Prediction Model for Survival of Younger Patients with Breast Cancer Using the Breast Cancer Public Staging Database

Prediction Model for Survival of Younger Patients with Breast Cancer Using the Breast Cancer Public Staging Database | 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 Article Prediction Model for Survival of Younger Patients with Breast Cancer Using the Breast Cancer Public Staging Database Ha Ye Jin Kang, Minsam Ko, Kwang Sun Ryu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4754097/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 28 Oct, 2024 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Breast cancer (BC) is a prevalent disease that contributes significantly to female mortality worldwide, particularly among young women, who often present with aggressive tumor. Despite the need for accurate prognosis in this demographic, existing studies have focused on broader age groups and often rely on the SEER database, which has limitations in variable selection. Data from 3,401 patients with BC were obtained from the Breast Cancer Public Staging Database. Patients were categorized as younger (n = 1,574) and older (n = 1,827). We utilized various survival models—Random Survival Forest, Gradient Boosting Survival, Extra Survival Trees (EST), and two penalized Cox proportional hazards models, Lasso and ElasticNet—to analyze and compare BC mortality characteristics between the groups. Additionally, older patients exhibited a higher prevalence of comorbidities compared to younger patients. The EST model outperformed the other models in predicting mortality for both age groups. Tumor stage was the primary variable used to train the model for mortality prediction in both groups. COPD was a significant variable only in younger patients with BC. Other variables exhibited varying degrees of consistency in each group. These findings can help identify high-risk young female patients with BC who require aggressive treatment by predicting the risk of mortality. Physical sciences/Mathematics and computing/Computer science Physical sciences/Engineering/Biomedical engineering Health sciences/Oncology/Cancer/Breast cancer Survival prediction model Breast cancer in young women Machine learning Breast cancer Figures Figure 1 Figure 2 Figure 3 Introduction Breast cancer (BC) is one of the most common cancers and the leading cause of cancer-related mortality among women worldwide [ 1 ]. Recent epidemiological evidence indicates a consistent upward trend in the prevalence of BC in young women (BCYW) [ 2 ]. In the United States, 18% of new BC cases and 11% of BC deaths occur in women younger than 50 years [ 3 ], BCYW tend to have a higher proportion of estrogen receptor (ER) negative, triple-negative, and HER2 + tumors [ 4 ]. Younger age is correlated with poorer prognostic characteristics of tumors, such as decreased tumor differentiation, increased Ki-67 expression, and greater lymph node infiltration, compared to females older than 50 years [ 5 ]. Given the unique challenges faced by BCYW, predicting their prognosis is crucial. Consequently, considerable research has been conducted to predict the survival of this specific population. Sun et al. proposed a nomogram to predict overall and cancer-specific survival in young patients with BC. The nomogram used the important feature of lymph node ratio to predict overall survival and BC-specific survival based on the Cox proportional hazards model. These nomograms provide more accurate individualized risk predictions of adversarial events and may assist clinicians in making decisions for young patients with BC [ 6 ]. Gong et al. developed and validated a comprehensive nomogram to predict survival in young women with BC, using SEER database and a competing risks model. This model demonstrated superior performance and efficacy compared to the TNM system in validation experiment [ 7 ]. Li et al. developed a model to predict the 3-year, 5-year, 7-year, and 10-year survival rates of young patients with BC using random forest survival, based on data from the SEER database [ 8 ]. Despite this effort, few studies have focused specifically on predicting the prognosis of BCYW compared to those on conducted based on the overall age of patients with BC [ 9 ]-[ 13 ]. Furthermore, most existing studies rely on the SEER database, which has inherent limitations in variable selection. To address these gaps, our study introduces a ML-based prognosis model for young patients with BC, incorporating comorbidities such as atrial fibrillation (AF), chronic kidney disease (CKD), chronic obstructive pulmonary disease (COPD), diabetes mellitus (DM), deep venous thrombosis (DVT), dyslipidemia (DYS), heart failure (HF), hypertension (HYP), liver disease (LD), myocardial infarction(MI), peripheral vascular disease (PVD), and stroke. Additionally, we conducted a comparative analysis to identify the variables preferred by machine learning algorithms in predicting adverse outcomes in younger and older patients with BC. Methods We developed a model to predict all-cause mortality in younger patients with BC using data from the Breast Cancer Public Staging Database (CPSD) provided by the National Cancer Data Center (NCDC) (Fig. 1 ). To achieve this, we first extracted data of patients diagnosed with BC between 2013 and 2015 from the Breast-CPSD. The data were divided into training and test datasets. Using the training data, we used random survival forest (RSF), gradient boost survival analysis (GBSA), extra survival tree (EST), penalized Cox probability hazard lasso (CoxPH-L) and ElasticNet (CoxPH-E). The performance of these predictions was evaluated on test data using the C-index metric. Ethics approval and consent to participate This study was approved by the Ethics Review Board of National Cancer Center Institutional Review Board (IRB NO. NCC2023-0260). The requirement for informed consent in this study was waived because the researcher accessed only anonymized data for analysis purposes. The pseudonymized data were analyzed in a secure environment provided by the National Cancer Data Centre, ensuring that only the results were exported. Data collection and other procedures were performed in accordance with principles of Good Clinical Practice and Declaration of Helsinki guidelines (1975, revised 1983), and with other relevant ethical regulations. Data source This study utilized the Breast-CPSD provided by the NCDC [ 14 ]. This database was constructed by linking data from the Breast Cancer Public Library Database (CPLD) of the NCDC and collaborative staging (CS) for cancer established in the Korea Central Cancer Registry (KCCR) [ 15 ], [ 16 ]. The Breast-CPSD includes data from 16,870 individuals who developed BC at primary sites C500–C506, C508, and C509 between 2012 and 2019. From these datasets, we excluded cohorts diagnosed with BC between 2016 and 2019 for 5-year mortality predictions and the 2012 cohort, for which screening information prior to cancer diagnosis was unavailable. The data were cleaned to remove missing or unknown entries. Subsequently, the dataset was divided into two cohorts: individuals aged < 50 years and those aged ≥ 51 years. For each cohort, 80% of the data were allocated to the training set to create survival models, whereas the remaining 20% constituted the test set, as shown in Fig. 2 . AF, CKD, COPD, DM, DVT, DYS, HF, HYP, LD, MI, PVD, and stroke were defined according to the International Classification of Diseases 10th Revision (ICD-10). Additionally, the primary endpoint was defined as all-cause mortality within 5 years of cancer diagnosis Survival machine learning models The modeling of time-to-event data in survival analysis requires specialized techniques to address specific challenges such as censoring, truncation, time-varying covariates, and covariate effects. Several models, including RSF, GBSA, EST, CoxPH-L, and CoxPH-E, have been employed for this purpose. RSF [ 17 ] extends the random forest algorithm proposed by Breiman et al. in 2001 [ 18 ] to survival analysis, effectively handling censored data and identifying important prognostic factors. The GBSA is derived from a gradient boosting machine [ 19 ] and applied to survival analysis involving censored data [ 20 ], [ 21 ]. The extra survival tree model, an extension of the extremely randomized tree model developed by Geurts et al. in 2005 [ 22 ], also considers censoring. The Cox proportional hazards model [ 23 ] is the standard approach for survival analysis and has been enhanced by penalization methods, including lasso [ 24 ] and ElasticNet [ 25 ] penalties. The performance of these models was assessed using the C-index [ 26 ]. In addition, permutation feature importance analysis was performed. Feature importance scoring, which assesses the values of all input features to determine their importance in decision-making mechanisms, is a critical step in mortality prediction for survival analysis. Overall, feature importance was assessed using Scikit-learn (version 1.0.2) [ 27 ]. Survival models were constructed using the scikit-survival package (version 0.17.2) [ 28 ], and the entire analysis was conducted using TensorFlow (version 1.15.5) and Python (version 3.7.5). Results Baseline characteristics of the patients Table 1 presents a comparison of the basic characteristics of the younger and older patient cohorts. The younger group had a higher ratio of ER, PR, past smokers, current smokers, weekly alcohol consumption (days), and vigorous physical activity (days per week). In contrast, the ratios of HER2, AF, CKD, COPD, DM, DVT, DYS, HF, HYP, LD, MI, PVD, and stroke were higher in the older group. Additionally, the younger group exhibited different ratios of height, weight, waist circumference, urinary protein, topography code, morphology code, and AJCC7 STAGE compared to the older group. The older group exhibited higher levels of BMI, systolic blood pressure, diastolic blood pressure, hemoglobin, fasting blood sugar, total cholesterol, serum glutamic oxaloacetic transaminase, serum glutamic pyruvic transaminase, gamma glutamyl transpeptidase, triglycerides, low-density lipoprotein, moderate physical activity (days per week), and physical activity (days per week). However, the younger group exhibited higher levels of high-density lipoprotein, serum creatine, estimated glomerular filtration rate, tumor size, weekly alcohol consumption (days), and vigorous physical activity (days per week). Table 1. Baseline characteristics between younger and older groups. Data are expressed as number of patients(percentage) or mean±standard deviation. Abbreviations: BMI, body mass index. Variables Older Group N = 1,824 Younger Group N = 1 ,574 Age (y) 59.75±7.05 44.35±4.35 BMI (kg/㎡) 23.85±2.81 22.68±2.73 Height (cm) 150 ≤ H <160 77.78 54.51 160 ≤ H <170 22 43.14 170 ≤ H 0.22 2.35 Weight (kg, %) 40 ≤ W < 50 12.26 14.42 50 ≤ W < 60 46.52 48.86 60 ≤ W < 70 31.25 27.32 70 ≤ W < 80 7.99 6.8 80 ≤ W < 90 1.64 1.91 90 ≤ W 0.33 0.7 Waist circumference (cm, %) 60 ≤ WC < 70 10.78 25.86 70 ≤ WC < 90 39.19 49.49 80 ≤ WC < 90 36.4 18.87 90 ≤ WC 13.63 5.78 Systolic blood pressure (mmHg) 124,50±15.40 115.60±13.62 Diastolic blood pressure (mmHg) 76.35±9.80 72.77±9.47 Haemoglobin level (g/dL) 13.12±1.15 12.77±1.32 Fasting blood sugar (mg/dL) 101.90±25.46 94.33±17.46 Total cholesterol (mg/dL) 202.60±39.86 189.50±32.72 Serum glutamic oxaloacetic transaminase (IU/L) 26.50±37.07 21.62±12.60 Serum glutamic pyruvic transaminase (IU/L) 23.85±30.93 18.44±17.40 Gamma glutamyl transpeptidase (IU/L) 27.96±37.14 21.79±27.36 Triglycerides (mg/dL) 124.90±72.32 98.22±65.30 High-density lipoprotein (mg/dL) 57.04±19.32 60.43±14.30 Low-density lipoprotein (mg/dL) 121.00±36.17 109.50±29.88 Serum creatine (mg/dL) 0.78±0.41 0.81±2.32 Estimated glomerular filtration rate (mL/min) 85.34±22.74 94.23±32.64 Protein in urine 1 negative (-) 95.35 94.98 2 positive (±) 2.41 3.11 3 positive (+1) 1.53 1.33 4 positive (+2) 0.55 0.32 5 positive (+3) 0.11 0.13 6 positive (+4) 0.05 0.13 Topography CODE (%) C500 0.66 0.44 C501 4.32 3.05 C502 14.4 15.69 C503 4.05 6.73 C504 36.84 35.01 C505 7.22 7.81 C506 0 0.06 C508 19.21 17.47 C509 13.3 13.72 Morphology CODE (%) 1. Squamous and transitional cell carcinoma (8051– 8084, 8120–8131)) 0.11 0 3. Adenocarcinoma (8140–8149, 8160–8163, 8190–8221, 8260–8337, 8350–8552, 8570–8576, 8940–8941) 98.36 98.98 4. Other specific carcinomas (8030–8046, 8150–8157, 8170–8180, 8230–8255, 8340–8347, 8560–8562, 8580–8671) 0.44 0.32 5. Unspecified carcinomas (NOS) (8010–8015, 8020–8022, 8050) 0.82 0.32 16. (Other specified types of cancer (8720-8790, 8930-8936, 8950-8983, 9000-9030, 9060-9110, 9260-9365, 9380-9539)) 0 0.06 17. Unspecified types of cancer (8000-8005) 0.27 0.32 AJCC7 STAGE IA(%) 46.52 46.19 IB(%) 1.97 1.78 IIA(%) 26.71 26.49 IIB(%) 13.03 12.77 III(%) 9.96 11.37 IV(%) 1.81 1.4 T-size 21.39±15.08 22.46±16.44 ER(%) 69.46 76.56 PR(%) 55.28 71.47 HER2(%) 33.44 28.78 Atrial fibrillation (%) 3.17 0.57 Chronic kidney disease (%) 1.26 0.38 Chronic obstructive pulmonary disease (%) 4.76 1.78 Diabetes (%) 31.42 13.6 Deep venous thrombosis (%) 2.13 1.52 Dyslipidaemia (%) 69.51 47.78 Heart failure (%) 5.47 2.54 Hypertension (%) 50.85 16.65 Liver disease (%) 40.72 35.9 Myocardial infarction (%) 0.93 0.13 Peripheral vascular disease (%) 17.41 6.86 Stroke (%) 0.88 0.13 Smoking status Non-smoker (%) 94.75 91.68 Past smoker (%) 1.81 2.92 Current smoker (%) 3.45 5.4 Weekly alcohol consumption (days) 0.33±0.96 0.61±1.03 Moderate physical activity (days in a week) 1.26±1.90 1.22±1.67 Physical activity Walking (days in a week) 2.83±2.48 2.80±2.37 Vigorous physical activity (days in a week) 0.88±1.66 0.94±1.53 Survival time (days) 1775.70±233.20 1797.00±173.10 All cause of death (%) 5.64 3.37 Model Performance Evaluation The performance of the RSF, GBSA, EST, CoxPH-L, and CoxPH-E models were compared based on the mean C-index and standard deviation (SD) for the prediction of mortality in Table 2. The RSF model achieved a C-index of 78.86±0.01 for the young cohort and 79.29±0.01 for the old cohort. The GBSA model had a C-index of 66.65±0.01 for the young cohort and 81.70±0.01 for the old cohort. The EST model showed a C-index of 87.19±0.01 for the young and 84.01±0.01 for the old cohorts. The CoxPH-L model was 73.86±0.01 for the young cohort and 81.70±0.01 for the old cohort. Finally, the CoxPH-E model had a mean C-index of 72.61±0.01 for the young cohort and 87.73±0.01 for the old cohort. Table 2. Mean C-index value from survival prediction models. Abbreviations: RSF, Random Survival Forest; GBSA, Gradient Boosting Survival; EST, Extra Survival Trees; CoxPH-L, Cox proportional hazards model Lasso; CoxPH-E, Cox proportional hazards model ElasticNet; C-index, concordance index. Model Young cohort 5-year mortality prediction Old cohort 5-year mortality prediction C-index C-index RSF 78.86±0.01 79.29±0.01 GBSA 66.65±0.01 81.70±0.01 EST 87.19±0.01 84.01±0.01 CoxPH-L 73.86±0.01 81.70±0.01 CoxPH-E 72.61±0.01 81.73±0.01 To construct the survival prediction models, we identified the most important features for each model and extracted the top 10 features in each model for analysis. In the young cohort, the RSF model highlighted AJCC7 stage, C509, COPD, ER status, age, physical activity “walking” (days per week), hemoglobin levels, weekly alcohol consumption (days), total cholesterol, and weight. The GBSA model identified AJCC7 STAGE, diastolic blood pressure, systolic blood pressure, ER, weekly alcohol consumption (days), fasting blood sugar, COPD, low-density lipoprotein, moderate physical activity (days per week), and C503. The EST model included AJCC7 STAGE, C509, COPD, ER, PR, DYS, physical activity walking (days per week), LD, age, and height. The CoxPH-L was used for total cholesterol, AJCC7 STAGE, low-density lipoprotein, triglyceride, high-density lipoprotein, COPD, PR, alcohol, C501, and C509 assays. The CoxPH-E model included total cholesterol, low-density lipoprotein, AJCC7 STAGE, triglycerides, high-density lipoprotein, COPD, weekly alcohol consumption (in days), C501, PR, and C509 levels. Within the old cohort, the RSF selected the AJCC7 STAGE, fasting blood sugar, T SIZE, ER, DYS, PR, estimated glomerular filtration rate, C509, HER2, and low-density lipoprotein levels. The GBSA model used AJCC7 stage, Tumor size, fasting blood sugar, age, BMI, high-density lipoprotein, estimated glomerular filtration rate, triglycerides, ER, and weight. The EST model included the AJCC7 STAGE, DYS, ER, fasting blood sugar, MCODE-3, C509, PR, T SIZE, HER2, and HF. The CoxPH-L model was assigned to the AJCC7 STAGE, fasting blood sugar, gamma glutamyl transpeptidase, serum creatine, PR, DYS, HYP, Vigorous physical activity (days per week), Physical activity “walking” (days per week), and PVD. The CoxPH-L model included AJCC7 stage, fasting blood sugar, gamma glutamyl transpeptidase, serum creatine, PR, DYS, HYP, vigorous physical activity (days/week), physical activity “walking” (days/week), and hemoglobin. Figure 3 depicts a heatmap showing the frequency distribution of variables utilized in developing the 5-year mortality prediction models in both the young and old patient cohorts. Different color intensities indicate the importance of each feature, with deeper colors signifying higher frequency. In both young and old cohorts, the AJCC stage consistently emerged as the most critical feature across all models. However, the significance of the other features varied significantly, not only between the models but also within each age cohort. Discussion BC is the leading cause of cancer-related deaths among women, and the number of younger patients with BC continues to increase. Younger patients with BC tend to have an unfavorable prognosis due to their unusual tumor characteristics. This highlights the need for a personalized treatment approach for younger patients with BC. Survival rates have been shown to differ between younger and older patients with BC, with notable differences in the basic characteristics of these populations. In particular, the frequency of co-morbidities varies significantly between younger and older patients in our experimental. These age-related physiological differences may result in different responses and outcomes, which should be considered when developing survival-prediction models. Although several nomogram studies have been conducted to consider these characteristics, ML methodologies that can account for the characteristics of each population and reflect complex causal factors that contribute to negative outcomes are needed. Recently, Li et al. compared the performance of ML-based survival prediction models with the traditional COX method for young patients with BC using the SEER database and reported that the ML methodology outperformed the Cox methodology [ 8 ]. However, an important point was not considered in this data source. Patients with BC have many comorbidities due to various reasons, and the impact of these comorbidities on negative prognosis has not been considered. In addition, information on the daily lifestyle of patients with cancer was not considered. To address these issues, we categorized patients with BC as young ( 50 year) and compared 5-year survival prediction using five survival ML models based on Breast-CPSD. In our experiment, the EST models split the nodes by randomly selecting attributes and determining thresholds, which is the key difference between the RFs models. The EST model outperformed the other ML models in both the older and younger cohorts. As the EST model allows for a wider range of threshold choices, it performs particularly well on datasets with many attributes. The algorithm captures the intricate relationships among various data subsets and effectively handles diverse attribute distributions. As a result of these characteristics, EST models outperform other ML models in both age groups [ 29 ]–[ 30 ]. Furthermore, 10 iterations were conducted to select the optimal model. At each stage, the variables deemed crucial for the ML model were identified and summarized. It is noteworthy that the COPD variable appears to be a highly significant predictor of mortality in young patients with BC, in contrast to the results observed in the older population. Previous studies have demonstrated that COPD plays a role in the development of lung, liver, and colorectal cancer [ 31 ]. However, our findings revealed that COPD was a significant predictor of negative prognosis in patients with BC. In addition, the Breast-CPSD includes screening data from the National Health Service, which permits the consideration of data on the general lifestyle of patients with cancer. In contrast to the older patient population, our experimental results indicated that weekly alcohol consumption (days) was a negative prognostic factor in younger patients with BC. In conclusion, the number of younger patients diagnosed with BC is increasing and studies have proposed classifying these patients into high-risk groups. However, few studies have focused on survival predictions based on machine learning (ML). In this study, we developed a model to predict the survival of young patients with breast cancer based on ML, which is expected to help identify patients with BC who require aggressive treatment. Nevertheless, given that the data used in this study were exclusively derived from female Korean patients with BC, further validation of the model in diverse populations is required in future studies. Declarations Acknowledgments This study was supported by a grant (no: 2310440-2) from the National Cancer Center of Korea, Basic Science Research Program through the National Research Foundation of Korea (NRF), funded by the Ministry of Education (No. NRF-2022R1F1A107504). Author contributions Conceptualization was managed by HYJK, MSK, and KSR; methodology, HYJK, MSK, and KSR; validation, HYJK, MSK, and KSR; investigation, HYJK; data curation, HYJK, and KSR; writing the original draft preparation, HYJK and KSR. All the authors assisted in drafting and editing the manuscript. Competing interests The authors declare that they have no competing interests. Data availability The data that support the findings of this study are available from Korea Clinical Data Utilization Network for Research Excellence (K-CURE) portal [14] but restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available. Data are, however, available from the corresponding author upon reasonable request and with permission of NCDC. The GitHub repository [32] contains all codes relevant to the current submission. References Anderson, B.O. et al. The Global Breast Cancer Initiative: a strategic collaboration to strengthen health care for non-communicable diseases. Lancet Oncol. 22, 578–581 (2021). Fernandes, U. et al. Breast cancer in young women: a rising threat: A 5-year follow-up comparative study. Porto Biomed J. 8, e213 (2023). doi: 10.1097/j.pbj.0000000000000213 . DeSantis, CE. et al. Breast cancer statistics, 2019. CA Cancer J Clin. 69, 438–451 (2019). Shah, A.N. et al. Circulating tumor cells, circulating tumor DNA, and disease characteristics in young women with metastatic breast cancer. Breast Cancer Res. Treat., 187, 397–405 (2021). Pruessmann, J. et al. Conditional Disease-Free and Overall Survival of 1858 Young Women with Non-Metastatic Breast Cancer and with Participation in a Post-Therapeutic Rehab Programme according to Clinical Subtypes. Breast Care. 16, 163–172 (2020). Sun, Y. Nomograms for prediction of overall and cancer-specific survival in young breast cancer. Breast Cancer Research Treat, 184, 597–613 (2020).. Guo, L. W. Development and validation of nomograms for predicting overall and breast cancer-specific survival among patients with triple-negative breast cancer. Cancer manag Res. 10, 5881–5894 (2018). Li, L. W., Liu, X., Shen, M. L., Zhao, M. J., & Liu, H. Development and validation of a random survival forest model for predicting long-term survival of early-stage young breast cancer patients based on the SEER database and an external validation cohort. Am J Cancer Res. 14, 1609–1621 (2024). Sedighi-Maman Z, Mondello A. A two-stage modeling approach for breast cancer survivability prediction. Int J Med Inform. 149, 104438 (2021). doi: 10.1016/j.ijmedinf.2021.104438 . Li, J. Predicting breast cancer 5-year survival using machine learning: A systematic review. PloS one, 16, e0250370 (2021). Boeri C, et al. Machine Learning techniques in breast cancer prognosis prediction: A primary evaluation. Cancer Med. 9, 3234–3243 (2020). doi: 10.1002/cam4.2811 . Liu P, et al. Optimizing Survival Analysis of XGBoost for Ties to Predict Disease Progression of Breast Cancer. IEEE Trans Biomed Eng. 68, 148–160 (2021). doi: 10.1109/TBME.2020.2993278 Ganggayah, M.D, et al. Predicting factors for survival of breast cancer patients using machine learning techniques. BMC Med Inform Decis Mak. 19, 48 (2019). https://doi.org/10.1186/s12911-019-0801-4 Home page. National Cancer Center. Cancer data. National Cancer Center. . Accessed 11 July 2024 Korea central cancer registry. "KCCR Survey." Korea Central Cancer Registry. kccrsurvey.cancer.go.kr/index.do . Accessed 11 July 2024. Choi DW, et al. Data resource profile: The cancer public library database in South Korea. Cancer Res Treat. Apr 30 (2024). doi: 10.4143/crt.2024.207 Ishwaran, H., Kogalur, U. B., Blackstone, E. H. and Lauer, M. SRandom survival forests. The annals of applied statistics 841–860 (2008). Breiman, L. Random Forests. Machine Learning. 45, 5–32 (2001). https://doi.org/10.1023/A:1010933404324 J. H. Friedman. ‘‘Greedy function approximation: A gradient boosting machine,’’ Ann. Statist. 29, 1189–1232 (2001). Chen Y., Jia Z., Mercola D., Xie X. A gradient boosting algorithm for survival analysis via direct optimization of concordance index. Comput Math Methods Med . 2013, 873595 (2013). doi: 10.1155/2013/873595 . Bai, M., Zheng, Y., & Shen, Y. Gradient boosting survival tree with applications in credit scoring. Journal of the Operational Research Society, 73, 39–55 (2022). Geurts, P., Ernst, D. & Wehenkel, L. Extremely randomized trees. Mach. Learn. 63, 3–42 (2006) Cox, D. R. Regression models and life-tables. Journal of the Royal Statistical Society: Series B (Methodological). 34, 187–202 (1972). Tibshirani R. The lasso method for variable selection in the cox model. Stat Med. 16, 85–95 (1997). https://doi.org/10.1002/(SICI)1097-0258(19970228)16:43.0.CO;2-3 . Zou H, Hastie T. Regularization and variable selection via the elastic-net. J R Stat Soc. 67, 301–20 (2005). https://doi.org/10.1111/j.1467-9868.2005.00503.x . Harrell FE, Califf RM, Pryor DB, Lee KL, Rosati RA. Evaluating the yield of medical tests. JAMA. 247, 2543–6 (1982). Pedregosa F, et al. "Scikit-learn: Machine Learning in Python." *. J Mach Learn Res. 12, 2825–30 (2011). Pölsterl S. "scikit-survival: A Library for Time-to-Event Analysis Built on Top of scikit-learn." *. J Mach Learn Res. 21, 1–6 (2020). Ghazwani, M., Begum, M.Y. Computational intelligence modeling of hyoscine drug solubility and solvent density in supercritical processing: gradient boosting, extra trees, and random forest models. Sci Rep. 13, 10046 (2023). https://doi.org/10.1038/s41598-023-37232-8 Wehenkel, L., Ernst, D. & Geurts, P. Ensembles of extremely randomized trees and some generic applications. In Proceedings of Robust Methods for Power System State Estimation and Load Forecasting (2006) Ahn, S. V., Lee, E., Park, B., Jung, J. H., Park, J. E., Sheen, S. S., … Park, J.H. (2020). Cancer development in patients with COPD: a retrospective analysis of the National Health Insurance Service-National Sample Cohort in Korea. BMC pulmonary medicine. 20, 1–10. Kwang Sun Ryu (2024). Breast Cancer Survival Prediction. GitHub. https://github.com/KwangSun-Ryu/Breast-cancer-survival-prediction.git Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 28 Oct, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 23 Sep, 2024 Reviews received at journal 19 Sep, 2024 Reviews received at journal 03 Sep, 2024 Reviewers agreed at journal 02 Sep, 2024 Reviewers agreed at journal 26 Aug, 2024 Reviewers invited by journal 12 Aug, 2024 Editor assigned by journal 06 Aug, 2024 Editor invited by journal 22 Jul, 2024 Submission checks completed at journal 18 Jul, 2024 First submitted to journal 17 Jul, 2024 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-4754097","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":338647600,"identity":"2c288552-42a4-41b2-a55c-a3535bc9dfc1","order_by":0,"name":"Ha Ye Jin Kang","email":"","orcid":"","institution":"Department of Applied Artificial Intelligence, Hanyang University","correspondingAuthor":false,"prefix":"","firstName":"Ha","middleName":"Ye Jin","lastName":"Kang","suffix":""},{"id":338647601,"identity":"62e02a29-ef44-4b90-bb7d-5f284cedabac","order_by":1,"name":"Minsam Ko","email":"","orcid":"","institution":"Department of Applied Artificial Intelligence, Hanyang University","correspondingAuthor":false,"prefix":"","firstName":"Minsam","middleName":"","lastName":"Ko","suffix":""},{"id":338647602,"identity":"fbb5baf3-1d95-4be6-a723-0a535dd3ab2a","order_by":2,"name":"Kwang Sun Ryu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIiWNgGAWjYDACZhBRwMDAxt98ACrERowWAwYGPoljCURqYYBqkWPIMSBOizk788PHBQZ2iW0MZ749+FHDkM/PwJb2AZ8Wy2Y2Y+MZBsmJbcy92w17jjFYzmxgOzwDr5MO87BJ8xgwA205u02asYHBwOAAezN+XxzmYf/NY1AP1JLzDKzFnggtbMw8BodBWtggtjCwHSaghc1YeobBceM2iWNmkj3HJAwkDrMl49dy/vDDzwUV1bLz+5ufSfyosTHgb28zxqsFBECx6dgAYUtAI5cILfZEqBsFo2AUjIKRCgCLeDzlitB+jwAAAABJRU5ErkJggg==","orcid":"","institution":"National Cancer Data Center, National Cancer Center","correspondingAuthor":true,"prefix":"","firstName":"Kwang","middleName":"Sun","lastName":"Ryu","suffix":""}],"badges":[],"createdAt":"2024-07-17 06:42:37","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4754097/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4754097/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-76331-y","type":"published","date":"2024-10-28T16:05:08+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":62657967,"identity":"54030fdd-12b0-41db-804a-c55c572d214d","added_by":"auto","created_at":"2024-08-17 02:13:30","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":70068,"visible":true,"origin":"","legend":"\u003cp\u003eResearch Framework of Prediction Model for BC. CPSD, cancer public staging database; BC, breast cancer; C-index, concordance index.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-4754097/v1/7f75665b97c2fff9c05ebe0c.png"},{"id":62657965,"identity":"18a6070d-7546-4db1-ac11-28899eeba0b7","added_by":"auto","created_at":"2024-08-17 02:13:30","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":76224,"visible":true,"origin":"","legend":"\u003cp\u003eFlow diagram of patients\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-4754097/v1/a3a2d5ba2dd631f6d94676a6.png"},{"id":62657966,"identity":"c58ebd49-6a20-41ea-a1a9-2cee1c6b15c7","added_by":"auto","created_at":"2024-08-17 02:13:30","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":222387,"visible":true,"origin":"","legend":"\u003cp\u003eMortality prediction models with Feature Importance by age group. BMI, body mass index; ER, estrogen receptor; HF, heart failure; HER2, human epidermal growth factor receptor 2 ; LD, liver disease; PVD, peripheral vascular disease ; PR, progesterone receptor; T-size, tumor-size\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-4754097/v1/c99f157aaec491a7c9b5b130.png"},{"id":68206889,"identity":"d11a0b12-4ff8-4c6e-9c3f-214ed35f0280","added_by":"auto","created_at":"2024-11-04 16:33:41","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":900493,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4754097/v1/d3cb2d71-0886-4691-93f2-f3ebd298d90e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prediction Model for Survival of Younger Patients with Breast Cancer Using the Breast Cancer Public Staging Database","fulltext":[{"header":"Introduction","content":"\u003cp\u003eBreast cancer (BC) is one of the most common cancers and the leading cause of cancer-related mortality among women worldwide [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Recent epidemiological evidence indicates a consistent upward trend in the prevalence of BC in young women (BCYW) [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. In the United States, 18% of new BC cases and 11% of BC deaths occur in women younger than 50 years [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e], BCYW tend to have a higher proportion of estrogen receptor (ER) negative, triple-negative, and HER2\u0026thinsp;+\u0026thinsp;tumors [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Younger age is correlated with poorer prognostic characteristics of tumors, such as decreased tumor differentiation, increased Ki-67 expression, and greater lymph node infiltration, compared to females older than 50 years [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Given the unique challenges faced by BCYW, predicting their prognosis is crucial. Consequently, considerable research has been conducted to predict the survival of this specific population.\u003c/p\u003e \u003cp\u003eSun et al. proposed a nomogram to predict overall and cancer-specific survival in young patients with BC. The nomogram used the important feature of lymph node ratio to predict overall survival and BC-specific survival based on the Cox proportional hazards model. These nomograms provide more accurate individualized risk predictions of adversarial events and may assist clinicians in making decisions for young patients with BC [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Gong et al. developed and validated a comprehensive nomogram to predict survival in young women with BC, using SEER database and a competing risks model. This model demonstrated superior performance and efficacy compared to the TNM system in validation experiment [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Li et al. developed a model to predict the 3-year, 5-year, 7-year, and 10-year survival rates of young patients with BC using random forest survival, based on data from the SEER database [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Despite this effort, few studies have focused specifically on predicting the prognosis of BCYW compared to those on conducted based on the overall age of patients with BC [\u003cspan additionalcitationids=\"CR10 CR11 CR12\" citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]-[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. Furthermore, most existing studies rely on the SEER database, which has inherent limitations in variable selection.\u003c/p\u003e \u003cp\u003eTo address these gaps, our study introduces a ML-based prognosis model for young patients with BC, incorporating comorbidities such as atrial fibrillation (AF), chronic kidney disease (CKD), chronic obstructive pulmonary disease (COPD), diabetes mellitus (DM), deep venous thrombosis (DVT), dyslipidemia (DYS), heart failure (HF), hypertension (HYP), liver disease (LD), myocardial infarction(MI), peripheral vascular disease (PVD), and stroke. Additionally, we conducted a comparative analysis to identify the variables preferred by machine learning algorithms in predicting adverse outcomes in younger and older patients with BC.\u003c/p\u003e"},{"header":"Methods","content":"\u003cp\u003e We developed a model to predict all-cause mortality in younger patients with BC using data from the Breast Cancer Public Staging Database (CPSD) provided by the National Cancer Data Center (NCDC) (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). To achieve this, we first extracted data of patients diagnosed with BC between 2013 and 2015 from the Breast-CPSD. The data were divided into training and test datasets. Using the training data, we used random survival forest (RSF), gradient boost survival analysis (GBSA), extra survival tree (EST), penalized Cox probability hazard lasso (CoxPH-L) and ElasticNet (CoxPH-E). The performance of these predictions was evaluated on test data using the C-index metric.\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e \u003cp\u003eThis study was approved by the Ethics Review Board of National Cancer Center Institutional Review Board (IRB NO. NCC2023-0260). The requirement for informed consent in this study was waived because the researcher accessed only anonymized data for analysis purposes. The pseudonymized data were analyzed in a secure environment provided by the National Cancer Data Centre, ensuring that only the results were exported. Data collection and other procedures were performed in accordance with principles of Good Clinical Practice and Declaration of Helsinki guidelines (1975, revised 1983), and with other relevant ethical regulations.\u003c/p\u003e \u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eData source\u003c/h2\u003e \u003cp\u003eThis study utilized the Breast-CPSD provided by the NCDC [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. This database was constructed by linking data from the Breast Cancer Public Library Database (CPLD) of the NCDC and collaborative staging (CS) for cancer established in the Korea Central Cancer Registry (KCCR) [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e], [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. The Breast-CPSD includes data from 16,870 individuals who developed BC at primary sites C500\u0026ndash;C506, C508, and C509 between 2012 and 2019. From these datasets, we excluded cohorts diagnosed with BC between 2016 and 2019 for 5-year mortality predictions and the 2012 cohort, for which screening information prior to cancer diagnosis was unavailable. The data were cleaned to remove missing or unknown entries. Subsequently, the dataset was divided into two cohorts: individuals aged\u0026thinsp;\u0026lt;\u0026thinsp;50 years and those aged\u0026thinsp;\u0026ge;\u0026thinsp;51 years. For each cohort, 80% of the data were allocated to the training set to create survival models, whereas the remaining 20% constituted the test set, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. AF, CKD, COPD, DM, DVT, DYS, HF, HYP, LD, MI, PVD, and stroke were defined according to the International Classification of Diseases 10th Revision (ICD-10). Additionally, the primary endpoint was defined as all-cause mortality within 5 years of cancer diagnosis\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eSurvival machine learning models\u003c/h2\u003e \u003cp\u003eThe modeling of time-to-event data in survival analysis requires specialized techniques to address specific challenges such as censoring, truncation, time-varying covariates, and covariate effects. Several models, including RSF, GBSA, EST, CoxPH-L, and CoxPH-E, have been employed for this purpose. RSF [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e] extends the random forest algorithm proposed by Breiman et al. in 2001 [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e] to survival analysis, effectively handling censored data and identifying important prognostic factors. The GBSA is derived from a gradient boosting machine [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e] and applied to survival analysis involving censored data [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e], [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. The extra survival tree model, an extension of the extremely randomized tree model developed by Geurts et al. in 2005 [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e], also considers censoring. The Cox proportional hazards model [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e] is the standard approach for survival analysis and has been enhanced by penalization methods, including lasso [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e] and ElasticNet [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e] penalties.\u003c/p\u003e \u003cp\u003eThe performance of these models was assessed using the C-index [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. In addition, permutation feature importance analysis was performed. Feature importance scoring, which assesses the values of all input features to determine their importance in decision-making mechanisms, is a critical step in mortality prediction for survival analysis. Overall, feature importance was assessed using Scikit-learn (version 1.0.2) [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. Survival models were constructed using the scikit-survival package (version 0.17.2) [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e], and the entire analysis was conducted using TensorFlow (version 1.15.5) and Python (version 3.7.5).\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eBaseline characteristics of the patients\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eTable 1 presents a comparison of the basic characteristics of the younger and older patient cohorts. The younger group had a higher ratio of ER, PR, past smokers, current smokers, weekly alcohol consumption (days), and vigorous physical activity (days per week). In contrast, the ratios of HER2, AF, CKD, COPD, DM, DVT, DYS, HF, HYP, LD, MI, PVD, and stroke were higher in the older group. Additionally, the younger group exhibited different ratios of height, weight, waist circumference, urinary protein, topography code, morphology code, and AJCC7 STAGE compared to the older group.\u003c/p\u003e\n\u003cp\u003eThe older group exhibited higher levels of BMI, systolic blood pressure, diastolic blood pressure, hemoglobin, fasting blood sugar, total cholesterol, serum glutamic oxaloacetic transaminase, serum glutamic pyruvic transaminase, gamma glutamyl transpeptidase, triglycerides, low-density lipoprotein, moderate physical activity (days per week), and physical activity (days per week). However, the younger group exhibited higher levels of high-density lipoprotein, serum creatine, estimated glomerular filtration rate, tumor size, weekly alcohol consumption (days), and vigorous physical activity (days per week).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 1.\u003c/strong\u003e Baseline characteristics between younger and older groups. Data are expressed as number of patients(percentage) or mean\u0026plusmn;standard deviation. Abbreviations: BMI, body mass index.\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"596\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e\u003cstrong\u003eOlder\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eGroup\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eN =\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e1,824\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e\u003cstrong\u003eYounger\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eGroup\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eN = 1\u003c/strong\u003e\u003cstrong\u003e,574\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eAge (y)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e59.75\u0026plusmn;7.05\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e44.35\u0026plusmn;4.35\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eBMI (kg/㎡)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e23.85\u0026plusmn;2.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e22.68\u0026plusmn;2.73\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eHeight (cm)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e150 \u0026le; H \u0026lt;160\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e77.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e54.51\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e160 \u0026le; H \u0026lt;170\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e43.14\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e170 \u0026le; H\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e2.35\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eWeight (kg, %)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e40 \u0026le; W \u0026lt; 50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e12.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e14.42\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e50 \u0026le; W \u0026lt; 60\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e46.52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e48.86\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e60 \u0026le; W \u0026lt; 70\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e31.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e27.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e70 \u0026le; W \u0026lt; 80\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e7.99\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e6.8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e80 \u0026le; W \u0026lt; 90\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e1.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e1.91\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e90 \u0026le; W\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eWaist circumference (cm, %)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e60 \u0026le; WC \u0026lt; 70\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e10.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e25.86\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e70 \u0026le; WC \u0026lt; 90\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e39.19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e49.49\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e80 \u0026le; WC \u0026lt; 90\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e36.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e18.87\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e90 \u0026le; WC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e13.63\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e5.78\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eSystolic blood pressure (mmHg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e124,50\u0026plusmn;15.40\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e115.60\u0026plusmn;13.62\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eDiastolic blood pressure (mmHg)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e76.35\u0026plusmn;9.80\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e72.77\u0026plusmn;9.47\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eHaemoglobin level (g/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e13.12\u0026plusmn;1.15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e12.77\u0026plusmn;1.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eFasting blood sugar (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e101.90\u0026plusmn;25.46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e94.33\u0026plusmn;17.46\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eTotal cholesterol (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e202.60\u0026plusmn;39.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e189.50\u0026plusmn;32.72\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eSerum glutamic oxaloacetic transaminase (IU/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e26.50\u0026plusmn;37.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e21.62\u0026plusmn;12.60\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eSerum glutamic pyruvic transaminase (IU/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e23.85\u0026plusmn;30.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e18.44\u0026plusmn;17.40\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eGamma glutamyl transpeptidase (IU/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e27.96\u0026plusmn;37.14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e21.79\u0026plusmn;27.36\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eTriglycerides (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e124.90\u0026plusmn;72.32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e98.22\u0026plusmn;65.30\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eHigh-density lipoprotein (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e57.04\u0026plusmn;19.32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e60.43\u0026plusmn;14.30\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eLow-density lipoprotein (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e121.00\u0026plusmn;36.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e109.50\u0026plusmn;29.88\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eSerum creatine (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.78\u0026plusmn;0.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.81\u0026plusmn;2.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eEstimated glomerular filtration rate (mL/min)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e85.34\u0026plusmn;22.74\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e94.23\u0026plusmn;32.64\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eProtein in urine\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e1 negative (-)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e95.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e94.98\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e2 positive (\u0026plusmn;)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e2.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e3.11\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e3 positive (+1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e1.53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e1.33\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e4 positive (+2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e5 positive (+3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.13\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e6 positive (+4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.05\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.13\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eTopography\u0026nbsp;CODE (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eC500\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.44\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eC501\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e4.32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e3.05\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eC502\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e14.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e15.69\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eC503\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e4.05\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e6.73\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eC504\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e36.84\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e35.01\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eC505\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e7.22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e7.81\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eC506\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.06\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eC508\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e19.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e17.47\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eC509\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e13.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e13.72\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eMorphology CODE (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e1. Squamous and transitional cell carcinoma (8051\u0026ndash; 8084, 8120\u0026ndash;8131))\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e3. Adenocarcinoma (8140\u0026ndash;8149, 8160\u0026ndash;8163, 8190\u0026ndash;8221, 8260\u0026ndash;8337, 8350\u0026ndash;8552, 8570\u0026ndash;8576, 8940\u0026ndash;8941)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e98.36\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e98.98\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e4. Other specific carcinomas (8030\u0026ndash;8046, 8150\u0026ndash;8157, 8170\u0026ndash;8180, 8230\u0026ndash;8255, 8340\u0026ndash;8347, 8560\u0026ndash;8562, 8580\u0026ndash;8671)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e5. Unspecified carcinomas (NOS) (8010\u0026ndash;8015, 8020\u0026ndash;8022, 8050)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e16. (Other specified types of cancer (8720-8790, 8930-8936, 8950-8983, 9000-9030, 9060-9110, 9260-9365, 9380-9539))\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.06\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003e17.\u0026nbsp;Unspecified types of cancer (8000-8005)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eAJCC7 STAGE\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eIA(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e46.52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e46.19\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eIB(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e1.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e1.78\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eIIA(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e26.71\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e26.49\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eIIB(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e13.03\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e12.77\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eIII(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e9.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e11.37\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eIV(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e1.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e1.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eT-size\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e21.39\u0026plusmn;15.08\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e22.46\u0026plusmn;16.44\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eER(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e69.46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e76.56\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003ePR(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e55.28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e71.47\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eHER2(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e33.44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e28.78\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eAtrial fibrillation (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e3.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.57\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eChronic kidney disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e1.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.38\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eChronic obstructive pulmonary disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e4.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e1.78\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eDiabetes (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e31.42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e13.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eDeep venous thrombosis (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e2.13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e1.52\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eDyslipidaemia (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e69.51\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e47.78\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eHeart failure (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e5.47\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e2.54\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eHypertension (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e50.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e16.65\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eLiver disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e40.72\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e35.9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eMyocardial infarction (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.13\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003ePeripheral vascular disease (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e17.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e6.86\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eStroke (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.13\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eSmoking status\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eNon-smoker\u0026nbsp;(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e94.75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e91.68\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003ePast smoker\u0026nbsp;(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e1.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e2.92\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eCurrent smoker\u0026nbsp;(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e3.45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e5.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eWeekly alcohol consumption (days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.33\u0026plusmn;0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.61\u0026plusmn;1.03\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eModerate physical activity (days in a week)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e1.26\u0026plusmn;1.90\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e1.22\u0026plusmn;1.67\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003ePhysical activity Walking (days in a week)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e2.83\u0026plusmn;2.48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e2.80\u0026plusmn;2.37\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eVigorous physical activity (days in a week)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e0.88\u0026plusmn;1.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e0.94\u0026plusmn;1.53\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eSurvival time (days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e1775.70\u0026plusmn;233.20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e1797.00\u0026plusmn;173.10\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"53.18791946308725%\"\u003e\n \u003cp\u003eAll cause of death (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.154362416107382%\"\u003e\n \u003cp\u003e5.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"23.65771812080537%\"\u003e\n \u003cp\u003e3.37\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eModel Performance Evaluation\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe performance of the RSF, GBSA, EST, CoxPH-L, and CoxPH-E models were compared based on the mean C-index and standard deviation (SD) for the prediction of mortality in Table 2. The RSF model achieved a C-index of 78.86\u0026plusmn;0.01 for the young cohort and 79.29\u0026plusmn;0.01 for the old cohort. The GBSA model had a C-index of 66.65\u0026plusmn;0.01 for the young cohort and 81.70\u0026plusmn;0.01 for the old cohort. The EST model showed a C-index of 87.19\u0026plusmn;0.01 for the young and 84.01\u0026plusmn;0.01 for the old cohorts. The CoxPH-L model was 73.86\u0026plusmn;0.01 for the young cohort and 81.70\u0026plusmn;0.01 for the old cohort. Finally, the CoxPH-E model had a mean C-index of 72.61\u0026plusmn;0.01 for the young cohort and 87.73\u0026plusmn;0.01 for the old cohort.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2.\u003c/strong\u003e Mean C-index value from survival prediction models. Abbreviations: RSF, Random Survival Forest; GBSA, Gradient Boosting Survival; EST, Extra Survival Trees; CoxPH-L, Cox proportional hazards model Lasso; CoxPH-E, Cox proportional hazards model ElasticNet; C-index, concordance index.\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"602\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"25.45757071547421%\" rowspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eModel\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"35.607321131447584%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eYoung cohort 5-year mortality prediction\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"38.935108153078204%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eOld cohort 5-year mortality prediction\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"47.767857142857146%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eC-index\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"52.232142857142854%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eC-index\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"25.45757071547421%\" valign=\"top\"\u003e\n \u003cp\u003eRSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"35.607321131447584%\" valign=\"top\"\u003e\n \u003cp\u003e78.86\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"38.935108153078204%\" valign=\"top\"\u003e\n \u003cp\u003e79.29\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"25.45757071547421%\" valign=\"top\"\u003e\n \u003cp\u003eGBSA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"35.607321131447584%\" valign=\"top\"\u003e\n \u003cp\u003e66.65\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"38.935108153078204%\" valign=\"top\"\u003e\n \u003cp\u003e81.70\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"25.45757071547421%\" valign=\"top\"\u003e\n \u003cp\u003eEST\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"35.607321131447584%\" valign=\"top\"\u003e\n \u003cp\u003e87.19\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"38.935108153078204%\" valign=\"top\"\u003e\n \u003cp\u003e84.01\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"25.45757071547421%\" valign=\"top\"\u003e\n \u003cp\u003eCoxPH-L\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"35.607321131447584%\" valign=\"top\"\u003e\n \u003cp\u003e73.86\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"38.935108153078204%\" valign=\"top\"\u003e\n \u003cp\u003e81.70\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"25.45757071547421%\" valign=\"top\"\u003e\n \u003cp\u003eCoxPH-E\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"35.607321131447584%\" valign=\"top\"\u003e\n \u003cp\u003e72.61\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"38.935108153078204%\" valign=\"top\"\u003e\n \u003cp\u003e81.73\u0026plusmn;0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eTo construct the survival prediction models, we identified the most important features for each model and extracted the top 10 features in each model for analysis. In the young cohort, the RSF model highlighted AJCC7 stage, C509, COPD, ER status, age, physical activity \u0026ldquo;walking\u0026rdquo; (days per week), hemoglobin levels, weekly alcohol consumption (days), total cholesterol, and weight. The GBSA model identified AJCC7 STAGE, diastolic blood pressure, systolic blood pressure, ER, weekly alcohol consumption (days), fasting blood sugar, COPD, low-density lipoprotein, moderate physical activity (days per week), and C503. The EST model included AJCC7 STAGE, C509, COPD, ER, PR, DYS, physical activity walking (days per week), LD, age, and height. The CoxPH-L was used for total cholesterol, AJCC7 STAGE, low-density lipoprotein, triglyceride, high-density lipoprotein, COPD, PR, alcohol, C501, and C509 assays. The CoxPH-E model included total cholesterol, low-density lipoprotein, AJCC7 STAGE, triglycerides, high-density lipoprotein, COPD, weekly alcohol consumption (in days), C501, PR, and C509 levels. Within the old cohort, the RSF selected the AJCC7 STAGE, fasting blood sugar, T SIZE, ER, DYS, PR, estimated glomerular filtration rate, C509, HER2, and low-density lipoprotein levels. The GBSA model used AJCC7 stage, Tumor size, fasting blood sugar, age, BMI, high-density lipoprotein, estimated glomerular filtration rate, triglycerides, ER, and weight. The EST model included the AJCC7 STAGE, DYS, ER, fasting blood sugar, MCODE-3, C509, PR, T SIZE, HER2, and HF. The CoxPH-L model was assigned to the AJCC7 STAGE, fasting blood sugar, gamma glutamyl transpeptidase, serum creatine, PR, DYS, HYP, Vigorous physical activity (days per week), Physical activity \u0026ldquo;walking\u0026rdquo; (days per week), and PVD. The CoxPH-L model included AJCC7 stage, fasting blood sugar, gamma glutamyl transpeptidase, serum creatine, PR, DYS, HYP, vigorous physical activity (days/week), physical activity \u0026ldquo;walking\u0026rdquo; (days/week), and hemoglobin.\u003c/p\u003e\n\u003cp\u003eFigure 3 depicts a heatmap showing the frequency distribution of variables utilized in developing the 5-year mortality prediction models in both the young and old patient cohorts. Different color intensities indicate the importance of each feature, with deeper colors signifying higher frequency. In both young and old cohorts, the AJCC stage consistently emerged as the most critical feature across all models. However, the significance of the other features varied significantly, not only between the models but also within each age cohort.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eBC is the leading cause of cancer-related deaths among women, and the number of younger patients with BC continues to increase. Younger patients with BC tend to have an unfavorable prognosis due to their unusual tumor characteristics. This highlights the need for a personalized treatment approach for younger patients with BC.\u003c/p\u003e \u003cp\u003eSurvival rates have been shown to differ between younger and older patients with BC, with notable differences in the basic characteristics of these populations. In particular, the frequency of co-morbidities varies significantly between younger and older patients in our experimental. These age-related physiological differences may result in different responses and outcomes, which should be considered when developing survival-prediction models.\u003c/p\u003e \u003cp\u003eAlthough several nomogram studies have been conducted to consider these characteristics, ML methodologies that can account for the characteristics of each population and reflect complex causal factors that contribute to negative outcomes are needed. Recently, Li et al. compared the performance of ML-based survival prediction models with the traditional COX method for young patients with BC using the SEER database and reported that the ML methodology outperformed the Cox methodology [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. However, an important point was not considered in this data source. Patients with BC have many comorbidities due to various reasons, and the impact of these comorbidities on negative prognosis has not been considered. In addition, information on the daily lifestyle of patients with cancer was not considered.\u003c/p\u003e \u003cp\u003eTo address these issues, we categorized patients with BC as young (\u0026thinsp;\u0026lt;\u0026thinsp;=\u0026thinsp;50 year) and older(\u0026gt;\u0026thinsp;50 year) and compared 5-year survival prediction using five survival ML models based on Breast-CPSD. In our experiment, the EST models split the nodes by randomly selecting attributes and determining thresholds, which is the key difference between the RFs models. The EST model outperformed the other ML models in both the older and younger cohorts. As the EST model allows for a wider range of threshold choices, it performs particularly well on datasets with many attributes. The algorithm captures the intricate relationships among various data subsets and effectively handles diverse attribute distributions. As a result of these characteristics, EST models outperform other ML models in both age groups [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]\u0026ndash;[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. Furthermore, 10 iterations were conducted to select the optimal model. At each stage, the variables deemed crucial for the ML model were identified and summarized. It is noteworthy that the COPD variable appears to be a highly significant predictor of mortality in young patients with BC, in contrast to the results observed in the older population. Previous studies have demonstrated that COPD plays a role in the development of lung, liver, and colorectal cancer [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. However, our findings revealed that COPD was a significant predictor of negative prognosis in patients with BC. In addition, the Breast-CPSD includes screening data from the National Health Service, which permits the consideration of data on the general lifestyle of patients with cancer. In contrast to the older patient population, our experimental results indicated that weekly alcohol consumption (days) was a negative prognostic factor in younger patients with BC.\u003c/p\u003e \u003cp\u003eIn conclusion, the number of younger patients diagnosed with BC is increasing and studies have proposed classifying these patients into high-risk groups. However, few studies have focused on survival predictions based on machine learning (ML). In this study, we developed a model to predict the survival of young patients with breast cancer based on ML, which is expected to help identify patients with BC who require aggressive treatment. Nevertheless, given that the data used in this study were exclusively derived from female Korean patients with BC, further validation of the model in diverse populations is required in future studies.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgments\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was supported by a grant (no: 2310440-2) from the National Cancer Center of Korea, Basic Science Research Program through the National Research Foundation of Korea (NRF), funded by the Ministry of Education (No. NRF-2022R1F1A107504).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eConceptualization was managed by HYJK, MSK, and KSR; methodology, HYJK, MSK, and KSR; validation, HYJK, MSK, and KSR; investigation, HYJK; data curation, HYJK, and KSR; writing the original draft preparation, HYJK and KSR. All the authors assisted in drafting and editing the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data that support the findings of this study are available from Korea Clinical Data Utilization Network for Research Excellence (K-CURE) portal [14] but restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available. Data are, however, available from the corresponding author upon reasonable request and with permission of NCDC. The GitHub repository [32] contains all codes relevant to the current submission.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eAnderson, B.O. et al. The Global Breast Cancer Initiative: a strategic collaboration to strengthen health care for non-communicable diseases. Lancet Oncol. 22, 578\u0026ndash;581 (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFernandes, U. et al. Breast cancer in young women: a rising threat: A 5-year follow-up comparative study. Porto Biomed J. 8, e213 (2023). doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/j.pbj.0000000000000213\u003c/span\u003e\u003cspan address=\"10.1097/j.pbj.0000000000000213\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDeSantis, CE. et al. Breast cancer statistics, 2019. CA Cancer J Clin. 69, 438\u0026ndash;451 (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShah, A.N. et al. Circulating tumor cells, circulating tumor DNA, and disease characteristics in young women with metastatic breast cancer. Breast Cancer Res. Treat., 187, 397\u0026ndash;405 (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePruessmann, J. et al. Conditional Disease-Free and Overall Survival of 1858 Young Women with Non-Metastatic Breast Cancer and with Participation in a Post-Therapeutic Rehab Programme according to Clinical Subtypes. Breast Care. 16, 163\u0026ndash;172 (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSun, Y. Nomograms for prediction of overall and cancer-specific survival in young breast cancer. Breast Cancer Research Treat, 184, 597\u0026ndash;613 (2020)..\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuo, L. W. Development and validation of nomograms for predicting overall and breast cancer-specific survival among patients with triple-negative breast cancer. Cancer manag Res. 10, 5881\u0026ndash;5894 (2018).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi, L. W., Liu, X., Shen, M. L., Zhao, M. J., \u0026amp; Liu, H. Development and validation of a random survival forest model for predicting long-term survival of early-stage young breast cancer patients based on the SEER database and an external validation cohort. Am J Cancer Res. 14, 1609\u0026ndash;1621 (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSedighi-Maman Z, Mondello A. A two-stage modeling approach for breast cancer survivability prediction. Int J Med Inform. 149, 104438 (2021). doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.ijmedinf.2021.104438\u003c/span\u003e\u003cspan address=\"10.1016/j.ijmedinf.2021.104438\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi, J. Predicting breast cancer 5-year survival using machine learning: A systematic review. PloS one, 16, e0250370 (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBoeri C, et al. Machine Learning techniques in breast cancer prognosis prediction: A primary evaluation. Cancer Med. 9, 3234\u0026ndash;3243 (2020). doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/cam4.2811\u003c/span\u003e\u003cspan address=\"10.1002/cam4.2811\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu P, et al. Optimizing Survival Analysis of XGBoost for Ties to Predict Disease Progression of Breast Cancer. IEEE Trans Biomed Eng. 68, 148\u0026ndash;160 (2021). doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1109/TBME.2020.2993278\u003c/span\u003e\u003cspan address=\"10.1109/TBME.2020.2993278\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGanggayah, M.D, et al. Predicting factors for survival of breast cancer patients using machine learning techniques. BMC Med Inform Decis Mak. 19, 48 (2019). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s12911-019-0801-4\u003c/span\u003e\u003cspan address=\"10.1186/s12911-019-0801-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHome page. National Cancer Center. Cancer data. National Cancer Center. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e\u003c/span\u003e\u003cspan address=\"http://www.cancerdata.re.kr/en/index\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 11 July 2024\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKorea central cancer registry. \"KCCR Survey.\" Korea Central Cancer Registry. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ekccrsurvey.cancer.go.kr/index.do\u003c/span\u003e\u003cspan address=\"http://kccrsurvey.cancer.go.kr/index.do\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 11 July 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoi DW, et al. Data resource profile: The cancer public library database in South Korea. Cancer Res Treat. Apr 30 (2024). doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4143/crt.2024.207\u003c/span\u003e\u003cspan address=\"10.4143/crt.2024.207\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIshwaran, H., Kogalur, U. B., Blackstone, E. H. and Lauer, M. SRandom survival forests. The annals of applied statistics 841\u0026ndash;860 (2008).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBreiman, L. Random Forests. Machine Learning. 45, 5\u0026ndash;32 (2001). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1023/A:1010933404324\u003c/span\u003e\u003cspan address=\"10.1023/A:1010933404324\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJ. H. Friedman. \u0026lsquo;\u0026lsquo;Greedy function approximation: A gradient boosting machine,\u0026rsquo;\u0026rsquo; Ann. Statist. 29, 1189\u0026ndash;1232 (2001).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen Y., Jia Z., Mercola D., Xie X. A gradient boosting algorithm for survival analysis via direct optimization of concordance index. \u003cem\u003eComput Math Methods Med\u003c/em\u003e. 2013, 873595 (2013). doi: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1155/2013/873595\u003c/span\u003e\u003cspan address=\"10.1155/2013/873595\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBai, M., Zheng, Y., \u0026amp; Shen, Y. Gradient boosting survival tree with applications in credit scoring. Journal of the Operational Research Society, 73, 39\u0026ndash;55 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGeurts, P., Ernst, D. \u0026amp; Wehenkel, L. Extremely randomized trees. Mach. Learn. 63, 3\u0026ndash;42 (2006)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCox, D. R. Regression models and life-tables. Journal of the Royal Statistical Society: Series B (Methodological). 34, 187\u0026ndash;202 (1972).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTibshirani R. The lasso method for variable selection in the cox model. Stat Med. 16, 85\u0026ndash;95 (1997). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/(SICI)1097-0258(19970228)16:4\u0026lt;385::AID-SIM380\u0026gt;3.0.CO;2-3\u003c/span\u003e\u003cspan address=\"10.1002/(SICI)1097-0258(19970228)16:4%3C385::AID-SIM380%3E3.0.CO;2-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZou H, Hastie T. Regularization and variable selection via the elastic-net. J R Stat Soc. 67, 301\u0026ndash;20 (2005). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/j.1467-9868.2005.00503.x\u003c/span\u003e\u003cspan address=\"10.1111/j.1467-9868.2005.00503.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHarrell FE, Califf RM, Pryor DB, Lee KL, Rosati RA. Evaluating the yield of medical tests. JAMA. 247, 2543\u0026ndash;6 (1982).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePedregosa F, et al. \"Scikit-learn: Machine Learning in Python.\" *. J Mach Learn Res. 12, 2825\u0026ndash;30 (2011).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eP\u0026ouml;lsterl S. \"scikit-survival: A Library for Time-to-Event Analysis Built on Top of scikit-learn.\" *. J Mach Learn Res. 21, 1\u0026ndash;6 (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGhazwani, M., Begum, M.Y. Computational intelligence modeling of hyoscine drug solubility and solvent density in supercritical processing: gradient boosting, extra trees, and random forest models. Sci Rep. 13, 10046 (2023). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1038/s41598-023-37232-8\u003c/span\u003e\u003cspan address=\"10.1038/s41598-023-37232-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWehenkel, L., Ernst, D. \u0026amp; Geurts, P. Ensembles of extremely randomized trees and some generic applications. In Proceedings of Robust Methods for Power System State Estimation and Load Forecasting (2006)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAhn, S. V., Lee, E., Park, B., Jung, J. H., Park, J. E., Sheen, S. S., \u0026hellip; Park, J.H. (2020). Cancer development in patients with COPD: a retrospective analysis of the National Health Insurance Service-National Sample Cohort in Korea. \u0026lt;background-color:;i\u0026gt;BMC pulmonary medicine\u0026lt;/background-color:;i\u0026gt;. \u0026lt;background-color:;i\u0026gt;20\u0026lt;/background-color:;i\u0026gt;, 1\u0026ndash;10.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKwang Sun Ryu (2024). Breast Cancer Survival Prediction. GitHub. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/KwangSun-Ryu/Breast-cancer-survival-prediction.git\u003c/span\u003e\u003cspan address=\"https://github.com/KwangSun-Ryu/Breast-cancer-survival-prediction.git\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Survival prediction model, Breast cancer in young women, Machine learning, Breast cancer","lastPublishedDoi":"10.21203/rs.3.rs-4754097/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4754097/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBreast cancer (BC) is a prevalent disease that contributes significantly to female mortality worldwide, particularly among young women, who often present with aggressive tumor. Despite the need for accurate prognosis in this demographic, existing studies have focused on broader age groups and often rely on the SEER database, which has limitations in variable selection. Data from 3,401 patients with BC were obtained from the Breast Cancer Public Staging Database. Patients were categorized as younger (n\u0026thinsp;=\u0026thinsp;1,574) and older (n\u0026thinsp;=\u0026thinsp;1,827). We utilized various survival models\u0026mdash;Random Survival Forest, Gradient Boosting Survival, Extra Survival Trees (EST), and two penalized Cox proportional hazards models, Lasso and ElasticNet\u0026mdash;to analyze and compare BC mortality characteristics between the groups. Additionally, older patients exhibited a higher prevalence of comorbidities compared to younger patients. The EST model outperformed the other models in predicting mortality for both age groups. Tumor stage was the primary variable used to train the model for mortality prediction in both groups. COPD was a significant variable only in younger patients with BC. Other variables exhibited varying degrees of consistency in each group. These findings can help identify high-risk young female patients with BC who require aggressive treatment by predicting the risk of mortality.\u003c/p\u003e","manuscriptTitle":"Prediction Model for Survival of Younger Patients with Breast Cancer Using the Breast Cancer Public Staging Database","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-17 02:13:26","doi":"10.21203/rs.3.rs-4754097/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-23T05:10:09+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-19T09:44:20+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-03T11:58:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"189343291120897782514768869380982437852","date":"2024-09-02T11:55:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"161421807732819984500496077790140237584","date":"2024-08-26T12:49:54+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-12T13:33:46+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-08-06T06:53:45+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-07-23T03:40:33+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-18T11:43:49+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-07-17T06:41:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8713aada-839f-4341-83f3-ea446e6355f7","owner":[],"postedDate":"August 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":35874487,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":35874488,"name":"Physical sciences/Engineering/Biomedical engineering"},{"id":35874489,"name":"Health sciences/Oncology/Cancer/Breast cancer"}],"tags":[],"updatedAt":"2024-11-04T16:23:28+00:00","versionOfRecord":{"articleIdentity":"rs-4754097","link":"https://doi.org/10.1038/s41598-024-76331-y","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-10-28 16:05:08","publishedOnDateReadable":"October 28th, 2024"},"versionCreatedAt":"2024-08-17 02:13:26","video":"","vorDoi":"10.1038/s41598-024-76331-y","vorDoiUrl":"https://doi.org/10.1038/s41598-024-76331-y","workflowStages":[]},"version":"v1","identity":"rs-4754097","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4754097","identity":"rs-4754097","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}