2
|
Porreca A, Di Nicola M, Lucarelli G, Dorin VM, Soria F, Terracciano D, Mistretta FA, Luzzago S, Buonerba C, Cantiello F, Mari A, Minervini A, Veccia A, Antonelli A, Musi G, Hurle R, Busetto GM, Del Giudice F, Ferretti S, Perdonà S, Prete PD, Porreca A, Bove P, Crisan N, Russo GI, Damiano R, Amparore D, Porpiglia F, Autorino R, Piccinelli M, Brescia A, Tătaru SO, Crocetto F, Giudice AL, de Cobelli O, Schips L, Ferro M, Marchioni M. Time to progression is the main predictor of survival in patients with high-risk nonmuscle invasive bladder cancer: Results from a machine learning-based analysis of a large multi-institutional database. Urol Oncol 2024; 42:69.e17-69.e25. [PMID: 38302296 DOI: 10.1016/j.urolonc.2024.01.001] [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: 06/10/2023] [Revised: 11/13/2023] [Accepted: 01/01/2024] [Indexed: 02/03/2024]
Abstract
BACKGROUND In patients affected by high-risk nonmuscle invasive bladder cancer (HR-NMIBC) progression to muscle invasive status is considered as the main indicator of local treatment failure. We aimed to investigate the effect of progression and time to progression on overall survival (OS) and to investigate their validity as surrogate endpoints. METHODS A total of 1,510 patients from 18 different institutions treated for T1 high grade NMIBC, followed by a secondary transurethral resection and BCG intravesical instillation. We relied on random survival forest (RSF) to rank covariates based on OS prediction. Cox's regression models were used to quantify the effect of covariates on mortality. RESULTS During a median follow-up of 49.0 months, 485 (32.1%) patients progressed to MIBC, while 163 (10.8%) patients died. The median time to progression was 82 (95%CI: 78.0-93.0) months. In RSF time-to-progression and age were the most predictive covariates of OS. The survival tree defined 5 groups of risk. In multivariable Cox's regression models accounting for progression status as time-dependent covariate, shorter time to progression (as continuous covariate) was associated with longer OS (HR: 9.0, 95%CI: 3.0-6.7; P < 0.001). Virtually same results after time to progression stratification (time to progression ≥10.5 months as reference). CONCLUSION Time to progression is the main predictor of OS in patients with high risk NMIBC treated with BCG and might be considered a coprimary endpoint. In addition, models including time to progression could be considered for patients' stratification in clinical practice and at the time of clinical trials design.
Collapse
Affiliation(s)
- Annamaria Porreca
- Biostatistics Laboratory, Department of Medical, Oral and Biotechnological Sciences, "G. d'Annunzio" University of Chieti, Chieti, Italy
| | - Marta Di Nicola
- Biostatistics Laboratory, Department of Medical, Oral and Biotechnological Sciences, "G. d'Annunzio" University of Chieti, Chieti, Italy
| | - Giuseppe Lucarelli
- Urology, Andrology and Kidney Transplantation Unit, Department of Emergency and Organ Transplantation, University of Bari, Bari, Italy
| | - Vartolomei Mihai Dorin
- Department of Cell and Molecular Biology, George Emil Palade University of Medicine, Pharmacy, Sciences and Technology from Târgu Mureș, Târgu Mureș, Romania
| | - Francesco Soria
- Division of Urology, Department of Surgical Sciences, Torino School of Medicine, Torino, Italy
| | - Daniela Terracciano
- Department of Translational Medical Sciences, University Federico II, Napoli, Italy
| | | | - Stefano Luzzago
- Department of Urology, IEO European Institute of Oncology, IRCCS, Milan, Italy
| | - Carlo Buonerba
- CRTR Rare Tumors Reference Center, AOU Federico II, Napoli, Italy
| | - Francesco Cantiello
- Department of Urology, Magna Graecia University of Catanzaro, Catanzaro, Italy
| | - Andrea Mari
- Unit of Oncologic Minimally-Invasive Urology and Andrology, Department of Urology, Careggi Hospital, University of Florence, Florence, Italy
| | - Andrea Minervini
- Unit of Oncologic Minimally-Invasive Urology and Andrology, Department of Urology, Careggi Hospital, University of Florence, Florence, Italy
| | | | | | - Gennaro Musi
- Department of Urology, IEO European Institute of Oncology, IRCCS, Milan, Italy
| | - Rodolfo Hurle
- Department of Urology, Humanitas Clinical and Research Hospital, Rozzano, Milan, Italy
| | | | | | - Simone Ferretti
- Urology Unit, Department of Medical, Oral and Biotechnological Sciences, "SS. Annunziata" Hospital, "G. d'Annunzio" University of Chieti, Chieti, Italy
| | - Sisto Perdonà
- Uro-Gynecological Department, Istituto Nazionale per lo Studio e la Cura dei Tumori, Fondazione "G. Pascale"-IRCCS, Naples, Italy
| | - Paola Del Prete
- Scientific Directorate, Istituto Nazionale per lo Studio e la Cura dei Tumori, Fondazione "G. Pascale"-IRCCS, Naples, Italy
| | - Angelo Porreca
- Department of Robotic Urologic Surgery, Abano Terme Hospital, Abano Terme, Italy
| | - Pierluigi Bove
- Division of Urology, Department of Experimental Medicine and Surgery, Tor Vergata University of Rome, Rome, Italy
| | - Nicolae Crisan
- Department of Urology, University of Medicine and Pharmacy Iuliu Haţieganu, Cluj-Napoca, Romania
| | | | - Rocco Damiano
- Department of Urology, Magna Graecia University of Catanzaro, Catanzaro, Italy
| | - Daniele Amparore
- Division of Urology, Department of Oncology, School of Medicine, San Luigi Hospital, University of Turin, Orbassano, Turin, Italy
| | - Francesco Porpiglia
- Division of Urology, Department of Oncology, School of Medicine, San Luigi Hospital, University of Turin, Orbassano, Turin, Italy
| | | | - Mattia Piccinelli
- Department of Urology, IEO European Institute of Oncology, IRCCS, Milan, Italy
| | - Antonio Brescia
- Department of Urology, IEO European Institute of Oncology, IRCCS, Milan, Italy
| | - Sabin Octavian Tătaru
- I.O.S.U.D., George Emil Palade University of Medicine, Pharmacy, Sciences and Technology from Târgu Mureș, Târgu Mureș, Romania
| | - Felice Crocetto
- Department of Neurosciences, Science of Reproduction and Odontostomatology, University of Naples Federico II, 80131 Naples, Italy
| | | | - Ottavio de Cobelli
- Department of Urology, IEO European Institute of Oncology, IRCCS, Milan, Italy
| | - Luigi Schips
- Urology Unit, Department of Medical, Oral and Biotechnological Sciences, "SS. Annunziata" Hospital, "G. d'Annunzio" University of Chieti, Chieti, Italy
| | - Matteo Ferro
- Department of Urology, IEO European Institute of Oncology, IRCCS, Milan, Italy
| | - Michele Marchioni
- Urology Unit, Department of Medical, Oral and Biotechnological Sciences, "SS. Annunziata" Hospital, "G. d'Annunzio" University of Chieti, Chieti, Italy.
| |
Collapse
|
3
|
Xiao Z, Song Q, Wei Y, Fu Y, Huang D, Huang C. Use of survival support vector machine combined with random survival forest to predict the survival of nasopharyngeal carcinoma patients. Transl Cancer Res 2023; 12:3581-3590. [PMID: 38192980 PMCID: PMC10774032 DOI: 10.21037/tcr-23-316] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2023] [Accepted: 10/18/2023] [Indexed: 01/10/2024]
Abstract
Background The Cox regression model is not sufficiently accurate to predict the survival prognosis of nasopharyngeal carcinoma (NPC) patients. It is impossible to calculate and rank the importance of impact factors due to the low predictive accuracy of the Cox regression model. So, we developed a system. Using the SEER (The Surveillance, Epidemiology, and End Results) database data on NPC patients, we proposed the use of random survival forest (RSF) and survival-support vector machine (SVM) from the machine learning methods to develop a survival prediction system specifically for NPC patients. This approach aimed to make up for the insufficiency of the Cox regression model. We also used the Cox regression model to validate the development of the nomogram and compared it with machine learning methods. Methods A total of 1,683 NPC patients were extracted from the SEER database from January 2010 to December 2015. We used R language for modeling work, established the nomogram of survival prognosis of NPC patients by Cox regression model, ranked the correlation of influencing factors by RSF model VIMP (variable important) method, developed a survival prognosis system for NPC patients based on survival-SVM, and used C-index for model evaluation and performance comparison. Results Although the Cox regression models can be developed to predict the prognosis of NPC patients, their accuracy was lower than that of machine learning methods. When we substituted the data for the Cox model, the C-index for the training set was only 0.740, and the C-index for the test set was 0.721. In contrast, the C index of the survival-SVM model was 0.785. The C-index of the RSF model was 0.729. The importance ranking of each variable could be obtained according to the VIMP method. Conclusions The prediction results from the Cox model are not as good as those of the RSF method and survival-SVM based on the machine learning method. For the survival prognosis of NPC patients, the machine learning method can be considered for clinical application.
Collapse
Affiliation(s)
- Zhiwei Xiao
- School of Basic Medical Sciences, Guangxi Medical University, Nanning, China
| | - Qiong Song
- Key Laboratory of Longevity and Aging-related Diseases of Chinese Ministry of Education, Center for Translational Medicine, Guangxi Medical University, Nanning, China
| | - Yuekun Wei
- School of Information and Management, Guangxi Medical University, Nanning, China
| | - Yong Fu
- Life Sciences Institute, Guangxi Medical University, Nanning, China
| | - Daizheng Huang
- Life Sciences Institute, Guangxi Medical University, Nanning, China
| | - Chao Huang
- School of Information and Management, Guangxi Medical University, Nanning, China
| |
Collapse
|
4
|
Tran TT, Lee J, Gunathilake M, Kim J, Kim SY, Cho H, Kim J. A comparison of machine learning models and Cox proportional hazards models regarding their ability to predict the risk of gastrointestinal cancer based on metabolic syndrome and its components. Front Oncol 2023; 13:1049787. [PMID: 36937438 PMCID: PMC10018751 DOI: 10.3389/fonc.2023.1049787] [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: 10/03/2022] [Accepted: 01/20/2023] [Indexed: 03/06/2023] Open
Abstract
Background Little is known about applying machine learning (ML) techniques to identify the important variables contributing to the occurrence of gastrointestinal (GI) cancer in epidemiological studies. We aimed to compare different ML models to a Cox proportional hazards (CPH) model regarding their ability to predict the risk of GI cancer based on metabolic syndrome (MetS) and its components. Methods A total of 41,837 participants were included in a prospective cohort study. Incident cancer cases were identified by following up with participants until December 2019. We used CPH, random survival forest (RSF), survival trees (ST), gradient boosting (GB), survival support vector machine (SSVM), and extra survival trees (EST) models to explore the impact of MetS on GI cancer prediction. We used the C-index and integrated Brier score (IBS) to compare the models. Results In all, 540 incident GI cancer cases were identified. The GB and SSVM models exhibited comparable performance to the CPH model concerning the C-index (0.725). We also recorded a similar IBS for all models (0.017). Fasting glucose and waist circumference were considered important predictors. Conclusions Our study found comparably good performance concerning the C-index for the ML models and CPH model. This finding suggests that ML models may be considered another method for survival analysis when the CPH model's conditions are not satisfied.
Collapse
Affiliation(s)
- Tao Thi Tran
- Department of Cancer Control and Population Health, Graduate School of Cancer Science and Policy, Goyang-si, Gyeonggi-do, Republic of Korea
| | - Jeonghee Lee
- Department of Cancer Biomedical Science, Graduate School of Cancer Science and Policy, Goyang-si, Gyeonggi-do, Republic of Korea
| | - Madhawa Gunathilake
- Department of Cancer Biomedical Science, Graduate School of Cancer Science and Policy, Goyang-si, Gyeonggi-do, Republic of Korea
| | - Junetae Kim
- Department of Cancer Control and Population Health, Graduate School of Cancer Science and Policy, Goyang-si, Gyeonggi-do, Republic of Korea
| | - Sun-Young Kim
- Department of Cancer Control and Population Health, Graduate School of Cancer Science and Policy, Goyang-si, Gyeonggi-do, Republic of Korea
| | - Hyunsoon Cho
- Department of Cancer Control and Population Health, Graduate School of Cancer Science and Policy, Goyang-si, Gyeonggi-do, Republic of Korea
| | - Jeongseon Kim
- Department of Cancer Biomedical Science, Graduate School of Cancer Science and Policy, Goyang-si, Gyeonggi-do, Republic of Korea
- *Correspondence: Jeongseon Kim,
| |
Collapse
|