty-four patients referred for chest pain were enrolled. All the patients underwent coronary angiography and were investigated for polymorphism of the KLOTHO G395A gene. Coronary artery disease (CAD) was defined as > or = 50% diameter stenosis in at least one coronary artery. The other patients were considered to be controls. Homozygotes or heterozygotes for G395A were significantly more common in the CAD patients than in the controls (30.2% versus 21.5%, P = 0.039). In the subgroup aged < 60 years, the G395A mutant was more frequent in CAD than in control (35.3% versus 18.8%, P = 0.016), but in patients > or = 60 years, there was no difference (28.0% versus 24.1%, P = 0.473). Using multivariate analysis, we identified the KLOTHO gene G395A mutant as an independent risk factor of CAD (OR 1.712, 95% CI [1.066-2.749], P = 0.026). The frequency of the KLOTHO gene G395A mutant was not different between the calcified and noncalcified coronary artery groups (25.7%, 26.4%, respectively, P = 0.861) and an A allele carrier state was not an independent risk factor of coronary artery calcification. In conclusion, the KLOTHO gene G395A allele carrier state may be associated with CAD but not with coronary artery calcification in this Korean population.