Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Majalah Kesehatan FKUB Indonesian Journal of Cancer
Amalia, Nurlinah
Unknown Affiliation
Biochemistry, Genetics & Molecular Biology Immunology & microbiology Medicine & Pharmacology Public Health

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
HUBUNGAN BODY MASS INDEX DENGAN DENSITAS PARENKIM PAYUDARA DARI PEMERIKSAAN MAMOGRAFI Amalia, Nurlinah; Aurora, Habiba; Siswidiyati
Majalah Kesehatan Vol. 10 No. 4 (2023): Majalah Kesehatan
Publisher : Faculty of Medicine Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21776/majalahkesehatan.2023.010.04.3

Abstract

Body Mass Index (BMI) merupakan prediktor komposisi tubuh yang membandingkan tinggi badan dan berat badan. Peningkatan BMI sering digunakan sebagai penanda bahwa banyak deposit lemak pada tubuh, salah satunya di payudara. BMI dihubungkan dengan kemungkinan terjadinya perubahan densitas parenkim payudara yang merupakan prediktor terkuat kejadian tumor payudara. Oleh karena itu, penelitian ini bertujuan untuk mengetahui hubungan BMI dengan densitas parenkim payudara dari pemeriksaan mamografi. Penelitian ini bersifat analitik observasional dengan menggunakan metode cross sectional yang dilakukan pada 27 subjek penelitian yang berasal dari Perhimpunan Radiografer Indonesia (PARI) dan kelompok Dharma Wanita Universitas Brawijaya di RSUD dr. Saiful Anwar. Berdasarkan hasil penelitian didapatkan bahwa BMI memiliki hubungan yang signifikan dengan densitas parenkim payudara (Kruskal wallis, p=0,010) dan BMI berkorelasi negatif dengan densitas parenkim payudara (Spearman, p=0,000) dengan nilai correlation coefficient bersifat kuat (-0,626). Kesimpulan dari penelitian ini adalah BMI berkorelasi negatif dengan densitas parenkim payudara.
Potential Efficacy of Artificial Intelligence in Mammography for Breast Cancer Screening: Current Evidence from Meta-Analysis Amalia, Nurlinah; Nurdiana, Farah; Pradyaputri, Naura Shafa
Indonesian Journal of Cancer Vol 19, No 4 (2025): December
Publisher : http://dharmais.co.id/

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33371/ijoc.v19i4.1353

Abstract

Background: Artificial intelligence (AI), an advancing field of data science, has been applied in mammography screening for early detection of breast cancer in an effort to enhance screening participants' outcomes. Screening is crucial to halting the spread of breast cancer. These days, mammography is typically used in screenings conducted by radiologists. Therefore, alternative diagnostic methods are needed to provide a diagnostic solution that is efficient in terms of both time and resources. This review aims to evaluate the accuracy of AI applications in radiology, specifically in mammographic image interpretation, to determine whether AI can serve as an evidence-based recommendation for breast cancer screening. Methods: We conducted a systematic review and meta-analysis following the PRISMA guidelines. Literature searches were performed across multiple databases, including PubMed, ScienceDirect, and SpringerLink. The inclusion criteria were based on the PICOs framework, focusing on individuals at risk of breast cancer undergoing mammographic screening, where AI was used to interpret the images and compared to a radiologist. Exclusion criteria included studies involving patients with diagnosed breast cancer, non-human studies, non-English, books, paid articles, and review articles. The primary outcomes of interest were the sensitivity and specificity of AI in detecting breast cancer from mammograms. Meta-analysis was conducted using STATA software, while the Quality Assessment of Diagnostic Accuracy Studies (QUADAS) tool was employed to evaluate study qualityResults: A total of 2,412,102 mammograms from twenty-six studies were included in this analysis. The results indicated that AI demonstrated moderate sensitivity [84% (99.92% CI: 99.91 – 99.92)] and specificity [87% (99.97% CI: 99.97 – 99.97)] with a p-value (0.001). Conclusions: These results suggest that AI has potential as a breast cancer diagnosis tool in the future. Radiologists can become more accurate with AI algorithms, which are useful for screening, cutting down on unnecessary recall rates, and reducing effort.
Co-Authors Habiba Aurora Nurdiana, Farah Pradyaputri, Naura Shafa Siswidiyati