2
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A Decision-Making Supporting Prediction Method for Breast Cancer Neoadjuvant Chemotherapy

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Neoadjuvant chemotherapy (NAC) may increase the resection rate of breast cancer and shows promising effects on patient prognosis. It has become a necessary treatment choice and is widely used in the clinical setting. Benefitting from the clinical information obtained during NAC treatment, computational methods can improve decision-making by evaluating and predicting treatment responses using a multidisciplinary approach, as there are no uniformly accepted protocols for all institutions for adopting different treatment regiments. In this study, 166 Chinese breast cancer cases were collected from patients who received NAC treatment at the First Bethune Hospital of Jilin University. The Miller–Payne grading system was used to evaluate the treatment response. Four machine learning multiple classifiers were constructed to predict the treatment response against the 26 features extracted from the patients’ clinical data, including Random Forest (RF) model, Convolution Neural Network (CNN) model, Support Vector Machine (SVM) model, and Logistic Regression (LR) model, where the RF model achieved the best performance using our data. To allow a more general application, the models were reconstructed using only six selected features, and the RF model achieved the highest performance with 54.26% accuracy. This work can efficiently guide optimal treatment planning for breast cancer patients.

          Related collections

          Most cited references32

          • Record: found
          • Abstract: found
          • Article: not found

          Cancer statistics, 2020

          Each year, the American Cancer Society estimates the numbers of new cancer cases and deaths that will occur in the United States and compiles the most recent data on population-based cancer occurrence. Incidence data (through 2016) were collected by the Surveillance, Epidemiology, and End Results Program; the National Program of Cancer Registries; and the North American Association of Central Cancer Registries. Mortality data (through 2017) were collected by the National Center for Health Statistics. In 2020, 1,806,590 new cancer cases and 606,520 cancer deaths are projected to occur in the United States. The cancer death rate rose until 1991, then fell continuously through 2017, resulting in an overall decline of 29% that translates into an estimated 2.9 million fewer cancer deaths than would have occurred if peak rates had persisted. This progress is driven by long-term declines in death rates for the 4 leading cancers (lung, colorectal, breast, prostate); however, over the past decade (2008-2017), reductions slowed for female breast and colorectal cancers, and halted for prostate cancer. In contrast, declines accelerated for lung cancer, from 3% annually during 2008 through 2013 to 5% during 2013 through 2017 in men and from 2% to almost 4% in women, spurring the largest ever single-year drop in overall cancer mortality of 2.2% from 2016 to 2017. Yet lung cancer still caused more deaths in 2017 than breast, prostate, colorectal, and brain cancers combined. Recent mortality declines were also dramatic for melanoma of the skin in the wake of US Food and Drug Administration approval of new therapies for metastatic disease, escalating to 7% annually during 2013 through 2017 from 1% during 2006 through 2010 in men and women aged 50 to 64 years and from 2% to 3% in those aged 20 to 49 years; annual declines of 5% to 6% in individuals aged 65 years and older are particularly striking because rates in this age group were increasing prior to 2013. It is also notable that long-term rapid increases in liver cancer mortality have attenuated in women and stabilized in men. In summary, slowing momentum for some cancers amenable to early detection is juxtaposed with notable gains for other common cancers.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Pathological complete response and long-term clinical benefit in breast cancer: the CTNeoBC pooled analysis.

            Pathological complete response has been proposed as a surrogate endpoint for prediction of long-term clinical benefit, such as disease-free survival, event-free survival (EFS), and overall survival (OS). We had four key objectives: to establish the association between pathological complete response and EFS and OS, to establish the definition of pathological complete response that correlates best with long-term outcome, to identify the breast cancer subtypes in which pathological complete response is best correlated with long-term outcome, and to assess whether an increase in frequency of pathological complete response between treatment groups predicts improved EFS and OS. We searched PubMed, Embase, and Medline for clinical trials of neoadjuvant treatment of breast cancer. To be eligible, studies had to meet three inclusion criteria: include at least 200 patients with primary breast cancer treated with preoperative chemotherapy followed by surgery; have available data for pathological complete response, EFS, and OS; and have a median follow-up of at least 3 years. We compared the three most commonly used definitions of pathological complete response--ypT0 ypN0, ypT0/is ypN0, and ypT0/is--for their association with EFS and OS in a responder analysis. We assessed the association between pathological complete response and EFS and OS in various subgroups. Finally, we did a trial-level analysis to assess whether pathological complete response could be used as a surrogate endpoint for EFS or OS. We obtained data from 12 identified international trials and 11 955 patients were included in our responder analysis. Eradication of tumour from both breast and lymph nodes (ypT0 ypN0 or ypT0/is ypN0) was better associated with improved EFS (ypT0 ypN0: hazard ratio [HR] 0·44, 95% CI 0·39-0·51; ypT0/is ypN0: 0·48, 0·43-0·54) and OS (0·36, 0·30-0·44; 0·36, 0·31-0·42) than was tumour eradication from the breast alone (ypT0/is; EFS: HR 0·60, 95% CI 0·55-0·66; OS 0·51, 0·45-0·58). We used the ypT0/is ypN0 definition for all subsequent analyses. The association between pathological complete response and long-term outcomes was strongest in patients with triple-negative breast cancer (EFS: HR 0·24, 95% CI 0·18-0·33; OS: 0·16, 0·11-0·25) and in those with HER2-positive, hormone-receptor-negative tumours who received trastuzumab (EFS: 0·15, 0·09-0·27; OS: 0·08, 0·03, 0·22). In the trial-level analysis, we recorded little association between increases in frequency of pathological complete response and EFS (R(2)=0·03, 95% CI 0·00-0·25) and OS (R(2)=0·24, 0·00-0·70). Patients who attain pathological complete response defined as ypT0 ypN0 or ypT0/is ypN0 have improved survival. The prognostic value is greatest in aggressive tumour subtypes. Our pooled analysis could not validate pathological complete response as a surrogate endpoint for improved EFS and OS. US Food and Drug Administration. Copyright © 2014 Elsevier Ltd. All rights reserved.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Conditional variable importance for random forests

              Background Random forests are becoming increasingly popular in many scientific fields because they can cope with "small n large p" problems, complex interactions and even highly correlated predictor variables. Their variable importance measures have recently been suggested as screening tools for, e.g., gene expression studies. However, these variable importance measures show a bias towards correlated predictor variables. Results We identify two mechanisms responsible for this finding: (i) A preference for the selection of correlated predictors in the tree building process and (ii) an additional advantage for correlated predictor variables induced by the unconditional permutation scheme that is employed in the computation of the variable importance measure. Based on these considerations we develop a new, conditional permutation scheme for the computation of the variable importance measure. Conclusion The resulting conditional variable importance reflects the true impact of each predictor variable more reliably than the original marginal approach.
                Bookmark

                Author and article information

                Contributors
                Journal
                Front Oncol
                Front Oncol
                Front. Oncol.
                Frontiers in Oncology
                Frontiers Media S.A.
                2234-943X
                05 January 2021
                2020
                : 10
                : 592556
                Affiliations
                [1] 1Department of Breast Surgery, The First Hospital, Jilin University , Changchun, China
                [2] 2Department of Oncological Gynecology, The First Hospital, Jilin University , Changchun, China
                [3] 3School of Information Science and Technology, Northeast Normal University , Changchun, China
                [4] 4Institute of Computational Biology, Northeast Normal University , Changchun, China
                Author notes

                Edited by: Hong Zhu, Zhejiang University, China

                Reviewed by: Hao Lin, University of Electronic Science and Technology of China, China; Tingting Li, Peking University, China

                *Correspondence: Han Wang, wangh101@ 123456nenu.edu.cn ; Ye Du, duye316@ 123456126.com

                This article was submitted to Pharmacology of Anti-Cancer Drugs, a section of the journal Frontiers in Oncology

                Article
                10.3389/fonc.2020.592556
                7813988
                33469514
                522d01db-6627-478f-8eb3-7801f8532c47
                Copyright © 2021 Song, Man, Jin, Li, Wang and Du

                This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

                History
                : 28 August 2020
                : 16 November 2020
                Page count
                Figures: 4, Tables: 4, Equations: 6, References: 33, Pages: 10, Words: 5107
                Funding
                Funded by: National Natural Science Foundation of China 10.13039/501100001809
                Award ID: 81773171
                Funded by: Department of Science and Technology of Jilin Province 10.13039/501100011789
                Award ID: 20170311005YY, 20200404197YY, 20200201349JC, 20180414006GH
                Funded by: Fundamental Research Funds for the Central Universities 10.13039/501100012226
                Award ID: 2412019FZ052
                Categories
                Oncology
                Original Research

                Oncology & Radiotherapy
                breast cancer,treatment efficacy prediction,decision-making,multiple classification,neoadjuvant chemotherapy

                Comments

                Comment on this article