scholarly journals Penerapan dan Perbandingan Tiga Metode Analisis Pohon Keputusan pada Klasifikasi Penderita Kanker Payudara

2021 ◽  
Vol 1 (1) ◽  
pp. 19-27
Author(s):  
Jody Alwin irawadi ◽  
Siti Sunendiari
Keyword(s):  
Breast Cancer ◽  
Data Mining ◽  
Survival Analysis ◽  
Decision Tree ◽  
Cancer Patients ◽  
Total Error ◽  
Breast Cancer Patients ◽  
Total Error Rate ◽  
Decision Tree Classification ◽  
Exhaustive Chaid

Abstract. Today there is a considerable amount of work dealing with decision trees, especially in survival analysis (Ibrahim et al, 2008). Cases classified as survival analysis, like cancer patients.  This study discusses the application of data mining which is to obtain diagnostic results.  The classification technique uses information obtained from medical records of breast cancer patients in Yugoslavia.  A method for answering these problems through decision tree analysis using the CHAID, Exhaustive CHAID and CART methods.  Empirically aiming to compare performance of three decision tree classification methods so that the best method is obtained.  It was concluded that best method used in applying to the classification of breast cancer sufferers was the CART method because it was able to get the most significant variables at most four, namely inv-node, tumor size, deg-malig and breast parts.  Then it has a total accuracy rate with highest value of 84.9 percent and has a total error rate with lowest value of 15.1 percent. Abstrak. Dewasa ini ada cukup banyak pekerjaan yang berurusan dengan pohon keputusan, terutama dalam analisis survival (Ibrahim dkk, 2008). Kasus yang tergolong analisis survival seperti penderita penyakit kanker. Penelitian ini membahas mengenai penerapan data mining yang digunakan untuk mendapatkan hasil diagnostik. Pendekatan teknik klasifikasi dengan menggunakan informasi yang diperoleh pada rekam medis data penderita kanker payudara di Yugoslavia. Salah satu metode untuk menjawab permasalahan tersebut melalui analisis pohon keputusan dengan metode CHAID, Exhaustive CHAID dan CART. Secara empiris bertujuan untuk membandingkan kinerja tiga metode pengklasifikasi pohon keputusan agar didapatkan metode manakah yang terbaik. Maka disimpulkan bahwa metode terbaik yang digunakan dalam penerapan pada klasifikasi penderita kanker payudara adalah metode CART sebab mampu mendapatkan variabel signifikan yang paling banyak ada empat, yakni inv-node, ukuran tumor, deg-malig dan bagian payudara. Kemudian memiliki tingkat akurasi total dengan nilai tertinggi sebesar 84.9 persen dan memiliki total tingkat kesalahan dengan nilai yang terendah sebesar 15.1 persen.

scholarly journals Survival analysis of breast cancer patients in Yogyakarta

2021 ◽  
Vol 1722 ◽  
pp. 012060
Author(s):  
M. Ivan Ariful Fathoni ◽  
Gunardi ◽  
Fajar Adi-Kusumo ◽  
Susanna Hilda Hutajulu
Keyword(s):  
Breast Cancer ◽  
Survival Analysis ◽  
Cancer Patients ◽  
Breast Cancer Patients

A decision tree to predict four or more positive axillary lymph nodes in breast cancer patients with positive sentinel node biopsy: Determining necessity for regional nodal irradiation in the absence of axillary dissection

2009 ◽  
Vol 27 (15_suppl) ◽  
pp. e11540-e11540
Author(s):  
R. A. Macrorie-Fairweather ◽  
K. Albuquerque ◽  
K. Yao ◽  
J. Sinacore
Keyword(s):  
Breast Cancer ◽  
Decision Tree ◽  
Lymph Nodes ◽  
Cancer Patients ◽  
Axillary Lymph Nodes ◽  
P Value ◽  
Axillary Lymph ◽  
Breast Cancer Patients ◽  
Regional Nodal Irradiation ◽  
Interaction Detection

e11540 Background: Regional nodal irradiation (RNI) is indicated for breast cancer patients with ≥ 4 positive axillary lymph nodes (ALN). The need for RNI is unclear for women with T1–2 tumors and 1–3 positive sentinel lymph nodes (SLN) who don’t undergo axillary lymph node dissection (ALND). In an effort to guide clinician decision-making and potentially spare patients combined toxicities of ALND and radiation, the purpose of this study was to create a decision tree of clinicopathologic variables to predict patients with ≥ 4 positive ALN. Methods: We reviewed the records of 197 women with T1–2 tumors and 1–3 positive SLN. All patients underwent a complete ALND to determine the number of positive ALN. The patients were divided into 2 groups: < 4 or ≥ 4 positive ALN. Ten clinicopathologic predictive variables were identified for analysis: patient age, size of tumor, histological type, tumor grade, number of metastatic SLN, largest SLN metastasis size, detection method, estrogen receptor, Ki67 and lymphovascular invasion (LVI). The analysis used Chi-Square Automatic Interaction Detection (CHAID SPSS), a non-parametric, stepwise “regression tree” analysis, with Bonferroni adjusted p-values to create a decision tree. Results: 141 (72%) patients had < 4 and 56 (28%) had ≥ 4 positive ALN. Three variables were selected into the CHAID tree based upon maximum predictability: LVI, the number of metastatic SLNs, and largest SLN metastasis size. 100% of patients (N=42) had < 4 positive ALN if negative for LVI and had only 1 positive SLN with a metastasis size < 0.2cm (p-value < 0.0432). For patients with LVI (N=77), 13 of 14 (93%) had < 4 positive ALN if the SLN metastasis size was ≤ 0.2cm (p < .0014). The highest prevalence of ≥ 4 positive ALN were patients with LVI and a SLN metastasis size > 0.2cm. Conclusions: The CHAID analysis more accurately predicted patients with < 4 positive ALN compared to those with ≥4. The decision tree provides a new tool for the clinician to determine the necessity for RNI without ALND. No significant financial relationships to disclose.

Guideline adherence and clinical outcome in vulnerable and healthy breast cancer patients: Results of a prospective cross-sectional study in Germany.

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. e18132-e18132
Author(s):  
Elna Kuehnle ◽  
Wulf Siggelkow ◽  
Iris Schrader ◽  
Kristina Luebbe ◽  
Stefanie Noeding ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Survival Analysis ◽  
Clinical Outcome ◽  
Cancer Patients ◽  
Guideline Adherence ◽  
Cross Sectional Study ◽  
Breast Cancer Patients ◽  
Sectional Study ◽  
Cross Sectional ◽  
Vulnerable Patients

e18132 Background: In 2003 the German Cancer Society and the German Society for Breast Disease introduced a number of Quality Indicators (QIs) to improve standards of breast cancer care. Although QIs should be based on clinical evidence, evidence for important subpopulations (i.e. vulnerable patients) is often limited. In this prospective cross-sectional study we assessed conformity and non-conformity of guidelines and their impact on clinical outcome in a real-world setting. Methods: This prospective analysis included patients with primary breast cancer. Patients with stage IV and recurrent breast cancer were excluded. Data was collected from 2012-2016 in six certified breast care centers using a personal questionnaire and data from the patients' medical records. Guideline adherence to a set of 11 QIs was explored. Overall survival (OS) and disease free survival (DFS) were correlated with fulfillment of QIs and tumor characteristics. Results: Survival analysis was conducted in 2390 patients with a median follow-up of 16 months. 88 (4%) patients had a recurrent disease. 31 (1.3%) patients died of breast cancer. Tumor stage, grading, Her2- and hormone receptor status and Ki-67 correlated with DFS and OS. 1725/1907 patients (90.5%) received a guideline adherent treatment. The most prevalent reasons for non-conformity were old age (24.7%) and/or comorbidity (20.9%). Breast cancer specific DFS and OS were not significantly different between patients treated adherent or not adherent to the guidelines. In contrast, survival analysis of death other than breast cancer showed a significantly worse OS (p = 0.006) for patients not treated according to guideline recommendation. Conclusions: Conformity of clinical guidelines was observed in the majority of patients including healthy and vulnerable patients. These patients tended to have a longer breast cancer specific survival. Patients who were not considered suitable for guideline-adherent therapy died more often from other medical reasons rather than from breast cancer. In our study 10% of the patients had a limited life expectancy due to old age and co-morbidities with no assumed benefit from guideline adherence.

Long-term survival analysis of breast cancer patients treated with neoadjuvant chemotherapy

2016 ◽  
Vol 42 (5) ◽  
pp. S13
Author(s):  
Asma Munir ◽  
Sujatha Udayasankar ◽  
Anita Huws ◽  
Gill Dazeley ◽  
Yousef Sharaiha ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Survival Analysis ◽  
Neoadjuvant Chemotherapy ◽  
Cancer Patients ◽  
Breast Cancer Patients ◽  
Term Survival ◽  
Long Term Survival

A Novel Data Mining on Breast Cancer Survivability Using MLP Ensemble Learners

2019 ◽  
Vol 63 (3) ◽  
pp. 435-447
Author(s):  
Mohsen Salehi ◽  
Jafar Razmara ◽  
Shahriar Lotfi
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Data Mining ◽  
Cancer Patients ◽  
Cancer Incidence ◽  
The United States ◽  
Machine Learning Techniques ◽  
Breast Cancer Patients ◽  
Stacked Generalization ◽  
Learning Techniques

Abstract Breast cancer survivability has always been an important and challenging issue for researchers. Different methods have been utilized mostly based on machine learning techniques for prediction of survivability among cancer patients. The most comprehensive available database of cancer incidence is SEER in the United States, which has been frequently used for different research purposes. In this paper, a new data mining has been performed on the SEER database in order to investigate the ability of machine learning techniques for survivability prediction of breast cancer patients. To this end, the data related to breast cancer incidence have been preprocessed to remove unusable records from the dataset. In sequel, two machine learning techniques were developed based on the Multi-Layer Perceptron (MLP) learner machine including MLP stacked generalization and mixture of MLP-experts to make predictions over the database. The machines have been evaluated using K-fold cross-validation technique. The evaluation of the predictors revealed an accuracy of 84.32% and 83.86% by the mixture of MLP-experts and MLP stacked generalization methods, respectively. This indicates that the predictors can be significantly used for survivability prediction suggesting time- and cost-effective treatment for breast cancer patients.

Sign in / Sign up

Export Citation Format

Share Document