Application of Artificial Intelligence (AI) System in Opportunistic Screening and Diagnostic Population in a Middle-income Nation
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Artificial intelligence (AI) in mammography shows effectiveness in diverse populations, comparable to traditional methods. AI enhances diagnostic accuracy and reduces unnecessary biopsies, improving breast lesion diagnosis efficiency.
Area Of Science
- Radiology and Medical Imaging
- Artificial Intelligence in Healthcare
- Oncology
Background
- Mammography is a key tool for breast cancer screening, with AI showing promise in improving diagnostic performance.
- Validation of AI in mammography has primarily occurred in high-income nations.
- This study addresses the need to evaluate AI effectiveness in a middle-income, multi-ethnic population.
Purpose Of The Study
- To evaluate the effectiveness of artificial intelligence (AI) in mammography within a diverse population in a middle-income nation.
- To compare the diagnostic performance of AI-assisted mammography with traditional interpretation methods.
- To assess AI's impact on breast density and BI-RADS category assessments.
Main Methods
- A retrospective analysis of 543 mammograms from a diverse Malaysian population (Malays, Chinese, Indians).
- Independent interpretation by three breast radiologists, with and without AI support, assessing breast density and BI-RADS categories.
- Comparison of accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) between AI-assisted and traditional readings.
Main Results
- AI demonstrated substantial agreement with radiologists in density (κ=0.606) and BI-RADS assessment (κ=0.74).
- AI performance was comparable to traditional methods, with sensitivity, specificity, PPV, and NPV values for radiologist+AI at 81.0%, 93.1%, 55.5%, and 97.0%.
- AI enhanced lesion diagnosis accuracy and reduced unnecessary biopsies, particularly for BI-RADS 4 lesions, with similar performance to 2D mammography (AUC 0.925 vs 0.871).
Conclusions
- AI software can assist in accurate breast lesion diagnosis, improving efficiency in mixed opportunistic screening and diagnostic settings.
- AI integration did not negatively impact radiologists' performance, showing substantial inter-reader agreement.
- AI in mammography shows potential for improved diagnostic accuracy and reduced unnecessary biopsies in diverse populations.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
Related Concept Videos
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Disease surveillance is the systematic collection, analysis, and interpretation of health data essential to the planning, implementation, and evaluation of public health practice. This process integrates data dissemination to entities responsible for preventing and controlling disease, injury, and disability. Surveillance systems provide crucial information for action, helping public health authorities make informed decisions to manage and prevent outbreaks, ensure public safety, optimize...