Industry Payments to Cardiology Fellows and Early-Career Cardiologists.

This cohort study evaluates marketing payments from pharmaceutical and medical device manufacturers to physician trainees before and after fellowship graduation.

Association of Genomic Prostate Score at positive margin with recurrence after radical prostatectomy.

OBJECTIVES: To evaluate the utility of the 17-gene Genomic Prostate Score® (GPS; MDxHealth, Irvine, CA, USA) performed on prostate cancer at the positive margin of the radical prostatectomy (RP) for its association with risk of subsequent biochemical recurrence (BCR). PATIENTS AND METHODS: We designed a case-cohort for the outcome of BCR, selecting 223 from a cohort of 813 RP patients treated at Johns Hopkins from 2008 to 2017 with positive margins and available clinical data; of these, 213 had available tissue and clinical data. RNA was isolated from formalin-fixed paraffin-embedded tumour tissue adjacent to the positive surgical margin and the GPS was evaluable in 203 of these patients with a score ranging from 0 to 100, with higher scores indicating higher risk. All patients underwent RP with or without adjuvant radiation therapy (ART). The statistical analysis employed Cox proportional hazards regression models for outcome of BCR weighted for case-cohort design. RESULTS: In univariable analysis, every 20-unit increase in the GPS was associated with a nearly threefold increase in risk of BCR (hazard ratio [HR] per 20 units 2.82, P < 0.001). In a multivariable Cox model adjusted for age, race, Cancer of the Prostate Risk Assessment Postsurgical score, Grade Group at the positive margin, and ART, the GPS was significantly associated with BCR (HR 1.56 per 20 units; 95% confidence interval 1.11-2.19; P = 0.011). The study is limited by its retrospective and single institution design. CONCLUSIONS: The GPS at the positive surgical margin could help stratify prognosis and inform clinical decision-making regarding adjuvant therapy after RP.

ERAS for Ambulatory TURBT: Enhancing Bladder Cancer Care (EMBRACE) randomised controlled trial protocol.

INTRODUCTION: Transurethral resection of bladder tumour (TURBT) is one of the more common procedures performed by urologists. It is often described as an 'incision-free' and 'well-tolerated' operation. However, many patients experience distress and discomfort with the procedure. Substantial opportunity exists to improve the TURBT experience. An enhanced recovery after surgery (ERAS) protocol designed by patients with bladder cancer and their providers has been developed. METHODS AND ANALYSIS: This is a single-centre, randomised controlled trial to investigate the effectiveness of an ERAS protocol compared with usual care in patients with bladder cancer undergoing ambulatory TURBT. The ERAS protocol is composed of preoperative, intraoperative and postoperative components designed to optimise each phase of perioperative care. 100 patients with suspected or known bladder cancer aged ≥18 years undergoing initial or repeat ambulatory TURBT will be enrolled. The change in Quality of Recovery 15 score, a measure of the quality of recovery, between the day of surgery and postoperative day 1 will be compared between the ERAS and control groups. ETHICS AND DISSEMINATION: The trial has been approved by the Johns Hopkins Institutional Review Board #00392063. Participants will provide informed consent to participate before taking part in the study. Results will be reported in a separate publication. TRIAL REGISTRATION NUMBER: NCT05905276.

Predicting prostate cancer grade reclassification on active surveillance using a deep Learning-Based grading algorithm.

Deep learning (DL)-based algorithms to determine prostate cancer (PCa) Grade Group (GG) on biopsy slides have not been validated by comparison to clinical outcomes. We used a DL-based algorithm, AIRAProstate, to re-grade initial prostate biopsies in two independent PCa active surveillance (AS) cohorts. In a cohort initially diagnosed with GG1 PCa using only systematic biopsies (n = 138), upgrading of the initial biopsy to ≥GG2 by AIRAProstate was associated with rapid or extreme grade reclassification on AS (odds ratio 3.3, p = .04), whereas upgrading of the initial biopsy by contemporary uropathologist reviews was not associated with this outcome. In a contemporary validation cohort that underwent prostate magnetic resonance imaging before initial biopsy (n = 169), upgrading of the initial biopsy (all contemporary GG1 by uropathologist grading) by AIRAProstate was associated with grade reclassification on AS (hazard ratio 1.7, p = .03). These results demonstrate the utility of a DL-based grading algorithm in PCa risk stratification for AS.

Trends in Industry-Sponsored Research Payments to Physician Principal Investigators.

This cohort study investigates trends in total and per-physician industry-sponsored research payments to physician principal investigators from 2015 to 2022.

Characterization of structural, biochemical, pharmacokinetic, and pharmacodynamic properties of the LSD1 inhibitor bomedemstat in preclinical models.

INTRODUCTION: Lysine-specific demethylase 1 (LSD1) is emerging as a critical mediator of tumor progression in metastatic castration-resistant prostate cancer (mCRPC). Neuroendocrine prostate cancer (NEPC) is increasingly recognized as an adaptive mechanism of resistance in mCRPC patients failing androgen receptor axis-targeted therapies. Safe and effective LSD1 inhibitors are necessary to determine antitumor response in prostate cancer models. For this reason, we characterize the LSD1 inhibitor bomedemstat to assess its clinical potential in NEPC as well as other mCRPC pathological subtypes. METHODS: Bomedemstat was characterized via crystallization, flavine adenine dinucleotide spectrophotometry, and enzyme kinetics. On-target effects were assessed in relevant prostate cancer cell models by measuring proliferation and H3K4 methylation using western blot analysis. In vivo, pharmacokinetic (PK) and pharmacodynamic (PD) profiles of bomedemstat are also described. RESULTS: Structural, biochemical, and PK/PD properties of bomedemstat, an irreversible, orally-bioavailable inhibitor of LSD1 are reported. Our data demonstrate bomedemstat has >2500-fold greater specificity for LSD1 over monoamine oxidase (MAO)-A and -B. Bomedemstat also demonstrates activity against several models of advanced CRPC, including NEPC patient-derived xenografts. Significant intra-tumoral accumulation of orally-administered bomedemstat is measured with micromolar levels achieved in vivo (1.2 ± 0.45 µM at the 7.5 mg/kg dose and 3.76 ± 0.43 µM at the 15 mg/kg dose). Daily oral dosing of bomedemstat at 40 mg/kg/day is well-tolerated, with on-target thrombocytopenia observed that is rapidly reversible following treatment cessation. CONCLUSIONS: Bomedemstat provides enhanced specificity against LSD1, as revealed by structural and biochemical data. PK/PD data display an overall safety profile with manageable side effects resulting from LSD1 inhibition using bomedemstat in preclinical models. Altogether, our results support clinical testing of bomedemstat in the setting of mCRPC.

Development and Validation of an 18-Gene Urine Test for High-Grade Prostate Cancer.

Importance: Benefits of prostate cancer (PCa) screening with prostate-specific antigen (PSA) alone are largely offset by excess negative biopsies and overdetection of indolent cancers resulting from the poor specificity of PSA for high-grade PCa (ie, grade group [GG] 2 or greater). Objective: To develop a multiplex urinary panel for high-grade PCa and validate its external performance relative to current guideline-endorsed biomarkers. Design, Setting, and Participants: RNA sequencing analysis of 58 724 genes identified 54 markers of PCa, including 17 markers uniquely overexpressed by high-grade cancers. Gene expression and clinical factors were modeled in a new urinary test for high-grade PCa (MyProstateScore 2.0 [MPS2]). Optimal models were developed in parallel without prostate volume (MPS2) and with prostate volume (MPS2+). The locked models underwent blinded external validation in a prospective National Cancer Institute trial cohort. Data were collected from January 2008 to December 2020, and data were analyzed from November 2022 to November 2023. Exposure: Protocolized blood and urine collection and transrectal ultrasound-guided systematic prostate biopsy. Main Outcomes and Measures: Multiple biomarker tests were assessed in the validation cohort, including serum PSA alone, the Prostate Cancer Prevention Trial risk calculator, and the Prostate Health Index (PHI) as well as derived multiplex 2-gene and 3-gene models, the original 2-gene MPS test, and the 18-gene MPS2 models. Under a testing approach with 95% sensitivity for PCa of GG 2 or greater, measures of diagnostic accuracy and clinical consequences of testing were calculated. Cancers of GG 3 or greater were assessed secondarily. Results: Of 761 men included in the development cohort, the median (IQR) age was 63 (58-68) years, and the median (IQR) PSA level was 5.6 (4.6-7.2) ng/mL; of 743 men included in the validation cohort, the median (IQR) age was 62 (57-68) years, and the median (IQR) PSA level was 5.6 (4.1-8.0) ng/mL. In the validation cohort, 151 (20.3%) had high-grade PCa on biopsy. Area under the receiver operating characteristic curve values were 0.60 using PSA alone, 0.66 using the risk calculator, 0.77 using PHI, 0.76 using the derived multiplex 2-gene model, 0.72 using the derived multiplex 3-gene model, and 0.74 using the original MPS model compared with 0.81 using the MPS2 model and 0.82 using the MPS2+ model. At 95% sensitivity, the MPS2 model would have reduced unnecessary biopsies performed in the initial biopsy population (range for other tests, 15% to 30%; range for MPS2, 35% to 42%) and repeat biopsy population (range for other tests, 9% to 21%; range for MPS2, 46% to 51%). Across pertinent subgroups, the MPS2 models had negative predictive values of 95% to 99% for cancers of GG 2 or greater and of 99% for cancers of GG 3 or greater. Conclusions and Relevance: In this study, a new 18-gene PCa test had higher diagnostic accuracy for high-grade PCa relative to existing biomarker tests. Clinically, use of this test would have meaningfully reduced unnecessary biopsies performed while maintaining highly sensitive detection of high-grade cancers. These data support use of this new PCa biomarker test in patients with elevated PSA levels to reduce the potential harms of PCa screening while preserving its long-term benefits.

Likelihood of sampling prostate cancer at systematic biopsy as a function of gland volume and number of cores.

BACKGROUND: Pre-biopsy multiparametric magnetic resonance imaging (mpMRI) of the prostate is used to conduct targeted prostate biopsy (TB), guided by ultrasound and registered (fused) to the MRI. Systematic biopsy (SB) continues to be used together with TB or in mpMRI-negative patients. There is insufficient evidence on how to use SB to inform clinical decision-making in the mpMRI era. The purpose of this study was to estimate the effect of prostate volume and number of SB cores on sampling clinically significant prostate cancer (csPCa) using a simulation method based on clinical data. METHODS: SBs were simulated using data from 42 patients enrolled in a transrectal ultrasound robot-assisted biopsy trial. Linear mixed models were used to examine the relationship between the number of SB cores and prostate volume on 1) clinically significant cancer detection probability (csCDP) and 2) percent of mpMRI depicted regions of interest (ROIs) sampled with the SB. RESULTS: Median values and interquartile range (IQR) were 47.16 cm3 (35.61-65.57) for prostate volume, 0.57 cm3 (0.39-0.83) for ROI volume, and 4.0 (2-4) for PI-RADS v2.1 scores on MRI. csCDP increased with the increasing number of simulated SB cores and decreased substantially with larger prostate volume. Similarly, the percent of ROIs sampled increased with the increasing number of simulated SB cores and was lower for prostate volumes ≥60 cm3 compared to glands <60 cm3. CONCLUSIONS: The effect of the number of SBs performed on detecting csPCa varies largely with gland volume. The common 12-core SB can achieve adequate cancer detection and sampling of ROIs in smaller glands, but not in larger glands. In addition to TB or in mpMRI-negative patients, the number of SB cores can be adjusted to prostate volume. Performing 12-core SB alone in ≥60 cm3 glands results in inadequate sampling and potential PCa underdiagnosis.

Immunomodulatory response to neoadjuvant nivolumab in non-metastatic clear cell renal cell carcinoma.

Novel perioperative strategies are needed to reduce recurrence rates in patients undergoing nephrectomy for high-risk, non-metastatic clear cell renal cell carcinoma (ccRCC). We conducted a prospective, phase I trial of neoadjuvant nivolumab prior to nephrectomy in 15 evaluable patients with non-metastatic ccRCC. We leveraged tissue from that cohort to elucidate the effects of PD-1 inhibition on immune cell populations in ccRCC and correlate the evolving immune milieu with anti-PD-1 response. We found that nivolumab durably induces a pro-inflammatory state within the primary tumor, and baseline immune infiltration within the primary tumor correlates with nivolumab responsiveness. Nivolumab increases CTLA-4 expression in the primary tumor, and subsequent nephrectomy increases circulating concentrations of sPD-L1, sPD-L3 (sB7-H3), and s4-1BB. These findings form the basis to consider neoadjuvant immune checkpoint inhibition (ICI) for high-risk ccRCC while the tumor remains in situ and provide the rationale for perioperative strategies of novel ICI combinations.

The Association of Subspecialty and Sex with Industry Payments to Internal Medicine Physicians Who Recently Completed Training.

BACKGROUND: Financial relationships with drug and medical device companies may impact quality of care and academic research. However, little is known when and how these financial relationships develop among newly independent physicians who recently completed from residency or fellowship programs in internal medicine (IM). OBJECTIVE: To compare patterns of industry payments among IM graduates. DESIGN: Retrospective, observational cohort study. SUBJECTS: IM graduates from residency or fellowship programs between January 2015 and December 2019. MAIN MEASURES: We analyzed Open Payments reports made between July 2015 and June 2021 to recent graduates of U.S. Accreditation Council for Graduate Medical Education (ACGME)-accredited residency and fellowship programs in IM. The primary outcome was general payments accepted by these physicians, stratified by procedural (i.e., critical care medicine/pulmonary medicine, cardiac/cardiovascular disease, and gastroenterology) and non-procedural (i.e., infectious disease, general internal medicine, and other specialties) subspecialties. The secondary outcomes included general payments stratified by sex and age at residency or fellowship training completion. KEY RESULTS: There were 41,669 IM physicians with a median age of 33.0 years. In the first 3 years after completion, the proportion of physicians accepting any general payments was 72.6%, 91.9%, and 86.8% in Critical Care Medicine/Pulmonary Medicine, Cardiac/Cardiovascular Disease, and Gastroenterology, compared to 56.1%, 52.6%, and 52.3% in Infectious Disease, General Internal Medicine, and Other Specialties (p<0.0001). After adjusting for confounding variables, the procedural group showed an increased hazard ratio (HR) for accepting any general payments and at least $5000 of general payments compared to the non-procedural group. The HRs of accepting any general payments in the procedural subspecialty were 2.26 (95% CI, 2.11-2.42) and 2.83 (95% CI, 2.70-2.97) in female and male physicians, respectively (p-value < 0.0001). CONCLUSION: Industry financial relationships among newly independent physicians in IM exist immediately after completion of training and are influenced by subspecialty, sex, and age.

Characterization of HOXB13 expression patterns in localized and metastatic castration-resistant prostate cancer.

HOXB13 is a key lineage homeobox transcription factor that plays a critical role in the differentiation of the prostate gland. Several studies have suggested that HOXB13 alterations may be involved in prostate cancer development and progression. Despite its potential biological relevance, little is known about the expression of HOXB13 across the disease spectrum of prostate cancer. To this end, we validated a HOXB13 antibody using genetic controls and investigated HOXB13 protein expression in murine and human developing prostates, localized prostate cancers, and metastatic castration-resistant prostate cancers. We observed that HOXB13 expression increases during later stages of murine prostate development. All localized prostate cancers showed HOXB13 protein expression. Interestingly, lower HOXB13 expression levels were observed in higher-grade tumors, although no significant association between HOXB13 expression and recurrence or disease-specific survival was found. In advanced metastatic prostate cancers, HOXB13 expression was retained in the majority of tumors. While we observed lower levels of HOXB13 protein and mRNA levels in tumors with evidence of lineage plasticity, 84% of androgen receptor-negative castration-resistant prostate cancers and neuroendocrine prostate cancers (NEPCs) retained detectable levels of HOXB13. Notably, the reduced expression observed in NEPCs was associated with a gain of HOXB13 gene body CpG methylation. In comparison to the commonly used prostate lineage marker NKX3.1, HOXB13 showed greater sensitivity in detecting advanced metastatic prostate cancers. Additionally, in a cohort of 837 patients, 383 with prostatic and 454 with non-prostatic tumors, we found that HOXB13 immunohistochemistry had a 97% sensitivity and 99% specificity for prostatic origin. Taken together, our studies provide valuable insight into the expression pattern of HOXB13 during prostate development and cancer progression. Furthermore, our findings support the utility of HOXB13 as a diagnostic biomarker for prostate cancer, particularly to confirm the prostatic origin of advanced metastatic castration-resistant tumors. © 2023 The Pathological Society of Great Britain and Ireland.

Risk of Biochemical Recurrence in Patients With Grade Group 1 Prostate Cancer With Extraprostatic Extension Treated With Radical Prostatectomy.

PURPOSE: We sought to examine the association of extraprostatic extension (EPE) with biochemical recurrence (BCR) separately in men with Grade Group (GG) 1 and GG2 prostate cancer (PCa) treated with radical prostatectomy. MATERIALS AND METHODS: We reviewed our institutional database of patients who underwent radical prostatectomy for PCa between 2005 and 2022 and identified patients with GG1 and GG2 disease on final pathology. Fine-Gray competing risk models with an interaction between EPE (yes vs no) and GG (GG1 vs GG2) were used to examine the relationship between disease group and BCR-free survival. RESULTS: The cohort consisted of 6309 men, of whom 169/2740 (6.2%) with GG1 disease had EPE while 1013/3569 (28.4%) with GG2 disease had EPE. Median follow-up was 4 years. BCR occurred in 400/6309 (6.3%) patients. For men with GG1, there was no statistically significant difference in BCR-free survival for men with vs without EPE (subdistribution HR = 0.88; 95% CI: 0.37-2.09). However, for GG2 patients BCR-free survival was significantly worse for those with vs without EPE (subdistribution HR = 1.97, 95% CI: 1.54-2.52). CONCLUSIONS: Although there is a subset of GG1 PCas capable of invading through the prostatic capsule, patients with GG1 PCa and EPE at prostatectomy experience similar biochemical recurrence and survival outcomes compared to GG1 patients without EPE. However, among men with GG2, EPE connotes a worse prognosis.

Industry Payments Received by Residents During Training.

Importance: Those responsible for medical education-specialties, sponsoring institutions, and program directors (PD)-are independently associated with the professional identity formation of the trainees with respect to potential conflicts of interest. Objective: To identify the relative degree to which factors in the training environment are associated with resident acceptance of payments from pharmaceutical and medical device companies. Design, Setting, and Participants: Cross-sectional, retrospective study of residents enrolled in the 3 largest primary-care specialties (internal medicine [IM], family medicine [FM], obstetrics and gynecology [OBGYN]) and 3 largest surgical disciplines (general surgery [GS], orthopedic surgery, and urology) during academic year 2020 to 2021. All analyses were conducted January through August 2023. Exposures: Specialty, sponsoring institutions' ownership (nonprofit, for-profit, federal government, local government, or state government), and the number of payments PDs accepted. Main outcomes and measures: Modified Poisson regression assessed the relative risk of ownership, specialty, and PD behavior on residents' acceptance of industry payments as recorded in the Open Payments Program (OPP) database. Results: In total, there were 124 715 residents in all training programs during 2020 to 2021, 12% of whom received payments totaling $6.4 million. There were 65 992 residents in training during 2020 to 2021 in the 6 specialties evaluated in this study, with 4438 in orthopedics, 1779 in urology, 9177 in GS, 5819 in OBGYN, 14 493 in FM, and 30 286 in IM. OPP records $3.9 million in payments to the 8750 residents (13.4%) who received at least 1 industry payment. The record of all payments to residents in OPP totals $6.4 million. Compared with residents in federal sponsoring institutions, those affiliated with for-profit institutions were 3.50 (95% CI, 2.32-5.28) times more likely to accept industry payments, while those affiliated with nonprofit organizations were 2.00 (95% CI, 1.36-2.93) times more likely to accept payments. Compared with IM, residents in each of the following specialties have an elevated risk of accepting payments: orthopedics, 3.21 (95% CI, 2.73-3.77) times; urology, 2.95 (95% CI, 2.44-3.56) times; GS, 1.21 (95% CI, 1.00-1.45) times; OBGYN, 1.30 (95% CI, 1.05-1.62) times. The difference in the risk of accepting a payment between FM and IM residents was not statistically significant. The number of payments PDs accepted slightly elevated the risk of residents to accept a payment by 1.01 (95% CI, 1.01-1.01). Conclusions and relevance: In this cross-sectional, retrospective study, receipt of industry payments by residents was associated with specialty, institutional control, and PD behavior.

Baseline prostate health index risk category and risk category changes during active surveillance predict grade reclassification.

BACKGROUND: It is not known whether baseline prostate health index (PHI) at the initiation of active surveillance (AS) or repeated PHI testing during AS is of clinical value after confirmatory biopsy in AS men followed with multiparametric magnetic resonance imaging (mpMRI). METHODS: We identified 382 AS patients with no greater than Grade Group 1 (GG1) prostate cancer on diagnostic and confirmatory biopsy, at least one mpMRI and PHI test, of which 241 had at least 2 PHI tests. Grade reclassification (GR) was defined as ≥GG2 on surveillance biopsy. PHI risk categories 1 to 4 were as defined by the manufacturer. Associations between baseline PHI risk category or baseline PSA density (PSAD), change in PHI risk categories over time or PSAD changes over time and GR were evaluated with multivariable Cox proportional hazard regression models adjusted for age, Prostate Imaging-Reporting and Data System score and number of positive cores. RESULTS: Men with baseline PHI scores in the highest risk categories had lower rates of GR-free survival (log-rank P < 0.001), as did those who increased in PHI risk category or remained in a high PHI risk category during surveillance (log-rank P = 0.032). On multivariable regression, baseline PHI risk category was a predictor of GR (risk category 4 [vs. 1] hazard ratio [HR] 2.74, 95% confidence interval [CI] 1.32-5.66, P = 0.002, model C-index 0.764, Akaike Information Criterion [AIC] 797), as were PHI risk category changes over time (risk category 4 [vs. 1] HR 4.20, 95% CI 1.76-10.05, P = 0.002, C-index 0.759, AIC 489). Separate models with baseline PSAD and PSAD changes over time yielded C-indices of 0.709 (AIC 809) and 0.733 (AIC 495) respectively. CONCLUSIONS: Baseline PHI risk category and PHI changes over time were both independent predictors of GR after confirmatory biopsy, but the added benefit over PSAD seemed modest. However, baseline PHI and PHI risk category changes provided clinically useful risk stratification for time to GR, so further evaluation of PHI's ability to help reduce the frequency of mpMRI and/or surveillance biopsies with more PHI data points over time may be warranted.

Predicting Prostate Cancer Molecular Subtype With Deep Learning on Histopathologic Images.

Microscopic examination of prostate cancer has failed to reveal a reproducible association between molecular and morphologic features. However, deep-learning algorithms trained on hematoxylin and eosin (H&E)-stained whole slide images (WSI) may outperform the human eye and help to screen for clinically-relevant genomic alterations. We created deep-learning algorithms to identify prostate tumors with underlying ETS-related gene (ERG) fusions or PTEN deletions using the following 4 stages: (1) automated tumor identification, (2) feature representation learning, (3) classification, and (4) explainability map generation. A novel transformer-based hierarchical architecture was trained on a single representative WSI of the dominant tumor nodule from a radical prostatectomy (RP) cohort with known ERG/PTEN status (n = 224 and n = 205, respectively). Two distinct vision transformer-based networks were used for feature extraction, and a distinct transformer-based model was used for classification. The ERG algorithm performance was validated across 3 RP cohorts, including 64 WSI from the pretraining cohort (AUC, 0.91) and 248 and 375 WSI from 2 independent RP cohorts (AUC, 0.86 and 0.89, respectively). In addition, we tested the ERG algorithm performance in 2 needle biopsy cohorts comprised of 179 and 148 WSI (AUC, 0.78 and 0.80, respectively). Focusing on cases with homogeneous (clonal) PTEN status, PTEN algorithm performance was assessed using 50 WSI reserved from the pretraining cohort (AUC, 0.81), 201 and 337 WSI from 2 independent RP cohorts (AUC, 0.72 and 0.80, respectively), and 151 WSI from a needle biopsy cohort (AUC, 0.75). For explainability, the PTEN algorithm was also applied to 19 WSI with heterogeneous (subclonal) PTEN loss, where the percentage tumor area with predicted PTEN loss correlated with that based on immunohistochemistry (r = 0.58, P = .0097). These deep-learning algorithms to predict ERG/PTEN status prove that H&E images can be used to screen for underlying genomic alterations in prostate cancer.

Development and External Validation of a Machine Learning Model for Prediction of Lymph Node Metastasis in Patients with Prostate Cancer.

BACKGROUND: Pelvic lymph node dissection (PLND) is the gold standard for diagnosis of lymph node involvement (LNI) in patients with prostate cancer. The Roach formula, Memorial Sloan Kettering Cancer Center (MSKCC) calculator, and Briganti 2012 nomogram are elegant and simple traditional tools used to estimate the risk of LNI and select patients for PLND. OBJECTIVE: To determine whether machine learning (ML) can improve patient selection and outperform currently available tools for predicting LNI using similar readily available clinicopathologic variables. DESIGN, SETTING, AND PARTICIPANTS: Retrospective data for patients treated with surgery and PLND between 1990 and 2020 in two academic institutions were used. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: We trained three models (two logistic regression models and one gradient-boosted trees-based model [XGBoost]) on data provided from one institution (n = 20267) with age, prostate-specific antigen (PSA) levels, clinical T stage, percentage positive cores, and Gleason scores as inputs. We externally validated these models using data from another institution (n = 1322) and compared their performance to that of the traditional models using the area under the receiver operating characteristic curve (AUC), calibration, and decision curve analysis (DCA). RESULTS AND LIMITATIONS: LNI was present in 2563 patients (11.9%) overall, and in 119 patients (9%) in the validation data set. XGBoost had the best performance among all the models. On external validation, its AUC outperformed that of the Roach formula by 0.08 (95% confidence interval [CI] 0.042-0.12), the MSKCC nomogram by 0.05 (95% CI 0.016-0.070), and the Briganti nomogram by 0.03 (95% CI 0.0092-0.051; all p < 0.05). It also had better calibration and clinical utility in terms of net benefit on DCA across relevant clinical thresholds. The main limitation of the study is its retrospective design. CONCLUSIONS: Taking all measures of performance together, ML using standard clinicopathologic variables outperforms traditional tools in predicting LNI. PATIENT SUMMARY: Determining the risk of cancer spread to the lymph nodes in patients with prostate cancer allows surgeons to perform lymph node dissection only in patients who need it and avoid the side effects of the procedure in those who do not. In this study, we used machine learning to develop a new calculator to predict the risk of lymph node involvement that outperformed traditional tools currently used by oncologists.

ERG Status at the Margin Is Associated With Biochemical Recurrence After Radical Prostatectomy With Positive Surgical Margins.

Positive surgical margins at radical prostatectomy are associated with an increased risk of biochemical recurrence (BCR). However, there is considerable variability in outcomes, suggesting that molecular biomarkers-when assessed specifically at the margin tumor tissue-may be useful to stratify prognosis in this group. We used a case-cohort design for the outcome of BCR, selecting 215 patients from a cohort of 813 patients undergoing prostatectomy treated at the Johns Hopkins from 2008 to 2017 with positive margins and available clinical data. Tissue microarrays were created from the tumor adjacent to the positive margin and stained for PTEN, ERG, and Ki-67. Cases were scored dichotomously (PTEN and ERG) or by the Ki-67 staining index using previously validated protocols. The analysis used Cox proportional hazards models weighted for the case-cohort design. Overall, 20% (37/185) of evaluable cases had PTEN loss and 38% (71/185) had ERG expression, and the median Ki-67 expression was 0.42%. In multivariable analysis adjusting for the CAPRA-S score, adjuvant radiation, and grade group at the positive margin, ERG-positive tumors were associated with a higher risk of BCR compared to those that were ERGnegative (hazard ratio [HR], 2.4; 95% CI, 1.2-4.9; P = .012) regardless of PTEN status at the margin, and adding ERG to clinicopathologic variables increased the concordance index from 0.827 to 0.847. PTEN loss was associated with an increased risk of BCR on univariable analysis (HR, 3.19; 95% CI, 1.72-5.92; P = .0002), but this association did not remain after adjusting for clinicopathologic variables (HR, 1.06; 95% CI, 0.49-2.29; P = .890). Thus, in the setting of prostate tumors with positive surgical margins after prostatectomy, ERG-positive tumors with or without PTEN loss at the positive margin are associated with a significantly higher risk of BCR after adjusting for clinicopathologic variables. If validated, ERG status may be helpful in decision-making surrounding adjuvant therapy after prostatectomy.