• Je něco špatně v tomto záznamu ?

Deep Learning-based Recalibration of the CUETO and EORTC Prediction Tools for Recurrence and Progression of Non-muscle-invasive Bladder Cancer

M. Jobczyk, K. Stawiski, M. Kaszkowiak, P. Rajwa, W. Różański, F. Soria, SF. Shariat, W. Fendler

. 2022 ; 5 (1) : 109-112. [pub] 20210603

Jazyk angličtina Země Nizozemsko

Typ dokumentu časopisecké články, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/bmc22019426

Despite being standard tools for decision-making, the European Organisation for Research and Treatment of Cancer (EORTC), European Association of Urology (EAU), and Club Urologico Espanol de Tratamiento Oncologico (CUETO) risk groups provide moderate performance in predicting recurrence-free survival (RFS) and progression-free survival (PFS) in non-muscle-invasive bladder cancer (NMIBC). In this retrospective combined-cohort data-mining study, the training group consisted of 3570 patients with de novo diagnosed NMIBC. Predictors included gender, age, T stage, histopathological grading, tumor burden and diameter, EORTC and CUETO scores, and type of intravesical treatment. The models developed were externally validated using an independent cohort of 322 patients. Models were trained using Cox proportional-hazards deep neural networks (deep learning; DeepSurv) with a proprietary grid search of hyperparameters. For patients treated with surgery and bacillus Calmette-Guérin-treated patients, the models achieved a c index of 0.650 (95% confidence interval [CI] 0.649-0.650) for RFS and 0.878 (95% CI 0.873-0.874) for PFS in the training group. In the validation group, the c index was 0.651 (95% CI 0.648-0.654) for RFS and 0.881 (95% CI 0.878-0.885) for PFS. After inclusion of patients treated with mitomycin C, the c index for RFS models was 0.6415 (95% CI 0.6412-0.6417) for the training group and 0.660 (95% CI 0.657-0.664) for the validation group. Models for PFS achieved a c index of 0.885 (95% CI 0.885-0.885) for the training set and 0.876 (95% CI 0.873-0.880) for the validation set. Our tool outperformed standard-of-care risk stratification tools and showed no evidence of overfitting. The application is open source and available at https://biostat.umed.pl/deepNMIBC/. PATIENT SUMMARY: We created and validated a new tool to predict recurrence and progression of early-stage bladder cancer. The application uses advanced artificial intelligence to combine state-of-the-art scales, outperforms these scales for prediction, and is freely available online.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22019426
003      
CZ-PrNML
005      
20220804135639.0
007      
ta
008      
220720s2022 ne f 000 0|eng||
009      
AR
024    7_
$a 10.1016/j.euo.2021.05.006 $2 doi
035    __
$a (PubMed)34092528
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a ne
100    1_
$a Jobczyk, Mateusz $u Department of Urology, Copernicus Memorial Hospital, Medical University of Lodz, Lodz, Poland; Department of Urology, The Hospital Ministry of the Interior and Administration, Lodz, Poland
245    10
$a Deep Learning-based Recalibration of the CUETO and EORTC Prediction Tools for Recurrence and Progression of Non-muscle-invasive Bladder Cancer / $c M. Jobczyk, K. Stawiski, M. Kaszkowiak, P. Rajwa, W. Różański, F. Soria, SF. Shariat, W. Fendler
520    9_
$a Despite being standard tools for decision-making, the European Organisation for Research and Treatment of Cancer (EORTC), European Association of Urology (EAU), and Club Urologico Espanol de Tratamiento Oncologico (CUETO) risk groups provide moderate performance in predicting recurrence-free survival (RFS) and progression-free survival (PFS) in non-muscle-invasive bladder cancer (NMIBC). In this retrospective combined-cohort data-mining study, the training group consisted of 3570 patients with de novo diagnosed NMIBC. Predictors included gender, age, T stage, histopathological grading, tumor burden and diameter, EORTC and CUETO scores, and type of intravesical treatment. The models developed were externally validated using an independent cohort of 322 patients. Models were trained using Cox proportional-hazards deep neural networks (deep learning; DeepSurv) with a proprietary grid search of hyperparameters. For patients treated with surgery and bacillus Calmette-Guérin-treated patients, the models achieved a c index of 0.650 (95% confidence interval [CI] 0.649-0.650) for RFS and 0.878 (95% CI 0.873-0.874) for PFS in the training group. In the validation group, the c index was 0.651 (95% CI 0.648-0.654) for RFS and 0.881 (95% CI 0.878-0.885) for PFS. After inclusion of patients treated with mitomycin C, the c index for RFS models was 0.6415 (95% CI 0.6412-0.6417) for the training group and 0.660 (95% CI 0.657-0.664) for the validation group. Models for PFS achieved a c index of 0.885 (95% CI 0.885-0.885) for the training set and 0.876 (95% CI 0.873-0.880) for the validation set. Our tool outperformed standard-of-care risk stratification tools and showed no evidence of overfitting. The application is open source and available at https://biostat.umed.pl/deepNMIBC/. PATIENT SUMMARY: We created and validated a new tool to predict recurrence and progression of early-stage bladder cancer. The application uses advanced artificial intelligence to combine state-of-the-art scales, outperforms these scales for prediction, and is freely available online.
650    _2
$a umělá inteligence $7 D001185
650    12
$a deep learning $7 D000077321
650    _2
$a progrese nemoci $7 D018450
650    _2
$a ženské pohlaví $7 D005260
650    _2
$a lidé $7 D006801
650    _2
$a mužské pohlaví $7 D008297
650    _2
$a invazivní růst nádoru $7 D009361
650    _2
$a lokální recidiva nádoru $x patologie $7 D009364
650    _2
$a prognóza $7 D011379
650    _2
$a retrospektivní studie $7 D012189
650    _2
$a hodnocení rizik $7 D018570
650    12
$a nádory močového měchýře $x patologie $7 D001749
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Stawiski, Konrad $u Department of Biostatistics and Translational Medicine, Medical University of Lodz, Lodz, Poland. Electronic address: konrad@konsta.com.pl
700    1_
$a Kaszkowiak, Marcin $u Department of Biostatistics and Translational Medicine, Medical University of Lodz, Lodz, Poland
700    1_
$a Rajwa, Paweł $u Department of Urology, Medical University of Silesia, Zabrze, Poland; Department of Urology, Medical University of Vienna, Vienna, Austria
700    1_
$a Różański, Waldemar $u Department of Urology, Copernicus Memorial Hospital, Medical University of Lodz, Lodz, Poland
700    1_
$a Soria, Francesco $u Department of Urology, Medical University of Vienna, Vienna, Austria; Division of Urology, Department of Surgical Sciences, Torino School of Medicine, Turin, Italy
700    1_
$a Shariat, Shahrokh F $u Department of Urology, Medical University of Vienna, Vienna, Austria; Karl Landsteiner Institute of Urology and Andrology, Vienna, Austria; Department of Urology, Weill Cornell Medical College, New York, NY, USA; Department of Urology, University of Texas Southwestern, Dallas, TX, USA; Department of Urology, Second Faculty of Medicine, Charles University, Prague, Czech Republic; Institute for Urology and Reproductive Health, Sechenov University, Moscow, Russia
700    1_
$a Fendler, Wojciech $u Department of Biostatistics and Translational Medicine, Medical University of Lodz, Lodz, Poland; Department of Radiation Oncology, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, USA
773    0_
$w MED00205913 $t European urology oncology $x 2588-9311 $g Roč. 5, č. 1 (2022), s. 109-112
856    41
$u https://pubmed.ncbi.nlm.nih.gov/34092528 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20220720 $b ABA008
991    __
$a 20220804135633 $b ABA008
999    __
$a ok $b bmc $g 1822851 $s 1170669
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2022 $b 5 $c 1 $d 109-112 $e 20210603 $i 2588-9311 $m European urology oncology $n Eur Urol Oncol $x MED00205913
LZP    __
$a Pubmed-20220720

Najít záznam

Citační ukazatele

Pouze přihlášení uživatelé

Možnosti archivace