scholarly journals Automatic BIRCH thresholding with features transformation for hierarchical breast cancer clustering

Author(s):  
Ahmad Alzu'bi ◽  
Maysarah Barham

<p>Breast cancer is one of the most common diseases diagnosed in women over the world. The balanced iterative reducing and clustering using hierarchies (BIRCH) has been widely used in many applications. However, clustering the patient records and selecting an optimal threshold for the hierarchical clusters still a challenging task. In addition, the existing BIRCH is sensitive to the order of data records and influenced by many numerical and functional parameters. Therefore, this paper proposes a unique BIRCH-based algorithm for breast cancer clustering. We aim at transforming the medical records using the breast screening features into sub-clusters to group the subject cases into malignant or benign clusters. The basic BIRCH clustering is firstly fed by a set of normalized features then we automate the threshold initialization to enhance the tree-based sub-clustering procedure. Additionally, we present a thorough analysis on the performance impact of tuning BIRCH with various relevant linkage functions and similarity measures. Two datasets of the standard breast cancer wisconsin (BCW) benchmarking collection are used to evaluate our algorithm. The experimental results show a clustering accuracy of 97.7% in 0.0004 seconds only, thereby confirming the efficiency of the proposed method in clustering the patient records and making timely decisions.</p>

Author(s):  
Viviane Veiga ◽  
Maria Luiza Campos ◽  
Carlos Roberto Lyra da Silva ◽  
Patrícia Henning ◽  
João Moreira

The world is experiencing a pandemic caused by the variant of the Coronavirus named SARS-CoV-2, causing the infectious disease COVID-19. Global actions are being carried out to combat this virus, including the Virus Outbreak Data Network (VODAN), which aims to establish a federated data infrastructure aligned with the FAIR principles and which supports the data collect from medical records of patients infected with high contagion. FIOCRUZ, which coordinates the GO FAIR Brazil Health network, took over the VODAN BR network in partnership with UNIRIO and UFRJ, with the participation of the hospitals Gaffrée and Guinle, Municipal São José and Israelita Albert Einstein. This article aims to present the national infrastructure aligned with the guidelines and the international network, for collecting and managing data from patient records, of these hospitals, infected with COVID-19, to establish an information model that supports the confrontation of this and other possible pandemics.


Author(s):  
Elma Elmika ◽  
Mateus Sakundarno Adi

Breast cancer is the most popular neither in advanced nor developing countries within case of 38 per 100,000 women. Breast cancer is still one of the health problems that occur in women in the world but does not rule out the possibility of men. This study aims to found the description of the age, and sex of breast cancer patients at Ibnu Sina Hospital Makassar. This research method was used a cross-sectional study with secondary data from medical records in 2018-2019 diagnosed with breast cancer. The data obtained of the number of annual cases, age, sex, and the number of cases that died. The results showed that in 2019, it was twice as high as 70.8% patients with a diagnosis of breast cancer, with an average age of 45-65 years, in female-dominated sex, but in this study there were 1.1 % male, the highest number of deaths occurred in 2018 with 12 cases 60.0%. The conclusion of this research is breast cancer are generally dominated from women but does not ruled out the possibility of occurring in the men, ages 45-65 who are middle-aged or elderly. So it is expected to always have a routine check as a preventative stage. Keywords: age; gender; breast cancer ABSTRAK Kanker payudara adalah kanker terbanyak di negara maju maupun negara berkembang dengan insiden 38 per 100.000 perempuan. Kanker payudara masih menjadi salah satu masalah kesehatan yang terjadi pada perempuan di dunia, namun tidak menutup kemungkinan terjadi pada laki-laki. Penelitian ini bertujuan mengetahui gambaran umur, dan jenis kelamin pasien kanker payudara di RS Ibnu Sina Makassar. Metode penelitian ini menggunakan cross-sectional dengan data sekunder rekam medis tahun 2018-2019 yang terdiagnosis kanker payudara. Data yang diperoleh yaitu jumlah kasus per tahun, umur, jenis kelamin, dan jumlah kasus meninggal. Hasil penelitian menunjukkan pada tahun 2019 dua kali lipat lebih tinggi dengan 70,8% pasien dengan terdiagnosis kanker payudara, dengan rata-rata usia 45-65 tahun, pada jenis kelamin didominasi oleh perempuan namun pada penelitian ini terdapat 1,1% berjenis kelamin laki-laki, kasus meninggal terbanyak yaitu pada tahun 2018 dengan 12 kasus 60,0%. Kesimpulan dari penelitian ini adalah kanker payudara umumnya di dominasi oleh perempuan namun tidak menutup kemungkinan terjadi pada laki-laki, usia 45-65 yang merupakan usia setengah baya atau lansia. Jadi diharapkan untuk selalu pemeriksaan rutin sebagai tahap pencegahan. Kata kunci: umur; jenis kelamin; kanker payudara


2016 ◽  
pp. 33-50
Author(s):  
Pier Giuseppe Rossi

The subject of alignment is not new to the world of education. Today however, it has come to mean different things and to have a heuristic value in education according to research in different areas, not least for neuroscience, and to attention to skills and to the alternation framework.This paper, after looking at the classic references that already attributed an important role to alignment in education processes, looks at the strategic role of alignment in the current context, outlining the shared construction processes and focusing on some of the ways in which this is put into effect.Alignment is part of a participatory, enactive approach that gives a central role to the interaction between teaching and learning, avoiding the limits of behaviourism, which has a greater bias towards teaching, and cognitivism/constructivism, which focus their attention on learning and in any case, on that which separates a teacher preparing the environment and a student working in it.


2020 ◽  
Vol 2 (1) ◽  
pp. 23-37
Author(s):  
Syarifudin Syarifudin

Each religious sect has its own characteristics, whether fundamental, radical, or religious. One of them is Insan Al-Kamil Congregation, which is in Cijati, South Cikareo Village, Wado District, Sumedang Regency. This congregation is Sufism with the concept of self-purification as the subject of its teachings. So, the purpose of this study is to reveal how the origin of Insan Al-Kamil Congregation, the concept of its purification, and the procedures of achieving its purification. This research uses a descriptive qualitative method with a normative theological approach as the blade of analysis. In addition, the data generated is the result of observation, interviews, and document studies. From the collected data, Jamaah Insan Al-Kamil adheres to the core teachings of Islam and is the tenth regeneration of Islam Teachings, which refers to the Prophet Muhammad SAW. According to this congregation, self-perfection becomes an obligation that must be achieved by human beings in order to remember Allah when life is done. The process of self-purification is done when human beings still live in the world by knowing His God. Therefore, the peak of self-purification is called Insan Kamil. 


2020 ◽  
Vol 1 (3) ◽  
pp. 49-56
Author(s):  
Feruza Mamatova ◽  

The present paper aims to compare the principles of choosing a marriage partner and analyse the status of being in the marrriage in the frame of family traditions that are totally inherent to the both of the nations: English and Uzbek. It is known that interconnection and cross-cultural communication between the countries of these two nationalities have been recently developed. The purpose to give an idea about these types of family traditions and prevent any misunderstanding that might occur in the communications makes our investigation topical one. The research used phraseological units as an object and the marriage aspects as the subject


2019 ◽  
Vol 95 (2) ◽  
pp. 231-245
Author(s):  
Erik Ode

Abstract De-Finition. Poststructuralist Objections to the Limitation of the Other The metaphysic tradition always tried to structure the world by definitions and scientific terms. Since poststructuralist authors like Derrida, Foucault and Deleuze have claimed the ›death of the subject‹ educational research cannot ignore the critical objections to its own methods. Definitions and identifications may be a violation of the other’s right to stay different and undefined. This article tries to discuss the scientific limitations of the other in a pedagogical, ethical and political perspective.


2018 ◽  
Vol 28 (1) ◽  
pp. 73-78
Author(s):  
Venelin Terziev ◽  
Marin Georgiev

The subject of this article is the genesis of the professional culture of personnel management. The last decades of the 20th century were marked by various revolutions - scientific, technical, democratic, informational, sexual, etc. Their cumulative effect has been mostly reflected in the professional revolution that shapes the professional society around the world. This social revolution has global consequences. In addition to its extensive parameters, it also has intensive ones related to the deeply-rooted structural changes in the ways of working and thinking, as well as in the forms of its social organization. The professional revolutions in the history of Modern Times stem from this theory.Employees’ awareness and accountability shall be strengthened. The leader must be able to formulate and bring closer to the employees the vision of the organization and its future goal, to which all shall aspire. He should pay attention not to the "letter" but to the "spirit" of this approach.


2020 ◽  
Vol 14 (3) ◽  
pp. 459-464
Author(s):  
Alevtina Vasilevna Kamitova ◽  
Tatyana Ivanovna Zaitseva

The paper reflects the specificity of the fundamental ideas of the artistic world of M. G. Atamanov, which includes a wide range of literary facts from the content level of the text of the works to their poetics. A particularly important role in the works of M. G. Atamanov is played by cross-cutting themes and images that reflect the author's individual style and his idea of national-ethnic identity. The subject of the research is the book of essays “Mon - Udmurt. Maly mynym vös’?” (“I am Udmurt. Why does it hurt?”), which most vividly reflected the main spiritual and artistic searches of M. G. Atamanov, associated with his ideas about the Udmurt people. The main motives and plots of the works included in the book under consideration are accumulated around the concept of “Udmurtness”. The comprehension of “Udmurtness” is modeled in his essays through specific leit themes: native language, Udmurt people, national culture, mentality, geographic and topographic features of the Udmurt people’ places of residence, the Orthodox idea. The “Udmurt theme” is recognized and comprehended by the writer through the prism of national identity.


2019 ◽  
Vol 65 (5) ◽  
pp. 664-671
Author(s):  
Ilya Pyatnitskiy ◽  
O. Puchkova ◽  
Viktor Gombolevskiy ◽  
Lyudmila Nizovtsova ◽  
Natalya Vetsheva ◽  
...  

The article presents a literature review of the PubMed database and the Cochrane library, aimed at analyzing the current situation and problems in the field of breast cancer screening in the world and Russia to form an idea of the key elements in organizing an effective screening program in the Russian healthcare system, as well as the possibilities of using new technologies when organizing such programs.


Author(s):  
B. Mathura Bai ◽  
N. Mangathayaru ◽  
B. Padmaja Rani ◽  
Shadi Aljawarneh

: Missing attribute values in medical datasets are one of the most common problems faced when mining medical datasets. Estimation of missing values is a major challenging task in pre-processing of datasets. Any wrong estimate of missing attribute values can lead to inefficient and improper classification thus resulting in lower classifier accuracies. Similarity measures play a key role during the imputation process. The use of an appropriate and better similarity measure can help to achieve better imputation and improved classification accuracies. This paper proposes a novel imputation measure for finding similarity between missing and non-missing instances in medical datasets. Experiments are carried by applying both the proposed imputation technique and popular benchmark existing imputation techniques. Classification is carried using KNN, J48, SMO and RBFN classifiers. Experiment analysis proved that after imputation of medical records using proposed imputation technique, the resulting classification accuracies reported by the classifiers KNN, J48 and SMO have improved when compared to other existing benchmark imputation techniques.


Sign in / Sign up

Export Citation Format

Share Document