Will the kidney function be reduced in patients with renal cell carcinoma following laparoscopic partial nephrectomy? Baseline eGFR, warm ischemia time, and RENAL nephrometry score could tell

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.

Prediction of surgical decision and postoperative renal function using RENAL nephrometry score for localized renal masses: A prospective study

Purpose

The purpose of the study is to assess the value of RENAL nephrometry score (RNS) in predicting surgical decisions, complications, and decreases in kidney function in patients with localized renal tumors.

Methods

Cases with solitary, solid, and enhancing renal masses were included, scheduled for nephron-sparing surgery (NSS), and assessed using routine laboratory and radiological data necessary for calculating the RENAL score. The primary endpoint was conversion to radical nephrectomy (RN), while the secondary endpoint was the prediction of a drop in renal function assessed by postoperative estimated glomerular filtration rate (eGFR) at the last follow-up visit compared with the preoperative values. The association between the scoring system and perioperative outcomes was evaluated.

Results

In all, 84 cases were included, NSS was accomplished in 67 cases while conversion to RN was mandatory in 17 patients, median (interquartile range) RENAL score was 6.2 (4-10) for NSS and 9.7 (6-12) for RN (P < 0.001). Higher grades of complications were observed in the high-complexity subgroup. eGFR was 79.8 that dropped to 75.6 ml/min/1.73 m2 in the late value in patients who underwent NSS, while it was 82.9 that dropped to 58.3 ml/min/1.73 m2 in the late value in patients who converted into RN (P < 0.001). The percentage of drop in eGFR was significantly higher in the moderate and high-risk groups, which was positively correlated with the warm ischemia time. Regression analysis revealed that the continuous RENAL score was a more significant predictor of conversion to RN than tumor size alone. In the 67 NNS cases, the percentage decrease in eGFR was predicted using the continuous RENAL score.

Conclusion

The RNS is a significant predictor of conversion to RN and can predict the percentage decrease in eGFR after NSS. Further investigations and follow-ups are necessary.

Impact of ischemia time during partial nephrectomy on short- and long-term renal function

OBJECTIVE

Partial nephrectomy is the gold standard treatment in small renal tumours. During partial nephrectomy, the renal artery is clamped which creates transient ischemia. This can damage nephrons and may affect kidney function immediately postoperatively and on long-term.In the present study, we investigated the effect of ischemia time during partial nephrectomy with regards to affection of renal function immediately post-operatively and 1-year post-surgery.

MATERIALS AND METHOD

A retrospective cohort study including 124 patients who underwent partial nephrectomy at a single regional hospital in the period from 2018 to 2020 was conducted.

RESULTS

We divided patients into subgroups based on the ischemia time: [0-8], [9-13] and [14-29] minutes. The mean value for kidney function was an eGFR (mL/min) of 73.9 before and 66.8 at a 12-month post-surgery. We found no significant correlation between ischemia time and renal function. Noticeably, none of the patients had ischemia time greater than 30 min.

CONCLUSION

In this cohort, the duration of ischemia time was not associated with differences in renal affection neither on short term nor long term parameters if the ischemia time was kept below 30 min.

Identification of predictive factors for outcomes after robot-assisted partial nephrectomy based on three-dimensional reconstruction of preoperative enhanced computerized tomography

Background

Information from the RENAL score is limited. This study aimed to identify new parameters based on three-dimensional (3D) reconstruction of preoperative enhanced computerized tomography (CT) for predicting outcomes after robot-assisted partial nephrectomy (RPN).

Materials and methods

The records of kidney cancer patients who underwent RPN at Tongji Hospital from March 2015 to July 2019 were reviewed. Demographic data, laboratory examinations, postoperative hospitalization time, and enhanced CT were retrospectively collected. Some tumor parameters were obtained from 3D reconstruction of CT data. The association between these predictive factors and outcomes after RPN was analyzed.

Results

A larger tumor bed area (TBA) was associated with a longer warm ischemia time (WIT) (P-value <0.001) and tumor resection time (P-value <0.001). Moreover, TBA was significantly associated with the elevation of postoperative creatinine (P-value = 0.005). TBA (P = 0.008), distance from the tumor to the first bifurcation of the renal artery (DTA) (P <0.034), and RENAL score (P = 0.005) were significantly associated with WIT in univariate logistic regression. In multivariate logistic regression, TBA (P = 0.026) and DTA (P = 0.048) were independent risk factors for prolonged WIT (over 25 min). The predictive effect of the combination of TBA, DTA, and RENAL score was higher than the predictive effect of RENAL score alone for WIT (area under curve: 0.786 versus 0.72).

Conclusion

TBA and DTA are independently associated with the WIT of RPN, which provides additional assessment value for the complexity of kidney cancer in RPN over the RENAL score.

Mixed Reality: A Step Further for Planning Complex Renal Tumors(RENAL nephrometry score of 7 or higher)

OBJECTIVES

Mixed reality (MR) technology has emerged in recent years and allows three-dimensional visualization, multi-angle observation, remote vision, and virtual-real interaction. This study aims to explore the influence of MR technology on the outcomes and strategy planning of robotic surgery for complex renal tumors.

PATIENTS AND METHODS

A total of 92 patients with complex renal tumors were enrolled in this study from June 2018 to June 2020. All patients were diagnosed in our department by magnetic resonance imaging（MRI）. This trial follows CONSORT guidelines and adopts a parallel single blind design and randomizes patients with a random number table. The study was approved by the institutional review board, and written informed consent was obtained from each participant. All surgeries were performed by 3 experienced and high-volume surgeons. The demographic indicators, intraoperative and postoperative complications, renal function outcomes, pathological results, and surgical strategies were recorded. Student's t-test and Wilcoxon rank-sum were used to compare continuous variables, and Pearson's chi-squared and Fisher's exact tests were used to compare categorical variables.

RESULTS

WIT is mainly composed of tumor resection time and reconstruction time, and the reconstruction time accounts for a larger proportion. For urologists treating complex renal tumors, MR technology can help them reduce warm ischemia time (21.3±4.0 vs 23.6±5.9min, P=0.031), reconstruction time (15.4±3.8 vs 17.2±4.2min, P=0.034), estimated blood loss (P=0.044), operation time (125.7±26.3 vs 144.6±27.9min, P=0.001) and intraoperative complications (P=0.030).

CONCLUSIONS

MR assisted surgery can reduce the incidence of intraoperative complications, improve perioperative outcomes, which may be a good preoperative tool for planning complex renal tumors.

Identifying the predictors of estimated glomerular filtration rate after partial nephrectomy with a nonlinear regression model

PURPOSE

To evaluate the effect of partial nephrectomy on renal function and to identify predictors of estimated glomerular filtration rate (eGFR) at 6 months after partial nephrectomy.

METHODS

Medical data of 154 consecutive patients who underwent partial nephrectomy for a renal mass between January 2015 and March 2020 were retrospectively analysed. The primary outcome measure was eGFR at 6 months postoperatively. An ordinary least regression analysis using a restricted cubic spline for continuous variables was performed to examine the association between primary outcome measure and candidate predictors.

RESULTS

Of the patients, 66 (42.9%) were females and 88 (57.1%) were males with a median age of 60 (range, 50 to 67) years. The median baseline eGFR was 90.40 (range, 74.96 to 102.97) mL/min/1.73 m² , while the median eGFR at 6 months was 77.12 (range, 61.06 to 91.93) mL/min/1.73 m² (P < .001). Baseline eGFR (regression coefficient (β) = 22.7, 95%CI: 18.8 to 26.5, P < .001) was found to be most significant predictor with the postoperative eGFR levels at 6 months. In addition, advanced tumour size (β = -3.17, 95%CI: -5.33 to -1.01, P < .001) and presence of hypertension (β = -3.48, 95%CI: -6.96 to -0.003, P = .049) were also found to be inversely associated with the postoperative eGFR levels at 6 months.

CONCLUSION

Baseline eGFR values, tumour size, and presence of hypertension are significant predictors of eGFR values in the mid-term in patients undergoing partial nephrectomy.