One night of sleep vital signs may Predict Illness several years ahead and over 100 health conditions

Amazing stuff!

"Difficulty sleeping often precedes heart disease, psychiatric disorders, and many other illnesses. Researchers used data gathered during sleep studies to detect such conditions.

What’s new: SleepFM is a system that classifies Alzheimer’s, Parkinson’s, prostate cancer, stroke, congestive heart failure, and many other conditions based on a person’s vital signs while asleep — as much as 6 years before they show symptoms. ...

Input/output: Recordings of one night of sleep in, disease classifications out

Architecture: Convolutional neural network encoder, transformer, LSTM

Performance: Can accurately classify over 130 conditions ...

How it works: SleepFM comprises a convolutional neural network (CNN), transformer, and LSTM. The authors trained the system in two stages:

(i) to encode patterns in sleep data and

(ii) to classify diseases.

The training data comprised roughly 585,000 hours of sleep-study recordings that included, in addition to each patient’s age and sex, signals of activity in the brain, heart, respiratory system (airflow, snoring, and blood oxygen level), and leg muscles. The data was mostly proprietary but included public datasets.

The authors trained the CNN and transformer together.  ...

The authors added the LSTM and separately trained it, given 9 hours of sleep data as well as the subject’s age and sex, to classify more than 1,000 diseases.

Results: The authors compared SleepFM’s performance on a proprietary test set to the same system without pretraining and a vanilla neural network that was trained on only demographic information.

Across 14 general categories of disease ..."

From the abstract:

"Sleep is a fundamental biological process with broad implications for physical and mental health, yet its complex relationship with disease remains poorly understood. Polysomnography (PSG)—the gold standard for sleep analysis—captures rich physiological signals but is underutilized due to challenges in standardization, generalizability and multimodal integration.

To address these challenges, we developed SleepFM, a multimodal sleep foundation model trained with a new contrastive learning approach that accommodates multiple PSG configurations.

Trained on a curated dataset of over 585,000 hours of PSG recordings from approximately 65,000 participants across several cohorts, SleepFM produces latent sleep representations that capture the physiological and temporal structure of sleep and enable accurate prediction of future disease risk.

From one night of sleep, SleepFM accurately predicts 130 conditions with a C-Index of at least 0.75 (Bonferroni-corrected P < 0.01), including all-cause mortality (C-Index, 0.84), dementia (0.85), myocardial infarction (0.81), heart failure (0.80), chronic kidney disease (0.79), stroke (0.78) and atrial fibrillation (0.78).

Moreover, the model demonstrates strong transfer learning performance on a dataset from the Sleep Heart Health Study—a dataset that was excluded from pretraining—and performs competitively with specialized sleep-staging models such as U-Sleep and YASA on common sleep analysis tasks, achieving mean F1 scores of 0.70–0.78 for sleep staging and accuracies of 0.69 and 0.87 for classifying sleep apnea severity and presence.

This work shows that foundation models can learn the language of sleep from multimodal sleep recordings, enabling scalable, label-efficient analysis and disease prediction."

The New Open-Weights Leader, Big AI’s Political Influence, Predicting Illness, Faster Reasoning

New AI model predicts disease risk while you sleep "Stanford Medicine scientists and their colleagues created the first artificial intelligence model that can predict more than 100 health conditions from one night’s sleep."

A multimodal sleep foundation model for disease prediction (open access)

Fig. 1: Overview of SleepFM framework.

The health benefits of intermittent fasting. Really!

I believe intermittent fasting for its health benefits has been recognized and recommended for several decades at least!

"In 2018, Courtney Peterson published what proved to be a landmark paper in the burgeoning field of intermittent fasting [???]. The study, which found that pre-diabetic men could dramatically improve their blood sugar control by eating during a shorter daily window starting in the early morning, has now been cited more than 1,600 times according to Google Scholar. It also jump started her career: She now leads one of the largest randomized controlled trials of intermittent fasting in humans, in addition to other studies looking at how intermittent fasting and meal timing may benefit aspects of cardiometabolic health including weight loss, blood sugar, blood pressure, aging, and even cancer prognosis."

The health benefits of intermittent fasting | Harvard T.H. Chan School of Public Health "Intermittent fasting researcher Courtney Peterson joins Harvard Chan School and will direct Department of Nutrition’s new research kitchen."

Smartphone use in the bathroom raise risk of hemorrhoids. Really!

I have serious doubts about these claims!

"Hemorrhoids are among the most frequent gastrointestinal complaints in the United States, sending millions of people to clinics and emergency rooms each year and costing the health system hundreds of millions of dollars.

Despite their prevalence, the causes remain poorly defined. Constipation, straining, pregnancy, and low-fiber diets have all been implicated, but physician-investigator Trisha Pasricha and colleagues wondered whether the modern habit of lingering in the bathroom with a phone might also play a role.

In a study of 125 adults undergoing routine colonoscopy at Beth Israel Deaconess Medical Center, the team surveyed participants about toilet habits, smartphone use, diet, and activity levels, then compared responses with direct colonoscopy findings. 

The results revealed some surprising patterns:

• Two-thirds of participants admitted to using their phones on the toilet.
• Smartphone use on the toilet was associated with a 46 percent increased risk of having hemorrhoids.
• Phone users were five times more likely to sit for more than five minutes per trip.
• Younger adults were especially prone to the habit.
• Smartphone users reported less weekly exercise than non-users.

..."

Does this cellphone habit raise risk of hemorrhoids? — Harvard Gazette "Gastroenterologist Trisha Pasricha discusses why new findings may change how you think about bathroom routines"

Gastroenterologist Trisha Pasricha. She cares about hemorrhoids. Too bad I don't have any hemorrhoids! Just kidding! 😊

Researchers identify almost 300 genetic disorders that can be treated before birth

Good news!

Again it is disgusting and annoying how Harvard U avoided to say "woman" for most likely ideological reasons! Women are either "pregnancies" or "patients" or "families" or "individuals".

"A new study identifies nearly 300 genetic disorders that can be treated during pregnancy or in the first week of life, forming the basis for a “treatable fetal findings list” that could be offered to pregnant patients.

The findings could improve the diagnosis of genetic conditions in pregnancy and enhance the treatment options available for fetuses that have these conditions ...

Over the past decade, genomic sequencing has become a vital tool to help inform prenatal diagnoses. Genomic sequencing tests, combined with family history, can help identify genes responsible for ultrasound abnormalities. They can also uncover incidental findings that may predispose a fetus or newborn to serious but treatable conditions, such as a heart condition that can be treated with medications or a gastrointestinal disorder that can be managed with fluid and electrolyte therapies. ...

Through a literature review, the authors identified a total of 296 genetic conditions, ranging from disorders with emerging fetal therapies to those where immediate postnatal treatment can prevent irreversible harm. The authors emphasize that timely detection of these conditions could reduce morbidity and mortality, offering families unprecedented opportunities for early intervention. ..."

From the abstract:

"The use of genomic sequencing (GS) for prenatal diagnosis of fetuses with sonographic abnormalities has grown tremendously over the past decade.

Fetal GS also offers an opportunity to identify incidental genomic variants that are unrelated to the fetal phenotype but may be relevant to fetal and newborn health. There are currently no guidelines for reporting incidental findings from fetal GS.

In the United States, GS for adults and children is recommended to include a list of “secondary findings” genes (ACMG SF v.3.2) that are associated with disorders for which surveillance or treatment can reduce morbidity and mortality. The genes on ACMG SF v.3.2 predominantly cause adult-onset disorders.

Importantly, many genetic disorders with fetal and infantile onset are treatable as well.

A proposed solution is to create a “treatable fetal findings list,” which can be offered to pregnant individuals undergoing fetal GS or, eventually, as a standalone cell-free fetal DNA screening test.

In this integrative review, we propose criteria for a treatable fetal findings list, then identify genetic disorders with clinically available or emerging fetal interventions and those for which clinical detection and intervention in the first week of life might lead to improved outcomes. Finally, we synthesize the potential benefits, limitations, and risks of a treatable fetal findings list."

Researchers ID genetic disorders that can be treated before birth — Harvard Gazette "Timely detection could reduce morbidity, offers opportunities for early intervention"

Advancing precision care in pregnancy through a treatable fetal findings list (no public access)

Advancing precision care in pregnancy through an actionable fetal findings list (preprint, open access)

Atlas of SARS-CoV-2 Antiviral Defenses

Very recommendable! Impressive research! The science of virology received such a booster shot from the global pandemic! We have probably seen rapid and significant advances in such a short time like never before with the appearance of a new pathogen.

"The researchers created an atlas that charts how 152 different antibodies attack a major piece of the SARS-CoV-2 machinery, the spike protein as it has evolved since 2020. The research identifies antibodies that are able to neutralize the newer strains, while identifying regions of the spike protein that have become more resistant to attack.  

The work can help illuminate strategies for broadly protective COVID-19 booster vaccines. ..."

Atlas of Antiviral Defenses | Harvard Medical School Study charts how antibodies attack SARS-CoV-2 variants

Memory B cell repertoire for recognition of evolving SARS-CoV-2 spike

Repeat Cancer Offenders

Good news! Cancer is history!

"Most cancer-related deaths occur not from the first tumor to arise in a patient but from cancers that reappear months or years after treatment.

Scientists think that a group of rare cancer cells, called persister cells, might contribute to such recurrence. Persister cells account for only a fraction of cancer cells; as their name suggests, they persist despite drug treatment, can survive in the body long enough to gain new mutations that enable them to evade drugs, and ultimately, drive recurrent tumor growth. ...

Although scientists knew cycling persister cells existed, their relative rarity among persisters—roughly 5 in 1,000 persister cells retain the ability to “cycle” or divide—has made them difficult to isolate and characterize. ...
To their surprise, the researchers also found that cycling persister cells relied on metabolism based on fatty acids, rather than glucose—typically, cancer cells are known to thrive on sugar. These observations were consistent across multiple cancer cell lines, in a mouse model of cancer and in samples from human lung tumors."

"Non-genetic mechanisms have recently emerged as important drivers of cancer therapy failure, where some cancer cells can enter a reversible drug-tolerant persister state in response to treatment. Although most cancer persisters remain arrested in the presence of the drug, a rare subset can re-enter the cell cycle under constitutive drug treatment. Little is known about the non-genetic mechanisms that enable cancer persisters to maintain proliferative capacity in the presence of drugs. To study this rare, transiently resistant, proliferative persister population, we developed Watermelon, a high-complexity expressed barcode lentiviral library for simultaneous tracing of each cell’s clonal origin and proliferative and transcriptional states. Here we show that cycling and non-cycling persisters arise from different cell lineages with distinct transcriptional and metabolic programs. ... The Watermelon system enabled the identification of rare persister lineages that are preferentially poised to proliferate under drug pressure, thus exposing new vulnerabilities that can be targeted to delay or even prevent disease recurrence."

Repeat Offenders | Harvard Medical School Analysis shows how a rare population of cancer cells contributes to disease relapse

Cycling cancer persister cells arise from lineages with distinct programs (no public access)