Predictive model of prognosis index for invasive micropapillary carcinoma of the breast based on machine learning: A SEER population-based study

Predictive model of prognosis index for invasive micropapillary carcinoma of the breast based on machine learning: A SEER population-based study | 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 Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Predictive model of prognosis index for invasive micropapillary carcinoma of the breast based on machine learning: A SEER population-based study Zirong Jing, Yushuai Yu, Xin Yu, Qing Wang, Kaiyan Huang, Chuangui Song This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3977224/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background Invasive micropapillary carcinoma (IMPC) is a rare subtype of breast cancer. Its epidemiological features, treatment principles, and prognostic factors remain controversial. Objective This study aimed to develop an improved machine learning-based model to predict the prognosis of patients with invasive micropapillary carcinoma. Methods A total of 1123 patients diagnosed with IMPC after surgery between 1998 and 2019 were identified from the Surveillance, Epidemiology, and End Results (SEER) database for survival analysis. Univariate and multivariate analyses were performed to explore independent prognostic factors for the overall and disease-specific survival of patients with IMPC. Five machine learning algorithms were developed to predict the 5-year survival of these patients. Results Cox regression analysis indicated that patients aged > 65 years had a significantly worse prognosis than those younger in age, while unmarried patients had a better prognosis than married patients. Patients diagnosed between 2001 and 2005 had a significant risk reduction of mortality compared with other periods. The XGBoost model outperformed the other models with a precision of 0.818 and an area under the curve of 0.863. Important features established using the XGBoost model were the year of diagnosis, age, histological type, and primary site, representing the four most relevant variables for explaining the 5-year survival status. Conclusions A machine learning model for IMPC in patients with breast cancer was developed to estimate the 5-year OS. The XGBoost model had a promising performance and can help clinicians determine the early prognosis of patients with IMPC; therefore, the model can improve clinical outcomes by influencing management strategies and patient health care decisions. breast cancer machine learning micropapillary carcinoma prognosis Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 1. Introduction Breast cancer is the most common cancer and the second most common cause of cancer-related death among women worldwide. 1 The pathological types of breast cancer are predominantly non-specific invasive ductal carcinomas and invasive micropapillary carcinoma (IMPC), a rare pathological type that accounts for approximately 3–6% of all invasive breast cancers. 2 IMPC was first discovered by Luna-Moré et al. 3 as atypical tumour cells with a papillary or papillary-like structure, no fibrovascular core, and a special spatial arrangement with cell polarity reversal. 4–7 IMPC is often characterised by the early detection of large masses and high axillary lymph node metastasis, 8–9 which is an important factor leading to late-stage and post-operative local recurrence in patients. Over the past 30 years, IMPC has become a popular research topic, both domestically and internationally. 10–12 Due to the lack of targeted diagnosis and treatment programs, the current clinical application of IMPC is still based on invasive breast cancer, meaning that the treatment strategy might not be adequately precise. Therefore, we built a machine learning model based on the unique pathological abnormalities and prognostic factors of these individuals with IMPC to develop more accurate diagnoses and treatment plans for these patients. The data for this study were sourced from the Surveillance, Epidemiology, and End Results (SEER) database, which contains a wide range of cancer-related diagnoses, treatments, and survival outcomes and covers approximately 28% of cancer patients in the United States. 13–14 Our study thus aimed to incorporate multiple possible prognostic factors into a single mathematical model to construct an accurate prognostic indicator system for predicting IMPC. We aimed to use a combination of machine learning and the SEER database to construct an efficient mathematical model for multiple factors, such as column line graphs, 15–16 that are otherwise difficult to construct. Firstly, we evaluated the epidemiology, clinicopathological features, treatment modalities, and prognosis of IMPC. In addition, a thorough prediction model with 10 prognostic parameters (age, year of onset, race, marital status, primary lesion location, pathological type, TNM staging, surgical status, and radiation therapy status) was built utilising machine learning techniques. We believe the predictive model established in this study has a high correlation and accuracy, which can help doctors perform better treatment. 2. Methods 2.1 Patient selection This study used the SEER*Stat software (version 8.4.2; https://seer.cancer.gov/SEER ). IMPC patients diagnosed between 1998 and 2019 were first located in the SEER database. International Classification of Diseases (ICD) code O-3 morphology 8507/3, 2) IMPC as the sole or initial primary tumour with histological confirmation, 3) comprehensive clinicopathological and follow-up data, and 4) known causes of mortality and survival times were the inclusion criteria. The following were the exclusion criteria: 1) unidentified race; 2) unidentified histological grade; 3) unidentified clinical stage; 4) unidentified ER status; 5) unidentified HR status; and 6) unidentified cause of death. 2.2 Data collection A detailed patient selection workflow is shown in Fig. 1 . After excluding patients with incomplete information, 1123 patients with IMPC were enrolled in the study and randomly assigned to training and validation cohorts at a 4:1 ratio. The variables included patient age, race, year of diagnosis, marital status, primary tumour site, histology, TNM stage, surgical status, radiotherapy status, and chemotherapy status. The primary endpoints were overall survival (OS) and disease-specific survival (DSS). The OS was defined as the period from the patient's diagnosis to their death (the last follow-up visit was the time to death for patients who were lost to follow-up before their death). The duration between an IMPC-caused diagnosis and death was designated as the DSS. 2.3 Statistical analysis The influence of different factors on the incidence and prognosis of IMPC was explored by dividing the study population into groups according to age and race. R Studio software was used to screen for statistically significant variables (P < 0.05 was considered statistically significant) in the univariate Cox regression models. Multivariate Cox regression analyses were performed on these statistically significant variables to determine independent prognostic indicators, risk ratios, and 95% confidence intervals (CIs) related to DSS and OS. Survival curves were generated using the Kaplan-Meier method, and the log-rank test was used to determine differences in the demographic and clinical characteristics of patients with IMPC. Factors associated with the outcome were determined using Cox proportional risk regression models to determine the hazard ratios (HRs) associated with 95% CIs. Statistical analyses were performed using SPSS (version 26.0; IBM, Armonk, New York, United States), and P-values < 0.05 were considered statistically different. Ten categorical indicators were gathered, including age, race, year of diagnosis, marital status, primary tumour site, histology, TNM stage, surgery status, radiation status, and chemotherapy status. (Fig. 1 ) to create a machine learning model for predicting the 5-year survival. The software program "Missile Forest" was used to estimate missing values of the dataset. Out of all the patients recruited, 1.8 per 1,000 (n = 2) were excluded because of unknown primary site, 2.7 per 1,000 (n = 3) had missing information about the histologic type, and 1.8 per 1,000 (n = 1) lacked surgical treatment information. The "Missile Forest" algorithm performed well because the percentage of missing values was far lower than the severe missingness cut-off value of 75%. 17 Prior to developing the machine learning model, a 4:1 randomisation process was used to separate all patients with invasive breast cancer into training and test groups. Five machine learning algorithms—SVM, k-nearest neighbour (KNN), Random Forest, Extra Trees, and XGBoost—were employed in our investigation. For each model, a 10-fold internal cross-validation was used to identify the ideal parameters that yielded the best level of accuracy. A test set was used to assess each machine learning algorithm's performance using metrics for sensitivity, accuracy, precision, NPV, and area under the curve (AUC) of the subjects' working characteristics. Feature importance based on the "partial_dependence" package was used to assess each element's contribution to the machine learning model. All analyses were conducted using Python (version 3.8; Python Software Foundation, Wilmington, Delaware, United States). 3. Results The baseline clinical characteristics of the patients are presented in Table 1 . Overall, 1123 eligible patients were included in our study. Of these, 639 (56.9%) and 484 (43.1%) were aged < 65 years and ≥ 65 years, respectively. There were 863 (76.8%) and 107 (9.5%) White and Black participants, respectively. TNM staging was distributed as follows: 513 (45.7%) cases were stage I, 369 (32.9%) cases were stage II, 186 (16.6%) cases were stage III, and 35 (3.1%) cases were stage IV. HR+/HER2- was the most common IMPC histological type, followed by HR+/HER2 + in 14% of cases; triple-negative breast cancer was the least common type. Additionally, registered patients tended to receive localised treatments, including surgery (no surgery: n = 70 [6.2%] vs. mastectomy: n = 1051 [93.6%]) and radiation therapy (no radiotherapy: n = 447 [39.8%] vs. radiotherapy: n = 676 [60.2%]), whereas approximately the same proportion of patients were treated with and without chemotherapy (no chemotherapy: n = 593 [52.8%] vs. chemotherapy: n = 530 [47.2%]). Table 1 Baseline characteristics of MPC Characteristics Patients (N = 1123), n (%) Age (years) < 65 639 (56.9) ≥ 65 Race 484 (43.1) White 863 (76.8) Black 107 (9.5) Othera Marital status 153 (13.6) Married 893 (79.5) Not marriedb Unkonw Year of diagnosis 184 (16.4) 46 (4.1) 2001–2005 50 (4.5) 2006–2010 190 (16.9) 2011–2015 486(43.3) 2016–2019 Primary site 397 (35.4) Axillary tail 3 (0.3) Central portion 62 (5.5) Inner quadrant 159 (14.2) Lower-inner quadrant 86 (7.7) Lower-outer quadrant 73 (6.5) Nipple 3 (0.3) Overlapping lesion 274 (24.4) Upper-outer quadrant 312 (27.8) NAc Histologic type 151 (13.4) HR-/HER2- 32(2.8) HR-/HER2+ 37 (3.3) HR+/HER2- 666 (59.3) HR+/HER2+ 157 ( 14 ) Not available 199 (17.7) NA Stage 32 (2.8) I 513 (45.7) II 369 (32.9) Ⅲ 186 (16.6) IV 35 (3.1) NA Surgery approach 20 (1.8) No surgery 70 (6.2) BCS d 584 (52) Mastectomy 467 (41.6) NA Radiation status 2 (0.2) No 447 (39.8) Yes Chemotherapy status 676 (60.2) No 593 (52.8) Yes 530 (47.2) a Other includes American Indian/Alaskan Native, Asian/Pacific Islander, and unknown. b Not married includes divorced, separated, single (never married), unmarried or domestic partner, and widowed. c NA: not available d BCS: breast-conserving surgery 3.1 Survival Analysis The median follow-up period of the enrolled patients was 52 months. Kaplan-Meier curves for OS and DSS based on different demographic and clinical characteristics at baseline are shown in Figs. 2 and 3 , respectively. In our analysis, patients aged > 65 years had a significantly worse prognosis than those younger in age, and unmarried patients had a better prognosis than married patients, suggesting that age and marital status are important prognostic factors. Figures 2 D and 3 D display the Kaplan-Meier curves for the time of disease diagnosis; the periods from 2001 to 2005 are superior to the other periods. Survival was shorter in patients with the HR-/HER2- subtype than in those with other histological subtypes. Patients with IMPC who received localised therapy demonstrated a unique survival benefit compared with those who did not receive localised therapy. It was also discovered that the primary site of the breast had an impact on the prognosis of IMPC patients; those whose original tumor site was in the outer lower quadrant of the breast had a worse prognosis than those whose primary tumor site was in another breast quadrant. Race was not associated with prognosis. Regarding treatment, local surgery, chemotherapy, and radiotherapy resulted in better OS and DSS; the univariate Cox regression analysis for each variable is shown in Appendix 1. The results of the multifactorial Cox regression analysis are presented in Table 2 . Independent predictors included age, diagnosis year, surgery status, chemotherapy, and radiation. At the time of diagnosis, patients over 65 years old had a higher chance of dying than those under 65 ([OS] HR: 4.034, 95% CI: 2.762–5.890, P < 0.001; [DSS] HR: 2.120, 95% CI: 1.249–3.599, P < 0.005). Mortality was significantly higher in patients diagnosed with stages Ⅲ and IV than in patients diagnosed at an early stage ([OS] HR: 3.910, 95% CI: 1.934–7.930, P = 0.000; [DSS] HR: 52.589, 95% CI: 17.448–158.504, P = 0.000). Local therapy is an important treatment for patients with IMPC and translates into a significant survival benefit. Regardless of breast-conserving or total mastectomy, surgical treatment substantially reduced the risk of disease-specific and all-cause mortality: breast-conserving surgery ([OS] HR: 0.260, 95% CI: 0.145–0.464, P = 0.000; [DSS] HR: 0.222, 95% CI: 0.087–0.565, P = 0.002); mastectomy ([OS] HR: 0.237, 95% CI: 0.136–0.414, P = 0.000; [DSS] HR: 0.303, 95% CI: 0.128–0.719, P = 0.007). Similarly, The risk of both disease-specific and all-cause mortality was decreased by radiation therapy([OS] HR: 0.589, 95% CI: 0.404–0.859, P = 0.006; [DSS] HR: 0.560, 95% CI: 0.320–0.982, P = 0.043); However, those who received chemotherapy and those who did not did not significantly vary in terms of OS or DSS([OS] HR: 0.806, 95% CI: 0.530–1.224, P = 0.311; DSS, HR: 0.992, 95% CI: 0.552–1.780, P = 0.977). Additionally, although there was a difference in OS between married and unmarried participants, DSS was not significantly different ([OS] HR: 1.851, 95% CI: 1.067–3.213, P = 0.029; DSS, HR: 1.124, 95% CI: 0.541–2.334, P = 0.754). The OS and DSS did not significantly differ between races ([OS] HR: 1.046, 95% CI: 0.607–1.801, P = 0.871; [DSS] HR: 0.459, 95% CI: 0.174–1.213, P = 0.116). Table 2 Multivariate Cox proportional hazard model of disease-specific survival and overall survival in all patients. Variables DSS OS P- value HR 95.0% Exp(B) CI P- value HR 95.0% Exp(B) CI lower upper lower upper Age (years) < 65 Reference —— Reference —— ≥ 65 .005 2.120 1.249 3.599 .000 4.034 2.762 5.890 Race Reference —— Reference —— White .282 .692 Black .116 .459 .174 1.213 .871 1.046 .607 1.801 Other .936 1.032 .482 2.208 .392 1.234 .763 1.995 Marital status Reference —— Reference —— Not married .862 .058 Married .754 1.124 .541 2.334 .029 1.851 1.067 3.213 Unkonw .806 .851 .235 3.081 .698 1.198 .481 2.988 Year of diagnosis 2001–2005 Reference —— Reference —— 2006–2010 .010 4.494 1.442 14.011 .025 2.225 1.103 4.487 2011–2015 .047 5.235 1.019 26.908 .090 2.299 .877 6.024 2016–2019 .238 2.841 .502 16.089 .207 1.960 .690 5.571 Primary site Nipple Reference —— Reference —— Central portion .994 .678 .000 7.836E + 43 .902 487.095 .000 3.765E + 45 Inner quadrant .919 185.489 .000 6.962E + 45 .892 942.804 .000 7.256E + 45 Lower-inner quadrant .919 181.875 .000 6.837E + 45 .896 718.931 .000 5.541E + 45 Upper-outer quadrant .919 182.921 .000 6.856E + 45 .889 1119.279 .000 8.610E + 45 Lower-outer quadrant .909 347.880 .000 1.305E + 46 .883 1614.270 .000 1.242E + 46 Axillary tail .865 5914.744 .000 2.277E + 47 .869 3962.962 .000 3.119E + 46 Overlapping lesion .921 161.460 .000 6.055E + 45 .892 962.588 .000 7.406E + 45 NA .922 150.285 .000 5.639E + 45 .891 979.304 .000 7.535E + 45 Histologic type NA Reference —— Reference —— HR-/HER2- .095 2.958 .829 10.557 .006 4.656 1.557 13.924 HR-/HER2+ .464 .518 .089 3.015 .652 1.364 .353 5.276 HR+/HER2- .088 .389 .132 1.149 .986 .992 .391 2.518 HR+/HER2+ .154 .393 .109 1.418 .666 1.253 .449 3.494 Not available .588 .653 .140 3.052 .888 1.082 .364 3.211 Stage NA Reference —— Reference —— I .002 4.365 1.717 11.096 .199 1.301 .870 1.944 II .000 13.981 5.162 37.870 .000 3.143 1.908 5.178 III .000 52.589 17.448 158.504 .000 3.910 1.934 7.903 IV .028 7.287 1.240 42.836 .163 2.123 .737 6.117 Surgery approach No surgery Reference —— Reference —— BCS .002 .222 .087 .565 .000 .260 .145 .464 Mastectomy .007 .303 .128 .719 .000 .237 .136 .414 NA .025 .018 .001 .599 .070 .060 .003 1.263 Radiation status Reference —— Reference —— No Yes .043 .560 .320 .982 .006 .589 .404 .859 Chemotherapy status No Reference —— Reference —— Yes .977 .992 .552 1.780 .311 .806 .530 1.224 3.2 Machine learning-based 5-year survival prediction in patients with IMPC Five machine learning models were trained on a dataset of 1123 individuals in order to forecast the 5-year survival rate following an IMPC diagnosis. Table 3 lists the performances of these five algorithms, and Fig. 4 displays the confusion matrix that results. For the test dataset, the sensitivities for the SVM, KNN, Random Forest, Extra Trees, and XGBoost models were 0.863, 0.829, 0.863, 0.846, and 0.863, respectively. The AUSs for the SVM, KNN, Random Forest, Extra Trees, and XGBoost models were 0.989, 0.968, 0.947, 0.936, 0.979, respectively. Figure 5 displays the operating characteristic curves and decision curve analysis for the five receiver models. We mainly concentrated on assessing the sensitivity of high-risk patients whose fatalities happened in the fifth year due to the design of our study. The XGBoost model outperformed the other four models in terms of accuracy, precision, sensitivity, and net present value. The XGBoost algorithm turned out to be the most appropriate model for this investigation because the model also showed a high AUC. The four most important variables that describe the 5-year survival status are radiation, surgery, PR status, and ER status. Appendix 3 lists the importance scores for each variable utilized in the XGBoost model. Table 3 Model performance for the 5-year survival. Algorithms Accuracy Speificity Precision PPV NPV AUC a SVM-train 0.868 0.992 0.912 0.912 0.864 0.936 SVM-test 0.863 0.989 0.889 0.889 0.861 0.814 KNN-train 0.859 0.971 0.761 0.761 0.870 0.861 KNN-test 0.829 0.968 0.667 0.667 0.843 0.743 RandomForest-train 0.959 0.989 0.949 0.949 0.962 0,986 RandomForest-test 0.863 0.947 0.706 0.706 0.890 0.787 ExtraTrees-train 0.964 1.000 1.000 1.000 0.957 0.994 ExtraTrees-test 0.846 0.936 0.647 0.647 0.880 0.751 XGBoost-train 0.878 0.984 0.867 0.867 0.880 0.931 XGBoost-test 0.863 0.979 0.818 0.818 0.868 0.863 a AUC: area under the curve. 4. Discussion In 2022, breast cancer fully surpassed lung cancer as the most common cancer, with the highest incidence rate worldwide. 1 Micropapillary carcinoma is a rare pathological subtype of breast cancer with a low incidence, and its treatment is primarily based on invasive ductal carcinoma owing to the lack of specialised guidelines. Currently, the treatment of patients with breast cancer is mainly based on a combination of surgery, chemotherapy, endocrine therapy, targeted therapy, immunotherapy, and other therapeutic modalities, which has substantially improved the disease control rate and quality of life of patients compared with previous simple surgical or medical treatment. 18,19 Patients with IMPC have a high rate of clinical lymph node metastasis, which was reported to be up to 84.45% or more in one study. 8 This has to do with the tumor's significant lymphovascular invasiveness. The microcapillary histological pattern's underlying biology is detrimental to the tumor's lymphatic route.Additionally, IMPC is classified as simple versus mixed, with simple IMPC exhibiting more aggressive behaviour, lower locoregional recurrence-free survival, and more locoregional recurrences than mixed IMPC. 20 Scholars such as Verras 21 have argued that Breast surgeons should be aware that IMPC may necessitate broader margins of excision, even in the absence of particular recommendations. Radiation therapy, being younger than 65, and having an ER positive status have all been demonstrated to be protective variables. Larger tumors, younger age, Black racial background, and absence of hormone receptor expression were also substantially linked to regional lymph node involvement. Although surgery can effectively slow the growth of IMPC, there are no predictive factors for patients who have had surgery. As a result, machine learning has helped personalized medicine gain traction and has been suggested as a way to enhance illness prediction.In this study, we analysed 1123 patients with IMPC breast cancer in the SEER database to identify age, marital status, stage, ER status, surgery, radiotherapy, and chemotherapy as factors affecting prognosis. These features were further utilised to build a machine learning model for predicting 5-year OS. Patients with IMPC who were 65 years of age or older, single, had a stage III–IV tumor, and had a negative ER status were all associated with poor postoperative prognoses. While there was no difference in overall survival (OS) between mastectomy and breast-conserving surgery, the prognosis of patients was much improved by surgery, radiation, and chemotherapy. Developing a new technology that reliably and accurately judges tumour prognosis is of great significance for the early diagnosis of patients with breast micropapillary carcinoma. Currently, our diagnosis of patients with breast micropapillary carcinoma is mainly based on its clinical and pathological characteristics; however, the currently available information is not sufficient for clinical physicians to effectively treat the disease. Meng et al. 22 and Zhang 23 evaluated the survival of IMPC using column line analysis; however, there were still issues such as selection bias, sample bias, and molecular-level deletions, which limited the accuracy of this method. In addition, methods that had a significant impact on patient prognosis —therapies, including radiation, chemotherapy, and surgery, were left out of this model since the data did not support their inclusion. Such omissions have filled all the controversy over the results. In medical practice, machine learning has gained increasing research attention in areas such as disease diagnosis, prognosis, and treatment plan formulation. 24–26 This method achieves the maximum utilisation of data by adaptively adjusting the weights of each factor. A critical point of significance for the early prognostic determination of patients with micropapillary breast cancer, the 5-year survival rate was used in this study as a predictive endpoint. Compared with other methods, 27–30 XGBoost has better predictive performance and broad application prospects. Machine learning methods were previously used to predict the recurrence of invasive breast cancer at 5 and 10 years of age. The XGBoost model constructed earlier (XGBoost) had a higher AUC, indicating that good prediction results could still be obtained under small-sample conditions. When establishing the XGBoost model, factors such as year of diagnosis, age, histological type, and site of origin were considered to have the greatest impact on the 5-year survival rate. Age and histological type are currently recognised as important prognostic factors, which is consistent with other research results. 31 Undoubtedly, patients with micropapillary carcinoma of the breast have more underlying diseases, poor drug resistance, or suboptimal health due to the advanced age of disease onset, which may have a direct negative impact on survival time. The sample size in our study was sufficient to comprehend the incidence and prognostic variables of cancer during the previous 30 years. Consequently, new machine learning algorithm-based models have been developed to forecast the 5-year survival rate. Among them, the XGBoost method showed the best performance regarding the AUC, precision, accuracy, sensitivity, and NPV score. This project is expected to provide an efficient early diagnostic method for tumour-related diseases, laying the foundation for clinical physicians to develop personalised treatment plans, management strategies, and treatment plans. This model may therefore help identify patients with a higher risk of adverse outcomes who require more aggressive treatment. This was a retrospective study with certain limitations. By 2010, about 31.2% of patients with breast cancer had not detected HER2, which made the clinical prognostic effect of HER2. In addition, no data for simple and mixed pathological subtyping of patients with IMPC were available in the SEER database, which will also have an impact on the research results. Although the influence of M stage on the univariate analysis was significant, we did not use M stage as a parameter in the model due to the small number of samples with distant metastasis in the tumour tissue, and the possibility of errors in the research conclusions. In conclusion, this model has a good application value for the post-operative prognosis of patients with IMPC. 5. Conclusions In this study, we analysed the prognostic data of patients with IMPC and breast cancer using the SEER database. A machine learning predictive model based on a large cohort was constructed to determine the 5-year OS. The model can help clinicians identify the prognosis of patients with IMPC at an early stage, which will enable them to make very accurate clinical decisions and patient treatment going forward. Declarations Acknowledgements The authors thank reviewers for helpful comments on the manuscript. Conflict of interest disclosure The authors declare that they have no competing interests. Funding Statement None. Ethical approval statement Our primary data were extracted from the publicly available SEER database. After agreeing to a data use agreement for the SEER 1998–2019 research data file, we were granted authorisation to extract and use the data. As a result, informed consent and human subject research ethics evaluations were not required for this study. We verified that all statistical analyses were carried out in compliance with the guidelines of the SEER Program and that the data of enrolled patients was either anonymous or de-identified. Consent to participate Not required Consent for publication All of the authors are aware of and agree to the content of the paper and their being listed as a co-author of the paper. Authors contribution CGS conceived and designed the study. ZRJ and YSY performed the experiments. XY, MYH ,QW,KYH analyzed the data. Z-RJ wrote the manuscript. All authors have read and approved this manuscript. Data availability statement The data used to support the findings of this study are available from the corresponding author upon request. References Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin. 2022;72(1):7–33. 10.3322/caac.21708 . Ye F, Yu P, Li N, et al. Prognosis of invasive micropapillary carcinoma compared with invasive ductal carcinoma in breast: A meta-analysis of PSM studies. Breast. 2020;51:11–20. 10.1016/j.breast.2020.01.041 . Luna-Moré S, De Los Santos F, Bretón JJ, Cañadas MA, `Estrogen, Receptors P. C-ERBB-2, p53, and BCL-2 in Thirty-three Invasive Micropapillary Breast Carcinomas. Pathol - Res Pract. 1996;192(1):27–32. 10.1016/S0344-0338(96)80126-9 . Bayramoglu H, Zekioglu O, Erhan Y, Çiriş M, Özdemir N. Fine-needle aspiration biopsy of invasive micropapillary carcinoma of the breast: A report of five cases. Diagn Cytopathol. 2002;27(4):214–7. 10.1002/dc.10176 . Öngürü Ö, Deveci S, Günhan Ö. Cytological findings of invasive micropapillary carcinoma of the breast: a report of two cases. Cytopathology. 2002;13(3):160–3. 10.1046/j.1365-2303.2002.00390.x . Kim MJ, Gong G, Joo HJ, Ahn SH, Ro JY. Immunohistochemical and Clinicopathologic Characteristics of Invasive Ductal Carcinoma of Breast With Micropapillary Carcinoma Component. Arch Pathol Lab Med. 2005;129(10):1277–82. 10.5858/2005-129-1277-IACCOI . Ota D, Toyarna T, Ichihara S, Mizutani M, Kamei K, Iwata H. A case of invasive micropapillary carcinoma of the breast. Breast Cancer. 2007;14(3):323–6. 10.2325/jbcs.14.323 . Chen L, Lang YF, gang R, et al. Breast Carcinoma With Micropapillary Features: Clinicopathologic Study and Long-Term Follow-Up of 100 Cases. Int J Surg Pathol. 2008;16(2):155–63. 10.1177/1066896907307047 . Nassar H, Wallis T, Andea A, Dey J, Adsay V, Visscher D. Clinicopathologic Analysis of Invasive Micropapillary Differentiation in Breast Carcinoma. Mod Pathol. 2001;14(9):836–41. 10.1038/modpathol.3880399 . Vieira TC, Oliveira EA, Dos Santos BJ, et al. COX-2 expression in mammary invasive micropapillary carcinoma is associated with prognostic factors and acts as a potential therapeutic target in comparative oncology. Front Vet Sci. 2022;9:983110. 10.3389/fvets.2022.983110 . Shi Q, Shao K, Jia H. Genomic alterations and evolution of cell clusters in metastatic invasive micropapillary carcinoma of the breast. Nat Commun. 2022;13(1):111. 10.1038/s41467-021-27794-4 . Xu J, Ma H, Wang Q, Zhang H. Expression of autocrine motility factor receptor (AMFR) in human breast and lung invasive micropapillary carcinomas. Int J Exp Pathol. 2023;104(1):43–51. 10.1111/iep.12462 . Hu G, Hu G, Zhang C, et al. Adjuvant chemotherapy could not bring survival benefit to HR-positive, HER2-negative, pT1b-c/N0–1/M0 invasive lobular carcinoma of the breast: a propensity score matching study based on SEER database. BMC Cancer. 2020;20(1):136. 10.1186/s12885-020-6614-0 . Yoon TI, Jeong J, Lee S, et al. Survival Outcomes in Premenopausal Patients With Invasive Lobular Carcinoma. JAMA Netw Open. 2023;6(11):e2342270. 10.1001/jamanetworkopen.2023.42270 . Ye FG, Xia C, Ma D, Lin PY, Hu X, Shao ZM. Nomogram for predicting preoperative lymph node involvement in patients with invasive micropapillary carcinoma of breast: a SEER population-based study. BMC Cancer. 2018;18(1):1085. 10.1186/s12885-018-4982-5 . Liu J, Xi W, Zhou J, Gao W, Wu Q. Nomogram predicting overall prognosis for invasive micropapillary carcinoma of the breast: a SEER-b­ ased population study. Open Access. Tang F, Ishwaran H. Sci J. 2017;10(6):363–77. 10.1002/sam.11348 . Random forest missing data algorithms. Stat Anal Data Min ASA Data. Mutebi M, Anderson BO, Duggan C, et al. Breast cancer treatment: A phased approach to implementation. Cancer. 2020;126(S10):2365–78. 10.1002/cncr.32910 . Takahashi M, Cortés J, Dent R, et al. Pembrolizumab Plus Chemotherapy Followed by Pembrolizumab in Patients With Early Triple-Negative Breast Cancer: A Secondary Analysis of a Randomized Clinical Trial. JAMA Netw Open. 2023;6(11):e2342107. 10.1001/jamanetworkopen.2023.42107 . Eren Kupik G, Altundağ K. The Clinicopathological Characteristics of Pure and Mixed Invasive Micropapillary Breast Carcinomas: A Single Center Experience. Balk Med J. 2022;39(4):275–81. 10.4274/balkanmedj.galenos.2022.2022-4-7 . Verras GI, Mulita F, Tchabashvili L, et al. A rare case of invasive micropapillary carcinoma of the breast. Menopausal Rev. 2022;21(1):73–80. 10.5114/pm.2022.113834 . Meng X, Ma H, Yin H, et al. Nomogram Predicting the Risk of Locoregional Recurrence After Mastectomy for Invasive Micropapillary Carcinoma of the Breast. Clin Breast Cancer. 2021;21(4):e368–76. 10.1016/j.clbc.2020.12.003 . Zhang T. Nomograms for predicting overall survival and cancer-specific survival in patients with invasive micropapillary carcinoma: Based on the SEER database. Demircioğlu A. The effect of preprocessing filters on predictive performance in radiomics. Eur Radiol Exp. 2022;6(1):40. 10.1186/s41747-022-00294-w . Huang W, Shang Q, Xiao X, Zhang H, Gu Y, Yang L, Shi G, Yang Y, Hu Y, Yuan Y, Ji A, Chen L. Raman spectroscopy and machine learning for the classification of esophageal squamous carcinoma. Spectrochim Acta Mol Biomol Spectrosc. 2022;281:121654. 10.1016. Delen D, Walker G, Kadam A. Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med. 2005;34(2):113–27. 10.1016/j.artmed.2004.07.002 . Huang Y, Chen W, Zhang X, et al. Prediction of Tumor Shrinkage Pattern to Neoadjuvant Chemotherapy Using a Multiparametric MRI-Based Machine Learning Model in Patients With Breast Cancer. Front Bioeng Biotechnol. 2021;9:662749. 10.3389/fbioe.2021.662749 . Kurrant D, Omer M, Abdollahi N, Mojabi P, Fear E, LoVetri J. Evaluating Performance of Microwave Image Reconstruction Algorithms: Extracting Tissue Types with Segmentation Using Machine Learning. J Imaging. 2021;7(1):5. 10.3390/jimaging7010005 . Rakshit P, Zaballa O, Pérez A, Gómez-Inhiesto E, Acaiturri-Ayesta MT, Lozano JA. A machine learning approach to predict healthcare cost of breast cancer patients. Sci Rep. 2021;11(1):12441. 10.1038/s41598-021-91580-x . Gutiérrez-Cárdenas J, Wang Z. Classification of Breast Cancer and Breast Neoplasm Scenarios Based on Machine Learning and Sequence Features from lncRNAs–miRNAs-Diseases Associations. Interdiscip Sci Comput Life Sci. 2021;13(4):572–81. 10.1007/s12539-021-00451-6 . Sun Y, Gu W, Wang G, Zhou X. The Clinicopathological and Prognostic Characteristics of Mucinous Micropapillary Carcinoma of the Breast. In Review; 2021. 10.21203/rs.3.rs-506309/v1 . Additional Declarations No competing interests reported. Supplementary Files table1.docx table2.docx Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies 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-3977224","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":274245586,"identity":"d92bdfc4-4c96-4b55-a120-3e4d48590dd0","order_by":0,"name":"Zirong Jing","email":"","orcid":"","institution":"Clinical Oncology School of Fujian Medical University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Zirong","middleName":"","lastName":"Jing","suffix":""},{"id":274245587,"identity":"aaaac2e2-1688-4d00-9e01-5d738b568e1a","order_by":1,"name":"Yushuai Yu","email":"","orcid":"","institution":"Clinical Oncology School of Fujian Medical University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yushuai","middleName":"","lastName":"Yu","suffix":""},{"id":274245588,"identity":"cfe9657e-32b5-461c-a51e-606fd8675689","order_by":2,"name":"Xin Yu","email":"","orcid":"","institution":"Clinical Oncology School of Fujian Medical University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Yu","suffix":""},{"id":274245589,"identity":"41e65036-b39e-42c9-9541-7d6e59530822","order_by":3,"name":"Qing Wang","email":"","orcid":"","institution":"Clinical Oncology School of Fujian Medical University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Qing","middleName":"","lastName":"Wang","suffix":""},{"id":274245590,"identity":"72c32251-08e8-45e8-a50e-fde2f60e5de4","order_by":4,"name":"Kaiyan Huang","email":"","orcid":"","institution":"Clinical Oncology School of Fujian Medical University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Kaiyan","middleName":"","lastName":"Huang","suffix":""},{"id":274245591,"identity":"7bf84a85-7529-4013-84a9-7956afd4e792","order_by":5,"name":"Chuangui Song","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYPACCTn7w8zHwEw2duK0WBgzHGdLY2BIAGphJk5LRWLDeR4zsBYGQlrk23sPv/jxSyKxsZnn24OPP7bJ8zEzMH74mINbi8GZc2mWvX0Sxs3MvNsNZyTcNmxjZmCWnLkNjxaJHDNjxh4J2TZm3m3SPAm3GYFa2IBsPA6bAdHC2MPM8wykxZ6gFoYbOcaPGX5IKM5g5mEDaUkkqMXgzBkzxt4GCWMDZjYzyRlpt5PbmBmb8fpFvr3H+MOPP3VyBvyHn0l8sLltO7+9+eCHj/gcBow7CcY2FAHGBrzqgYD5A8MfQmpGwSgYBaNgRAMAXVhLHDw0yHwAAAAASUVORK5CYII=","orcid":"","institution":"Clinical Oncology School of Fujian Medical University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Chuangui","middleName":"","lastName":"Song","suffix":""}],"badges":[],"createdAt":"2024-02-22 01:31:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3977224/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3977224/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":51565015,"identity":"7b393b6e-7170-48db-b631-ce6b54a3deb6","added_by":"auto","created_at":"2024-02-23 18:59:25","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":117209,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eThe workflow of the patient selection process.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-3977224/v1/fca6742fb9b9060acf261cd4.png"},{"id":51565017,"identity":"f65cb3ec-0924-4f8f-abc2-693005149460","added_by":"auto","created_at":"2024-02-23 18:59:26","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":340102,"visible":true,"origin":"","legend":"\u003cp\u003eKaplan-Meier estimate of overall survival by subgroup analysis:(A) age,(B) race,(C)marital status, (D)year of diagnosis; (E)primary tumor site,(F)Histologic type;(G)Stage,(H) surgery status,(I)radiation status, and(J)chemotherapy status.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-3977224/v1/1e6d5e9cd1c95fd6803a7c0e.png"},{"id":51565019,"identity":"5bbce946-5543-4504-8f8f-6601f54d47c7","added_by":"auto","created_at":"2024-02-23 18:59:26","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":326057,"visible":true,"origin":"","legend":"\u003cp\u003eKaplan-Meier estimate of disease-specific survival by subgroup analysis: (A) age, (B) race, (C) marital status, (D) year of diagnosis, (E)primary tumor site, (F) Histologic type, (G) Stage, (H) surgery status, (I) radiation status, and (J) chemotherapy status.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-3977224/v1/1e71a07c4323244ac4ec5d70.png"},{"id":51565779,"identity":"fa5b933f-97ca-41f8-9768-51d1121711a6","added_by":"auto","created_at":"2024-02-23 19:07:26","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":204322,"visible":true,"origin":"","legend":"\u003cp\u003e(A) Coefficients of 10 folds validation. (B) MSE (mean standard error) of 10 folds validation. (C) The histogram based on the selected features.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-3977224/v1/2f7cb14f278068d486fa0202.png"},{"id":51565021,"identity":"c56ad7e1-d7b8-406c-b1d8-d589158a493b","added_by":"auto","created_at":"2024-02-23 18:59:26","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":319267,"visible":true,"origin":"","legend":"\u003cp\u003eDecision curve analyses (DCA)\u003cu\u003e and \u003c/u\u003eReceiver operating characteristic curves for all models. ROCs for all models: (A) K-nearest neighbor; (B) Catboost; (C) decision tree; (D) random Forest; (E) gradient booster. ROC: receiver operating characteristic curve.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-3977224/v1/a4dfaa130cca9a1d1ac4ac5b.png"},{"id":51577489,"identity":"417ad52e-5f93-4ee3-8b39-707b0f564ee5","added_by":"auto","created_at":"2024-02-24 06:28:07","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1463304,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3977224/v1/e87ebad1-cd37-4627-b54a-d73569ad94c9.pdf"},{"id":51565016,"identity":"64c12340-4861-45a9-8f52-b4d61618458c","added_by":"auto","created_at":"2024-02-23 18:59:26","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":34924,"visible":true,"origin":"","legend":"","description":"","filename":"table1.docx","url":"https://assets-eu.researchsquare.com/files/rs-3977224/v1/792f4e7b6ee18ebfc1236e5e.docx"},{"id":51565018,"identity":"7faba054-08df-419e-ab3a-dcd3af697b57","added_by":"auto","created_at":"2024-02-23 18:59:26","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":17478,"visible":true,"origin":"","legend":"","description":"","filename":"table2.docx","url":"https://assets-eu.researchsquare.com/files/rs-3977224/v1/bd741becbbd1c112da923017.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predictive model of prognosis index for invasive micropapillary carcinoma of the breast based on machine learning: A SEER population-based study","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eBreast cancer is the most common cancer and the second most common cause of cancer-related death among women worldwide.\u003csup\u003e1\u003c/sup\u003e The pathological types of breast cancer are predominantly non-specific invasive ductal carcinomas and invasive micropapillary carcinoma (IMPC), a rare pathological type that accounts for approximately 3\u0026ndash;6% of all invasive breast cancers.\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eIMPC was first discovered by Luna-Mor\u0026eacute; et al.\u003csup\u003e3\u003c/sup\u003e as atypical tumour cells with a papillary or papillary-like structure, no fibrovascular core, and a special spatial arrangement with cell polarity reversal.\u003csup\u003e4\u0026ndash;7\u003c/sup\u003e IMPC is often characterised by the early detection of large masses and high axillary lymph node metastasis,\u003csup\u003e8\u0026ndash;9\u003c/sup\u003e which is an important factor leading to late-stage and post-operative local recurrence in patients. Over the past 30 years, IMPC has become a popular research topic, both domestically and internationally.\u003csup\u003e10\u0026ndash;12\u003c/sup\u003e Due to the lack of targeted diagnosis and treatment programs, the current clinical application of IMPC is still based on invasive breast cancer, meaning that the treatment strategy might not be adequately precise. Therefore, we built a machine learning model based on the unique pathological abnormalities and prognostic factors of these individuals with IMPC to develop more accurate diagnoses and treatment plans for these patients. The data for this study were sourced from the Surveillance, Epidemiology, and End Results (SEER) database, which contains a wide range of cancer-related diagnoses, treatments, and survival outcomes and covers approximately 28% of cancer patients in the United States.\u003csup\u003e13\u0026ndash;14\u003c/sup\u003e Our study thus aimed to incorporate multiple possible prognostic factors into a single mathematical model to construct an accurate prognostic indicator system for predicting IMPC.\u003c/p\u003e \u003cp\u003eWe aimed to use a combination of machine learning and the SEER database to construct an efficient mathematical model for multiple factors, such as column line graphs, \u003csup\u003e15\u0026ndash;16\u003c/sup\u003e that are otherwise difficult to construct. Firstly, we evaluated the epidemiology, clinicopathological features, treatment modalities, and prognosis of IMPC. In addition, a thorough prediction model with 10 prognostic parameters (age, year of onset, race, marital status, primary lesion location, pathological type, TNM staging, surgical status, and radiation therapy status) was built utilising machine learning techniques. We believe the predictive model established in this study has a high correlation and accuracy, which can help doctors perform better treatment.\u003c/p\u003e"},{"header":"2. Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Patient selection\u003c/h2\u003e \u003cp\u003eThis study used the SEER*Stat software (version 8.4.2; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://seer.cancer.gov/SEER\u003c/span\u003e\u003cspan address=\"https://seer.cancer.gov/SEER\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). IMPC patients diagnosed between 1998 and 2019 were first located in the SEER database. International Classification of Diseases (ICD) code O-3 morphology 8507/3, 2) IMPC as the sole or initial primary tumour with histological confirmation, 3) comprehensive clinicopathological and follow-up data, and 4) known causes of mortality and survival times were the inclusion criteria. The following were the exclusion criteria: 1) unidentified race; 2) unidentified histological grade; 3) unidentified clinical stage; 4) unidentified ER status; 5) unidentified HR status; and 6) unidentified cause of death.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Data collection\u003c/h2\u003e \u003cp\u003eA detailed patient selection workflow is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. After excluding patients with incomplete information, 1123 patients with IMPC were enrolled in the study and randomly assigned to training and validation cohorts at a 4:1 ratio. The variables included patient age, race, year of diagnosis, marital status, primary tumour site, histology, TNM stage, surgical status, radiotherapy status, and chemotherapy status. The primary endpoints were overall survival (OS) and disease-specific survival (DSS). The OS was defined as the period from the patient's diagnosis to their death (the last follow-up visit was the time to death for patients who were lost to follow-up before their death). The duration between an IMPC-caused diagnosis and death was designated as the DSS.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Statistical analysis\u003c/h2\u003e \u003cp\u003eThe influence of different factors on the incidence and prognosis of IMPC was explored by dividing the study population into groups according to age and race. R Studio software was used to screen for statistically significant variables (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant) in the univariate Cox regression models. Multivariate Cox regression analyses were performed on these statistically significant variables to determine independent prognostic indicators, risk ratios, and 95% confidence intervals (CIs) related to DSS and OS.\u003c/p\u003e \u003cp\u003eSurvival curves were generated using the Kaplan-Meier method, and the log-rank test was used to determine differences in the demographic and clinical characteristics of patients with IMPC. Factors associated with the outcome were determined using Cox proportional risk regression models to determine the hazard ratios (HRs) associated with 95% CIs. Statistical analyses were performed using SPSS (version 26.0; IBM, Armonk, New York, United States), and P-values\u0026thinsp;\u0026lt;\u0026thinsp;0.05 were considered statistically different. Ten categorical indicators were gathered, including age, race, year of diagnosis, marital status, primary tumour site, histology, TNM stage, surgery status, radiation status, and chemotherapy status. (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e) to create a machine learning model for predicting the 5-year survival.\u003c/p\u003e \u003cp\u003eThe software program \"Missile Forest\" was used to estimate missing values of the dataset. Out of all the patients recruited, 1.8 per 1,000 (n\u0026thinsp;=\u0026thinsp;2) were excluded because of unknown primary site, 2.7 per 1,000 (n\u0026thinsp;=\u0026thinsp;3) had missing information about the histologic type, and 1.8 per 1,000 (n\u0026thinsp;=\u0026thinsp;1) lacked surgical treatment information. The \"Missile Forest\" algorithm performed well because the percentage of missing values was far lower than the severe missingness cut-off value of 75%.\u003csup\u003e17\u003c/sup\u003e Prior to developing the machine learning model, a 4:1 randomisation process was used to separate all patients with invasive breast cancer into training and test groups. Five machine learning algorithms\u0026mdash;SVM, k-nearest neighbour (KNN), Random Forest, Extra Trees, and XGBoost\u0026mdash;were employed in our investigation. For each model, a 10-fold internal cross-validation was used to identify the ideal parameters that yielded the best level of accuracy. A test set was used to assess each machine learning algorithm's performance using metrics for sensitivity, accuracy, precision, NPV, and area under the curve (AUC) of the subjects' working characteristics. Feature importance based on the \"partial_dependence\" package was used to assess each element's contribution to the machine learning model. All analyses were conducted using Python (version 3.8; Python Software Foundation, Wilmington, Delaware, United States).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results","content":"\u003cp\u003eThe baseline clinical characteristics of the patients are presented in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. Overall, 1123 eligible patients were included in our study. Of these, 639 (56.9%) and 484 (43.1%) were aged\u0026thinsp;\u0026lt;\u0026thinsp;65 years and \u0026ge;\u0026thinsp;65 years, respectively. There were 863 (76.8%) and 107 (9.5%) White and Black participants, respectively. TNM staging was distributed as follows: 513 (45.7%) cases were stage I, 369 (32.9%) cases were stage II, 186 (16.6%) cases were stage III, and 35 (3.1%) cases were stage IV. HR+/HER2- was the most common IMPC histological type, followed by HR+/HER2\u0026thinsp;+\u0026thinsp;in 14% of cases; triple-negative breast cancer was the least common type. Additionally, registered patients tended to receive localised treatments, including surgery (no surgery: n\u0026thinsp;=\u0026thinsp;70 [6.2%] vs. mastectomy: n\u0026thinsp;=\u0026thinsp;1051 [93.6%]) and radiation therapy (no radiotherapy: n\u0026thinsp;=\u0026thinsp;447 [39.8%] vs. radiotherapy: n\u0026thinsp;=\u0026thinsp;676 [60.2%]), whereas approximately the same proportion of patients were treated with and without chemotherapy (no chemotherapy: n\u0026thinsp;=\u0026thinsp;593 [52.8%] vs. chemotherapy: n\u0026thinsp;=\u0026thinsp;530 [47.2%]).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eBaseline characteristics of MPC\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCharacteristics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePatients (N\u0026thinsp;=\u0026thinsp;1123), n (%)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAge (years)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e639 (56.9)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;65\u003c/p\u003e \u003cp\u003e\u003cb\u003eRace\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e484 (43.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWhite\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e863 (76.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBlack\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e107 (9.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOthera\u003c/p\u003e \u003cp\u003e\u003cb\u003eMarital status\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e153 (13.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMarried\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e893 (79.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNot marriedb\u003c/p\u003e \u003cp\u003eUnkonw\u003c/p\u003e \u003cp\u003e\u003cb\u003eYear of diagnosis\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e184 (16.4)\u003c/p\u003e \u003cp\u003e46 (4.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2001\u0026ndash;2005\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e50 (4.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2006\u0026ndash;2010\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e190 (16.9)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2011\u0026ndash;2015\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e486(43.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2016\u0026ndash;2019\u003c/p\u003e \u003cp\u003e\u003cb\u003ePrimary site\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e397 (35.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAxillary tail\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (0.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCentral portion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e62 (5.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInner quadrant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e159 (14.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLower-inner quadrant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e86 (7.7)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLower-outer quadrant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e73 (6.5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNipple\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3 (0.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOverlapping lesion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e274 (24.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUpper-outer quadrant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e312 (27.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNAc\u003c/p\u003e \u003cp\u003e\u003cb\u003eHistologic type\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e151 (13.4)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR-/HER2-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e32(2.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR-/HER2+\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e37 (3.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR+/HER2-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e666 (59.3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR+/HER2+\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e157 (\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNot available\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e199 (17.7)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003cp\u003e\u003cb\u003eStage\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e32 (2.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e513 (45.7)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eII\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e369 (32.9)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eⅢ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e186 (16.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e35 (3.1)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003cp\u003e\u003cb\u003eSurgery approach\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e20 (1.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo surgery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e70 (6.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBCS\u003csup\u003ed\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e584 (52)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMastectomy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e467 (41.6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003cp\u003e\u003cb\u003eRadiation status\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2 (0.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e447 (39.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003cp\u003e\u003cb\u003eChemotherapy status\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e676 (60.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e593 (52.8)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e530 (47.2)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003csup\u003ea\u003c/sup\u003eOther includes American Indian/Alaskan Native, Asian/Pacific Islander, and unknown.\u003c/p\u003e \u003cp\u003e \u003csup\u003eb\u003c/sup\u003eNot married includes divorced, separated, single (never married), unmarried or domestic partner, and widowed.\u003c/p\u003e \u003cp\u003e \u003csup\u003ec\u003c/sup\u003eNA: not available\u003c/p\u003e \u003cp\u003e \u003csup\u003ed\u003c/sup\u003eBCS: breast-conserving surgery\u003c/p\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Survival Analysis\u003c/h2\u003e \u003cp\u003eThe median follow-up period of the enrolled patients was 52 months. Kaplan-Meier curves for OS and DSS based on different demographic and clinical characteristics at baseline are shown in Figs.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, respectively. In our analysis, patients aged\u0026thinsp;\u0026gt;\u0026thinsp;65 years had a significantly worse prognosis than those younger in age, and unmarried patients had a better prognosis than married patients, suggesting that age and marital status are important prognostic factors. Figures\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eD and \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eD display the Kaplan-Meier curves for the time of disease diagnosis; the periods from 2001 to 2005 are superior to the other periods. Survival was shorter in patients with the HR-/HER2- subtype than in those with other histological subtypes. Patients with IMPC who received localised therapy demonstrated a unique survival benefit compared with those who did not receive localised therapy. It was also discovered that the primary site of the breast had an impact on the prognosis of IMPC patients; those whose original tumor site was in the outer lower quadrant of the breast had a worse prognosis than those whose primary tumor site was in another breast quadrant.\u003c/p\u003e \u003cp\u003eRace was not associated with prognosis. Regarding treatment, local surgery, chemotherapy, and radiotherapy resulted in better OS and DSS; the univariate Cox regression analysis for each variable is shown in Appendix 1. The results of the multifactorial Cox regression analysis are presented in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. Independent predictors included age, diagnosis year, surgery status, chemotherapy, and radiation. At the time of diagnosis, patients over 65 years old had a higher chance of dying than those under 65 ([OS] HR: 4.034, 95% CI: 2.762\u0026ndash;5.890, P\u0026thinsp;\u0026lt;\u0026thinsp;0.001; [DSS] HR: 2.120, 95% CI: 1.249\u0026ndash;3.599, P\u0026thinsp;\u0026lt;\u0026thinsp;0.005). Mortality was significantly higher in patients diagnosed with stages Ⅲ and IV than in patients diagnosed at an early stage ([OS] HR: 3.910, 95% CI: 1.934\u0026ndash;7.930, P\u0026thinsp;=\u0026thinsp;0.000; [DSS] HR: 52.589, 95% CI: 17.448\u0026ndash;158.504, P\u0026thinsp;=\u0026thinsp;0.000).\u003c/p\u003e \u003cp\u003eLocal therapy is an important treatment for patients with IMPC and translates into a significant survival benefit. Regardless of breast-conserving or total mastectomy, surgical treatment substantially reduced the risk of disease-specific and all-cause mortality: breast-conserving surgery ([OS] HR: 0.260, 95% CI: 0.145\u0026ndash;0.464, P\u0026thinsp;=\u0026thinsp;0.000; [DSS] HR: 0.222, 95% CI: 0.087\u0026ndash;0.565, P\u0026thinsp;=\u0026thinsp;0.002); mastectomy ([OS] HR: 0.237, 95% CI: 0.136\u0026ndash;0.414, P\u0026thinsp;=\u0026thinsp;0.000; [DSS] HR: 0.303, 95% CI: 0.128\u0026ndash;0.719, P\u0026thinsp;=\u0026thinsp;0.007). Similarly, The risk of both disease-specific and all-cause mortality was decreased by radiation therapy([OS] HR: 0.589, 95% CI: 0.404\u0026ndash;0.859, P\u0026thinsp;=\u0026thinsp;0.006; [DSS] HR: 0.560, 95% CI: 0.320\u0026ndash;0.982, P\u0026thinsp;=\u0026thinsp;0.043); However, those who received chemotherapy and those who did not did not significantly vary in terms of OS or DSS([OS] HR: 0.806, 95% CI: 0.530\u0026ndash;1.224, P\u0026thinsp;=\u0026thinsp;0.311; DSS, HR: 0.992, 95% CI: 0.552\u0026ndash;1.780, P\u0026thinsp;=\u0026thinsp;0.977). Additionally, although there was a difference in OS between married and unmarried participants, DSS was not significantly different ([OS] HR: 1.851, 95% CI: 1.067\u0026ndash;3.213, P\u0026thinsp;=\u0026thinsp;0.029; DSS, HR: 1.124, 95% CI: 0.541\u0026ndash;2.334, P\u0026thinsp;=\u0026thinsp;0.754). The OS and DSS did not significantly differ between races ([OS] HR: 1.046, 95% CI: 0.607\u0026ndash;1.801, P\u0026thinsp;=\u0026thinsp;0.871; [DSS] HR: 0.459, 95% CI: 0.174\u0026ndash;1.213, P\u0026thinsp;=\u0026thinsp;0.116).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eMultivariate Cox proportional hazard model of disease-specific survival and overall survival in all patients.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"4\" nameend=\"c5\" namest=\"c2\"\u003e \u003cp\u003eDSS\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"4\" nameend=\"c9\" namest=\"c6\"\u003e \u003cp\u003eOS\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cem\u003eP-\u003c/em\u003evalue\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eHR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003e95.0% Exp(B) CI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cem\u003eP-\u003c/em\u003evalue\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eHR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e \u003cp\u003e95.0% Exp(B) CI\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003elower\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eupper\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003elower\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003eupper\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAge (years)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.005\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.120\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.249\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e3.599\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e4.034\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e2.762\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.890\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eRace\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWhite\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.282\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.692\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBlack\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.116\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.459\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.174\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.213\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.871\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.046\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.607\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e1.801\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.936\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.032\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.482\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e2.208\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.392\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.234\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.763\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e1.995\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMarital status\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNot married\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.862\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.058\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMarried\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.754\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.124\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.541\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e2.334\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.029\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.851\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e1.067\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e3.213\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUnkonw\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.806\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.851\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.235\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e3.081\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.698\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.198\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.481\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e2.988\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eYear of diagnosis\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2001\u0026ndash;2005\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2006\u0026ndash;2010\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.010\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.494\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.442\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e14.011\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e2.225\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e1.103\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e4.487\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2011\u0026ndash;2015\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.047\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5.235\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e26.908\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.090\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e2.299\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.877\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e6.024\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2016\u0026ndash;2019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.238\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.841\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.502\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e16.089\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.207\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.960\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.690\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.571\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePrimary site\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNipple\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCentral portion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.994\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.678\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e7.836E\u0026thinsp;+\u0026thinsp;43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.902\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e487.095\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e3.765E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInner quadrant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.919\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e185.489\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e6.962E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.892\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e942.804\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e7.256E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLower-inner quadrant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.919\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e181.875\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e6.837E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.896\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e718.931\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.541E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUpper-outer quadrant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.919\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e182.921\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e6.856E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.889\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1119.279\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e8.610E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLower-outer quadrant\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.909\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e347.880\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.305E\u0026thinsp;+\u0026thinsp;46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.883\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1614.270\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e1.242E\u0026thinsp;+\u0026thinsp;46\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAxillary tail\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.865\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5914.744\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e2.277E\u0026thinsp;+\u0026thinsp;47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.869\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e3962.962\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e3.119E\u0026thinsp;+\u0026thinsp;46\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOverlapping lesion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.921\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e161.460\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e6.055E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.892\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e962.588\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e7.406E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.922\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e150.285\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5.639E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.891\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e979.304\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e7.535E\u0026thinsp;+\u0026thinsp;45\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eHistologic type\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR-/HER2-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.095\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.958\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.829\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e10.557\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.006\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e4.656\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e1.557\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e13.924\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR-/HER2+\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.464\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.518\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.089\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e3.015\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.652\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.364\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.353\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.276\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR+/HER2-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.088\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.389\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.132\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.149\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.986\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e.992\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.391\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e2.518\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHR+/HER2+\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.154\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.393\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.109\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.418\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.666\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.253\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.449\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e3.494\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNot available\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.588\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.653\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.140\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e3.052\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.888\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.082\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.364\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e3.211\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eStage\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.002\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.365\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.717\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e11.096\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.199\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.301\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.870\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e1.944\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eII\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13.981\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.162\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e37.870\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e3.143\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e1.908\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e5.178\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIII\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e52.589\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e17.448\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e158.504\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e3.910\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e1.934\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e7.903\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.028\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.287\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.240\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e42.836\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.163\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e2.123\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.737\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e6.117\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eSurgery approach\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo surgery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBCS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.002\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.222\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.087\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e.565\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e.260\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.145\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e.464\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMastectomy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.007\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.303\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.128\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e.719\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e.237\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.136\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e.414\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.018\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e.599\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.070\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e.060\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.003\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e1.263\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eRadiation status\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.043\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.560\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.320\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e.982\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.006\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e.589\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.404\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e.859\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eChemotherapy status\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReference\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026mdash;\u0026mdash;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e.977\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e.992\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e.552\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.780\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e.311\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e.806\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e.530\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e1.224\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Machine learning-based 5-year survival prediction in patients with IMPC\u003c/h2\u003e \u003cp\u003eFive machine learning models were trained on a dataset of 1123 individuals in order to forecast the 5-year survival rate following an IMPC diagnosis. Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e lists the performances of these five algorithms, and Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e displays the confusion matrix that results. For the test dataset, the sensitivities for the SVM, KNN, Random Forest, Extra Trees, and XGBoost models were 0.863, 0.829, 0.863, 0.846, and 0.863, respectively. The AUSs for the SVM, KNN, Random Forest, Extra Trees, and XGBoost models were 0.989, 0.968, 0.947, 0.936, 0.979, respectively. Figure\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e displays the operating characteristic curves and decision curve analysis for the five receiver models.\u003c/p\u003e \u003cp\u003eWe mainly concentrated on assessing the sensitivity of high-risk patients whose fatalities happened in the fifth year due to the design of our study. The XGBoost model outperformed the other four models in terms of accuracy, precision, sensitivity, and net present value. The XGBoost algorithm turned out to be the most appropriate model for this investigation because the model also showed a high AUC. The four most important variables that describe the 5-year survival status are radiation, surgery, PR status, and ER status. Appendix 3 lists the importance scores for each variable utilized in the XGBoost model.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eModel performance for the 5-year survival.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlgorithms\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSpeificity\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003ePPV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNPV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eAUC\u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSVM-train\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.868\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.992\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.912\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.912\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.864\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.936\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSVM-test\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.863\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.989\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.889\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.889\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.861\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.814\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKNN-train\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.859\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.971\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.761\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.761\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.870\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.861\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKNN-test\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.829\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.968\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.667\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.667\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.843\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.743\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRandomForest-train\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.959\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.989\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.949\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.949\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.962\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0,986\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRandomForest-test\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.863\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.947\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.706\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.706\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.890\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.787\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eExtraTrees-train\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.964\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.957\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.994\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eExtraTrees-test\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.846\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.936\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.647\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.647\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.880\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.751\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGBoost-train\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.878\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.984\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.867\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.867\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.880\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.931\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGBoost-test\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.863\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.979\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.818\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.818\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.868\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.863\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003csup\u003ea\u003c/sup\u003eAUC: area under the curve.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eIn 2022, breast cancer fully surpassed lung cancer as the most common cancer, with the highest incidence rate worldwide.\u003csup\u003e1\u003c/sup\u003e Micropapillary carcinoma is a rare pathological subtype of breast cancer with a low incidence, and its treatment is primarily based on invasive ductal carcinoma owing to the lack of specialised guidelines. Currently, the treatment of patients with breast cancer is mainly based on a combination of surgery, chemotherapy, endocrine therapy, targeted therapy, immunotherapy, and other therapeutic modalities, which has substantially improved the disease control rate and quality of life of patients compared with previous simple surgical or medical treatment.\u003csup\u003e18,19\u003c/sup\u003e Patients with IMPC have a high rate of clinical lymph node metastasis, which was reported to be up to 84.45% or more in one study.\u003csup\u003e8\u003c/sup\u003e This has to do with the tumor's significant lymphovascular invasiveness. The microcapillary histological pattern's underlying biology is detrimental to the tumor's lymphatic route.Additionally, IMPC is classified as simple versus mixed, with simple IMPC exhibiting more aggressive behaviour, lower locoregional recurrence-free survival, and more locoregional recurrences than mixed IMPC.\u003csup\u003e20\u003c/sup\u003e Scholars such as Verras\u003csup\u003e21\u003c/sup\u003e have argued that Breast surgeons should be aware that IMPC may necessitate broader margins of excision, even in the absence of particular recommendations.\u003c/p\u003e \u003cp\u003eRadiation therapy, being younger than 65, and having an ER positive status have all been demonstrated to be protective variables. Larger tumors, younger age, Black racial background, and absence of hormone receptor expression were also substantially linked to regional lymph node involvement. Although surgery can effectively slow the growth of IMPC, there are no predictive factors for patients who have had surgery. As a result, machine learning has helped personalized medicine gain traction and has been suggested as a way to enhance illness prediction.In this study, we analysed 1123 patients with IMPC breast cancer in the SEER database to identify age, marital status, stage, ER status, surgery, radiotherapy, and chemotherapy as factors affecting prognosis. These features were further utilised to build a machine learning model for predicting 5-year OS. Patients with IMPC who were 65 years of age or older, single, had a stage III\u0026ndash;IV tumor, and had a negative ER status were all associated with poor postoperative prognoses. While there was no difference in overall survival (OS) between mastectomy and breast-conserving surgery, the prognosis of patients was much improved by surgery, radiation, and chemotherapy.\u003c/p\u003e \u003cp\u003eDeveloping a new technology that reliably and accurately judges tumour prognosis is of great significance for the early diagnosis of patients with breast micropapillary carcinoma. Currently, our diagnosis of patients with breast micropapillary carcinoma is mainly based on its clinical and pathological characteristics; however, the currently available information is not sufficient for clinical physicians to effectively treat the disease. Meng et al.\u003csup\u003e22\u003c/sup\u003e and Zhang\u003csup\u003e23\u003c/sup\u003e evaluated the survival of IMPC using column line analysis; however, there were still issues such as selection bias, sample bias, and molecular-level deletions, which limited the accuracy of this method. In addition, methods that had a significant impact on patient prognosis \u0026mdash;therapies, including radiation, chemotherapy, and surgery, were left out of this model since the data did not support their inclusion. Such omissions have filled all the controversy over the results.\u003c/p\u003e \u003cp\u003eIn medical practice, machine learning has gained increasing research attention in areas such as disease diagnosis, prognosis, and treatment plan formulation.\u003csup\u003e24\u0026ndash;26\u003c/sup\u003e This method achieves the maximum utilisation of data by adaptively adjusting the weights of each factor. A critical point of significance for the early prognostic determination of patients with micropapillary breast cancer, the 5-year survival rate was used in this study as a predictive endpoint. Compared with other methods,\u003csup\u003e27\u0026ndash;30\u003c/sup\u003e XGBoost has better predictive performance and broad application prospects. Machine learning methods were previously used to predict the recurrence of invasive breast cancer at 5 and 10 years of age. The XGBoost model constructed earlier (XGBoost) had a higher AUC, indicating that good prediction results could still be obtained under small-sample conditions. When establishing the XGBoost model, factors such as year of diagnosis, age, histological type, and site of origin were considered to have the greatest impact on the 5-year survival rate. Age and histological type are currently recognised as important prognostic factors, which is consistent with other research results.\u003csup\u003e31\u003c/sup\u003e Undoubtedly, patients with micropapillary carcinoma of the breast have more underlying diseases, poor drug resistance, or suboptimal health due to the advanced age of disease onset, which may have a direct negative impact on survival time.\u003c/p\u003e \u003cp\u003eThe sample size in our study was sufficient to comprehend the incidence and prognostic variables of cancer during the previous 30 years. Consequently, new machine learning algorithm-based models have been developed to forecast the 5-year survival rate. Among them, the XGBoost method showed the best performance regarding the AUC, precision, accuracy, sensitivity, and NPV score. This project is expected to provide an efficient early diagnostic method for tumour-related diseases, laying the foundation for clinical physicians to develop personalised treatment plans, management strategies, and treatment plans. This model may therefore help identify patients with a higher risk of adverse outcomes who require more aggressive treatment.\u003c/p\u003e \u003cp\u003eThis was a retrospective study with certain limitations. By 2010, about 31.2% of patients with breast cancer had not detected HER2, which made the clinical prognostic effect of HER2. In addition, no data for simple and mixed pathological subtyping of patients with IMPC were available in the SEER database, which will also have an impact on the research results. Although the influence of M stage on the univariate analysis was significant, we did not use M stage as a parameter in the model due to the small number of samples with distant metastasis in the tumour tissue, and the possibility of errors in the research conclusions. In conclusion, this model has a good application value for the post-operative prognosis of patients with IMPC.\u003c/p\u003e"},{"header":"5. Conclusions","content":"\u003cp\u003eIn this study, we analysed the prognostic data of patients with IMPC and breast cancer using the SEER database. A machine learning predictive model based on a large cohort was constructed to determine the 5-year OS. The model can help clinicians identify the prognosis of patients with IMPC at an early stage, which will enable them to make very accurate clinical decisions and patient treatment going forward.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors thank reviewers for helpful comments on the manuscript.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest disclosure\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding Statement\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNone.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eOur primary data were extracted from the publicly available\u0026nbsp;SEER database. After agreeing to a data use agreement for the SEER 1998\u0026ndash;2019 research data file, we were granted authorisation to extract and use the data. As a result, informed consent and human subject research ethics evaluations were not required for this study. We verified that all statistical analyses were carried out in compliance with the guidelines of the SEER Program and that the data of enrolled patients was either anonymous or de-identified.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot required\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll of the authors are aware of and agree to the content of the paper and their being listed as a co-author of the paper.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors contribution\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eCGS conceived and designed the study. ZRJ and YSY performed the experiments. XY, MYH ,QW,KYH analyzed the data. Z-RJ wrote the manuscript. All authors have read and approved this manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data used to support the findings of this study are available from the corresponding author upon request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eSiegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin. 2022;72(1):7\u0026ndash;33. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3322/caac.21708\u003c/span\u003e\u003cspan address=\"10.3322/caac.21708\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYe F, Yu P, Li N, et al. Prognosis of invasive micropapillary carcinoma compared with invasive ductal carcinoma in breast: A meta-analysis of PSM studies. Breast. 2020;51:11\u0026ndash;20. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.breast.2020.01.041\u003c/span\u003e\u003cspan address=\"10.1016/j.breast.2020.01.041\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLuna-Mor\u0026eacute; S, De Los Santos F, Bret\u0026oacute;n JJ, Ca\u0026ntilde;adas MA, `Estrogen, Receptors P. C-ERBB-2, p53, and BCL-2 in Thirty-three Invasive Micropapillary Breast Carcinomas. Pathol - Res Pract. 1996;192(1):27\u0026ndash;32. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/S0344-0338(96)80126-9\u003c/span\u003e\u003cspan address=\"10.1016/S0344-0338(96)80126-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBayramoglu H, Zekioglu O, Erhan Y, \u0026Ccedil;iriş M, \u0026Ouml;zdemir N. Fine-needle aspiration biopsy of invasive micropapillary carcinoma of the breast: A report of five cases. Diagn Cytopathol. 2002;27(4):214\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/dc.10176\u003c/span\u003e\u003cspan address=\"10.1002/dc.10176\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003e\u0026Ouml;ng\u0026uuml;r\u0026uuml; \u0026Ouml;, Deveci S, G\u0026uuml;nhan \u0026Ouml;. Cytological findings of invasive micropapillary carcinoma of the breast: a report of two cases. Cytopathology. 2002;13(3):160\u0026ndash;3. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1046/j.1365-2303.2002.00390.x\u003c/span\u003e\u003cspan address=\"10.1046/j.1365-2303.2002.00390.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim MJ, Gong G, Joo HJ, Ahn SH, Ro JY. Immunohistochemical and Clinicopathologic Characteristics of Invasive Ductal Carcinoma of Breast With Micropapillary Carcinoma Component. Arch Pathol Lab Med. 2005;129(10):1277\u0026ndash;82. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.5858/2005-129-1277-IACCOI\u003c/span\u003e\u003cspan address=\"10.5858/2005-129-1277-IACCOI\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOta D, Toyarna T, Ichihara S, Mizutani M, Kamei K, Iwata H. A case of invasive micropapillary carcinoma of the breast. Breast Cancer. 2007;14(3):323\u0026ndash;6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2325/jbcs.14.323\u003c/span\u003e\u003cspan address=\"10.2325/jbcs.14.323\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen L, Lang YF, gang R, et al. Breast Carcinoma With Micropapillary Features: Clinicopathologic Study and Long-Term Follow-Up of 100 Cases. Int J Surg Pathol. 2008;16(2):155\u0026ndash;63. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/1066896907307047\u003c/span\u003e\u003cspan address=\"10.1177/1066896907307047\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNassar H, Wallis T, Andea A, Dey J, Adsay V, Visscher D. Clinicopathologic Analysis of Invasive Micropapillary Differentiation in Breast Carcinoma. Mod Pathol. 2001;14(9):836\u0026ndash;41. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/modpathol.3880399\u003c/span\u003e\u003cspan address=\"10.1038/modpathol.3880399\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVieira TC, Oliveira EA, Dos Santos BJ, et al. COX-2 expression in mammary invasive micropapillary carcinoma is associated with prognostic factors and acts as a potential therapeutic target in comparative oncology. Front Vet Sci. 2022;9:983110. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fvets.2022.983110\u003c/span\u003e\u003cspan address=\"10.3389/fvets.2022.983110\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShi Q, Shao K, Jia H. Genomic alterations and evolution of cell clusters in metastatic invasive micropapillary carcinoma of the breast. Nat Commun. 2022;13(1):111. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41467-021-27794-4\u003c/span\u003e\u003cspan address=\"10.1038/s41467-021-27794-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXu J, Ma H, Wang Q, Zhang H. Expression of autocrine motility factor receptor (AMFR) in human breast and lung invasive micropapillary carcinomas. Int J Exp Pathol. 2023;104(1):43\u0026ndash;51. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/iep.12462\u003c/span\u003e\u003cspan address=\"10.1111/iep.12462\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu G, Hu G, Zhang C, et al. Adjuvant chemotherapy could not bring survival benefit to HR-positive, HER2-negative, pT1b-c/N0\u0026ndash;1/M0 invasive lobular carcinoma of the breast: a propensity score matching study based on SEER database. BMC Cancer. 2020;20(1):136. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12885-020-6614-0\u003c/span\u003e\u003cspan address=\"10.1186/s12885-020-6614-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYoon TI, Jeong J, Lee S, et al. Survival Outcomes in Premenopausal Patients With Invasive Lobular Carcinoma. JAMA Netw Open. 2023;6(11):e2342270. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jamanetworkopen.2023.42270\u003c/span\u003e\u003cspan address=\"10.1001/jamanetworkopen.2023.42270\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYe FG, Xia C, Ma D, Lin PY, Hu X, Shao ZM. Nomogram for predicting preoperative lymph node involvement in patients with invasive micropapillary carcinoma of breast: a SEER population-based study. BMC Cancer. 2018;18(1):1085. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12885-018-4982-5\u003c/span\u003e\u003cspan address=\"10.1186/s12885-018-4982-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu J, Xi W, Zhou J, Gao W, Wu Q. Nomogram predicting overall prognosis for invasive micropapillary carcinoma of the breast: a SEER-b\u0026shy; ased population study. Open Access.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTang F, Ishwaran H. Sci J. 2017;10(6):363\u0026ndash;77. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/sam.11348\u003c/span\u003e\u003cspan address=\"10.1002/sam.11348\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Random forest missing data algorithms. Stat Anal Data Min ASA Data.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMutebi M, Anderson BO, Duggan C, et al. Breast cancer treatment: A phased approach to implementation. Cancer. 2020;126(S10):2365\u0026ndash;78. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/cncr.32910\u003c/span\u003e\u003cspan address=\"10.1002/cncr.32910\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTakahashi M, Cort\u0026eacute;s J, Dent R, et al. Pembrolizumab Plus Chemotherapy Followed by Pembrolizumab in Patients With Early Triple-Negative Breast Cancer: A Secondary Analysis of a Randomized Clinical Trial. JAMA Netw Open. 2023;6(11):e2342107. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jamanetworkopen.2023.42107\u003c/span\u003e\u003cspan address=\"10.1001/jamanetworkopen.2023.42107\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEren Kupik G, Altundağ K. The Clinicopathological Characteristics of Pure and Mixed Invasive Micropapillary Breast Carcinomas: A Single Center Experience. Balk Med J. 2022;39(4):275\u0026ndash;81. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4274/balkanmedj.galenos.2022.2022-4-7\u003c/span\u003e\u003cspan address=\"10.4274/balkanmedj.galenos.2022.2022-4-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVerras GI, Mulita F, Tchabashvili L, et al. A rare case of invasive micropapillary carcinoma of the breast. Menopausal Rev. 2022;21(1):73\u0026ndash;80. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.5114/pm.2022.113834\u003c/span\u003e\u003cspan address=\"10.5114/pm.2022.113834\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMeng X, Ma H, Yin H, et al. Nomogram Predicting the Risk of Locoregional Recurrence After Mastectomy for Invasive Micropapillary Carcinoma of the Breast. Clin Breast Cancer. 2021;21(4):e368\u0026ndash;76. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.clbc.2020.12.003\u003c/span\u003e\u003cspan address=\"10.1016/j.clbc.2020.12.003\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang T. Nomograms for predicting overall survival and cancer-specific survival in patients with invasive micropapillary carcinoma: Based on the SEER database.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDemircioğlu A. The effect of preprocessing filters on predictive performance in radiomics. Eur Radiol Exp. 2022;6(1):40. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s41747-022-00294-w\u003c/span\u003e\u003cspan address=\"10.1186/s41747-022-00294-w\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang W, Shang Q, Xiao X, Zhang H, Gu Y, Yang L, Shi G, Yang Y, Hu Y, Yuan Y, Ji A, Chen L. Raman spectroscopy and machine learning for the classification of esophageal squamous carcinoma. Spectrochim Acta Mol Biomol Spectrosc. 2022;281:121654. 10.1016.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDelen D, Walker G, Kadam A. Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med. 2005;34(2):113\u0026ndash;27. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.artmed.2004.07.002\u003c/span\u003e\u003cspan address=\"10.1016/j.artmed.2004.07.002\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang Y, Chen W, Zhang X, et al. Prediction of Tumor Shrinkage Pattern to Neoadjuvant Chemotherapy Using a Multiparametric MRI-Based Machine Learning Model in Patients With Breast Cancer. Front Bioeng Biotechnol. 2021;9:662749. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fbioe.2021.662749\u003c/span\u003e\u003cspan address=\"10.3389/fbioe.2021.662749\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKurrant D, Omer M, Abdollahi N, Mojabi P, Fear E, LoVetri J. Evaluating Performance of Microwave Image Reconstruction Algorithms: Extracting Tissue Types with Segmentation Using Machine Learning. J Imaging. 2021;7(1):5. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/jimaging7010005\u003c/span\u003e\u003cspan address=\"10.3390/jimaging7010005\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRakshit P, Zaballa O, P\u0026eacute;rez A, G\u0026oacute;mez-Inhiesto E, Acaiturri-Ayesta MT, Lozano JA. A machine learning approach to predict healthcare cost of breast cancer patients. Sci Rep. 2021;11(1):12441. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41598-021-91580-x\u003c/span\u003e\u003cspan address=\"10.1038/s41598-021-91580-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuti\u0026eacute;rrez-C\u0026aacute;rdenas J, Wang Z. Classification of Breast Cancer and Breast Neoplasm Scenarios Based on Machine Learning and Sequence Features from lncRNAs\u0026ndash;miRNAs-Diseases Associations. Interdiscip Sci Comput Life Sci. 2021;13(4):572\u0026ndash;81. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s12539-021-00451-6\u003c/span\u003e\u003cspan address=\"10.1007/s12539-021-00451-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSun Y, Gu W, Wang G, Zhou X. The Clinicopathological and Prognostic Characteristics of Mucinous Micropapillary Carcinoma of the Breast. In Review; 2021. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.21203/rs.3.rs-506309/v1\u003c/span\u003e\u003cspan address=\"10.21203/rs.3.rs-506309/v1\" targettype=\"DOI\" 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":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"breast cancer, machine learning, micropapillary carcinoma, prognosis","lastPublishedDoi":"10.21203/rs.3.rs-3977224/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3977224/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eInvasive micropapillary carcinoma (IMPC) is a rare subtype of breast cancer. Its epidemiological features, treatment principles, and prognostic factors remain controversial.\u003c/p\u003e\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eThis study aimed to develop an improved machine learning-based model to predict the prognosis of patients with invasive micropapillary carcinoma.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eA total of 1123 patients diagnosed with IMPC after surgery between 1998 and 2019 were identified from the Surveillance, Epidemiology, and End Results (SEER) database for survival analysis. Univariate and multivariate analyses were performed to explore independent prognostic factors for the overall and disease-specific survival of patients with IMPC. Five machine learning algorithms were developed to predict the 5-year survival of these patients.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eCox regression analysis indicated that patients aged\u0026thinsp;\u0026gt;\u0026thinsp;65 years had a significantly worse prognosis than those younger in age, while unmarried patients had a better prognosis than married patients. Patients diagnosed between 2001 and 2005 had a significant risk reduction of mortality compared with other periods. The XGBoost model outperformed the other models with a precision of 0.818 and an area under the curve of 0.863. Important features established using the XGBoost model were the year of diagnosis, age, histological type, and primary site, representing the four most relevant variables for explaining the 5-year survival status.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eA machine learning model for IMPC in patients with breast cancer was developed to estimate the 5-year OS. The XGBoost model had a promising performance and can help clinicians determine the early prognosis of patients with IMPC; therefore, the model can improve clinical outcomes by influencing management strategies and patient health care decisions.\u003c/p\u003e","manuscriptTitle":"Predictive model of prognosis index for invasive micropapillary carcinoma of the breast based on machine learning: A SEER population-based study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-23 18:59:21","doi":"10.21203/rs.3.rs-3977224/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"02e3bdab-500e-44b2-924d-f8ad0ab873e0","owner":[],"postedDate":"February 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-03-05T11:32:05+00:00","versionOfRecord":[],"versionCreatedAt":"2024-02-23 18:59:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3977224","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3977224","identity":"rs-3977224","version":["v1"]},"buildId":"cTy_lsJlmDsVRNrSptgXS","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}