AI Model Holds Promise For Autism Assessment, Brain Mapping
Researchers hope the new model can help toward improving backlogged assessment pathways. Other news is on the reporting of hospital-acquired infections, long covid among older adults, a drug trial for late-stage breast cancer, and more.
Scientists have developed and tested a deep-learning model that could support clinicians by providing accurate results and clear, explainable insights—including a model-estimated probability score for autism. The model, outlined in a study published in eClinicalMedicine, was used to analyze resting-state fMRI data—a non-invasive method that indirectly reflects brain activity via blood-oxygenation changes. (9/18)
When a hospitalized patient shows signs of a dangerous, potentially deadly infection, you’d expect clinicians to move quickly: testing to figure out what’s wrong, then treating with the right medicines. But that’s not always what happens. And the reason is often financial: Federal regulators can fine hospitals hundreds of thousands or even millions of dollars if too many of their patients get hospital-acquired infections. (Bannow, 9/22)
A study of COVID-19 patients from 33 states found that those aged 70 and older were less likely to be classified as having long COVID compared with younger adults, US researchers reported earlier this month in the Journal of the American Geriatrics Society. (Dall, 9/19)
Regarding medical treatments —
Roche said a drug combination including its investigational giredestrant met the main goals in a late-stage clinical trial for breast cancer. The Swiss pharmaceutical company said Monday that the study achieved positive results, showing that giredestrant in combination with everolimus significantly improved progression-free survival in patients with advanced breast cancer. The trial evaluated the efficacy of the all-oral drug combination against standard-of-care endocrine therapy plus everolimus, Roche said. (Calatayud, 9/22)
An analysis of antibiotic sales data from 37 countries found that implementation of national action plans (NAPs) for addressing antimicrobial resistance (AMR) was not associated with changes in antibiotic sales, researchers reported yesterday in Infection Control & Hospital Epidemiology. The study by researchers with the University of Pittsburgh School of Medicine and the University of Toronto looked at pharmaceutical sales data from 37 countries 2 years before and 2 years after they implemented their NAPs. (Dall, 9/19)
Earlier initiation of biologic therapy for psoriasis led to complete skin clearance sooner and significantly more often as compared with starting later, a new analysis of a randomized trial showed. Patients who started guselkumab (Tremfya) within 2 years of diagnosis had a 50% higher rate of complete skin clearance after 20 weeks (53% vs 34%) and remained significantly higher at 28 weeks (56% vs 42%). A significant difference favoring earlier treatment persisted through 68 weeks of follow-up. (Bankhead, 9/20)
A quadruplet regimen elicited favorable outcomes in an older population of transplant-ineligible patients with newly diagnosed multiple myeloma (NDMM), according to phase II trial data. (Bassett, 9/20)
