MEDICAL EXPRESS - HEALTH INFORMATICS

1. New biomarkers to detect colorectal cancer found with AI and machine learning

   Machine learning and artificial intelligence (AI) techniques and analysis of large datasets have helped University of Birmingham researchers to discover proteins that have strong predictive potential for colorectal cancer.

2. Long-range connections between brain regions are scarce, but essential to speed up information transmission

   The human brain is formed by a complex network of neural connections and most of them link neighboring brain regions, which are also the most studied to date. But a recent neuroscientific study by Pompeu Fabra University (UPF) and the University of Oxford, published in Proceedings of the National Academy of Sciences, has revealed that connections between distant brain regions, though rarer and less frequent, play a fundamental role in explaining brain dynamics.

3. Deep learning model helps detect lung tumors on CT scans

   A new deep learning model shows promise in detecting and segmenting lung tumors, according to a study published today in Radiology. The findings of the study could have important implications for lung cancer treatment.

4. Graph machine learning model shows potential for predicting cancer genes

   The World Health Organization reports a steady increase in cancer patients worldwide, marking it as a major health threat. Preventing and treating cancer has become a global priority, with identifying cancer-driver genes being essential for understanding its development and advancing personalized therapies. However, current methods struggle with generalizability and interpretability, limiting their effectiveness across different cancer types and populations.

5. Brain network model can predict when people will feel surprised

   Surprise is a key human emotion that is typically felt when something that we are witnessing or experiencing differs from our expectations. This natural human response to the unexpected has been the focus of numerous psychology studies, which uncovered some of its underlying neural processes.

6. Algorithm to spot cancer warning signs in standard blood tests to be used by EU's NHS

   Scientists at the University of Exeter have found a new way of interpreting standard blood tests to help GPs spot cancer warning signs—and the test is now being integrated in an NHS trust.

7. Pandemic led to rapid adoption of telemental health for those with schizophrenia

   For Medicaid beneficiaries with schizophrenia, delivery of mental health care through telehealth (telemental health care) diffused rapidly after onset of the COVID-19 pandemic, according to a study published online Jan. 16 in JAMA Network Open.

8. AI can guide acquisition of diagnostic-quality lung ultrasound images

   Trained health care professionals (THCPs), including medical assistants, respiratory therapists, and nurses, with artificial intelligence (AI) assistance can achieve lung ultrasound (LUS) images with diagnostic quality that does not differ significantly from that achieved by experts, according to a study published online Jan. 15 in JAMA Cardiology.

9. Brain-controlled interface experiment provides empirical support for one-way neural activity paths

   Neural network models that are able to make decisions or store memories have long captured scientists' imaginations. In these models, a hallmark of the computation being performed by the network is the presence of stereotyped sequences of activity, akin to one-way paths. This idea was pioneered by John Hopfield, who was notably co-awarded the 2024 Nobel Prize in Physics. Whether one-way activity paths are used in the brain, however, has been unknown.

10. Researchers propose novel model to screen misreporting in dietary surveys

    An international team led by Prof. John Speakman from the Shenzhen Institutes of Advanced Technology of the Chinese Academy of Sciences derived a predictive model by combining classical statistics and machine learning for total energy expenditure, providing a more objective way to assess the validity of food intake records.

11. Study reveals AI's transformative impact on ICU care with smarter predictions and transparent insights

    Intensive care units (ICUs) face mounting pressure to effectively manage resources while delivering optimal patient care. Groundbreaking research published in the journal Information Systems Research highlights how a novel artificial intelligence (AI) model is revolutionizing ICU care by not only improving predictions of patient length of stay, but also equipping clinicians with clear, evidence-based insights to guide critical decisions.

12. AI helps predict memory issues, cognitive decline during menopausal transition

    Artificial intelligence might be able to more quickly and affordably identify menopausal women who are having problems with memory or cognition.

13. AI-driven approach reads heart cells' inner electrical signals from the outside

    A team of researchers led by the University of California San Diego and Stanford University has developed a noninvasive method to monitor the electrical activity inside heart muscle cells from the outside, avoiding the need to physically penetrate the cells.

14. Tagging gene-regulating DNA sequences with barcodes provides insights into human genome

    An international team of researchers has taken an important step toward understanding how gene expression is controlled across the human genome. The research is published in the journal Nature.

15. Meta's shift to 'community notes' risks hurting online health info providers more than ever

    Last week, social media giant Meta announced major changes to its content moderation practices. This includes an end to its fact-checking program, starting with the United States.

16. High-speed internet linked to lower COVID-19 death rates

    The mortality rate from COVID-19 was about 50% lower in U.S. counties with higher internet access in the summer and early fall of 2020.

17. Experts propose new framework for evaluating sex in clinical algorithms to reduce bias and ensure legality

    Many physicians are now using algorithms that consider a patient's sex, like heart disease risk assessment tools, to help with clinical decision-making. Reliance on these algorithms may result in men and women receiving different care or having different eligibility for health care resources, for example, placement on an organ transplant list.

18. Exploring novel deep learning-based models for cancer histopathology image analysis

    Histopathological evaluation of tumor specimens has long been essential in diagnosing breast cancer and guiding clinical decision-making. However, one of the key challenges in routine diagnostics includes the inter-observer and inter-lab variabilities present in the assessment of prognostic markers that could lead to under- and over-treatment of patients.

19. How one brain circuit encodes memories of both places and events

    Nearly 50 years ago, neuroscientists discovered cells within the brain's hippocampus that store memories of specific locations. These cells also play an important role in storing memories of events, known as episodic memories. While the mechanism of how place cells encode spatial memory has been well-characterized, it has remained a puzzle how they encode episodic memories.

20. Harnessing the brain power behind speech to help detect neurodegenerative disease

    There's a lot of brain power that goes into speech. First, there's a thought or idea, which the brain must translate into words. Those words are then translated into specific movements of the lungs, tongue and mouth to shape the sounds. Those movements then must be perfectly executed and timed with breath. If there is damage to the brain from a stroke or a brain disease, the timing of the movements or translation can go wrong.

21. AI helps to identify subjective cognitive decline during the menopause transition

    Artificial intelligence (AI) is positioned to make a major impact on almost every industry, including health care. A new study suggests that machine learning models can more quickly and affordably identify women with severe subjective cognitive decline during the menopause transition, effectively opening the door to better management of cognitive health.

22. Electronic patient-reported outcome monitoring system found to be beneficial

    Implementation of an electronic patient-recorded outcome (ePRO) monitoring system improves patient-physician communication in cardiovascular care, according to a study published online Jan. 14 in JAMA Network Open.

23. Software uncovers link between childhood maltreatment and higher risk of rheumatoid arthritis or psoriasis in later life

    University of Birmingham venture Dexter has demonstrated the power of its Dexter software platform in a study showing that people whose childhoods featured abuse, neglect or domestic abuse carry a significantly increased risk of developing rheumatoid arthritis or psoriasis in later life.

24. For healthy hearing, timing matters: Neuroscientists use AI to explore real-world auditory processing

    When sound waves reach the inner ear, neurons there pick up the vibrations and alert the brain. Encoded in their signals is a wealth of information that enables us to follow conversations, recognize familiar voices, appreciate music, and quickly locate a ringing phone or crying baby.

25. AI models tested for privacy-safe radiology report analysis

    Artificial intelligence (AI) and, above all, large language models (LLMs), which also form the basis for ChatGPT, are increasingly in demand in hospitals. However, patient data must always be protected. Researchers at the University Hospital Bonn (UKB) and the University of Bonn have now been able to show that local LLMs can help structure radiological findings in a privacy-safe manner, with all data remaining at the hospital.

26. AI tool can help counselors predict which college students are at risk of anxiety and depression disorders

    Mental Health America predicts that nearly 60 million Americans suffered from a mental illness in 2024, and research from the University of Alabama at Birmingham shows that post-traumatic stress disorder and acute stress disorder diagnoses have risen significantly in American college students since 2017.

27. Molecular breast imaging for supplemental breast screening

    If you are one of the millions of women identified as having dense breasts, your health care team may recommend supplemental or additional screening to check your breasts for cancer.

28. Rurality partly explains racial difference in distance to lung cancer screening, study suggests

    Differences in distance to lung cancer screening (LCS) facilities by race and ethnicity are partly explained by rurality, according to a study published online Jan. 14 in the Annals of Internal Medicine.

29. Vascular 'fingerprint' at the back of the eye can accurately predict stroke risk

    A vascular 'fingerprint' on the light sensitive tissue layer at the back of the eye—the retina—can predict a person's risk of stroke as accurately as traditional risk factors alone, but without the need for multiple invasive lab tests, finds research published online in the journal Heart.

30. Powered by machine learning, a new blood test can enable early detection of multiple cancers

    Oxford University researchers have unveiled a new blood test, powered by machine learning, that shows promise in detecting multiple types of cancer in their earliest stages, when the disease is hardest to detect.