Signs of Breast Cancer Could Be Spotted 3-6 Years Before Diagnosis Using AI Screening, Shows Massive Study

\
AI could have detected disease up to 6 years before 2014 breast cancer diagnosis screenings

Early warning signs of breast cancer could have been spotted years in advance using AI, suggests a new study that analyzed 88,963 mammograms performed during a 10-year period on over 31,000 patients.

The researchers showed that the latest artificial intelligence technology can provide an “early alert” for the disease up to six years before a diagnosis.

Swedish researchers tested three commercially available AI-based computer-assisted detection (AI-CAD) radiology systems on the mammogram data.

The findings, published in the journal Radiology, showed that cancer prediction scores issued by AI-CAD were elevated, on average, for people who were eventually diagnosed with breast cancer, while scores were low for those who remained cancer-free.

“Approximately 20% of breast cancer cases demonstrate mammographic signs that are already visible to AI around six years before diagnosis,” said senior co-author Professor Fredrik Strand, of Karolinska University Hospital, Stockholm.

“Our study confirms the potential of AI to, in some cases, find signs of cancer in the mammograms much earlier than when radiologists detected it.”

AI-based systems have shown promise for predicting 5-year risk of breast cancer and identifying women at risk of “interval” cancers between regular screening mammograms, but Prof. Strand’s team looked at their potential to flag mammographic signs that were present up to 10 years (in advance), after collecting mammograms from volunteers aged 40 to 74 across Sweden.

After these volunteer screening exams, two radiologists analyzed each mammogram, which was scheduled every two years—taken between 2008 and 2019.

Across that period, 12,072 of the participants (38.5%) were diagnosed with cancer by radiologist readers.

The AI-CAD systems successfully identified many of those cancers at earlier screening points.

It achieved 90% “specificity” (able to distinguish between a true positive and a true negative result) in nearly 20% of participants six years before their recorded diagnosis, up to 25% of individuals four years before diagnosis and up to nearly 40% two years before diagnosis.

“This study aims to add to the growing literature regarding the application of AI in breast cancer screening and how it can help play a role in earlier detection of breast cancer,” said Strand.

“Analyzing the AI scores of screened individuals over time could provide insight into how early detectable changes arise, potentially allowing for earlier intervention.” Signs of Breast Cancer Could Be Spotted 3-6 Years Before Diagnosis Using AI Screening, Shows Massive Study:
Read More........

Staggering Results Show HIV-Transmission Reduced 100% with Twice-Yearly Lenacapavir Injection


A 2-stage trial testing a new and acclaimed HIV-prevention drug has shown almost unthinkable results of no new infections among a sample size of 3,200 participants.

Called PURPOSE 1, the aim of the first trial was testing a subcutaneous injection of the drug Lenacapavir given twice a year to people in a high-HIV-incidence country, which in this case was Uganda or South Africa.

The results were nothing short of extraordinary—100% efficacy, not a single young woman contracted HIV.

This was followed up by PURPOSE 2, which expanded the geographical area significantly to more countries on more continents, and expanded the pool of individuals from beyond just young women to men—and to those of all ages. 5,000 participants took part.

The result was the same: 99.9% reduction in infection rates.

Both were considered phase 3 clinical trials, and were conducted in a randomized, double-blinded protocol, but were not tested against a placebo. Instead, the Lenacapavir injections were compared to the current standard of HIV prevention—a pill called Truvada or Descovy taken daily.

These both were also found to prevent HIV transmission by 99.9% during development, but must be taken every day to achieve this level of protection. As anyone who’s tried to stick to a once-a-day pill regime long-term will agree, it’s not an easy thing to maintain month after month.

By contrast, the twice-yearly injections are much easier to adhere to, and they also come with the added benefit of removing the social stigma of being seen taking a daily pill and therefore at risk of HIV transmission. This can be particularly alleviating in high-HIV-prevalent countries where male homosexuality is illegal, such as Uganda.

Indeed the superiority of a twice-yearly injection was so clear that both PURPOSE trials were halted early over ethical reasons. A 52-week follow-up screened for HIV developments.

Lenacapavir was named by Science Magazine as the Breakthrough of the Year in 2024, and was approved by the FDA for use in humans under the brand name Yeztugo.

It works to break down the HIVs capsid shell by binding to an “highly conserved” protein on the exterior. That means that no matter how many times or into what form the virus mutates, the exterior shell protein remains—presenting the perfect target for the drug.

In layman’s terms, the drug then works through the protein to disrupt the capsid shell, which the virus ‘takes down’ and ‘builds up’ several times during its lifecycle with perfect geometric precision. The disruption prevents the virus from completing its life cycle.

Initial R&D, regulation compliance, and proof of efficacy and safety requirements mean that producing Lenacapavir has cost its developer, Gilead Sciences, an undisclosed total cost that would be reasonable to estimate at well over a billion dollars based on normal pharma development costs.Gilead has nevertheless committed to providing the drug at cost in certain low-income regions and has licensed generic manufacturers to produce it for approximately $40 per year in 120 low and middle-income countries starting in 2027 Staggering Results Show HIV-Transmission Reduced 100% with Twice-Yearly Lenacapavir Injection
Read More........