Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog

Category: biotech/medical – Page 179

Artificial intelligence in medicine: How it works, how it fails

Artificial intelligence (AI) is transforming healthcare, with large language models emerging as important tools for clinical practice, education, and research. To use it safely and effectively, healthcare professionals need to understand how it works, and how it fails. Using practical clinical examples, the authors explain the subset of AI called large language models, highlighting their capabilities and their limitations.

Key Points

  • AI is trained on vast amounts of data, which can itself be biased, leading to biased results.

Red blood cells serve as a primary glucose sink to improve glucose tolerance at altitude

Martí-Mateos et al. show that red blood cells explain improved glucose tolerance at high altitude. By manipulating red blood cell number, they determine that these cells are necessary and sufficient for hypoxic hypoglycemia. This highlights red blood cells as unappreciated glucose regulators and reveals novel strategies to treat diabetes.

AI tool debuts with better genomic predictions and explanations

Artificial intelligence has taken the world by storm. In biology, AI tools called deep neural networks (DNNs) have proven invaluable for predicting the results of genomic experiments. Their usefulness has these tools poised to set the stage for efficient, AI-guided research and potentially lifesaving discoveries—if scientists can work out the kinks. The findings are published in the journal npj Artificial Intelligence.

“Right now, there are a lot of different AI tools where you’ll give an input, and they’ll give an output, but we don’t have a good way of assessing the certainty, or how confident they are, in their answers,” explains Cold Spring Harbor Laboratory (CSHL) Associate Professor Peter Koo. “They all come out in the same format, whether you’re using a large language model or DNNs used in genomics and other fields of biology.”

It’s one of the greatest challenges today’s researchers face. Now, Koo, former CSHL postdoc Jessica Zhou, and graduate student Kaeli Rizzo have devised a potential solution—DEGU (Distilling Ensembles for Genomic Uncertainty-aware models). DNNs trained using DEGU are more efficient and more accurate in their predictions than those learning via standard methods.

Abstract: A therapeutic target for terminating the long-lived autoimmune response!

Maureen A. Su find the epigenetic regulator UTX complexes with transcription factors TCF1 and STAT3 to promote pathogenicity of long-lived, stem-like progenitor T cells in models of type 1 diabetes (T1D)

1Department of Microbiology, Immunology, and Molecular Genetics, UCLA David Geffen School of Medicine, Los Angeles, California, USA.

2Department of Pediatrics and.

3Department of Genetics, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.

Complement Inhibition for Acute Neuromyelitis Optica Spectrum Disorder AttacksInsights From an International Case Series

These findings underscore the potential role of complement inhibition as a treatment option for acute NMOSD attacks, particularly in patients with insufficient response to standard therapies.

Background and Objectives.

Profile of a pimple

Sunny Y. Wong & team characterize gene expression changes that occur during acne pathogenesis and identify a therapeutic that reduces acne-like pustule formation in a mouse model of high fat diet-induced folliculitis:

The image shows prominent neutrophilic pustules from ear skin of the mouse model, stained for the neutrophil marker Ly6G (green) and KRT14 (red).

Address correspondence to: Sunny Y. Wong or Joseph S. Durgin, Department of Dermatology, University of Michigan, 1,500 E. Medical Center Dr., Ann Arbor, Michigan 48,109, USA. Email: [email protected] (SYW); [email protected] (JSD).

Japanese government panel endorses Sumitomo Pharma’s iPS-derived treatment for Parkinson’s

The expert council of the Japanese Ministry of Health has approved two regenerative medicine drugs based on induced pluripotent stem cells (iPSCs) — a cure for Parkinson’s disease and heart failure. If the health minister approves the experts’ decision, Japan will become the first country in the world to allow the commercial sale of such products — almost 20 years after the discovery of the technology itself.

Japan’s health ministry said on Thursday a panel of specialists had endorsed Sumitomo Pharma’s iPS cell-derived treatment for Parkinson’s disease, paving the way for the world’s first medical products based on the technology.

DOT1L provides transcriptional memory through PRC1.1 antagonism

Genetic off switch for cancer face_with_colon_three #cancer #cure

Neville, Ferguson et al. show that non-canonical Polycomb repressive complex 1.1-mediated gene silencing is antagonized by DOT1L and is required for the therapeutic efficacy of Menin and DOT1L inhibitors in mixed-lineage leukaemia.

/* */