New Staging System and Prognostic Model for Malignant Phyllodes Tumor Patients without Distant Metastasis: A Development and Validation Study

Simple Summary Malignant phyllodes tumor of the breast (MPTB) is a rare fibroepithelial tumor. Because of its rarity, research based on large clinical datasets is currently lacking. Moreover, the prognostic factors of MPTB have yet to be determined. Prognostic models and staging systems for MPTB patients are needed, but are also lacking. Here, we conducted a comparison between MPTB cases and invasive ductal carcinoma cases. Our findings reveal substantial differences in the clinical features of invasive ductal carcinoma and MPTB. We applied the KAPS algorithm to explore and establish a new stage- and age-stratification system. The system exhibited a good prognostic stratification ability for both the internal cohort and the external cohort. Furthermore, we developed independent prognostic models for MPTB using Cox proportional hazards regression and random survival forests (RSF). Finally, we built a user-friendly web app to allow researchers and doctors to access our model. Abstract Purpose: To build a new staging system and new prognostic models for MPTB. Methods: We performed a comprehensive analysis of the data from the SEER database. Results: We discussed the characteristics of MPTB by comparing 1085 MPTB cases with 382,718 invasive ductal carcinoma cases. We established a new stage- and age-stratification system for MPTB patients. Furthermore, we built two prognostic models for MPTB patients. The validity of these models was confirmed through multifaceted and multidata verification. Conclusions: Our study provided a staging system and prognostic models for MPTB patients, which can not only help to predict patient outcomes, but also enhance the understanding of the prognostic factors associated with MPTB.

[1]  V. Kouloulias,et al.  Successful Treatment of a Locally Recurrent and Metastatic Malignant Phyllodes Tumor with Accelerated Radiotherapy and Nab-Paclitaxel, Cisplatin, and Liposomal Doxorubicin Chemotherapy , 2021, Chemotherapy.

[2]  X. Qian,et al.  Apatinib treatment is effective for metastatic malignant phyllodes tumors of the breast: a case report , 2021, BMC Women's Health.

[3]  Amy M. Sitapati,et al.  NCCN Guidelines® Insights: Breast Cancer, Version 4.2021. , 2021, Journal of the National Comprehensive Cancer Network : JNCCN.

[4]  Gijs Geleijnse,et al.  Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival , 2021, Scientific Reports.

[5]  Wentian Li,et al.  On Fair Performance Comparison between Random Survival Forest and Cox Regression: An Example of Colorectal Cancer Study , 2021, SciMedicine Journal.

[6]  C. Roland,et al.  Outcomes of systemic therapy in metastatic phyllodes tumor of the breast , 2021, Breast Cancer Research and Treatment.

[7]  J. Lynch,et al.  Comparison of the Tree-Based Machine Learning Algorithms to Cox Regression in Predicting the Survival of Oral and Pharyngeal Cancers: Analyses Based on SEER Database , 2020, Cancers.

[8]  Peter C Austin,et al.  Graphical calibration curves and the integrated calibration index (ICI) for survival models , 2020, Statistics in medicine.

[9]  T. Gondo,et al.  Effective Treatment of a Malignant Breast Phyllodes Tumor with Doxorubicin-Ifosfamide Therapy , 2019, Case reports in oncological medicine.

[10]  H. Yao,et al.  Breast Phyllodes Tumors Recruit and Repolarize Tumor-Associated Macrophages via Secreting CCL5 to Promote Malignant Progression, Which Can Be Inhibited by CCR5 Inhibition Therapy , 2019, Clinical Cancer Research.

[11]  Hemant Ishwaran,et al.  Random Survival Forests , 2008, Wiley StatsRef: Statistics Reference Online.

[12]  Stephen B. Edge,et al.  Eighth Edition of the AJCC Cancer Staging Manual: Breast Cancer , 2018, Annals of Surgical Oncology.

[13]  S. Kuo,et al.  Effect of Lipodox in combination with bevacizumab in a patient with a metastatic malignant phyllodes breast tumor: A case report , 2017, Oncology letters.

[14]  Yanhong Zhang,et al.  Phyllodes Tumor of the Breast: Histopathologic Features, Differential Diagnosis, and Molecular/Genetic Updates. , 2016, Archives of pathology & laboratory medicine.

[15]  Benjamin R Saville,et al.  Decision curve analysis. , 2015, JAMA.

[16]  Seung-Mo Hong,et al.  K-Adaptive Partitioning for Survival Data: The kaps Add-on Package for R , 2013 .

[17]  D. Kleinbaum,et al.  Kaplan-Meier Survival Curves and the Log-Rank Test , 2012 .

[18]  Jeremy M. G. Taylor.  Random Survival Forests. , 2011, Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer.

[19]  Imran Kurt,et al.  The comparisons of random survival forests and Cox regression analysis with simulation and an application related to breast cancer , 2009, Expert Syst. Appl..

[20]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[21]  J. Tward,et al.  Malignant phyllodes tumor of the female breast , 2006, Cancer.

[22]  M. Ramdass,et al.  Phyllodes breast tumour showing invasive squamous-cell carcinoma with invasive ductal, clear-cell, secretory, and squamous components. , 2006, The Lancet. Oncology.

[23]  J. A. Ferreira,et al.  On the Benjamini-Hochberg method , 2006, math/0611265.

[24]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[25]  D. Rimm,et al.  X-Tile , 2004, Clinical Cancer Research.

[26]  M. Pagano,et al.  Survival analysis. , 1996, Nutrition.

[27]  J. Gower.  A General Coefficient of Similarity and Some of Its Properties , 1971 .