January 4, 2024 | AI took center stage in diagnostics stories in 2023, assessing breast cancer prognoses and helping identify biomarkers. But it’s also under the microscope as researchers seek to validate “black box” AI findings. Plus: news from Illumina and a call for more diverse cystic fibrosis screening. Here’s a look at the top stories from Diagnostics World as well as thought leaders in the industry. –The Editors
Prognostic Biomarker Scores Big For High-Risk Breast Cancer Cases
When artificial intelligence (AI) was used to assess breast cancer properties in patients given the worst prognosis, many of them were recategorized into a low-risk category where the best outcomes are expected suggesting that noncancerous elements in the tumor microenvironment, which were considered by the AI-based scoring of survival risk, may have been an important missing link all along.
Predictive Model For Gestational Diabetes Heads To Clinical Trials
An international team of researchers has found that gut microbes can help diagnose gestational diabetes mellitus (GDM) as early as the first trimester of pregnancy, months earlier than is happening currently.
Illumina Launches Program to Discount Pathogen Sequencing Tools for Public Health
Illumina has launched the Global Health Access Initiative to support access to pathogen sequencing tools for public health in low- and middle-income countries (LMICs) and reduced prices. The program will provide discounted prices for a range of sequencing applications and aim to address key barriers to genomic sequencing in-country.
The Last Mile In Preventing A Deadly Hospital Infection
A nine-month study of C. diff infections in hospital patients found that even the most aggressive infection prevention and control measures have their limitations, since infections aren’t necessarily a consequence of person-to-person transmission. They can result from dormant conditions associated with the patients themselves.
New AI Tool Uses Gene Sequencing Data To Predict Formation Site Of Cancer
Researchers at Dana-Farber Cancer Institute and Massachusetts Institute of Technology have developed a new tool, based on artificial intelligence, that predicts the likely site of formation for cancer of unknown primary (CUP) tumors.
For Equitable CF Screening, We Should Expand Our Definition of Pathogenic Variants
Comment: Cystic fibrosis (CF) screening continues to produce suboptimal results for people of non-European ancestry argue John Milligan and Ninad Pendse of Asuragen. The well-established CFTR2 database is populated almost entirely with data from people of European descent. We need to go beyond CFTR2, the authors argue, and improve coverage for all ancestries by embracing the vast amounts of data generated through large-scale sequencing studies.
Researchers In Japan Identify High-Potential Biomarker Of Gastric Cancer
Researchers have identified a biomarker for gastric (stomach) cancer that could fill the need for a more affordable and less complicated and time-consuming diagnostic option.
AI-Based Platform For Detecting AFib Put To The Test In VA Facilities
Investigators at Cedars-Sinai Medical Center are looking to minimize the biases in the data used by artificial intelligence (AI) algorithms, most recently a deep learning model trained on nearly a million electrocardiograms (ECGs) to identify people with abnormal heart rhythms.
NIH Program Tackles Bottlenecks In ‘Wild West’ Field Of exRNA Biology
A decade ago, the National Institutes of Health (NIH) launched a program designed to answer fundamental questions about extracellular RNA (exRNA), such as how it is used by cells and distant organs and if diseased and healthy cells produce different varieties of it. The program concluded in 2023, and Deborah Borfitz explores the technologies that emerged to address some of the biggest bottlenecks encountered by researchers.
Illumina Releases Updated TruSight Oncology Liquid Biopsy Assay
Illumina announced a new generation of its distributed liquid biopsy assay for genomic profiling. The new TruSight Oncology 500 ctDNA v2 (TSO 500 ctDNA v2) is a research assay that enables noninvasive comprehensive genomic profiling (CGP) of circulating tumor DNA (ctDNA) from blood when tissue testing is not available, or to complement tissue-based testing.
Using ML to Diagnose Chronic Kidney Disease in a Bias-Free, Privacy-Protecting, Physician-Friendly Manner
Carenostics is a healthcare AI startup founded with the mission of addressing the underdiagnosis, undertreatment, and health inequities of chronic disease using AI and ML on existing healthcare data. Their work on chronic kidney disease (CKD)—developed in close connection with Hackensack Meridian Health—attracted the judges’ attention in the 2023 Bio-IT World Innovative Practices Awards program.
Early Detection Of Alzheimer’s Disease From Blood A Near-Term Possibility
Within the next five years, general practitioners may have at their disposal a simple blood test for predicting the risk of Alzheimer’s disease (AD) two decades before any symptoms appear according to physicists at The Australian National University (ANU) who have coupled nanotechnology with machine learning to search for known biomarkers of disease onset.
Living Biobank Of Brain Metastasis Samples Enabling ‘Personalized Medicine 2.0’
Researchers at the CNIO (Spanish National Cancer Research Centre) are forwarding the idea that metastasis, rather than the primary tumor, should be the focus of cancer treatment, which would both further the cause of personalized medicine and generate biomarkers of sensitivity or resistance to specific drugs, and they’re relying on the world’s first repository of brain metastasis living samples.