Prophylactic Use of Biologic Mesh in Ileal Conduit (PUBMIC): A Randomized Clinical Trial.

PURPOSE: We assessed the effect of prophylactic biologic mesh on parastomal hernia (PSH) development in patients undergoing cystectomy and ileal conduit (IC). MATERIALS AND METHODS: This phase 3, randomized, controlled trial (NCT02439060) included 146 patients who underwent cystectomy and IC at the University of Southern California between 2015 and 2021. Follow-ups were physical exam and CT every 4 to 6 months up to 2 years. Patients were randomized 1:1 to receive FlexHD prophylactic biological mesh using sublay intraperitoneal technique vs standard IC. The primary end point was time to radiological PSH, and secondary outcomes included clinical PSH with/without surgical intervention and mesh-related complications. RESULTS: The 2 arms were similar in terms of baseline clinical features. All surgeries and mesh placements were performed without any intraoperative complications. Median operative time was 31 minutes longer in patients who received mesh, yet with no statistically significant difference (363 vs 332 minutes, P = .16). With a median follow-up of 24 months, radiological and clinical PSHs were detected in 37 (18 mesh recipients vs 19 controls) and 16 (8 subjects in both arms) patients, with a median time to radiological and clinical PSH of 8.3 and 15.5 months, respectively. No definite mesh-related adverse events were reported. Five patients (3 in the mesh and 2 in the control arm) required surgical PSH repair. Radiological PSH-free survival rates in the mesh and control groups were 74% vs 75% at 1 year and 69% vs 62% at 2 years. CONCLUSIONS: Implementation of biologic mesh at the time of IC construction is safe without significant protective effects within 2 years following surgery.

The effect of enhanced recovery after surgery on oncologic outcome following radical cystectomy for urothelial bladder carcinoma.

INTRODUCTION: Limited data are available regarding the effect of enhanced recovery after surgery (ERAS) protocols on the long-term outcomes of radical cystectomy (RC) in bladder cancer patients. The aim of this study is to evaluate the oncological outcomes in patients who underwent RC with ERAS protocol. METHODS: We reviewed the records of patients who underwent RC for primary urothelial bladder carcinoma with curative intent from January 2003 to August 2022. The primary and secondary outcomes were recurrence-free (RFS) and overall survival (OS). Multivariable Cox regression analysis was performed to evaluate the effect of ERAS on oncological outcomes. RESULTS: A total of 967 ERAS patients and 1144 non-ERAS patients were included in this study. The RFS rates at 1, 3, and 5 years after RC were 81%, 71.5%, and 69% in the ERAS cohort, respectively. This rate in the non-ERAS group was 81%, 71%, and 67% at 1, 3, and 5 years after RC, respectively (P = 0.50). However, ERAS patients had significantly better OS with 86%, 73%, and 67% survival rates at 1, 3, and 5 years compared to 84%, 68%, and 59.5% survival rates in the non-ERAS group, respectively (P = 0.002). In multivariable analysis adjusting for other relevant factors, ERAS was no longer independently associated with recurrence-free (HR = 0.96, 95% CI 0.76-1.22, P = 0.75) or overall survival (HR = 0.84, 95% CI 0.66-1.09, P = 0.28) following RC. CONCLUSION: ERAS protocols are associated with a shorter hospital stay, yet with no impact on long-term oncologic outcomes in patients undergoing RC for bladder cancer.

Blood-based liquid biopsy: A promising noninvasive test in diagnosis, surveillance, and prognosis of patients with upper tract urothelial carcinoma.

OBJECTIVES: To assess the efficacy of blood-based liquid biopsy in the diagnosis, surveillance, and prognosis of upper tract urothelial carcinoma (UTUC). METHODS AND MATERIALS: In this prospective study, peripheral blood samples were collected from patients with primary UTUC before surgery with curative intent and follow-up visits at University of Southern California between May 2021 and September 2022. The samples were analyzed using the third-generation comprehensive high-definition single-cell assay (HDSCA3.0) to detect rare events, including circulating tumor cells (CTCs) and oncosomes, based on the immunofluorescence signals of DAPI (D), cytokeratin (CK), CD45/CD31 (CD), and vimentin (V). The findings of pre-surgery liquid biopsies were compared with those of blood samples from normal donors (NDs) and matched follow-up liquid biopsies. The association between liquid biopsy findings and clinical data, including recurrence-free survival (RFS), was also assessed. RESULTS: Twenty-eight patients with UTUC were included, of whom 21 had follow-up samples. Significant differences in specific rare analytes were detected in the preoperative samples compared to the NDs. In the post- vs. presurgery matched analysis, a significant decrease was detected in total-, CK-, and CK|V oncosomes, as well as in D-, D|V-, and D|V|CD cells. With a median follow-up of 11 months, 8 patients had disease recurrence. Survival analysis demonstrated that patients with >1.95 preoperative CK|V oncosomes (p = 0.020) and those with >4.18 D|CK|V cells (p = 0.050) had worse RFS compared to other patients. CONCLUSIONS: This study demonstrated promising initial evidence for the biomarker role of CTCs and oncosomes in the diagnosis and surveillance of patients with UTUC.

Perioperative mortality for radical cystectomy in the modern Era: experience from a tertiary referral center

ABSTRACT Purpose To evaluate the perioperative mortality and contributing variables among patients who underwent radical cystectomy (RC) for bladder cancer in recent decades, with comparison between modern (after 2010) and premodern (before 2010) eras. Materials and Methods Using our institutional review board-approved database, we reviewed the records of patients who underwent RC for primary urothelial bladder carcinoma with curative intent from January 2003 to December 2019. The primary and secondary outcomes were 90- and 30-day mortality. Univariate and multivariable logistic regression models were applied to assess the impact of perioperative variables on 90-day mortality. Results A total of 2047 patients with a mean±SD age of 69.6±10.6 years were included. The 30- and 90-day mortality rates were 1.3% and 4.9%, respectively, and consistent during the past two decades. Among 100 deaths within 90 days, 18 occurred during index hospitalization. Infectious, pulmonary, and cardiac complications were the leading mortality causes. Multivariable analysis showed that age (Odds Ratio: OR 1.05), Charlson comorbidity index ≥ 2 (OR 1.82), blood transfusion (OR 1.95), and pathological node disease (OR 2.85) were independently associated with 90-day mortality. Nevertheless, the surgical approach and enhanced recovery protocols had no significant effect on 90-day mortality. Conclusion The 90-day mortality for RC is approaching five percent, with infectious, pulmonary, and cardiac complications as the leading mortality causes. Older age, higher comorbidity, blood transfusion, and pathological lymph node involvement are independently associated with 90-day mortality.

Perioperative mortality for radical cystectomy in the modern Era: experience from a tertiary referral center.

PURPOSE: To evaluate the perioperative mortality and contributing variables among patients who underwent radical cystectomy (RC) for bladder cancer in recent decades, with comparison between modern (after 2010) and premodern (before 2010) eras. MATERIALS AND METHODS: Using our institutional review board-approved database, we reviewed the records of patients who underwent RC for primary urothelial bladder carcinoma with curative intent from January 2003 to December 2019. The primary and secondary outcomes were 90- and 30-day mortality. Univariate and multivariable logistic regression models were applied to assess the impact of perioperative variables on 90-day mortality. RESULTS: A total of 2047 patients with a mean±SD age of 69.6±10.6 years were included. The 30- and 90-day mortality rates were 1.3% and 4.9%, respectively, and consistent during the past two decades. Among 100 deaths within 90 days, 18 occurred during index hospitalization. Infectious, pulmonary, and cardiac complications were the leading mortality causes. Multivariable analysis showed that age (Odds Ratio: OR 1.05), Charlson comorbidity index ≥ 2 (OR 1.82), blood transfusion (OR 1.95), and pathological node disease (OR 2.85) were independently associated with 90-day mortality. Nevertheless, the surgical approach and enhanced recovery protocols had no significant effect on 90-day mortality. CONCLUSION: The 90-day mortality for RC is approaching five percent, with infectious, pulmonary, and cardiac complications as the leading mortality causes. Older age, higher comorbidity, blood transfusion, and pathological lymph node involvement are independently associated with 90-day mortality.

Association between early postradical cystectomy kidney injury and perioperative outcome in enhanced recovery era.

OBJECTIVE: To evaluate the incidence and predictors of early postoperative acute kidney injury (EP-AKI) during index hospitalization following radical cystectomy and its association with postoperative outcomes. METHODS: All patients with bladder cancer who underwent radical cystectomy with intent-to-cure at our center between 2012 and 2020 were reviewed. EP-AKI during index hospitalization was evaluated using the Acute Kidney Injury Network criteria. The association between EP-AKI and demographics, clinicopathologic features, and perioperative outcomes, including length of hospital stay, complication rate, and readmission rate, were examined. A logistic regression analysis was performed to evaluate the predictors of EP-AKI. RESULTS: Overall, 435 patients met eligibility, of whom 112 (26%) experienced EP-AKI during index hospitalization (90 [21%] stage 1, 17 [4%] stage 2, and 5 [1%] stage 3). EP-AKI was associated with a longer mean operative time (6.8 vs. 6.1 hours; P < 0.001), higher mean length of hospital stay (6.3 vs. 5.6; P = 0.02), 30-day complication rate (71% vs. 51%; P < 0.001), 90-day complication rate (81% vs. 69%; P = 0.01) and 90-day readmission rate (37% vs. 33%; P = 0.04). The rate of complications increased at higher stages of AKI. On multivariable analysis, perioperative blood transfusion (OR: 1.84, P = 0.02) and continent diversion (OR: 3.29, P < 0.001) were independent predictors of EP-AKI. CONCLUSION: A quarter of cystectomy patients experience acute kidney injury during index hospitalization, which is associated with higher length of stay, postoperative complication, and readmission rates. Perioperative blood transfusion and continent diversion are independent predictors of such injury.

A Urine-based DNA Methylation Marker Test to Detect Upper Tract Urothelial Carcinoma: A Prospective Cohort Study.

PURPOSE: We explored the accuracy of a urine-based epigenetic test for detecting upper tract urothelial carcinoma. MATERIALS AND METHODS: Under an Institutional Review Board-approved protocol, urine samples were prospectively collected from primary upper tract urothelial carcinoma patients before radical nephroureterectomy, ureterectomy, or ureteroscopy between December 2019 and March 2022. Samples were analyzed with Bladder CARE, a urine-based test that measures the methylation levels of 3 cancer biomarkers (TRNA-Cys, SIM2, and NKX1-1) and 2 internal control loci using methylation-sensitive restriction enzymes coupled with quantitative polymerase chain reaction. Results were reported as the Bladder CARE Index score and quantitatively categorized as positive (>5), high risk (2.5-5), or negative (<2.5). The findings were compared with those of 1:1 sex/age-matched cancer-free healthy individuals. RESULTS: Fifty patients (40 radical nephroureterectomy, 7 ureterectomy, and 3 ureteroscopy) with a median (IQR) age of 72 (64-79) years were included. Bladder CARE Index results were positive in 47, high risk in 1, and negative in 2 patients. A significant correlation was found between Bladder CARE Index values and tumor size. Urine cytology was available for 35 patients, of whom 22 (63%) results were false-negative. Upper tract urothelial carcinoma patients had significantly higher Bladder CARE Index values compared to the controls (mean 189.3 vs 1.6, P < .001). The sensitivity, specificity, positive predictive value, and negative predictive value of the Bladder CARE test for detecting upper tract urothelial carcinoma were 96%, 88%, 89%, and 96%, respectively.Conclusions:Bladder CARE is an accurate urine-based epigenetic test for the diagnosis of upper tract urothelial carcinoma, with much higher sensitivity than standard urine cytology.

Obturator Nerve Injury in Robotic Pelvic Surgery: Scenarios and Management Strategies.

BACKGROUND: Obturator nerve injury (ONI) is an uncommon complication of pelvic surgery, usually reported in 0.2-5.7% of cases undergoing surgical treatment of urological and gynecological malignancies involving pelvic lymph node dissection (PLND). OBJECTIVE: To describe how an ONI may occur during robotic pelvic surgery and the corresponding management strategies. DESIGN, SETTING, AND PARTICIPANTS: We retrospectively analyzed video content on intraoperative ONI provided by robotic surgeons from high-volume centers. SURGICAL PROCEDURE: ONI was identified during PLND and managed according to the type of nerve injury. RESULTS AND LIMITATIONS: The management approach varies with the type of injury. Crush injury frequently occurs at an advanced stage of PLND. For a crush injury to the obturator nerve caused by a clip, management only requires its safe removal. Three situations can occur if the nerve is transected: (1) transection with feasible approximation and tension-free nerve anastomosis; (2) transection with challenging approximation requiring certain strategies for proper nerve anastomosis; and (3) transection with a hidden proximal nerve ending that may initially appear intact, but is clearly injured when revealed by further dissection. Each case has different management strategies with a common aim of prompt repair of the anatomic disruption to restore proper nerve conduction. CONCLUSIONS: ONI is a preventable complication that requires proper identification of the anatomy and high-risk areas when performing pelvic lymph node dissection. Prompt intraoperative recognition and repair using the management strategies described offer patients the best chance of recovery without sequelae. PATIENT SUMMARY: We describe the different ways in which the obturator nerve in the pelvic area can be damaged during urological or gynecological surgeries. This is a preventable complication and we describe how it can be avoided and different management options, depending on the type of nerve injury.

Radical cystectomy and urinary diversion outcomes in patients with single vs. double renal unit: A 2:1 matched-pair analysis.

OBJECTIVE: To evaluate perioperative and functional outcomes of radical cystectomy (RC) and urinary diversion (UD) in patients with a single kidney (SK) vs. double kidneys (DK). METHODS: We reviewed records of patients who underwent RC for bladder cancer with a history of prior or concurrent nephrectomy at USC between 2004 and 2020. Patients with chronic kidney disease who were already on dialysis were excluded. UD, perioperative complications, and postoperative glomerular filtration rate (GFR) of the SK group were compared with a group of patients who underwent RC with DK using 2:1 matching with respect to age, sex, preop GFR, and tumor stage. RESULTS: We included 186 patients (SK = 62 and DK = 124). Half of the SK patients underwent continent UD. SK patients had a higher length of hospital stay compared to the DK group; however, 90-day complications, readmission, and mortality rates were similar. In patients with continent diversion, SK vs. DK showed similar 90-day complications (71% vs. 69%, P = 1.0). SK patients had significantly lower GFRs at discharge, 3-, and 12-month following RC compared to the DK group. Postoperative GFRs of the SK patients with continent vs. incontinent UD were statistically similar. On multivariable analysis, UD (i.e. continent vs. incontinent) was not associated with post-op GFR decline at discharge, 3- and 12-month following RC. CONCLUSIONS: Perioperative outcomes of radical cystectomy patients with single kidney are similar to double kidney patients, except for more GFR decline in single kidney cases. Continent urinary diversion in single kidney is as safe as double kidney patients.

The Impact of Facility Surgical Caseload Volumes on Survival Outcomes in Patients Undergoing Radical Cystectomy.

The role of surgical experience and its impact on the survival requires further investigation. A cohort of patients undergoing radical cystectomy or anterior pelvic exenteration for localized bladder cancer between 2006 and 2013 at 1143 facilities across the United States was identified using the National Cancer Database and analyzed. Using overall survival (OS) as the primary outcome, the relationship between facility annual caseload (FAC) and facility annual surgical caseload (FASC) for those undergoing curative surgery was examined. Four volume groups (VG) depending on caseload using both FAC and FASC were defined. These included VG1: below 50th percentile, VG2: 50th−74th percentile, VG3: 75th−89th percentile, and VG4: 90th and above. Between 2006 and 2013, 27,272 patients underwent surgery for localized bladder cancer. The median OS was 59.66 months (95% CI: 57.79−61.77). OS improved significantly as caseload increased. The unadjusted median OS difference between VG1 and VG4 was 15.35 months (64.3 vs. 48.95 months, HR 1.19 95% CI: 1.13−1.25, p < 0.001) for FAC. This figure was 19.84 months (66.89 vs. 47.05 months, HR 1.25 95% CI: 1.18−1.32, p < 0.0001) for FASC. This analysis revealed a significant and clinically important survival advantage for curative bladder cancer surgery at highly experienced centers.

Impact of Patient, Surgical, and Perioperative Factors on Discharge Disposition after Radical Cystectomy.

Radical cystectomy (RC) is a complex procedure associated with lengthy hospital stays and high complication and readmission rates. We evaluated the impact of patient, surgical, and perioperative factors on discharge disposition following RC at a tertiary referral center. From 2012 to 2019, all bladder cancer patients undergoing RC at our institution were identified (n = 1153). Patients were classified based on discharge disposition: to home or to continued facility-based rehabilitation centers (CFRs, n = 180 (15.61%) patients). On multivariate analysis of patient factors only, age [Risk Ratio (RR): 1.07, p < 0.001)], single marital status (RR: 1.09, p < 0.001), and living alone prior to surgery (RR: 2.55, p = 0.004) were significant predictors of discharge to CFRs. Multivariate analysis of patient, surgical, and perioperative factors indicated age (RR: 1.09, p < 0.001), single marital status (RR: 3.9, p < 0.001), living alone prior to surgery (RR: 2.42, p = 0.01), and major post-operative (Clavien > 3) complications (RR: 3.44, p < 0.001) were significant independent predictors of discharge to CFRs. Of note, ERAS did not significantly impact discharge disposition. Specific patient and perioperative factors significantly impact discharge disposition. Patients who are older, living alone prior to surgery, and/or have a major post-operative complication are more likely to be discharged to CFRs after RC.

Chronic kidney disease and radical cystectomy for bladder cancer: perioperative and oncologic outcomes in 1,214 patients.

INTRODUCTION AND OBJECTIVE: To assess the impact of chronic kidney disease (CKD) on outcomes after radical cystectomy (RC) in patients with bladder cancer treated within a high-volume tertiary referral center. METHODS: We identified 1,214 patients who underwent RC with intent to cure from 2009 to 2019. The Modification of Diet in Renal Disease (MDRD) GFR (ml/min/1.73 m²) was calculated and patients were categorized by baseline GFR: Group A = GFR > 60, Group B = GFR > 30-59 and Group C = GFR < 30. Pre-, intra- and postoperative characteristics, oncological outcomes, and 90-day perioperative outcomes were compared. Multivariable logistic regression was used to control for confounding variables. RESULTS: We identified 722 (59.5%) patients in Group A, 448 (36.9%) in Group B, and 44 (3.6%) in Group C. Patients with worse CKD were older and had significantly worse overall comorbidity (all P < 0.001). Neoadjuvant chemotherapy was used in 352 patients (29%), including 182 (25.2%) in Group A, 153 in Group B (35.3%), and 12 in Group C (27.3%). On univariate analysis, worse CKD was associated with higher pathologic stage, lymph node metastases and positive soft tissue margins (all P < 0.0001). The rates of blood transfusion, 90-day complications and readmissions were higher in patients with worse CKD (P < 0.0001, P = 0.02, P = 0.04, respectively). Patients with worse CKD had worse overall survival (77% vs. 73% vs. 55%, P < 0.0001). On multivariable analysis, worse CKD was independently associated with adverse pathology (≥pT3 or node positive) (OR = 6.96, 95%CI 3.20-15.12), 90-day readmissions (OR 2.09, 95%CI 1.11-3.94) and perioperative transfusion (OR 2.08, 95%CI 1.05-4.11). Receipt of neoadjuvant chemotherapy was significantly associated with a decreased risk of adverse pathology (OR 0.51, 95%CI 0.36-0.74) and increased risk of transfusion (OR 2.24, 95%CI 1.70-2.96), but not with mortality, complications, readmissions or length or stay. CONCLUSION: CKD is prevalent in patients undergoing radical cystectomy. We found CKD to be independently associated with a higher likelihood of adverse pathology, 90-day readmissions, and transfusion.

An Enhanced Recovery After Surgery protocol for robotic-assisted laparoscopic nephrectomies utilizing a quadratus lumborum block.

Enhanced Recovery After Surgery (ERAS) protocols have been developed in several fields to reduce hospitalization lengths and overall costs. There have also been developments in multimodal analgesia methods to curtail opioid usage after surgery. Herein, we present the results of our initiation of an ERAS protocol for robotic-assisted laparoscopic partial and radical nephrectomies, employing a quadratus lumborum (QL) regional anesthetic block. We retrospectively reviewed 614 patients in our Institutional Review Board approved database who underwent robotic-assisted laparoscopic partial or radical nephrectomies from January 2017 to February 2020. An ERAS protocol utilizing multimodal analgesia (acetaminophen and gabapentin) and a QL block was developed and introduced in February 2019. We then compared the opioid consumption and perioperative outcomes of patients before and after ERAS protocol initiation. 192 ERAS patients (February 2019 to February 2020) were compared to 422 non-ERAS patients (January 2017 to January 2019). Baseline characteristics and the proportion of preoperative opioids users were similar between the two groups. There were no statistically significant differences in surgery length, hospitalization length, or complication rates. There were statistically significant differences in our primary endpoint, opioid consumption, on post-operative days 0 (p < 0.001), 1 (p < 0.001), and 2 (p < 0.001). The total opioid requirements over the course of admission were lower in the ERAS group compared to the non-ERAS group (p = 0.03). The initiation of an ERAS protocol employing multimodal analgesia and a QL block, for patients undergoing robotic-assisted laparoscopic partial or radical nephrectomies, can decrease opioid requirements without compromising perioperative outcomes.

Robotic Repair of Ureteroenteric Stricture Following Radical Cystectomy: A Multi-Institutional Experience.

OBJECTIVE: To examine the safety, feasibility and durability of robotic reimplantation of ureteroenteric stricture after radical cystectomy. MATERIALS AND METHODS: A retrospective multi-institutional review was performed for all patients undergoing robotic repair of ureteroenteric stricture from January 2010 to January 2019. Functional outcomes and complications were followed and data were analyzed with SPSS statistical software. RESULTS: A total of 46 patients and 58 renal units were identified, of which 15 had right sided, 19 left sided and 12 patients had bilateral strictures. Presentation of stricture was asymptomatic in 14 (30.4%) patients. Symptomatic presentations included infection in 22 (47.8%), worsening renal function in 11 (23.9%) and pain in 3 (6.5%) patients. Median time from cystectomy to diagnosis of stricture was 5 months (1-40). Median stricture length was 1.5 cm (range 0.5-10). All strictures were of benign etiology except for 4 (6.9%), which were due to malignancy. Overall, 49 (84.5%) ureters underwent primary re-implantation, while 9 (15.5%) required Boari-like advancement flaps prior to re-implantation. Median operative time was 190 min (range 45-540) with median estimated blood loss of 50 mL (range 25-2000) and median length of stay of 2 days (range 1-33, IQR 2-4). Seven (15.2%) patients experienced complications; 3 (6.5%) were low grade and 4 (8.7%) high grade. With median follow up of 18 months (range 1-51) the stricture recurrence rate was 8.6%. CONCLUSION: Robotic reimplantation of ureteroenteric strictures following radical cystectomy is safe and feasible in experienced centers with high success rates.

An Assessment Tool to Provide Targeted Feedback to Robotic Surgical Trainees: Development and Validation of the End-To-End Assessment of Suturing Expertise (EASE).

Purpose: To create a suturing skills assessment tool that comprehensively defines criteria around relevant sub-skills of suturing and to confirm its validity. Materials and Methods: 5 expert surgeons and an educational psychologist participated in a cognitive task analysis (CTA) to deconstruct robotic suturing into an exhaustive list of technical skill domains and sub-skill descriptions. Using the Delphi methodology, each CTA element was systematically reviewed by a multi-institutional panel of 16 surgical educators and implemented in the final product when content validity index (CVI) reached ≥0.80. In the subsequent validation phase, 3 blinded reviewers independently scored 8 training videos and 39 vesicourethral anastomoses (VUA) using EASE; 10 VUA were also scored using Robotic Anastomosis Competency Evaluation (RACE), a previously validated, but simplified suturing assessment tool. Inter-rater reliability was measured with intra-class correlation (ICC) for normally distributed values and prevalence-adjusted bias-adjusted Kappa (PABAK) for skewed distributions. Expert (≥100 prior robotic cases) and trainee (<100 cases) EASE scores from the non-training cases were compared using a generalized linear mixed model. Results: After two rounds of Delphi process, panelists agreed on 7 domains, 18 sub-skills, and 57 detailed sub-skill descriptions with CVI ≥ 0.80. Inter-rater reliability was moderately high (ICC median: 0.69, range: 0.51-0.97; PABAK: 0.77, 0.62-0.97). Multiple EASE sub-skill scores were able to distinguish surgeon experience. The Spearman's rho correlation between overall EASE and RACE scores was 0.635 (p=0.003). Conclusions: Through a rigorous CTA and Delphi process, we have developed EASE, whose suturing sub-skills can distinguish surgeon experience while maintaining rater reliability.

A Radiomic-based Machine Learning Algorithm to Reliably Differentiate Benign Renal Masses from Renal Cell Carcinoma.

BACKGROUND: A substantial proportion of patients undergo treatment for renal masses where active surveillance or observation may be more appropriate. OBJECTIVE: To determine whether radiomic-based machine learning platforms can distinguish benign from malignant renal masses. DESIGN, SETTING, AND PARTICIPANTS: A prospectively maintained single-institutional renal mass registry was queried to identify patients with a computed tomography-proven clinically localized renal mass who underwent partial or radical nephrectomy. INTERVENTION: Radiomic analysis of preoperative scans was performed. Clinical and radiomic variables of importance were identified through decision tree analysis, which were incorporated into Random Forest and REAL Adaboost predictive models. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The primary outcome was the degree of congruity between the virtual diagnosis and final pathology. Subanalyses were performed for small renal masses and patients who had percutaneous renal mass biopsies as part of their workup. Receiver operating characteristic curves were used to evaluate each model's discriminatory function. RESULTS AND LIMITATIONS: A total of 684 patients met the selection criteria. Of them, 76% had renal cell carcinoma; 57% had small renal masses, of which 73% were malignant. Predictive modeling differentiated benign pathology from malignant with an area under the curve (AUC) of 0.84 (95% confidence interval [CI] 0.79-0.9). In small renal masses, radiomic analysis yielded a discriminatory AUC of 0.77 (95% CI 0.69-0.85). When negative and nondiagnostic biopsies were supplemented with radiomic analysis, accuracy increased from 83.3% to 93.4%. CONCLUSIONS: Radiomic-based predictive modeling may distinguish benign from malignant renal masses. Clinical factors did not substantially improve the diagnostic accuracy of predictive models. Enhanced diagnostic predictability may improve patient selection before surgery and increase the utilization of active surveillance protocols. PATIENT SUMMARY: Not all kidney tumors are cancerous, and some can be watched. We evaluated a new method that uses radiographic features invisible to the naked eye to distinguish benign masses from true cancers and found that it can do so with acceptable accuracy.