Machine Learning News and Research

RSS

NIH funds AI project to advance Alzheimer’s research and treatment

The National Institutes of Health has renewed support for Artificial Intelligence for Alzheimer's Disease, or AI4AD. The new $12.6 million award to advance the project's next phase, AI4AD2, brings its total investment in AI4AD to $30.7 million.

1 Apr 2026

Blood test may detect cognitive decline years before symptoms

A blood test could help identify people at higher risk of cognitive decline years before a traditional diagnosis is possible – according to University of East Anglia research.

31 Mar 2026

Machine learning helps predict risks during stem cell therapy for myeloma

Multiple myeloma is a cancer in which plasma cells, which normally produce antibodies, multiply uncontrollably in the bone marrow.

31 Mar 2026

Higher sugar intake raises gallstone risk in adults, study finds

A cross-sectional NHANES study of 8,975 U.S. adults found that higher total dietary sugar intake was associated with higher odds of gallstones, with each 100 g/day increase linked to a 41% rise after full adjustment. The findings suggest sugar intake may be a modifiable gallstone risk factor, but the study relied on self-reported gallstones and cannot establish causation.

29 Mar 2026

AI improves personality testing with faster and more accurate results

Personality tests are widely used in workplaces to shape recruitment, leadership training and team building.

28 Mar 2026

New method reveals hidden protein motions for improved drug design

For many of us "protein" is the key element of a food order. However, beyond your preferred choice of meats or plant-based alternatives, proteins encompass a large class of complex biomolecules whose chemical structure is encoded in our genes.

27 Mar 2026

New AI system maps gene expression across the whole body

Understanding gene expression within the body has been a boon for 21st century biology and therapeutics, but most discoveries that use these technologies only focus on one organ or one small area of tissue.

27 Mar 2026

Machine learning model can predict 28-day mortality in sepsis patients

Sepsis is one of the most common and lethal syndromes encountered in intensive care units (ICUs), and acute respiratory failure (ARF) represents one of its most critical complications.

27 Mar 2026

Machine learning model predicts liver cancer risk with high accuracy

A machine learning model that analyzes patient demographics, electronic health record data, and routine blood test results predicted a patient's risk of hepatocellular carcinoma (HCC), the most common type of liver cancer, with high accuracy.

26 Mar 2026

New algorithm enables precise subtyping of metabolic liver disease

Metabolic-associated steatotic liver disease (MASLD) is a clinically heterogeneous condition with highly variable outcomes affecting more than 30% individuals globally.

26 Mar 2026

iXCells Biotechnologies joins international collaboration to evaluate chemotherapeutic toxicity in human organoids

iXCells Biotechnologies ("iXCells"), a leading provider of human cell-based solutions and custom iPSC services, today announced it has entered an international collaboration with Rosebud Biosciences ("Rosebud"), Kantify, and Incite to evaluate off-target chemotherapeutic toxicities in patient-specific organoids.

From iXCells Biotechnologies 25 Mar 2026

Optibrium introduces graphical interface for QuanSA to enhance ligand-based affinity predictions

Optibrium, a leading developer of software and AI solutions for molecular design, today announced a new QuanSA™ plugin for PyMOL, providing an intuitive Graphical User Interface (GUI) for its ligand-based binding affinity prediction method, part of the Company's BioPharmics 3D molecular modelling platform.

From Optibrium Ltd. 25 Mar 2026

Navigating the moral landscape of pediatric AI surgery

Technological innovation has always driven surgical progress, and AI now represents the next transformative wave. Machine learning models are now being developed to predict surgical risks, assist in diagnosing rare congenital disorders, analyze imaging data, and anticipate postoperative complications. Risk prediction tools have already shifted from traditional statistical methods to more complex machine learning approaches, improving their ability to account for nonlinear interactions.

25 Mar 2026

Palmatine improved fatty liver markers in a preclinical type 2 diabetes study

Researchers used a bioinformatics-plus-rat-model approach to investigate how palmatine may help treat T2DM-associated MASLD, identifying five core targets: ADRB2, BCL3, EGR1, FOS, and MAP3K8. In rats, palmatine improved liver injury, inflammation, oxidative stress, glycolipid metabolism, steatosis, and fibrosis, while reducing apoptosis-related signaling, providing a preclinical foundation for further therapeutic study.

23 Mar 2026

Webinar introduces advanced bioinformatics tool to interpret mutations in cancer genomes

A free open-access webinar will introduce the Cancer Genome Interpreter (CGI), an advanced bioinformatics tool to interpret mutations in cancer genomes developed by IRB Barcelona and co-created with European hospitals to turn complex cancer genomics into actionable insights.

23 Mar 2026

AI-powered ultrasound analysis identifies high-risk heart failure cases

Applying artificial intelligence techniques to cardiac ultrasound data may make it easier to identify patients with advanced heart failure, a new study has found.

23 Mar 2026

Machine learning speeds up AMP discovery for treating ulcerative colitis

Ulcerative colitis (UC) is a chronic inflammatory bowel disease characterized by recurrent intestinal inflammation, abdominal pain and diarrhea.

23 Mar 2026

Socioeconomic gaps shape vulnerability to air pollution mortality in Europe

Socioeconomic factors are widely recognized as potential modifiers of the relationship between air pollution and mortality, but the available evidence remains limited.

19 Mar 2026

Researchers use AI to reveal the true scale of COVID-19 mortality in the US

A machine learning model applied to US death certificate data estimated that over 155,000 COVID-19 deaths were unrecognized between March 2020 and December 2021, suggesting total mortality was about 19% higher than official counts. These undercounted deaths disproportionately affected marginalized populations, including racial minorities, lower-income groups, and residents of the Southern United States.

19 Mar 2026

New data hub aims to advance alternatives to animal testing

A research team at NYU Langone Health and Sage Bionetworks has been awarded a $25 million grant to establish the data hub and coordinating center for the National Institutes of Health's Complement-Animal Research in Experimentation (Complement-ARIE) program.

18 Mar 2026