Reduction of Variables for Predicting Breast Cancer Survivability Using Principal Component Analysis

Hussain, Sharaf; Quazilbash, Naveen Zehra; Bai, Samita; Khoja, Shakeel

doi:10.1109/cbms.2015.62

Cited by 8 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, Solti and Zhai [27] conducted a study that also supports the effectiveness of tree-based algorithms in predicting ten-year survival rates in breast cancer. In contrast, researchers in [28] employed Principal Component Analysis (PCA) as a technique for reducing the dimensionality of the SEER data spanning the years 1973-2010. The researchers discovered that by reducing the 14 cancer-related Surveillance, Epidemiology, and End Results (SEER) attributes to five components, which accounted for 98…”

Section: A Prediction Of Survivabilitymentioning

confidence: 99%

Survival-Based Treatment Planning Using Stage-Specific Machine Learning Models

Farrag,

Fadlullah,

Fouda

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The significance of prognostic survivability in determining optimal treatment strategies for critical illnesses is widely acknowledged. However, there has been a lack of emphasis on the advancement of treatment planning models based on survival outcomes within clinical decision support systems. The research presented in this paper proposes an innovative framework for the planning of treatment strategies based on survival outcomes in the context of multi-stage diseases, with the aim of effectively tackling this issue. Our proposed system aims to predict a comprehensive list of treatment combinations for cancer patients, specifically focusing on their expected survival outcomes. The proposed solution aims to enhance the decision-making process of medical professionals by providing them with comprehensive and comprehensible treatment recommendations. To conduct survivability classification and regression analysis for patients with identical cancer stages, a two-step approach is employed. This involves the development of stage-specific Machine Learning models using breast cancer data that includes treatment information. Based on a real dataset on cancer patients, we aim to investigate the performance of the models under different balancing strategies. Our contribution in this work is the formulation of a treatment planning inference system, which focuses on prognostic considerations. This system utilizes patient data and estimates the survivability associated with each treatment plan in order to predict the recommended course of action. This facilitates the integration of the developed survival prediction models into the process of treatment planning. Ultimately, the system generates visual representations that illustrate the comparative significance of different features, as well as the decision-making process employed by the model in order to yield easily comprehensible outcomes for a specific patient. The study presents experimental findings that illustrate the efficacy of our proposed framework in the domains of treatment planning and survival estimation.

show abstract

Section: A Prediction Of Survivabilitymentioning

confidence: 99%

Survival-Based Treatment Planning Using Stage-Specific Machine Learning Models

Farrag,

Fadlullah,

Fouda

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Dengan ini berarti data dengan ruang yang lebih banyak dikurangi ke ruang yang lebih rendah/sedikit. Dengan demikian, PCA merupakan suatu teknik seleksi data multivariat (multivariable) yang mengubah atau mentranformasi suatu matriks data original menjadi suatu kumpulan kombinasi homogen yang lebih sedikit namun menyerap sejumlah besar varian dari data awal [3]. Tujuan utamanya ialah mendefinisikan sebanyak mungkin jumlah keragaman data original dengan seminim mungkin principal component [4]…”

Section: Pendahuluanunclassified

PENERAPAN PRINCIPAL COMPONENT ANALYSIS (PCA) DALAM PENENTUAN FAKTOR DOMINAN YANG MEMPENGARUHI PRESTASI BELAJAR SISWA (Studi Kasus : SMK Raksana 2 Medan)

Nasution

2019

JurTI

View full text Add to dashboard Cite

- School is one of the facilities in the implementation and development of education. SMK Raksana 2 Medan is one of the best schools in North Sumatra. With differing abilities, students differ in their level of achievement. There are several factors that greatly affect student learning achievement, among others: talent, interest, student motivation, parental motivation, home learning facilities, quality teaching from teachers, school facilities, extracurricular, additional tutoring and student association. This study aims to simplify and reduce these factors so as to obtain dominant factors that influence student learning achievement by using Principal Component Analysis (PCA). The study was conducted by collecting data through questionnaires to respondents or research samples. Finally to obtain 3 factors: The main factor (PC1) has an eigenvalue of 3.11 with a variance of 31%. The supporting factor (PC2) has an eigenvalue of 1.50 with a variance of 15%. The additional factor (PC3) has an eigenvalue of 1.16 with a variance of 12%. The overall factor gives a cumulative diversity proportion of 57.70%, meaning that the three factors according to the perceptions of students who are respondents in this study can influence student achievement at SMK Raksana 2 Medan at 57.70%.Keywords - Education, Achievement, Principal Component Analysis, Eigenvalue, Factor Analysis Abstrak - Sekolah merupakan salah satu sarana dalam penyelenggaraan dan pengembangan pendidikan. SMK Raksana 2 Medan merupakan salah satu sekolah yang memiliki banyak prestasi terbaik di Sumatera Utara. Dengan berbeda-bedanya kemampuan siswa maka berbeda pula tingkat prestasinya. Terdapat beberapa faktor yang sangat mempengaruhi prestasi belajar siswa, antara lain: bakat, minat, motivasi siswa, motivasi orang tua, fasilitas belajar dirumah, kualitas pengajaran dari guru, fasilitas sekolah, ekstrakullikuler, les tambahan dan pergaulan siswa. Penelitian ini bertujuan untuk menyederhanakan dan mereduksi faktor – faktor tersebut sehingga memperoleh faktor dominan yang mempengaruhi prestasi belajar siswa dengan menggunakan metode analisis Principal Component Analysis (PCA). Penelitian dilakukan dengan mengumpulkan data melalui kuesioner kepada responden atau sampel penelitian yaitu siswa/i kelas X dan XI SMK Raksana 2 Medan, Sehingga diperoleh 3 faktor yaitu: faktor utama (PC1) memiliki nilai eigenvalue sebesar 3.11 dengan jumlah varians sebesar 31%. Faktor pendukung (PC2) memiliki nilai eigenvalue sebesar 1.50 dengan jumlah varians sebesar 15%. Faktor tambahan (PC3) memiliki nilai eigenvalue sebesar 1.16 dengan jumlah varians sebesar 12%. Keseluruhan faktor memberikan proporsi keragaman kumulatif sebesar 57.70%, artinya ketiga faktor tersebut menurut persepsi siswa/i yang menjadi responden dalam penelitian ini dapat mempengaruhi prestasi belajar siswa/i di SMK Raksana 2 Medan sebesar 57.70%. Kata Kunci - Pendidikan, Prestasi, Principal Component Analysis, Nilai Eigen, Faktor Analisis

show abstract

“…In brief, Principal Component Analysis is a method for selecting multiple variables (multivariables) from a data set. This method converts the original data matrix into a set of homogeneous combinations that are smaller but can accommodate a greater number of variations than the original data matrix (Hussain et al, 2015). The primary objective is to identify the most amount of the original data's variability with the fewest number of principal components as is humanly practicable (Dang, et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Validity Test Using Principal Component Analysis (PCA) Involving Research Instruments on Learner-Centeredness, Knowledge-Centeredness, and Assessment-Centeredness

Ismail¹,

Yoestara²

2022

proceeding

View full text Add to dashboard Cite

Instrument is an important element in research, including in educational research. In measuring learning environment formed in a teaching process, discrete variables need to be involved. Thence, understanding that teaching-learning process has varied pedagogical outcome(s), teachers and instructors can focus on their teaching orientation—learner-centeredness, knowledge-centeredness, or assessment-centeredness—and can avoid zoning-out of context during teaching with these factorial discrete variables. There are 15 factors determining the centeredness propensity in a research instrument developed based on Bransfrod et al. (2001). This study aims to simplify and reduce these factors to obtain dominant factors that influence the centeredness in a learning environment by using Principal Component Analysis (PCA). The study was conducted by collecting data through questionnaires to 10 respondents. Finally, 5 major factors were obtained. The main factor has an Eigenvalue of 3.95 with a variance of 26.38%. The second factor has an Eigenvalue of 3.51 with a variance of 23.43%. The third factor has an Eigenvalue of 2.46 with a variance of 16.44%. The fourth factor has an Eigenvalue of 1.95 with a variance of 12.99%. The fifth factor has an Eigenvalue of 1.10 with a variance of 7.37%. The overall factor gives a cumulative diversity proportion of 86.64%. Keywords: Construct validity, Assessment, Eigenvalue, and Principal Component Analysis.

show abstract

Reduction of Variables for Predicting Breast Cancer Survivability Using Principal Component Analysis

Cited by 8 publications

References 2 publications

Survival-Based Treatment Planning Using Stage-Specific Machine Learning Models

Survival-Based Treatment Planning Using Stage-Specific Machine Learning Models

PENERAPAN PRINCIPAL COMPONENT ANALYSIS (PCA) DALAM PENENTUAN FAKTOR DOMINAN YANG MEMPENGARUHI PRESTASI BELAJAR SISWA (Studi Kasus : SMK Raksana 2 Medan)

Validity Test Using Principal Component Analysis (PCA) Involving Research Instruments on Learner-Centeredness, Knowledge-Centeredness, and Assessment-Centeredness

Contact Info

Product

Resources

About