1
|
Porcaro AB, Bianchi A, Panunzio A, Gallina S, Serafin E, Tafuri A, Trabacchin N, Orlando R, Ornaghi PI, Mazzucato G, Vidiri S, D'Aietti D, Montanaro F, Brusa D, Patuzzo GM, Artoni F, Baielli A, Migliorini F, De Marco V, Veccia A, Brunelli M, Siracusano S, Cerruto MA, Antonelli A. Tumor upgrading among very favorable intermediate-risk prostate cancer patients treated with robot-assisted radical prostatectomy: how can it impact the clinical course? Int Urol Nephrol 2024; 56:2597-2605. [PMID: 38553619 DOI: 10.1007/s11255-024-04019-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2023] [Accepted: 03/02/2024] [Indexed: 07/25/2024]
Abstract
PURPOSE We sought to investigate predictors of unfavorable tumor upgrading in very favorable intermediate-risk (IR) prostate cancer (PCa) patients treated with robot-assisted radical prostatectomy, in addition to evaluate how it may affect the risk of disease progression. METHODS A very favorable subset of IR PCa patients presenting with prostate-specific antigen (PSA) < 10 ng/mL, percentage of biopsy positive cores (BPC) < 50%, and either International Society of Urological Pathology (ISUP) grade group 1 and clinical stage T2b or ISUP grade group 2 and clinical stage T1c-2b was identified. Unfavorable pathology at radical prostatectomy was defined as the presence of ISUP grade group > 2 (unfavorable tumor upgrading), extracapsular extension (ECE), and seminal vesicle invasion (SVI). Disease progression was defined as the event of biochemical recurrence and/or local recurrence and/or distant metastases. Associations were evaluated by Cox regression and logistic regression analyses. RESULTS Overall, 210 patients were identified between January 2013 and October 2020. Unfavorable tumor upgrading was detected in 71 (33.8%) cases, and adverse tumor stage, including ECE or SVI in 18 (8.6%) and 11 (5.2%) patients, respectively. Median (interquartile range) follow-up was 38.5 (16-61) months. PCa progression occurred in 24 (11.4%) patients. Very favorable IR PCa patients with unfavorable tumor upgrading at final pathology showed a persistent risk of disease progression, which hold significance after adjustment for all factors (Hazard Ratio [HR]: 5.95, 95% Confidence Interval [CI]: 1.97-17.92, p = 0.002) of which PSA was an independent predictor (HR: 1.52, 95% CI 1.12-2.08, p = 0.008). Moreover, these subjects were more likely to belong to the biopsy ISUP grade group 2. CONCLUSIONS Very favorable IR PCa patients hiding unfavorable tumor upgrading were more likely to experience disease progression. Unfavorable tumor upgrading involved about one-third of cases and was less likely to occur in patients presenting with biopsy ISUP grade group 1. Tumor misclassification is an issue to discuss, when counseling this subset of patients for active surveillance because of the risk of delayed active treatment.
Collapse
Affiliation(s)
- Antonio Benito Porcaro
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy.
| | - Alberto Bianchi
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | | | - Sebastian Gallina
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Emanuele Serafin
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | | | - Nicolò Trabacchin
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Rossella Orlando
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Paola Irene Ornaghi
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Giovanni Mazzucato
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Stefano Vidiri
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Damiano D'Aietti
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Francesca Montanaro
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Davide Brusa
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Giulia Marafioti Patuzzo
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Francesco Artoni
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Alberto Baielli
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Filippo Migliorini
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Vincenzo De Marco
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Alessandro Veccia
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Matteo Brunelli
- Department of Pathology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy
| | - Salvatore Siracusano
- Department of Life, Health and Environmental Sciences, University of L'Aquila, L'Aquila, Italy
| | - Maria Angela Cerruto
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| | - Alessandro Antonelli
- Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Piazzale Stefani 1, 37126, Verona, Italy
| |
Collapse
|
2
|
Tilki D, Chen MH, Huland H, Graefen M, D'Amico AV. Mortality Risk for Patients with Biopsy Gleason Grade Group 1 Prostate Cancer. Eur Urol Oncol 2024:S2588-9311(24)00156-1. [PMID: 38960834 DOI: 10.1016/j.euo.2024.06.009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2024] [Revised: 05/30/2024] [Accepted: 06/20/2024] [Indexed: 07/05/2024]
Abstract
BACKGROUND AND OBJECTIVE We investigated the association of clinical factors at presentation with the presence of unsampled high-risk prostate cancer (PC) and PC-specific mortality (PCSM) and all-cause mortality (ACM) following radical prostatectomy in patients with biopsy Gleason Grade Group (GGG) 1 PC. METHODS The study population comprised 10228 patients treated for GGG1 PC diagnosed via transrectal ultrasound (TRUS)-guided systematic biopsy (SBx; n = 9248) or combined biopsy (CBx; SBx + TRUS/magnetic resonance image [MRI] fusion biopsy; n = 980) from a cohort study at a university hospital in Hamburg, Germany. We used logistic, Fine and Grays, and Cox multivariable regression methods to calculate the adjusted odds ratio (aOR) of adverse pathology and adjusted hazard ratios (aHRs) for early prostate-specific antigen (PSA) failure (≤18 mo), PCSM, and ACM in relation to each clinical factor. KEY FINDINGS AND LIMITATIONS Irrespective of biopsy approach, percent positive biopsies (PPB) >50% and PSA >20 ng/ml were significantly associated with higher risk of adverse pathology (SBx: aOR 1.71 and 3.49; CBx: aOR 1.81 and 2.82, respectively) and early PSA failure (SBx: aHR 1.54 and 4.37; CBx: aHR 2.88 and 7.81, respectively). PPB >50% and PSA >20 ng/ml were also associated with higher risk of PCSM (aHRs 2.56 and 3.71) and ACM (aHRs 1.47 and 2.00) in the SBx group (all p ≤ 0.04). The study is limited by the single-institution cohort design. CONCLUSION AND CLINICAL IMPLICATION Maintaining the "cancer" classification for patients with GGG1 and either PPB >50% or PSA>20 ng/ml and considering rebiopsy to identify unsampled high-grade disease may minimize the risk of mortality for this subgroup. PATIENT SUMMARY For patients undergoing non-targeted prostate biopsy, approximately 1 in 12 with a biopsy result of grade group 1 prostate cancer may have more aggressive cancer than the result suggests. A very high PSA (prostate-specific antigen) level (>20 ng/ml) or the presence of grade group 1 cancer in more than 50% of the biopsy samples can identify patients at risk.
Collapse
Affiliation(s)
- Derya Tilki
- Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany; Department of Urology, University Hospital Hamburg-Eppendorf, Hamburg, Germany; Department of Urology, Koc University Hospital, Istanbul, Turkey
| | - Ming-Hui Chen
- Department of Statistics, University of Connecticut, Storrs, CT, USA
| | - Hartwig Huland
- Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Markus Graefen
- Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Anthony V D'Amico
- Department of Radiation Oncology, Brigham and Women's Hospital and Dana Farber Cancer Institute, Boston, MA, USA.
| |
Collapse
|
3
|
Porcaro AB, Panunzio A, Orlando R, Montanaro F, Baielli A, Artoni F, Gallina S, Bianchi A, Mazzucato G, Serafin E, Patuzzo GM, Veccia A, Rizzetto R, Brunelli M, Migliorini F, Bertolo R, Tafuri A, Cerruto MA, Antonelli A. The 2012 Briganti nomogram not only predicts lymph node involvement but also disease progression in surgically treated intermediate-risk prostate cancer patients with PSA <10 ng/mL, ISUP grade group 3, and clinical stage up to cT2b. Int Braz J Urol 2024; 50:450-458. [PMID: 38743063 PMCID: PMC11262719 DOI: 10.1590/s1677-5538.ibju.2024.0003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2024] [Accepted: 03/14/2024] [Indexed: 05/16/2024] Open
Abstract
PURPOSE We assessed the prognostic impact of the 2012 Briganti nomogram on prostate cancer (PCa) progression in intermediate-risk (IR) patients presenting with PSA <10ng/mL, ISUP grade group 3, and clinical stage up to cT2b treated with robot assisted radical prostatectomy eventually associated with extended pelvic lymph node dissection. MATERIALS AND METHODS From January 2013 to December 2021, data of surgically treated IR PCa patients were retrospectively evaluated. Only patients presenting with the above-mentioned features were considered. The 2012 Briganti nomogram was assessed either as a continuous and a categorical variable (up to the median, which was detected as 6%, vs. above the median). The association with PCa progression, defined as biochemical recurrence, and/or metastatic progression, was evaluated by Cox proportional hazard regression models. RESULTS Overall, 147 patients were included. Compared to subjects with a nomogram score up to 6%, those presenting with a score above 6% were more likely to be younger, had larger/palpable tumors, presented with higher PSA, underwent tumor upgrading, harbored non-organ confined disease, and had positive surgical margins at final pathology. PCa progression, which occurred in 32 (21.7%) cases, was independently predicted by the 2012 Briganti nomogram both considered as a continuous (Hazard Ratio [HR]:1.04, 95% Confidence Interval [CI]:1.01-1.08;p=0.021), and a categorical variable (HR:2.32; 95%CI:1.11-4.87;p=0.026), even after adjustment for tumor upgrading. CONCLUSIONS In IR PCa patients with PSA <10ng/mL, ISUP grade group 3, and clinical stage up to cT2b, the 2012 Briganti nomogram independently predicts PCa progression. In this challenging subset of patients, this tool can identify prognostic subgroups, independently by upgrading issues.
Collapse
Affiliation(s)
- Antonio Benito Porcaro
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Andrea Panunzio
- Department of UrologyVito Fazzi HospitalLecceItalyDepartment of Urology, Vito Fazzi Hospital, Lecce, Italy;
| | - Rossella Orlando
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Francesca Montanaro
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Alberto Baielli
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Francesco Artoni
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Sebastian Gallina
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Alberto Bianchi
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Giovanni Mazzucato
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Emanuele Serafin
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Giulia Marafioti Patuzzo
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Alessandro Veccia
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Riccardo Rizzetto
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Matteo Brunelli
- Department of PathologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItalyDepartment of Pathology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy
| | - Filippo Migliorini
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Riccardo Bertolo
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Alessandro Tafuri
- Department of UrologyVito Fazzi HospitalLecceItalyDepartment of Urology, Vito Fazzi Hospital, Lecce, Italy;
| | - Maria Angela Cerruto
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| | - Alessandro Antonelli
- Department of UrologyUniversity of VeronaAzienda Ospedaliera Universitaria IntegrataVeronaItaly Department of Urology, University of Verona, Azienda Ospedaliera Universitaria Integrata, Verona, Italy;
| |
Collapse
|
4
|
Sorce G, Stabile A, Pellegrino F, Mazzone E, Mattei A, Afferi L, Serni S, Minervini A, Roumiguiè M, Malavaud B, Valerio M, Rakauskas A, Marra G, Gontero P, Porpiglia F, Guo H, Zhuang J, Gandaglia G, Montorsi F, Briganti A. The impact of mpMRI-targeted vs systematic biopsy on the risk of prostate cancer downgrading at final pathology. World J Urol 2024; 42:248. [PMID: 38647689 DOI: 10.1007/s00345-024-04963-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2023] [Accepted: 03/25/2024] [Indexed: 04/25/2024] Open
Abstract
PURPOSE Although targeted biopsies (TBx) are associated with improved disease assessment, concerns have been raised regarding the risk of prostate cancer (PCa) overgrading due to more accurate biopsy core deployment in the index lesion. METHODS We identified 1672 patients treated with radical prostatectomy (RP) with a positive mpMRI and ISUP ≥ 2 PCa detected via systematic biopsy (SBx) plus TBx. We compared downgrading rates at RP (ISUP 4-5, 3, and 2 at biopsy, to a lower ISUP) for PCa detected via SBx only (group 1), via TBx only (group 2), and eventually for PCa detected with the same ISUP 2-5 at both SBx and TBx (group 3), using multivariable logistic regression models (MVA). RESULTS Overall, 12 vs 14 vs 6% (n = 176 vs 227 vs 96) downgrading rates were recorded in group 1 vs group 2 vs group 3, respectively (p < 0.001). At MVA, group 2 was more likely to be downgraded (OR 1.26, p = 0.04), as compared to group 1. Conversely, group 3 was less likely to be downgraded at RP (OR 0.42, p < 0.001). CONCLUSIONS Downgrading rates are highest when PCa is present in TBx only and, especially when the highest grade PCa is diagnosed by TBx cores only. Conversely, downgrading rates are lowest when PCa is identified with the same ISUP through both SBx and TBx. The presence of clinically significant disease at SBx + TBx may indicate a more reliable assessment of the disease at the time of biopsy potentially reducing the risk of downgrading at final pathology.
Collapse
Affiliation(s)
- G Sorce
- Unit of Urology, Division of Oncology, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, Milan, Italy
| | - A Stabile
- Unit of Urology, Division of Oncology, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, Milan, Italy.
- Department of Urology and Division of Experimental Oncology, Urological Research Institute, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132, Milan, Italy.
| | - F Pellegrino
- Unit of Urology, Division of Oncology, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, Milan, Italy
| | - E Mazzone
- Unit of Urology, Division of Oncology, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, Milan, Italy
| | - A Mattei
- Klinik Für Urologie, Luzerner Kantonsspital, Luzerner, Switzerland
| | - L Afferi
- Klinik Für Urologie, Luzerner Kantonsspital, Luzerner, Switzerland
| | - S Serni
- Department of Urological Robotic Surgery and Renal Transplantation, Careggi Hospital, University of Florence, Florence, Italy
| | - A Minervini
- Department of Urological Robotic Surgery and Renal Transplantation, Careggi Hospital, University of Florence, Florence, Italy
| | - M Roumiguiè
- Department of Urology and Renal Transplantation, Toulouse University Hospital, Toulouse, France
| | - B Malavaud
- Department of Urology and Renal Transplantation, Toulouse University Hospital, Toulouse, France
| | - M Valerio
- Department of Urology, Centre Hospitalier Universitaire Vaudois, Lausanne, Switzerland
| | - A Rakauskas
- Department of Urology, Centre Hospitalier Universitaire Vaudois, Lausanne, Switzerland
| | - G Marra
- Department of Urology, Città della Salute e della Scienza, University of Turin, Turin, Italy
| | - P Gontero
- Department of Urology, Città della Salute e della Scienza, University of Turin, Turin, Italy
| | - F Porpiglia
- Division of Urology, San Luigi Gonzaga Hospital, Orbassano, Turin, Italy
| | - H Guo
- Department of Urology, Drum Tower Hospital, Medical School of Nanjing University, Nanjing, China
| | - J Zhuang
- Department of Urology, Drum Tower Hospital, Medical School of Nanjing University, Nanjing, China
| | - G Gandaglia
- Unit of Urology, Division of Oncology, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, Milan, Italy
| | - F Montorsi
- Unit of Urology, Division of Oncology, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, Milan, Italy
| | - A Briganti
- Unit of Urology, Division of Oncology, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, Milan, Italy
| |
Collapse
|
5
|
Marvaso G, Isaksson LJ, Zaffaroni M, Vincini MG, Summers PE, Pepa M, Corrao G, Mazzola GC, Rotondi M, Mastroleo F, Raimondi S, Alessi S, Pricolo P, Luzzago S, Mistretta FA, Ferro M, Cattani F, Ceci F, Musi G, De Cobelli O, Cremonesi M, Gandini S, La Torre D, Orecchia R, Petralia G, Jereczek-Fossa BA. Can we predict pathology without surgery? Weighing the added value of multiparametric MRI and whole prostate radiomics in integrative machine learning models. Eur Radiol 2024:10.1007/s00330-024-10699-3. [PMID: 38507053 DOI: 10.1007/s00330-024-10699-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Revised: 01/29/2024] [Accepted: 02/18/2024] [Indexed: 03/22/2024]
Abstract
OBJECTIVE To test the ability of high-performance machine learning (ML) models employing clinical, radiological, and radiomic variables to improve non-invasive prediction of the pathological status of prostate cancer (PCa) in a large, single-institution cohort. METHODS Patients who underwent multiparametric MRI and prostatectomy in our institution in 2015-2018 were considered; a total of 949 patients were included. Gradient-boosted decision tree models were separately trained using clinical features alone and in combination with radiological reporting and/or prostate radiomic features to predict pathological T, pathological N, ISUP score, and their change from preclinical assessment. Model behavior was analyzed in terms of performance, feature importance, Shapley additive explanation (SHAP) values, and mean absolute error (MAE). The best model was compared against a naïve model mimicking clinical workflow. RESULTS The model including all variables was the best performing (AUC values ranging from 0.73 to 0.96 for the six endpoints). Radiomic features brought a small yet measurable boost in performance, with the SHAP values indicating that their contribution can be critical to successful prediction of endpoints for individual patients. MAEs were lower for low-risk patients, suggesting that the models find them easier to classify. The best model outperformed (p ≤ 0.0001) clinical baseline, resulting in significantly fewer false negative predictions and overall was less prone to under-staging. CONCLUSIONS Our results highlight the potential benefit of integrative ML models for pathological status prediction in PCa. Additional studies regarding clinical integration of such models can provide valuable information for personalizing therapy offering a tool to improve non-invasive prediction of pathological status. CLINICAL RELEVANCE STATEMENT The best machine learning model was less prone to under-staging of the disease. The improved accuracy of our pathological prediction models could constitute an asset to the clinical workflow by providing clinicians with accurate pathological predictions prior to treatment. KEY POINTS • Currently, the most common strategies for pre-surgical stratification of prostate cancer (PCa) patients have shown to have suboptimal performances. • The addition of radiological features to the clinical features gave a considerable boost in model performance. Our best model outperforms the naïve model, avoiding under-staging and resulting in a critical advantage in the clinic. •Machine learning models incorporating clinical, radiological, and radiomics features significantly improved accuracy of pathological prediction in prostate cancer, possibly constituting an asset to the clinical workflow.
Collapse
Affiliation(s)
- Giulia Marvaso
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | | | - Mattia Zaffaroni
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy.
| | - Maria Giulia Vincini
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy.
| | - Paul Eugene Summers
- Division of Radiology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Matteo Pepa
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Giulia Corrao
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | | | - Marco Rotondi
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Federico Mastroleo
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy
- University of Piemonte Orientale, Novara, Italy
| | - Sara Raimondi
- Department of Experimental Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Sarah Alessi
- Division of Radiology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Paola Pricolo
- Division of Radiology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Stefano Luzzago
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
- Division of Urology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Francesco Alessandro Mistretta
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
- Division of Urology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Matteo Ferro
- Division of Urology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Federica Cattani
- Medical Physics Unit, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Francesco Ceci
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
- Division of Nuclear Medicine, IEO European Institute of Oncology, IRCCS, Milan, Italy
| | - Gennaro Musi
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
- Division of Urology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Ottavio De Cobelli
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
- Division of Urology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Marta Cremonesi
- Radiation Research Unit, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Sara Gandini
- Department of Experimental Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Davide La Torre
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
- SKEMA Business School, Université Côte d'Azur, Sophia Antipolis, France
| | - Roberto Orecchia
- Scientific Directorate, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Giuseppe Petralia
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
- Division of Radiology, IEO European Institute of Oncology IRCCS, Milan, Italy
| | - Barbara Alicja Jereczek-Fossa
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, Milan, Italy
- Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| |
Collapse
|
6
|
Sorce G, Hoeh B, Flammia RS, Chierigo F, Hohenhorst L, Panunzio A, Nimer N, Tian Z, Gandaglia G, Tilki D, Terrone C, Gallucci M, Chun FKH, Antonelli A, Saad F, Shariat SF, Montorsi F, Briganti A, Karakiewicz PI. Rates of metastatic prostate cancer in newly diagnosed patients: Numbers needed to image according to risk level. Prostate 2022; 82:1210-1218. [PMID: 35652586 DOI: 10.1002/pros.24376] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/25/2022] [Revised: 05/07/2022] [Accepted: 05/13/2022] [Indexed: 12/31/2022]
Abstract
BACKGROUND The numbers needed to image to identify pelvic lymph node and/or distant metastases in newly diagnosed prostate cancer (PCa) patients according to risk level are unknown. METHODS Relying on Surveillance, Epidemiology, and End Results (2010-2016), we tabulated rates and proportions of patients with (a) lymph node or (b) distant metastases according to National Comprehensive Cancer Network (NCCN) risk level and calculated the number needed to image (NNI) for both endpoints. Multivariable logistic regression analyses were performed. RESULTS Of 145,939 newly diagnosed PCa patients assessable for analyses of pelvic lymph node metastases (cN1), 4559 (3.1%) harbored cN1 stage: 13 (0.02%), 18 (0.08%), 63 (0.3%), 512 (2.8%), and 3954 (14.9%) in low, intermediate favorable, intermediate unfavorable, high, and very high-risk levels. These resulted in NNI of 4619, 1182, 319, 35, and 7, respectively. Of 181,109 newly diagnosed PCa patients assessable for analyses of distant metastases (M1a-c ), 8920 (4.9%) harbored M1a-c stage: 50 (0.07%), 45 (0.1%), 161 (0.5%), 1290 (5.1%), and 7374 (22.0%) in low, intermediate favorable, intermediate unfavorable, high, and very high-risk. These resulted in NNI of 1347, 602, 174, 20, and 5, respectively. CONCLUSIONS Our observations perfectly validated the NCCN recommendations for imaging in newly diagnosed high and very high-risk PCa patients. However, in unfavorable intermediate-risk PCa patients, in whom bone and soft tissue imaging is recommended, the NNI might be somewhat elevated to support routine imaging in clinical practice.
Collapse
Affiliation(s)
- Gabriele Sorce
- Department of Urology and Division of Experimental Oncology, URI, Urological Research Institute, IRCCS San Raffaele Scientific Institute, Milan, Italy
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
| | - Benedikt Hoeh
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
- Department of Urology, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Rocco S Flammia
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
- Department of Maternal-Child and Urological Sciences, Policlinico Umberto I Hospital, Sapienza University Rome, Rome, Italy
| | - Francesco Chierigo
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
- Department of Surgical and Diagnostic Integrated Sciences (DISC), University of Genova, Genova, Italy
| | - Lukas Hohenhorst
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
- Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany
| | - Andrea Panunzio
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
- Department of Urology, Azienda Ospedaliera Universitaria Integrata di Verona, University of Verona, Verona, Italy
| | - Nancy Nimer
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
| | - Zhe Tian
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
| | - Giorgio Gandaglia
- Department of Urology and Division of Experimental Oncology, URI, Urological Research Institute, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Derya Tilki
- Martini-Klinik Prostate Cancer Center, University Hospital Hamburg-Eppendorf, Hamburg, Germany
- Department of Urology, University Hospital Hamburg-Eppendorf, Hamburg, Germany
- Department of Urology, Koc University Hospital, Istanbul, Turkey
| | - Carlo Terrone
- Department of Surgical and Diagnostic Integrated Sciences (DISC), University of Genova, Genova, Italy
| | - Michele Gallucci
- Department of Maternal-Child and Urological Sciences, Policlinico Umberto I Hospital, Sapienza University Rome, Rome, Italy
| | - Felix K H Chun
- Department of Urology, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Alessandro Antonelli
- Department of Urology, Azienda Ospedaliera Universitaria Integrata di Verona, University of Verona, Verona, Italy
| | - Fred Saad
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
| | - Shahrokh F Shariat
- Departments of Urology, Weill Cornell Medical College, New York, New York, USA
- Department of Urology, Second Faculty of Medicine, Charles University, Praga, Czech Republic
- Department of Urology, Comprehensive Cancer Center, Medical University of Vienna, Vienna, Austria
- Institute for Urology and Reproductive Health, I.M. Sechenov First Moscow State Medical University, Moscow, Russia
- Division of Urology, Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman, Jordan
- Department of Urology, University of Texas Southwestern, Dallas, Texas, USA
| | - Francesco Montorsi
- Department of Urology and Division of Experimental Oncology, URI, Urological Research Institute, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Alberto Briganti
- Department of Urology and Division of Experimental Oncology, URI, Urological Research Institute, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Pierre I Karakiewicz
- Cancer Prognostics and Health Outcomes Unit, Division of Urology, University of Montréal Health Center, Montréal, Québec, Canada
| |
Collapse
|