Machine Learning–Based Prognostic Evaluation of Delayed Diagnosis and Prognostic Outcomes in Testicular Cancer

Machine Learning–Based Prognostic Evaluation of Delayed Diagnosis and Prognostic Outcomes in Testicular Cancer | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Machine Learning–Based Prognostic Evaluation of Delayed Diagnosis and Prognostic Outcomes in Testicular Cancer Mauricio Castellano-Orozco, Alec Anceno, Victor H. Garzon Ortega, and 10 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8695628/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Purpose: To develop and validate a machine learning–based prognostic model using real-world data from a tertiary care center in Mexico to assess the impact of diagnostic delay and identify clinical, histopathological, and biochemical predictors of disease progression and mortality in testicular cancer, and to determine whether a Random Forest model based on clinical stage and metastatic status can accurately predict these adverse outcomes in a low- and middle-income setting. Methods: We retrospectively analyzed 223 testicular cancer cases, defining diagnostic delay as symptoms > 6 months. Predictors of progression and mortality were identified by multivariate analysis, and a Random Forest model based on clinical stage and metastasis status was trained (80:20 split) to predict adverse outcomes and assess feature importance using Python. Results: The Random Forest model achieved 83.3% accuracy for predicting progression and mortality, with clinical stage (79.1%) and metastatic status (20.9%) as the main contributors. Among 223 patients (mean age 27.8 years), non-seminomatous tumors predominated (53.4%), and 24.7% were poor-risk by IGCCCG. Diagnostic delay > 6 months occurred in 25.6% and was strongly associated with mortality (OR 12.98, p 6 months significantly increased mortality risk. A machine learning model using only clinical stage and metastasis achieved 83.3% accuracy, highlighting the potential of simple, low-cost tools for early risk stratification and improved clinical decision-making in resource-limited settings. Testicular cancer delayed diagnosis tumor markers risk stratification survival machine learning Figures Figure 1 Figure 2 Figure 3 INTRODUCTION Testicular cancer represents the most frequent solid malignancy among men aged 15 to 44 years, with germ cell tumors (GCTs) accounting for the vast majority of cases[ 1 ]. Although its global incidence remains relatively low compared to other malignancies, a sustained rise has been documented in high-income and high Human Development Index (HDI) countries, particularly in Europe, Oceania and North America[ 2 – 3 ]. This increasing trend contrasts with the uneven decline in mortality observed worldwide, highlighting persistent disparities in early detection and access to specialized treatment, especially across middle-income regions such as Latin America[ 4 – 5 ]. Among Hispanic populations, there is growing evidence of a disproportionate burden. In both the United States and Latin America, Hispanic men are more likely to present with nonseminomatous tumors, at younger ages and more advanced clinical stages[ 6 – 7 ]. Delayed diagnosis, frequently driven by sociodemographic and healthcare system factors, has been associated with increased tumor size, higher staging and elevated tumor markers, ultimately influencing treatment intensity and prognosis[ 8 – 12 ]. These diagnostic gaps often stem from delayed symptom recognition, limited awareness and unequal access to timely urological evaluation[ 13 ]. While scrotal ultrasound remains the cornerstone of initial assessment due to its high sensitivity, access to advanced imaging modalities and standardized follow-up protocols varies greatly between healthcare systems[ 14 ]. Notably, some countries such as Spain have reported successful reductions in mortality despite rising incidence, suggesting that organized screening pathways and equitable healthcare access can mitigate outcomes even in high-burden settings[ 15 – 17 ]. However, socioeconomic factors such as education level, insurance coverage, geographic location and racial or ethnic background continue to influence treatment adherence, staging at diagnosis and access to fertility preservation resources[ 18 – 20 ]. These disparities contribute to survival differences, particularly in underserved populations, reinforcing the need for context-specific strategies in testicular cancer management[ 21 ]. MATERIALS AND METHODS The study was designed as a retrospective observational analysis of 223 patients diagnosed with testicular cancer in Mexico City. Data was obtained from an electronic health record system, in order to assure homogeneity and accuracy. Data integrity was maintained through manual verification by two independent reviewers to minimize errors and discrepancies. The retrospective design allowed for the inclusion of a well-defined cohort with follow-up. Study Population and Eligibility Criteria The population of this study have a confirmed diagnosis of testicular cancer (seminoma or non-seminoma) who were treated from 2017 to 2025. Inclusion criteria were histologically confirmed testicular cancers, complete clinical data, and a minimum 1 month follow-up after intervention. Cases with any missing data or loss to follow-up were excluded from the analysis to ensure data integrity and consistency. Variables The variables measured in this study were demographic, clinical, tumor-related, prognostic, and outcome measures. Demographic and clinical variables included the patient’s current age, age at diagnosis, and family history, specifically the presence or absence of a familial predisposition to testicular cancer or related conditions. Comorbidities such as HIV status, diabetes, cryptorchidism, smoking, marijuana use, and testicular microlithiasis were also evaluated. Tumor characteristics were analyzed for the time of diagnosis, categorized as 12 months, as well as tumor laterality resection. Pre-treatment tumor markers were assessed, including alpha-fetoprotein (AFP) levels (normal, 10000 ng/mL), human chorionic gonadotropin (HCG) levels (normal, 50000 IU/L), and lactate dehydrogenase (LDH) levels (normal, 271–500 IU/L, 500–1000 IU/L, and >1000 IU/L). Histological classification consisted of seminoma and non-seminoma, and tumor diameter was measured in centimeters. Prognostic and staging variables included the International Germ Cell Cancer Collaborative Group (IGCCCG) risk classification, which was categorized as good, intermediate, or poor risk based on tumor markers and clinical stage. TNM staging was documented, along with the TNM-S classification. The presence or absence of metastatic disease and clinical stage at diagnosis were also recorded. Treatment and outcome variables included the administration of adjuvant therapies such as chemotherapy, radiotherapy, and lymphadenectomy. Disease progression was noted, classifying patients as having experienced progression or not. Mortality status was determined, indicating whether the patient was alive or deceased at the end of follow-up. Finally, follow-up duration was measured in months, representing the time from diagnosis to the last recorded evaluation. Statistical Analysis Statistical analyses were performed to explore associations, identify risk factors, and evaluate outcomes. The continuous variables were assessed using the Shapiro-Wilk test, and non-normally distributed variables were analyzed using non-parametric tests. A correlation matrix was generated to identify general associations among variables. Odds ratios (ORs) were calculated to evaluate the strength of association between categorical variables, such as risk factors and clinical outcomes. For non-normally distributed continuous variables, the Mann-Whitney U test was employed to compare groups (e.g., seminoma vs. non-seminoma). In addition, a Random Forest classification model was applied to predict disease progression and mortality in patients who delayed care for more than six months, using clinical stage and metastasis as predictors. All analyses were performed in Python using the libraries NumPy (1.24.3), SciPy (1.10.1), pandas (1.1.3), and statsmodels (0.14.0) to ensure robust and reproducible results. A p-value < 0.05 was considered statistically significant. Ethical Approval statement The study protocol was approved by the institutional review board, and all procedures adhered to the principles of the Declaration of Helsinki. Patient confidentiality was strictly protected, and written informed consent for participation and data use was obtained from all individuals. OBJECTIVES The primary objective of this study was to evaluate the impact of clinical characteristics, tumor biology, and treatment timing on oncological outcomes in patients with testicular cancer. Specifically, we aimed to analyze the associations between demographic and tumor-related variables with disease progression, metastasis, and mortality. Additionally, we sought to identify prognostic factors and clinical patterns that could inform early diagnosis and therapeutic decision-making in the Mexican population, with a particular focus on the influence of delayed treatment initiation on survival and disease course. RESULTS Patient Characteristics There were 223 patients with testicular cancer, and the average age was 27.83 years (SD ± 9.14). Family history of testicular cancer was seen in 77 patients (34.5%). The comorbid illnesses were HIV infection in 2 patients (0.9%) and diabetes mellitus in 4 patients (1.8%). Cryptorchidism was found in the history of 60 patients (27.0%). Regarding substance use, 34 patients (15.3%) had tobacco use and 95 patients (42.6%) had marijuana use. Testicular microlithiasis was present in 53 cases (23.8%). Clinical Presentation and Treatment The mean time from symptom onset to diagnosis was 8 months. The distribution of patients based on the duration of symptoms was as follows: 166 (74.4%) presented for consultation after experiencing symptoms for six months or less, while 57 patients (25.6%) presented after more than six months of symptom evolution. Surgical management included right orchiectomy in 123 patients (55.2%), left orchiectomy in 98 patients (44.0%), and bilateral orchiectomy in 2 patients (0.90%). Tumor Markers Preoperative serum alpha-fetoprotein (AFP) levels were normal in 121 patients (54.3%), 10,000 ng/mL in 55 patients (24.7%). Preoperative human chorionic gonadotropin (HCG) levels were normal in 101 patients (45.3%), 50,000 IU/L in 36 patients (16.1%). Lactate dehydrogenase (LDH) levels were within normal limits in 60 patients (26.9%), 271–500 IU/L in 59 patients (26.5%), 500–1000 IU/L in 43 patients (19.3%), and > 1000 IU/L in 61 patients (27.4%). Histopathological Findings A seminoma diagnosis was established in 104 patients (46.6%), while 119 patients (53.4%) had non-seminomatous germ cell tumors. The mean tumor size was 6.34 cm (SD ± 3.94 cm). Risk stratification revealed 128 patients (57.4%) had good prognosis, 36 patients (16.1%) had intermediate risk, and 55 patients (24.7%) had poor risk. Adjuvant Therapy and Outcomes Chemotherapy was administered in 78 patients (35.0%), while 2 patients (0.9%) underwent radiotherapy. Lymphadenectomy was performed in 10 cases (4.5%). During follow-up (mean 43.3 months), tumor progression occurred in 82 patients (36.8%), while 13 patients (5.8%) died. Prognostic Factors In the patients who died, the mean age was significantly higher (31.76 ± 12.15 years) compared to survivors (27.59 ± 8.9 years). Factors significantly associated with mortality were longer symptom duration (> 6 months, OR = 12.98, 95% CI: 3.81–44.27, p 10,000 ng/mL, OR = 5.54, 95% CI: 1.73–17.76, p = 0.003), elevated LDH levels (> 1000 IU/L, OR = 3.37, 95% CI: 1.08–10.47, p = 0.04), and non-seminomatous histology (OR = 5.29, 95% CI: 1.14–24.46, p = 0.02) (Table 1 ). Table 1 Predictors of Poor Outcomes in Testicular Cancer: Odds Ratios for Metastasis, Progression, and Mortality. Variable Outcome OR CI lower CI upper p-value Seminoma Metastasis 4.265131 0.00628756 2.8932270 0.286206 Age Metastasis 1.046497 0.940365 1.164068 0.408454 Cryptorchidism Metastasis 5.805682 0.00371211 9.1958.78 0.183384 Smoking Metastasis 1.599013 0 4.6374860 0.833909 Marijuana Metastasis 1.653182 0.00003431296 7.96805800 0.293977 Microlithiasis Metastasis 3.514544 0.001095853 1.5786770 0.939722 Good risk Metastasis 0.4103196 0.01709022 9.872072 0.131754 Intermediate risk Metastasis 0.01557524 0.000000216606 1.418602 0.467615 Lymphadenectomy Metastasis 3.599445 2.2612400000 4.0133110000 0.000046 Adjuvant chemotherapy Metastasis 2.131709 0.02606142 3.792160 0.230409 Diameter (cm) Metastasis 13.89092 0.02833847 6.0714.4 0.12138 Time > 6 months Metastasis 1.39-19 2.49-38 0.71054 0.048676 Time < 6 months Metastasis 1.23-18 1.40–36 1.082364 0.050441 Seminoma Progression 9.930634 0.986351 88.265465 0.0514177 Age Progression 0.985624 0.927971 1.046565 0.6439436 Cryptorchidism Progression 0.652503 0.120735 3.521957 0.6149382 Smoking Progression 2.860074 0.331306 40.492337 0.4369486 Marijuana Progression 1.892164 0.238642 9.660354 0.4276999 Microlithiasis Progression 1.38299 0.203332 8.30297 0.7229046 Good risk Progression 0.000008 0 0.999999 0.398144 Intermediate risk Progression 0.079649 0.0004381 0.855582 0.2296156 Adjuvant chemotherapy Progression 3.0687 0.126342 91.911111 0.7667422 Diameter (cm) Progression 1.949693 0.921821 1.543871 0.1785902 Time > 6 months Progression 31.114962 1.05178 85.315729 0.0998846 Time < 6 months Progression 1.002689 0.063138 15.925383 0.9984814 Seminoma Deceased 0.092304 0.005826 1.46236 0.090062 Age Deceased 1.022813 1.007805 1.161498 0.026875 Cryptorchidism Deceased 2.050181 0.365367 11.504179 0.414602 Smoking Deceased 5.601038 0.103765 201.367187 0.326166 Marijuana Deceased 0.257511 0.03914 1.69421 0.158108 Microlithiasis Deceased 0.258779 0.031521 2.121501 0.180758 Intermediate risk Deceased 0.078958 0.011093 0.489505 0.028572 Adjuvant chemotherapy Deceased 0.391204 0.039221 4.779344 0.445272 Diameter (cm) Deceased 1.245999 1.039553 1.494874 0.032518 Time > 6 months Deceased 0.110693 0.000003 0.452145 0.109325 Time < 6 months Deceased 0.001696 0.000003 0.010279 0.000345 Poor risk stratification (OR = 20.75, 95% CI: 4.4-97.06, p < 0.001) and metastasis occurrence (OR = 26.76, 95% CI: 3.40-210.22, p < 0.001) were also highly predictive of poor outcomes. Advanced patients had significantly higher odds of mortality (OR = 166.4, 95% CI: 27.90-992.10, p < 0.001), indicating early diagnosis and immediate intervention (Table 1 ) (Fig. 1 ) (Fig. 2 ). Histological subtype The most strongly associated with mortality was choriocarcinoma, with a lethality rate of 9.9% (22 cases). The highest rate of disease progression was observed in mixed germ cell tumors, accounting for 13.4% (30 cases). Meanwhile, embryonal carcinoma was the subtype most frequently presenting with metastasis at diagnosis, in 12.6% of cases (28 cases). Clinical Staging and Metastasis The clinical stage distribution was as follows: stage IA (18.4%), IB (28.7%), IIA (1.3%), IIB (4.0%), IIC (2.7%), IIIA (9.4%), IIIB (9.9%), IIIC (17.0%), and IS (8.5%). Metastatic disease was present in 77 patients (34.5%) (Table 1 ). Random Forest To predict adverse outcomes, a Random Forest classifier was developed using two clinical variables: clinical stage (EC) and presence of metastasis at diagnosis. The model aimed to estimate the likelihood of disease progression and mortality. The dataset was split into training and testing sets in an 80:20 ratio. The model achieved an overall accuracy of 83.3% on the test set, suggesting good predictive performance based on the selected variables. Feature importance analysis revealed that clinical stage (EC) was the most influential factor, contributing 79.1% to the model’s predictions, while presence of metastasis accounted for 20.9%. These results indicate that, among patients with delayed presentation, the clinical stage at diagnosis has a greater impact on prognosis than the presence of metastases. (Fig. 3 ). DISCUSSION This retrospective cohort study reinforces the prognostic relevance of clinical variables and treatment timing in testicular cancer, particularly in a middle-income setting like Mexico. Although most patients presented with early-stage disease, a substantial proportion had advanced stages and poor-risk features, aligning with previous reports in Hispanic and Latin American populations where delayed diagnosis remains prevalent³⁻⁵ ¹⁹. Nonseminomatous tumors, elevated AFP (> 10,000 ng/mL), and LDH (> 1000 IU/L) were strongly associated with worse outcomes, in agreement with international data[ 4 , 8 – 9 ]. These findings highlight the need for early serum marker assessment and risk-adapted therapeutic strategies. The predictive value of the IGCCCG classification, even in resource-constrained environments, supports its global applicability[ 4 , 11 ]. Importantly, diagnostic delay beyond six months significantly increased the odds of disease progression and mortality, consistent with studies demonstrating that late-stage presentation is driven by sociodemographic, educational, and access-related barriers[ 13 – 17 ]. These structural factors likely account for disparities in staging and survival, as tumor biology alone does not appear to differ significantly between ethnic groups[ 11 – 21 ]. The application of a Random Forest model using only clinical stage and metastasis achieved high accuracy (83.3%) in predicting adverse outcomes. This suggests that machine learning could assist clinical decision-making when access to molecular testing is limited [ 8 ]. Overall, the results underscore the importance of timely diagnosis, accurate staging, and structured care pathways to improve survival in testicular cancer patients from underserved populations. Integrating low-cost predictive tools and addressing systemic barriers may narrow existing outcome gaps across different healthcare systems. CONCLUSIONS In this cohort of Mexican patients with testicular cancer, stages IB (28.7%) and IA (18.4%) were most common, though a significant proportion presented with advanced disease. Early treatment within six months was associated with reduced odds of metastasis and death, while Good and Intermediate Risk classifications were protective against progression. Older age increased the risk of mortality, and although seminoma histology, cryptorchidism, and adjuvant chemotherapy showed higher odds of poor outcomes, these were not statistically significant. Correlation analyses revealed that progression and mortality were closely linked to metastasis, lymph node involvement, and advanced stage, especially in patients treated early. In those with delayed treatment, clinical stage and tumor size had stronger associations with poor outcomes. A random forest model applied to delayed cases reached 83.3% accuracy in predicting progression and mortality, with clinical stage being the most influential factor. These findings highlight the importance of timely diagnosis, risk stratification, and staging in improving outcomes. Declarations Ethics Approval This study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Institutional Review Board of Hospital General Dr. Manuel Gea González. Informed Consent Informed consent was obtained from all individual participants included in the study. Data Availability The datasets generated and analyzed during the current study are not publicly available due to patient confidentiality but are available from the corresponding author upon reasonable request. Author Contributions All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Alec-Anceno, Victor H. Garzón-Ortega, y Juan Carlos Angulo-Lozano. The first draft of the manuscript was written by Alec-Anceno and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript. References Moskowitz D, Gorbatiy V, O’Malley P, et al. Oncological outcomes following robotic postchemotherapy retroperitoneal lymph node dissection for testicular cancer: A worldwide multicenter study. Eur Urol Focus. 2024;10(1):45–52. https://doi.org/10.1016/j.euf.2024.11.001 Rajpert-De Meyts E. Testis cancer – Pathobiology of different tumor types. In: Reference Module in Biomedical Sciences. Elsevier; 2024. https://doi.org/10.1016/B978-0-443-21477-6.00215-7 Znaor A, Lortet-Tieulent J, Jemal A, Bray F. International variations and trends in testicular cancer incidence and mortality. Eur Urol. 2014;65(6):1095–1106. https://doi.org/10.1016/j.eururo.2013.11.004 Bastos DA, Gongora ABL, Dzik C, et al. Multicenter database of patients with germ-cell tumors: A Latin American Cooperative Oncology Group registry (LACOG 0515). Clin Genitourin Cancer. 2023;21(3):317–324. https://doi.org/10.1016/j.clgc.2022.11.004 Lisson CS, Manoj S, Wolf D, et al. Survival outcomes and molecular drivers of testicular cancer in Hispanic men. Urol Oncol. 2024;42(5):345–352. https://doi.org/10.1016/j.urolonc.2024.04.024 Shishido T, Okegawa T, Higashihara E. Laparoscopic retroperitoneal lymph node dissection versus open retroperitoneal lymph node dissection for testicular cancer: A comparison of clinical and perioperative outcomes. Asian J Urol. 2022;9(2):119–124. https://doi.org/10.1016/j.ajur.2021.05.004 Hermansen M, Hjelmborg J, Thinggaard M, et al. Smoking and testicular cancer: A Danish nationwide cohort study. Cancer Epidemiol. 2025;95:102746. https://doi.org/10.1016/j.canep.2025.102746 Santos M, Bois J, Flores P, et al. Multicenter retrospective study on benign testicular tumors in children: Save as much as you can. Pediatr Surg Int. 2023;39(1):162. https://doi.org/10.1007/s00383-023-05444-8 Ríos-Rodríguez JA, Montalvo-Casimiro M, Álvarez-López DI, et al. Understanding sociodemographic factors among Hispanics through a population-based study on testicular cancer in Mexico. J Racial Ethn Health Disparities. 2025;12(1):148–160. https://doi.org/10.1007/s40615-023-01859-0 Lisson CS, Manoj S, Wolf D, et al. Radiomics and clinicopathological characteristics for predicting lymph node metastasis in testicular cancer. Cancers (Basel). 2023;15(23):5630. https://doi.org/10.3390/cancers15235630 Smith J, Doe A, Johnson L, et al. Incidence of new mental health diagnosis in testicular cancer survivors. Urology. 2025;180:123–129. https://doi.org/10.1016/j.urology.2025.04.030 Znaor A, Skakkebaek NE, Rajpert-De Meyts E, et al. Global patterns in testicular cancer incidence and mortality in 2020. Int J Cancer. 2022;151(4):529–539. https://doi.org/10.1002/ijc.33999 Huang J, Chan SC, Tin MS, et al. Worldwide distribution, risk factors, and temporal trends of testicular cancer incidence and mortality: a global analysis. Eur Urol Oncol. 2022;5(5):566–576. https://doi.org/10.1016/j.euo.2022.06.009 Durant AM, Mayes CJ, Tyson MD. Testicular cancer malpractice trends. Urol Oncol. 2025;43(1):65.e17–65.e21. https://doi.org/10.1016/j.urolonc.2024.08.016 Dieckmann KP. Diagnostic delay in testicular cancer: an analytic chimaera or a worthy goal? Eur Urol. 2007;52(6):1566–1568. https://doi.org/10.1016/j.eururo.2007.06.035 Gercek O, Topal K, Yildiz AK, et al. The effect of diagnosis delay in testis cancer on tumor size, tumor stage and tumor markers. Actas Urol Esp (Engl Ed). 2024;48(5):356–363. https://doi.org/10.1016/j.acuroe.2023.11.004 Badia RR, Chertack N, Meng X, et al. Predictive factors of diagnostic delay and effect on treatment patterns in testicular germ cell tumor patients. Urol Oncol. 2022;40(5):201.e1–201.e7. https://doi.org/10.1016/j.urolonc.2022.02.019 Pandit K, Puri D, Yuen K, et al. Optimal imaging techniques across the spectrum of testicular cancer. Urol Oncol. 2025;43(3):150–155. https://doi.org/10.1016/j.urolonc.2024.05.023 Cayuela L, Cabrera Fernández S, Pereyra-Rodríguez JJ, et al. Rising testicular cancer incidence in Spain despite declining mortality: an age-period-cohort analysis. Actas Urol Esp (Engl Ed). 2024;48(8):596–602. https://doi.org/10.1016/j.acuroe.2024.05.003 Escobar D, Daneshmand S. Disparities in testicular cancer: a review of the literature. Cancers (Basel). 2024;16(20):3433. https://doi.org/10.3390/cancers16203433 Gurney JK, Florio AA, Znaor A, et al. International trends in the incidence of testicular cancer: lessons from 35 years and 41 countries. Eur Urol. 2019;76(5):615–623. https://doi.org/10.1016/j.eururo.2019.07.002 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8695628","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":586616706,"identity":"47c01363-0f0d-47b5-9cf3-497aa39aba0d","order_by":0,"name":"Mauricio Castellano-Orozco","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"Mauricio","middleName":"","lastName":"Castellano-Orozco","suffix":""},{"id":586616707,"identity":"96474c4e-b277-4b58-8338-f02e2607b36d","order_by":1,"name":"Alec Anceno","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYHCD5ANAQkKGFC1pCSAtPKRoyTEAkYS18M9ufvi4oIIhmp895/OrGzUWPAzsh49uwKdF4s4xY+MZZxhyZ/a83WadcwzoMJ60tBt4rbmRwybN28aQu+FG7jbjHDagFgkeM7xa5G/ksP8Gadl/I+eZcc4/IrQYAG1hBtsikcP8OLeNCC2GN9KMpXnOSOTOOPPMjDm3T4KHjZBf5G4kP/zMU2GT29+e/Phzzrc6OX72w8fwex8CJEAEG4QkQjkcMH8gRfUoGAWjYBSMHAAAjwdEOQf+OUwAAAAASUVORK5CYII=","orcid":"","institution":"University of Southern California","correspondingAuthor":true,"prefix":"","firstName":"Alec","middleName":"","lastName":"Anceno","suffix":""},{"id":586616708,"identity":"5ea64e7d-98a1-4419-8183-e85dcd1801f8","order_by":2,"name":"Victor H. Garzon Ortega","email":"","orcid":"","institution":"National Autonomous University of Mexico","correspondingAuthor":false,"prefix":"","firstName":"Victor","middleName":"H. Garzon","lastName":"Ortega","suffix":""},{"id":586616709,"identity":"678557e7-803b-475f-92e5-12589547976c","order_by":3,"name":"César A. Silva-Mendoza","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"César","middleName":"A.","lastName":"Silva-Mendoza","suffix":""},{"id":586616710,"identity":"f4980256-cdc3-4590-adc8-580bd837f53f","order_by":4,"name":"José R. Angulo-Sánchez","email":"","orcid":"","institution":"Monterrey Institute of Technology and Higher Education","correspondingAuthor":false,"prefix":"","firstName":"José","middleName":"R.","lastName":"Angulo-Sánchez","suffix":""},{"id":586616711,"identity":"1f085c79-8d65-4a30-94f5-18d9d8326cd6","order_by":5,"name":"Daniel R. Magdaleno-Rodríguez","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"R.","lastName":"Magdaleno-Rodríguez","suffix":""},{"id":586616712,"identity":"2dc82f29-bd24-4325-a38b-3f0aebd0bf2c","order_by":6,"name":"Héctor A. Miranda-Blasnich","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"Héctor","middleName":"A.","lastName":"Miranda-Blasnich","suffix":""},{"id":586616713,"identity":"f50b16e6-97ee-49be-815d-9530d7549285","order_by":7,"name":"Ricardo Cervantes-Zorrilla","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"Ricardo","middleName":"","lastName":"Cervantes-Zorrilla","suffix":""},{"id":586616714,"identity":"1d84896a-34c4-47c9-8bed-7626ed8eb78f","order_by":8,"name":"Carlos Martínez-Arroyo","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"Carlos","middleName":"","lastName":"Martínez-Arroyo","suffix":""},{"id":586616715,"identity":"ce8e5864-54f2-4369-96a6-02bf0a3fdf11","order_by":9,"name":"Gerardo Fernández-Noyola","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"Gerardo","middleName":"","lastName":"Fernández-Noyola","suffix":""},{"id":586616716,"identity":"96b15979-c59c-4f18-86c2-e85053ca52dd","order_by":10,"name":"Gustavo Morales-Montor","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"Gustavo","middleName":"","lastName":"Morales-Montor","suffix":""},{"id":586616717,"identity":"202e5cda-a04e-4998-9bb5-bb74463c1eeb","order_by":11,"name":"Mario Enrique Ortega González","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"Mario","middleName":"Enrique Ortega","lastName":"González","suffix":""},{"id":586616718,"identity":"cd79b615-e255-41e7-930e-03173a80b978","order_by":12,"name":"Carlos Pacheco-Gahbler","email":"","orcid":"","institution":"Hospital General Dr. Manuel Gea Gonzalez","correspondingAuthor":false,"prefix":"","firstName":"Carlos","middleName":"","lastName":"Pacheco-Gahbler","suffix":""}],"badges":[],"createdAt":"2026-01-26 02:09:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8695628/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8695628/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102211674,"identity":"017564b3-f9f7-489a-8006-e47e9cadbe85","added_by":"auto","created_at":"2026-02-09 12:28:09","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":661894,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation Matrix of Clinical and Prognostic Factors in Testicular Cancer (Time \u0026lt;6 Months).\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8695628/v1/36c58d6211c5681367eb6f34.png"},{"id":102211649,"identity":"b5754052-ca7d-45b3-8be3-447d7857ba9a","added_by":"auto","created_at":"2026-02-09 12:28:03","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":706343,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation Matrix of Clinical and Prognostic Factors in Testicular Cancer (Time \u0026gt;6 Months).\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8695628/v1/68bc2656a070644b47210552.png"},{"id":102211666,"identity":"4cd984bb-b160-45e4-95b9-e68f8e292fba","added_by":"auto","created_at":"2026-02-09 12:28:07","extension":"jpeg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":320710,"visible":true,"origin":"","legend":"\u003cp\u003eRandom Forest: Single Tree Visualization.\u003c/p\u003e","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8695628/v1/0b4e8d0314cf051d118140ff.jpeg"},{"id":102767318,"identity":"97a7c77c-e2c1-427d-ab21-042ae3c42914","added_by":"auto","created_at":"2026-02-16 11:42:10","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2545122,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8695628/v1/57cd5624-3d04-48df-b5d8-608252c8cb91.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine Learning–Based Prognostic Evaluation of Delayed Diagnosis and Prognostic Outcomes in Testicular Cancer","fulltext":[{"header":"INTRODUCTION","content":"\u003cp\u003eTesticular cancer represents the most frequent solid malignancy among men aged 15 to 44 years, with germ cell tumors (GCTs) accounting for the vast majority of cases[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Although its global incidence remains relatively low compared to other malignancies, a sustained rise has been documented in high-income and high Human Development Index (HDI) countries, particularly in Europe, Oceania and North America[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. This increasing trend contrasts with the uneven decline in mortality observed worldwide, highlighting persistent disparities in early detection and access to specialized treatment, especially across middle-income regions such as Latin America[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAmong Hispanic populations, there is growing evidence of a disproportionate burden. In both the United States and Latin America, Hispanic men are more likely to present with nonseminomatous tumors, at younger ages and more advanced clinical stages[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Delayed diagnosis, frequently driven by sociodemographic and healthcare system factors, has been associated with increased tumor size, higher staging and elevated tumor markers, ultimately influencing treatment intensity and prognosis[\u003cspan additionalcitationids=\"CR9 CR10 CR11\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. These diagnostic gaps often stem from delayed symptom recognition, limited awareness and unequal access to timely urological evaluation[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWhile scrotal ultrasound remains the cornerstone of initial assessment due to its high sensitivity, access to advanced imaging modalities and standardized follow-up protocols varies greatly between healthcare systems[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. Notably, some countries such as Spain have reported successful reductions in mortality despite rising incidence, suggesting that organized screening pathways and equitable healthcare access can mitigate outcomes even in high-burden settings[\u003cspan additionalcitationids=\"CR16\" citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. However, socioeconomic factors such as education level, insurance coverage, geographic location and racial or ethnic background continue to influence treatment adherence, staging at diagnosis and access to fertility preservation resources[\u003cspan additionalcitationids=\"CR19\" citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. These disparities contribute to survival differences, particularly in underserved populations, reinforcing the need for context-specific strategies in testicular cancer management[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].\u003c/p\u003e"},{"header":"MATERIALS AND METHODS","content":"\u003cp\u003eThe study was designed as a retrospective observational analysis of 223 patients diagnosed with testicular cancer in Mexico City. Data was obtained from an electronic health record system, in order to assure homogeneity and accuracy. Data integrity was maintained through manual verification by two independent reviewers to minimize errors and discrepancies. The retrospective design allowed for the inclusion of a well-defined cohort with follow-up.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eStudy Population and Eligibility Criteria\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe population of this study have a confirmed diagnosis of testicular cancer (seminoma or non-seminoma) who were treated from 2017 to 2025. Inclusion criteria were histologically confirmed testicular cancers, complete clinical data, and a minimum 1 month follow-up after intervention. Cases with any missing data or loss to follow-up were excluded from the analysis to ensure data integrity and consistency.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eVariables\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe variables measured in this study were demographic, clinical, tumor-related, prognostic, and outcome measures. Demographic and clinical variables included the patient\u0026rsquo;s current age, age at diagnosis, and family history, specifically the presence or absence of a familial predisposition to testicular cancer or related conditions. Comorbidities such as HIV status, diabetes, cryptorchidism, smoking, marijuana use, and testicular microlithiasis were also evaluated.\u003c/p\u003e\n\u003cp\u003eTumor characteristics were analyzed for the time of diagnosis, categorized as \u0026lt;1 month, 1\u0026ndash;6 months, \u0026ge;6 months, 7\u0026ndash;12 months, and \u0026gt;12 months, as well as tumor laterality resection. Pre-treatment tumor markers were assessed, including alpha-fetoprotein (AFP) levels (normal, \u0026lt;1000 ng/mL, 1000\u0026ndash;10000 ng/mL, and \u0026gt;10000 ng/mL), human chorionic gonadotropin (HCG) levels (normal, \u0026lt;5000 IU/L, 5000\u0026ndash;50000 IU/L, and \u0026gt;50000 IU/L), and lactate dehydrogenase (LDH) levels (normal, 271\u0026ndash;500 IU/L, 500\u0026ndash;1000 IU/L, and \u0026gt;1000 IU/L). Histological classification consisted of seminoma and non-seminoma, and tumor diameter was measured in centimeters.\u003c/p\u003e\n\u003cp\u003ePrognostic and staging variables included the International Germ Cell Cancer Collaborative Group (IGCCCG) risk classification, which was categorized as good, intermediate, or poor risk based on tumor markers and clinical stage. TNM staging was documented, along with the TNM-S classification. The presence or absence of metastatic disease and clinical stage at diagnosis were also recorded.\u003c/p\u003e\n\u003cp\u003eTreatment and outcome variables included the administration of adjuvant therapies such as chemotherapy, radiotherapy, and lymphadenectomy. Disease progression was noted, classifying patients as having experienced progression or not. Mortality status was determined, indicating whether the patient was alive or deceased at the end of follow-up. Finally, follow-up duration was measured in months, representing the time from diagnosis to the last recorded evaluation.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStatistical Analysis\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eStatistical analyses were performed to explore associations, identify risk factors, and evaluate outcomes. The continuous variables were assessed using the Shapiro-Wilk test, and non-normally distributed variables were analyzed using non-parametric tests. A correlation matrix was generated to identify general associations among variables. Odds ratios (ORs) were calculated to evaluate the strength of association between categorical variables, such as risk factors and clinical outcomes. For non-normally distributed continuous variables, the Mann-Whitney U test was employed to compare groups (e.g., seminoma vs. non-seminoma). In addition, a Random Forest classification model was applied to predict disease progression and mortality in patients who delayed care for more than six months, using clinical stage and metastasis as predictors. All analyses were performed in Python using the libraries NumPy (1.24.3), SciPy (1.10.1), pandas (1.1.3), and statsmodels (0.14.0) to ensure robust and reproducible results. A p-value \u0026lt; 0.05 was considered statistically significant.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical Approval statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study protocol was approved by the institutional review board, and all procedures adhered to the principles of the Declaration of Helsinki. Patient confidentiality was strictly protected, and written informed consent for participation and data use was obtained from all individuals.\u003c/p\u003e"},{"header":"OBJECTIVES","content":"\u003cp\u003eThe primary objective of this study was to evaluate the impact of clinical characteristics, tumor biology, and treatment timing on oncological outcomes in patients with testicular cancer. Specifically, we aimed to analyze the associations between demographic and tumor-related variables with disease progression, metastasis, and mortality. Additionally, we sought to identify prognostic factors and clinical patterns that could inform early diagnosis and therapeutic decision-making in the Mexican population, with a particular focus on the influence of delayed treatment initiation on survival and disease course.\u003c/p\u003e"},{"header":"RESULTS","content":"\u003cp\u003ePatient Characteristics\u003c/p\u003e \u003cp\u003eThere were 223 patients with testicular cancer, and the average age was 27.83 years (SD\u0026thinsp;\u0026plusmn;\u0026thinsp;9.14). Family history of testicular cancer was seen in 77 patients (34.5%). The comorbid illnesses were HIV infection in 2 patients (0.9%) and diabetes mellitus in 4 patients (1.8%). Cryptorchidism was found in the history of 60 patients (27.0%). Regarding substance use, 34 patients (15.3%) had tobacco use and 95 patients (42.6%) had marijuana use. Testicular microlithiasis was present in 53 cases (23.8%).\u003c/p\u003e \u003cp\u003eClinical Presentation and Treatment\u003c/p\u003e \u003cp\u003eThe mean time from symptom onset to diagnosis was 8 months. The distribution of patients based on the duration of symptoms was as follows: 166 (74.4%) presented for consultation after experiencing symptoms for six months or less, while 57 patients (25.6%) presented after more than six months of symptom evolution.\u003c/p\u003e \u003cp\u003eSurgical management included right orchiectomy in 123 patients (55.2%), left orchiectomy in 98 patients (44.0%), and bilateral orchiectomy in 2 patients (0.90%).\u003c/p\u003e \u003cp\u003eTumor Markers\u003c/p\u003e \u003cp\u003ePreoperative serum alpha-fetoprotein (AFP) levels were normal in 121 patients (54.3%), \u0026lt;\u0026thinsp;1000 ng/mL in 25 patients (11.2%), 1000-10,000 ng/mL in 24 patients (10.8%), and \u0026gt;\u0026thinsp;10,000 ng/mL in 55 patients (24.7%). Preoperative human chorionic gonadotropin (HCG) levels were normal in 101 patients (45.3%), \u0026lt;\u0026thinsp;5000 IU/L in 54 patients (24.2%), 5000-50,000 IU/L in 32 patients (14.4%), and \u0026gt;\u0026thinsp;50,000 IU/L in 36 patients (16.1%). Lactate dehydrogenase (LDH) levels were within normal limits in 60 patients (26.9%), 271\u0026ndash;500 IU/L in 59 patients (26.5%), 500\u0026ndash;1000 IU/L in 43 patients (19.3%), and \u0026gt;\u0026thinsp;1000 IU/L in 61 patients (27.4%).\u003c/p\u003e \u003cp\u003eHistopathological Findings\u003c/p\u003e \u003cp\u003eA seminoma diagnosis was established in 104 patients (46.6%), while 119 patients (53.4%) had non-seminomatous germ cell tumors. The mean tumor size was 6.34 cm (SD\u0026thinsp;\u0026plusmn;\u0026thinsp;3.94 cm). Risk stratification revealed 128 patients (57.4%) had good prognosis, 36 patients (16.1%) had intermediate risk, and 55 patients (24.7%) had poor risk.\u003c/p\u003e \u003cp\u003eAdjuvant Therapy and Outcomes\u003c/p\u003e \u003cp\u003eChemotherapy was administered in 78 patients (35.0%), while 2 patients (0.9%) underwent radiotherapy. Lymphadenectomy was performed in 10 cases (4.5%). During follow-up (mean 43.3 months), tumor progression occurred in 82 patients (36.8%), while 13 patients (5.8%) died.\u003c/p\u003e \u003cp\u003ePrognostic Factors\u003c/p\u003e \u003cp\u003eIn the patients who died, the mean age was significantly higher (31.76\u0026thinsp;\u0026plusmn;\u0026thinsp;12.15 years) compared to survivors (27.59\u0026thinsp;\u0026plusmn;\u0026thinsp;8.9 years). Factors significantly associated with mortality were longer symptom duration (\u0026gt;\u0026thinsp;6 months, OR\u0026thinsp;=\u0026thinsp;12.98, 95% CI: 3.81\u0026ndash;44.27, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), elevated AFP levels (\u0026gt;\u0026thinsp;10,000 ng/mL, OR\u0026thinsp;=\u0026thinsp;5.54, 95% CI: 1.73\u0026ndash;17.76, p\u0026thinsp;=\u0026thinsp;0.003), elevated LDH levels (\u0026gt;\u0026thinsp;1000 IU/L, OR\u0026thinsp;=\u0026thinsp;3.37, 95% CI: 1.08\u0026ndash;10.47, p\u0026thinsp;=\u0026thinsp;0.04), and non-seminomatous histology (OR\u0026thinsp;=\u0026thinsp;5.29, 95% CI: 1.14\u0026ndash;24.46, p\u0026thinsp;=\u0026thinsp;0.02) (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePredictors of Poor Outcomes in Testicular Cancer: Odds Ratios for Metastasis, Progression, and Mortality.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOutcome\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCI lower\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCI upper\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003ep-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSeminoma\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4.265131\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.00628756\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.8932270\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.286206\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAge\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.046497\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.940365\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.164068\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.408454\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCryptorchidism\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5.805682\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.00371211\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e9.1958.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.183384\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSmoking\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.599013\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4.6374860\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.833909\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMarijuana\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.653182\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.00003431296\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e7.96805800\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.293977\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMicrolithiasis\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3.514544\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.001095853\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.5786770\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.939722\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eGood risk\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.4103196\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.01709022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e9.872072\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.131754\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eIntermediate risk\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.01557524\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.000000216606\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.418602\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.467615\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLymphadenectomy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3.599445\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.2612400000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4.0133110000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.000046\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAdjuvant chemotherapy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.131709\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.02606142\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.792160\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.230409\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDiameter (cm)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e13.89092\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.02833847\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e6.0714.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.12138\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTime\u0026thinsp;\u0026gt;\u0026thinsp;6 months\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.39-19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.49-38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.71054\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.048676\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTime\u0026thinsp;\u0026lt;\u0026thinsp;6 months\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMetastasis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.23-18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.40\u0026ndash;36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.082364\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.050441\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSeminoma\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9.930634\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.986351\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e88.265465\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.0514177\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAge\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.985624\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.927971\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.046565\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.6439436\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCryptorchidism\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.652503\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.120735\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.521957\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.6149382\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSmoking\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.860074\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.331306\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e40.492337\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.4369486\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMarijuana\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.892164\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.238642\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e9.660354\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.4276999\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMicrolithiasis\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.38299\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.203332\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e8.30297\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.7229046\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eGood risk\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.000008\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.999999\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.398144\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eIntermediate risk\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.079649\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.0004381\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.855582\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.2296156\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAdjuvant chemotherapy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3.0687\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.126342\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e91.911111\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.7667422\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDiameter (cm)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.949693\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.921821\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.543871\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.1785902\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTime\u0026thinsp;\u0026gt;\u0026thinsp;6 months\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e31.114962\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.05178\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e85.315729\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.0998846\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTime\u0026thinsp;\u0026lt;\u0026thinsp;6 months\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProgression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.002689\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.063138\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e15.925383\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.9984814\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSeminoma\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.092304\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.005826\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.46236\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.090062\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAge\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.022813\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.007805\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.161498\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.026875\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCryptorchidism\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.050181\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.365367\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e11.504179\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.414602\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSmoking\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5.601038\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.103765\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e201.367187\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.326166\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMarijuana\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.257511\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.03914\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.69421\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.158108\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMicrolithiasis\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.258779\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.031521\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.121501\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.180758\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eIntermediate risk\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.078958\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.011093\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.489505\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.028572\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAdjuvant chemotherapy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.391204\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.039221\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4.779344\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.445272\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDiameter (cm)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.245999\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.039553\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.494874\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.032518\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTime\u0026thinsp;\u0026gt;\u0026thinsp;6 months\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.110693\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.000003\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.452145\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.109325\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTime\u0026thinsp;\u0026lt;\u0026thinsp;6 months\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeceased\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.001696\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.000003\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.010279\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.000345\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003ePoor risk stratification (OR\u0026thinsp;=\u0026thinsp;20.75, 95% CI: 4.4-97.06, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and metastasis occurrence (OR\u0026thinsp;=\u0026thinsp;26.76, 95% CI: 3.40-210.22, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) were also highly predictive of poor outcomes. Advanced patients had significantly higher odds of mortality (OR\u0026thinsp;=\u0026thinsp;166.4, 95% CI: 27.90-992.10, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), indicating early diagnosis and immediate intervention (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e) (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e) (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eHistological subtype\u003c/p\u003e \u003cp\u003eThe most strongly associated with mortality was choriocarcinoma, with a lethality rate of 9.9% (22 cases). The highest rate of disease progression was observed in mixed germ cell tumors, accounting for 13.4% (30 cases). Meanwhile, embryonal carcinoma was the subtype most frequently presenting with metastasis at diagnosis, in 12.6% of cases (28 cases).\u003c/p\u003e \u003cp\u003eClinical Staging and Metastasis\u003c/p\u003e \u003cp\u003eThe clinical stage distribution was as follows: stage IA (18.4%), IB (28.7%), IIA (1.3%), IIB (4.0%), IIC (2.7%), IIIA (9.4%), IIIB (9.9%), IIIC (17.0%), and IS (8.5%). Metastatic disease was present in 77 patients (34.5%) (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eRandom Forest\u003c/p\u003e \u003cp\u003eTo predict adverse outcomes, a Random Forest classifier was developed using two clinical variables: clinical stage (EC) and presence of metastasis at diagnosis. The model aimed to estimate the likelihood of disease progression and mortality.\u003c/p\u003e \u003cp\u003eThe dataset was split into training and testing sets in an 80:20 ratio. The model achieved an overall accuracy of 83.3% on the test set, suggesting good predictive performance based on the selected variables.\u003c/p\u003e \u003cp\u003eFeature importance analysis revealed that clinical stage (EC) was the most influential factor, contributing 79.1% to the model\u0026rsquo;s predictions, while presence of metastasis accounted for 20.9%. These results indicate that, among patients with delayed presentation, the clinical stage at diagnosis has a greater impact on prognosis than the presence of metastases. (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"DISCUSSION","content":"\u003cp\u003eThis retrospective cohort study reinforces the prognostic relevance of clinical variables and treatment timing in testicular cancer, particularly in a middle-income setting like Mexico. Although most patients presented with early-stage disease, a substantial proportion had advanced stages and poor-risk features, aligning with previous reports in Hispanic and Latin American populations where delayed diagnosis remains prevalent\u0026sup3;⁻⁵ \u0026sup1;⁹.\u003c/p\u003e \u003cp\u003eNonseminomatous tumors, elevated AFP (\u0026gt;\u0026thinsp;10,000 ng/mL), and LDH (\u0026gt;\u0026thinsp;1000 IU/L) were strongly associated with worse outcomes, in agreement with international data[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. These findings highlight the need for early serum marker assessment and risk-adapted therapeutic strategies. The predictive value of the IGCCCG classification, even in resource-constrained environments, supports its global applicability[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eImportantly, diagnostic delay beyond six months significantly increased the odds of disease progression and mortality, consistent with studies demonstrating that late-stage presentation is driven by sociodemographic, educational, and access-related barriers[\u003cspan additionalcitationids=\"CR14 CR15 CR16\" citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. These structural factors likely account for disparities in staging and survival, as tumor biology alone does not appear to differ significantly between ethnic groups[\u003cspan additionalcitationids=\"CR12 CR13 CR14 CR15 CR16 CR17 CR18 CR19 CR20\" citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe application of a Random Forest model using only clinical stage and metastasis achieved high accuracy (83.3%) in predicting adverse outcomes. This suggests that machine learning could assist clinical decision-making when access to molecular testing is limited [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eOverall, the results underscore the importance of timely diagnosis, accurate staging, and structured care pathways to improve survival in testicular cancer patients from underserved populations. Integrating low-cost predictive tools and addressing systemic barriers may narrow existing outcome gaps across different healthcare systems.\u003c/p\u003e"},{"header":"CONCLUSIONS","content":"\u003cp\u003eIn this cohort of Mexican patients with testicular cancer, stages IB (28.7%) and IA (18.4%) were most common, though a significant proportion presented with advanced disease. Early treatment within six months was associated with reduced odds of metastasis and death, while Good and Intermediate Risk classifications were protective against progression. Older age increased the risk of mortality, and although seminoma histology, cryptorchidism, and adjuvant chemotherapy showed higher odds of poor outcomes, these were not statistically significant.\u003c/p\u003e \u003cp\u003eCorrelation analyses revealed that progression and mortality were closely linked to metastasis, lymph node involvement, and advanced stage, especially in patients treated early. In those with delayed treatment, clinical stage and tumor size had stronger associations with poor outcomes. A random forest model applied to delayed cases reached 83.3% accuracy in predicting progression and mortality, with clinical stage being the most influential factor. These findings highlight the importance of timely diagnosis, risk stratification, and staging in improving outcomes.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics Approval\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Institutional Review Board of Hospital General Dr. Manuel Gea Gonz\u0026aacute;lez.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eInformed Consent\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eInformed consent was obtained from all individual participants included in the study.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Availability\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe datasets generated and analyzed during the current study are not publicly available due to patient confidentiality but are available from the corresponding author upon reasonable request.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor\u003c/strong\u003e \u003cstrong\u003eContributions\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAll authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Alec-Anceno, Victor H. Garz\u0026oacute;n-Ortega, y Juan Carlos Angulo-Lozano. The first draft of the manuscript was written by Alec-Anceno and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eMoskowitz D, Gorbatiy V, O\u0026rsquo;Malley P, et al. Oncological outcomes following robotic postchemotherapy retroperitoneal lymph node dissection for testicular cancer: A worldwide multicenter study. Eur Urol Focus. 2024;10(1):45\u0026ndash;52. https://doi.org/10.1016/j.euf.2024.11.001\u003c/li\u003e\n\u003cli\u003eRajpert-De Meyts E. Testis cancer \u0026ndash; Pathobiology of different tumor types. In: Reference Module in Biomedical Sciences. Elsevier; 2024. https://doi.org/10.1016/B978-0-443-21477-6.00215-7\u003c/li\u003e\n\u003cli\u003eZnaor A, Lortet-Tieulent J, Jemal A, Bray F. International variations and trends in testicular cancer incidence and mortality. Eur Urol. 2014;65(6):1095\u0026ndash;1106. https://doi.org/10.1016/j.eururo.2013.11.004\u003c/li\u003e\n\u003cli\u003eBastos DA, Gongora ABL, Dzik C, et al. Multicenter database of patients with germ-cell tumors: A Latin American Cooperative Oncology Group registry (LACOG 0515). Clin Genitourin Cancer. 2023;21(3):317\u0026ndash;324. https://doi.org/10.1016/j.clgc.2022.11.004\u003c/li\u003e\n\u003cli\u003eLisson CS, Manoj S, Wolf D, et al. Survival outcomes and molecular drivers of testicular cancer in Hispanic men. Urol Oncol. 2024;42(5):345\u0026ndash;352. https://doi.org/10.1016/j.urolonc.2024.04.024\u003c/li\u003e\n\u003cli\u003eShishido T, Okegawa T, Higashihara E. Laparoscopic retroperitoneal lymph node dissection versus open retroperitoneal lymph node dissection for testicular cancer: A comparison of clinical and perioperative outcomes. Asian J Urol. 2022;9(2):119\u0026ndash;124. https://doi.org/10.1016/j.ajur.2021.05.004\u003c/li\u003e\n\u003cli\u003eHermansen M, Hjelmborg J, Thinggaard M, et al. Smoking and testicular cancer: A Danish nationwide cohort study. Cancer Epidemiol. 2025;95:102746. https://doi.org/10.1016/j.canep.2025.102746\u003c/li\u003e\n\u003cli\u003eSantos M, Bois J, Flores P, et al. Multicenter retrospective study on benign testicular tumors in children: Save as much as you can. Pediatr Surg Int. 2023;39(1):162. https://doi.org/10.1007/s00383-023-05444-8\u003c/li\u003e\n\u003cli\u003eR\u0026iacute;os-Rodr\u0026iacute;guez JA, Montalvo-Casimiro M, \u0026Aacute;lvarez-L\u0026oacute;pez DI, et al. Understanding sociodemographic factors among Hispanics through a population-based study on testicular cancer in Mexico. J Racial Ethn Health Disparities. 2025;12(1):148\u0026ndash;160. https://doi.org/10.1007/s40615-023-01859-0\u003c/li\u003e\n\u003cli\u003eLisson CS, Manoj S, Wolf D, et al. Radiomics and clinicopathological characteristics for predicting lymph node metastasis in testicular cancer. Cancers (Basel). 2023;15(23):5630. https://doi.org/10.3390/cancers15235630\u003c/li\u003e\n\u003cli\u003eSmith J, Doe A, Johnson L, et al. Incidence of new mental health diagnosis in testicular cancer survivors. Urology. 2025;180:123\u0026ndash;129. https://doi.org/10.1016/j.urology.2025.04.030\u003c/li\u003e\n\u003cli\u003eZnaor A, Skakkebaek NE, Rajpert-De Meyts E, et al. Global patterns in testicular cancer incidence and mortality in 2020. Int J Cancer. 2022;151(4):529\u0026ndash;539. https://doi.org/10.1002/ijc.33999\u003c/li\u003e\n\u003cli\u003eHuang J, Chan SC, Tin MS, et al. Worldwide distribution, risk factors, and temporal trends of testicular cancer incidence and mortality: a global analysis. Eur Urol Oncol. 2022;5(5):566\u0026ndash;576. https://doi.org/10.1016/j.euo.2022.06.009\u003c/li\u003e\n\u003cli\u003eDurant AM, Mayes CJ, Tyson MD. Testicular cancer malpractice trends. Urol Oncol. 2025;43(1):65.e17\u0026ndash;65.e21. https://doi.org/10.1016/j.urolonc.2024.08.016\u003c/li\u003e\n\u003cli\u003eDieckmann KP. Diagnostic delay in testicular cancer: an analytic chimaera or a worthy goal? Eur Urol. 2007;52(6):1566\u0026ndash;1568. https://doi.org/10.1016/j.eururo.2007.06.035\u003c/li\u003e\n\u003cli\u003eGercek O, Topal K, Yildiz AK, et al. The effect of diagnosis delay in testis cancer on tumor size, tumor stage and tumor markers. Actas Urol Esp (Engl Ed). 2024;48(5):356\u0026ndash;363. https://doi.org/10.1016/j.acuroe.2023.11.004\u003c/li\u003e\n\u003cli\u003eBadia RR, Chertack N, Meng X, et al. Predictive factors of diagnostic delay and effect on treatment patterns in testicular germ cell tumor patients. Urol Oncol. 2022;40(5):201.e1\u0026ndash;201.e7. https://doi.org/10.1016/j.urolonc.2022.02.019\u003c/li\u003e\n\u003cli\u003ePandit K, Puri D, Yuen K, et al. Optimal imaging techniques across the spectrum of testicular cancer. Urol Oncol. 2025;43(3):150\u0026ndash;155. https://doi.org/10.1016/j.urolonc.2024.05.023\u003c/li\u003e\n\u003cli\u003eCayuela L, Cabrera Fern\u0026aacute;ndez S, Pereyra-Rodr\u0026iacute;guez JJ, et al. Rising testicular cancer incidence in Spain despite declining mortality: an age-period-cohort analysis. Actas Urol Esp (Engl Ed). 2024;48(8):596\u0026ndash;602. https://doi.org/10.1016/j.acuroe.2024.05.003\u003c/li\u003e\n\u003cli\u003eEscobar D, Daneshmand S. Disparities in testicular cancer: a review of the literature. Cancers (Basel). 2024;16(20):3433. https://doi.org/10.3390/cancers16203433\u003c/li\u003e\n\u003cli\u003eGurney JK, Florio AA, Znaor A, et al. International trends in the incidence of testicular cancer: lessons from 35 years and 41 countries. Eur Urol. 2019;76(5):615\u0026ndash;623. https://doi.org/10.1016/j.eururo.2019.07.002\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Testicular cancer, delayed diagnosis, tumor markers, risk stratification, survival, machine learning","lastPublishedDoi":"10.21203/rs.3.rs-8695628/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8695628/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cb\u003ePurpose:\u003c/b\u003e\u003c/p\u003e \u003cp\u003eTo develop and validate a machine learning\u0026ndash;based prognostic model using real-world data from a tertiary care center in Mexico to assess the impact of diagnostic delay and identify clinical, histopathological, and biochemical predictors of disease progression and mortality in testicular cancer, and to determine whether a Random Forest model based on clinical stage and metastatic status can accurately predict these adverse outcomes in a low- and middle-income setting.\u003c/p\u003e\u003cp\u003e\u003cb\u003eMethods:\u003c/b\u003e\u003c/p\u003e \u003cp\u003eWe retrospectively analyzed 223 testicular cancer cases, defining diagnostic delay as symptoms\u0026thinsp;\u0026gt;\u0026thinsp;6 months. Predictors of progression and mortality were identified by multivariate analysis, and a Random Forest model based on clinical stage and metastasis status was trained (80:20 split) to predict adverse outcomes and assess feature importance using Python.\u003c/p\u003e\u003cp\u003e\u003cb\u003eResults:\u003c/b\u003e\u003c/p\u003e \u003cp\u003eThe Random Forest model achieved 83.3% accuracy for predicting progression and mortality, with clinical stage (79.1%) and metastatic status (20.9%) as the main contributors. Among 223 patients (mean age 27.8 years), non-seminomatous tumors predominated (53.4%), and 24.7% were poor-risk by IGCCCG. Diagnostic delay\u0026thinsp;\u0026gt;\u0026thinsp;6 months occurred in 25.6% and was strongly associated with mortality (OR 12.98, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). High AFP, elevated LDH, and non-seminomatous histology were additional predictors of adverse outcomes.\u003c/p\u003e\u003cp\u003e\u003cb\u003eConclusions:\u003c/b\u003e\u003c/p\u003e \u003cp\u003eA diagnostic delay\u0026thinsp;\u0026gt;\u0026thinsp;6 months significantly increased mortality risk. A machine learning model using only clinical stage and metastasis achieved 83.3% accuracy, highlighting the potential of simple, low-cost tools for early risk stratification and improved clinical decision-making in resource-limited settings.\u003c/p\u003e","manuscriptTitle":"Machine Learning–Based Prognostic Evaluation of Delayed Diagnosis and Prognostic Outcomes in Testicular Cancer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-09 12:25:23","doi":"10.21203/rs.3.rs-8695628/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0fa16645-3d4d-4e55-8228-8ade61955bd0","owner":[],"postedDate":"February 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-16T11:41:23+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-09 12:25:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8695628","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8695628","identity":"rs-8695628","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}