Video playback experienced delays and failures, including content not loading, frozen ads, and incomplete ad loading. Additionally, there were issues with excessive volume on ads and various other problems, such as ads not loading, ads affecting page loading, content shifting during ad loading, and repetitive ads. In a new early-stage study, artificial intelligence (AI) outperformed doctors with years of training and experience in detecting breast cancers and reduced doctors' workload in reading mammograms by almost half. However, it is important to note that AI determining cancer presence in patients is not currently a reality. Further research is still needed. The study, published in The Lancet Oncology, demonstrated the safety and potential effectiveness of AI for breast cancer detection. Previous studies have focused on AI's ability to predict breast cancer risk using models or retrospective data analysis. This study is believed to be the first randomized control trial to compare AI-assisted breast cancer detection with human detection by well-trained radiologists. It analyzed scans from over 80, 000 women in Sweden who underwent mammograms between April 2021 and July 2022. Half of the participants had their mammograms read by AI before being reviewed by a radiologist, while the other half were assessed by two radiologists without AI assistance. All radiologists involved in the study were highly experienced. The group that utilized AI had a 20% higher detection rate for cancers compared to the group assessed solely by radiologists. The researchers did not observe an increase in false positives with the use of AI. Furthermore, the AI group experienced a 44% reduction in reading workload compared to the group without AI. While the study did not measure the exact time saved by AI, the researchers estimated that if a radiologist typically reads 50 mammograms per hour, a single radiologist would save four to six months when reading approximately 40, 000 screening exams with AI assistance, compared to the workload of two radiologists alone. Dr. Kristina Lång, an associate professor of radiology diagnostics at Lund University in Sweden and co-author of the study, emphasized that the greatest potential of AI is reducing the overwhelming reading load faced by radiologists. In Europe, it is recommended for two radiologists to screen mammograms, while the US does not have the same guideline.

Both regions, however, face a shortage of radiologists, according to the Radiological Society of North America. If further research supports the effectiveness of AI in breast cancer detection, it could help alleviate staff shortages and enhance radiologists' performance. The demand for radiologists is expected to rise with the aging global population and increased need for medical imaging. Many radiologists view AI as a valuable tool that improves accuracy rather than a threat to their job security. Dr. Stamatia Destounis, a breast imaging specialist at Elizabeth Wende Breast Care in Rochester, New York, who was not involved in the study, explained that early breast cancer detection is crucial, and any technology that enhances breast screening can make a significant difference. Although mammography is not flawless, as it can miss approximately 20% of breast cancers, AI has the potential to aid in pattern detection. However, Dr. Laura Heacock, a breast radiologist at NYU Langone Perlmutter Cancer Center, noted that AI's role in screening mammograms is only a fraction of a radiologist's broader medical practice. She emphasized that AI works best when paired with highly trained radiologists who ultimately make the final diagnosis, comparing it to a tool like a stethoscope for a cardiologist. AI algorithms can offer more advanced feature recognition and application compared to the computer-aided detection (CAD) systems currently in use. Despite being an emerging technology, AI is already making strides in various areas, such as drug discovery and development, improved doctor-patient communication, and even exam question creation for medical licensing. Numerous AI programs are also being developed to assist doctors in cancer detection. One such program at MIT aims to identify high-risk future breast cancer cases based on current mammograms, a task that doctors are currently unable to accomplish. These programs show promise, as AI is able to complement less-experienced doctors and flag rare cases that they may not have encountered before. Dr. Heacock eagerly awaits further advancements in AI research.