Medical Bulletin 09/January/2026 - Video

Here are the top medical news for today:

New AI model predicts disease risk during sleep monitoring sessions

Your sleep tonight might reveal diseases lurking years in your future. A groundbreaking study from Stanford Medicine, published in Nature Medicine, shows that artificial intelligence can analyze a single night of sleep data to predict your risk of developing over 100 health conditions—from cancer and heart disease to dementia and Parkinson's. The model, called SleepFM, was trained on nearly 600,000 hours of sleep recordings from 65,000 people, learning to read the body's hidden signals in ways human doctors never could.

Sleep clinics have long collected incredibly detailed physiological data—brain waves, heart rhythms, breathing patterns, eye movements, and leg activity—all recorded continuously through a process called polysomnography. Yet most of that rich information has gone underutilized. Modern AI changes that equation.

The Stanford team built a "foundation model," similar to how ChatGPT learns language patterns from vast text, but here the model learns the "language of sleep." They split sleep recordings into five-second chunks and used a novel training technique called leave-one-out contrastive learning, which hides one data stream and challenges the model to reconstruct it from the others. This forced the AI to understand how brain signals, heart activity, breathing, and muscle movements all relate and interact.

After training, researchers tested SleepFM on two fronts. First, it performed as well as or better than current clinical models at standard sleep tasks—identifying sleep stages and diagnosing sleep apnea severity. Then came the ambitious test: predicting future disease. Using 35,000 patients from Stanford's sleep center with up to 25 years of health records, the model analyzed over 1,000 disease categories.

Results were striking. SleepFM predicted Parkinson's disease (89% accuracy), dementia (85%), and several cancers with high precision. It even predicted heart attacks and overall mortality risk with 81-84% accuracy. The model excelled because it didn't rely on isolated signals—combinations of misaligned body rhythms (a sleeping brain paired with an alert heart, for instance) proved most predictive.

This breakthrough suggests that one night's sleep could eventually become a powerful screening tool for disease prevention.

REFERENCE: Thapa, R., Kjaer, M.R., He, B. et al. A multimodal sleep foundation model for disease prediction. Nat Med (2026). https://doi.org/10.1038/s41591-025-04133-4

Breast milk bacteria found to influence infant gut microbiome formation

Breast milk isn't just nutrition—it's also a delivery system for trillions of tiny passengers. A new study published in Nature Communications reveals that human milk carries its own unique community of bacteria that seeds a baby's developing gut microbiome, shaping everything from nutrient absorption to immune system strength. Researchers analyzed 507 milk and infant stool samples from 195 mother-infant pairs, uncovering how specific bacterial strains travel from mother to child through breastfeeding—and sometimes in unexpected ways.

The breast milk microbiome has long been a mystery because milk's high fat content and low bacterial load make it notoriously difficult to study. Most prior research used quick but limited techniques that only examined a small slice of bacterial DNA. A team led by Pamela Ferretti at the University of Chicago and collaborators from the University of Minnesota and Oklahoma University Health Sciences Center took a different approach—they used metagenomic analysis, a deep-dive technique that examines nearly the entire bacterial genome. This allowed them to track not just which bacteria were present, but which exact strains moved from mother to infant.

The findings surprised researchers. Breast milk was dominated by bifidobacteria, particularly Bifidobacterium longum, which showed up in over 50% of milk samples and colonized 98% of infants' guts. Previous studies had reported other bacteria like Staphylococcus and Streptococcus as dominant.

Even more intriguing, the team identified 12 instances where the exact same bacterial strain appeared in both mother's milk and baby's gut—definitive proof of vertical transmission through breastfeeding. Some strains were beneficial, while others were potentially harmful bacteria like E. coli and Klebsiella that can cause infection under certain conditions. All mothers and infants in the study were healthy, suggesting these microbes reflect normal microbial diversity rather than disease.

The researchers also discovered evidence of "retrograde flow"—oral bacteria from the baby traveling back into the mother's breast during feeding, enriching milk's microbial composition. This groundbreaking work nearly doubled available data on milk microbiomes and opens doors to understanding how early-life microbial exposure shapes lifelong health.

REFERENCE: Ferretti, P., et al. (2025). Assembly of the infant gut microbiome and resistome are linked to bacterial strains in mother’s milk. Nature Communications. DOI: 10.1038/s41467-025-66497-y. https://www.nature.com/articles/s41467-025-66497-y

Lack of physical activity linked to increased heart attack risk: Study

Sitting may be slowly killing us—and the numbers are getting worse, not better. A comprehensive global study spanning three decades reveals that deaths from heart disease linked to physical inactivity are rising steadily worldwide, even as awareness of exercise's benefits grows. Using decades of health data combined with genetic analysis, researchers have now confirmed that the connection between inactivity and heart attacks isn't just correlation—it's genuinely causal.

Heart disease remains the world's leading cause of death, with heart attacks accounting for a massive share of that burden. Yet the true scale of how physical inactivity contributes to these deaths has remained unclear. A new analysis tackled that question by examining Global Burden of Disease data from 1990 to 2021, tracking mortality trends tied to low physical activity across the globe. Simultaneously, researchers used genetic analysis to probe whether exercise truly protects the heart or whether other lifestyle factors deserve the credit.

The epidemiological findings painted a sobering picture. Between 1990 and 2021, deaths from heart disease linked to insufficient activity climbed at an average rate of 0.70% annually—a persistent upward trend despite decades of public health messaging about exercise. Aging populations, urbanization, and increasingly sedentary work styles appear to be fueling this rise, suggesting that knowing exercise is beneficial hasn't translated into action for billions worldwide.

To strengthen the evidence, researchers employed Mendelian randomization—a genetic technique that uses inherited variations to test whether physical activity causes heart protection or merely correlates with it. They analyzed genome-wide data from thousands of people, comparing those genetically predisposed to higher activity levels with less active counterparts. The results were compelling: individuals with genetic markers favoring more exercise had 83% lower risk of heart attack compared to sedentary peers—an odds ratio of 0.17.

This genetic evidence powerfully supports the idea that movement itself—not merely the lifestyles of active people—directly shields the heart.

Together, the data send a clear message: physical inactivity is a major, growing, and preventable driver of global heart disease. The solution remains unchanged: move more, sit less.

REFERENCE: Guo Y et al. Physical activity and myocardial infarction risk: insights from the global burden of disease study 1990–2021 and Mendelian randomization analysis. BMC Cardiovasc Disord. 2025;DOI: 10.1186/s12872-025-05453-6.