The opportunity that Artificial Intelligence has to reduce breast cancer mortality
Breast cancer represents an urgent global priority. Breast Cancer cancer is the most common tumor globally and the leading cause of death in women worldwide due to cancer. With over 210,000 new diagnoses and over 68,000 lives lost annually, breast cancer is a growing onset epidemic in the healthcare landscape of Latin America. The World Health Organization (WHO) emphasizes the importance of finding methods to improve the early detection of breast cancer and thus increase the survival rate worldwide.
Types Of Breast Cancer
Breast cancer can be categorized into invasive and non-invasive types. Non-invasive breast cancer remains confined to the lobules or ducts where it originated, such as lobular carcinoma within the mammary lobes or ductal carcinoma in situ within the mammary ducts. Invasive breast cancer occurs when abnormal cells break away from the lobules or milk ducts and spread to nearby breast tissues or other body parts through the immune system or systemic circulation. Common sites of metastasis include the brain, bones, lungs, and liver.
?
Breast Cancer In LATAM
Breast cancer poses significant challenges in Latin America,? particularly concerning early diagnosis and access to evidence-based, multidisciplinary treatment alternatives. The disease affects women in Latin America at a younger age compared to Europe or North America, yet routine mammograms are not commonly performed in most hospitals. Approximately 115,000 women are diagnosed with breast cancer yearly in Latin America, resulting in 37,000 deaths.?
Incidence and mortality rates have steadily increased over the past few decades, influenced by various risk factors, including demographics, socioeconomics, genetics, and lifestyle choices.?
The 5-year survival rate in Latin America is around 70%, considerably lower than the over 80% achieved in North America and Europe due to improved treatments and earlier diagnosis. Early diagnosis plays a crucial role in breast cancer survival, with the European Union leading in this regard with a 90% early diagnosis rate. Latin America's average early diagnosis rate is between 60% and 70%, with countries like Peru, Colombia, and Mexico detecting 50% of cases at advanced stages.?
The costs associated with breast cancer diagnosis and treatment are directly linked to the disease's stage, with stage IV patients in Latin America facing three to four times higher costs than stage I patients. Insufficient funding and limited resources result in suboptimal diagnosis and treatment for some patients, contributing to higher morbidity and mortality rates and further burdening healthcare systems. Although healthcare spending in Latin America falls short of European and US standards, efforts are underway to expand universal health access with the involvement of the private sector.
Breast cancer diagnosis, early detection and screening
Unquestionably, short of prevention, the most important prognostic element for breast cancer is an early diagnosis. A timely diagnosis has a positive impact on the final outcome of the disease. Late-stage diagnosis of breast cancer is more frequent in low- and middle-income countries, less than 50% of the cases diagnosed are categorized in stages I and II.?
Even if screening mammographs reduce the proportion of higher stage at diagnosis and have demonstrated reduction in breast cancer mortality, screening programs may not be ideally applicable to resource-limited healthcare systems. Screening programs require high investments, are difficult to implement and naturally involve a large number of patients. Thus, early detection of breast cancer is an important challenge, especially in? low- and middle-income countries.
领英推荐
Artificial Intelligence in Breast Cancer detection and Treatment?
AI has great potential in breast cancer research and diagnosis. One study by Kallenberg et al. utilized a sparse convolutional autoencoder to classify mammographic images of breast cancer patients and healthy individuals, achieving promising case classification performance. Another study by Gastounioti et al. employed convolutional neural networks to analyze radiomic feature maps derived from mammographic images, improving breast cancer risk prediction compared to conventional methods. Overall, the screenings supported by AI resulted in 20% cancers detected compared with 5 per 1,000 with the standard approach.
AI has also been focused on early detection, addressing the high rate of false positives and negatives in mammogram interpretation. McKinney et al. developed an AI program that outperformed human radiologists in predicting breast cancer, reducing reading workload by 44% and increasing accuracy. Additionally, computer-aided diagnosis (CAD) systems based on AI have assisted clinicians in decision-making. Conan et al. demonstrated that using an AI-based CAD system improved radiologists' reading accuracy and reduced reading time for breast cancer detection. The researchers calculated that if radiologists read about 50 mammograms an hour, it would have taken a single radiologist four to six months less to read about 40,000 screening exams with the help of AI than it would take two radiologists alone.
The application of AI in breast cancer research and diagnosis holds significant promise for improving outcomes. These AI systems can learn from large datasets and identify patterns and features that may not be easily recognizable to human observers. By analyzing mammographic images and other patient data, AI algorithms can enhance the accuracy of breast cancer detection, risk prediction, and decision-making. The use of AI-based tools has the potential to reduce false positives and negatives, leading to more precise diagnoses and early interventions.?
How does Arkangel solve these challenges??
Accurate diagnosis and treatment of breast cancer can be challenging due to limited clinical data and the complexity of the disease. However, with the integration of advanced image analysis techniques, we can revolutionize the approach to breast cancer care.?
At Arkangel AI, we utilize comprehensive clinical and operative data, including images, to improve diagnostic accuracy and enhance clinical outcomes for patients with breast cancer. By leveraging the power of artificial intelligence and machine learning, our software analyzes images related to breast cancer. It identifies patterns and risk factors that may contribute to the development of the disease. This enables healthcare professionals to make more accurate and personalized diagnoses, improving treatment plans and patient outcomes. AI caused a 21% (868/4104 cases) increase in the number of examinations with abnormal interpretation. Moreover, AI would save 100?000 radiologist reads while increasing consensus discussion.
Furthermore, AI-powered predictive analytics can assist healthcare providers in making informed decisions regarding patient care and prognosis. AI can predict disease progression and patient outcomes by analyzing various patient factors, such as medical history, genetic information, and lifestyle. This information helps healthcare professionals optimize treatment strategies, allocate resources effectively, and provide proactive interventions for individuals at higher risk of developing breast cancer.
Takeaways
Do you want to learn more about how you can also apply AI to detect early Breast Cancer? Get a consultation with us!
References