The power of prayer in primary care; Mayo Clinic, Microsoft and medicine; moving data from routinely collected to scientific breakthrough — Morning Medical Update

Seeking diving healing and help

Researchers found a five-minutes session of proximal intercessory prayer, i.e., led by a trained volunteer in person, helped reduce pain and anxiety in primary care patients, when compared with music. It could be a cheap, safe complement to medical treatment, with effects that can last for weeks and no adverse events. Prayer is the most common form of complementary medicine in the United States, but is little-studied, according to the findings from the University of Maryland School of Medicine. The findings were published in Annals of Internal Medicine, and here is an accompanying news release.

More clinical AI coming

The Mayo Clinic and Microsoft this month announced a new partnership to make Mayo Clinic knowledge available through a new frontier artificial intelligence program. The project aims to “synthesize diverse clinical data to support earlier diagnoses, more personalized treatment decisions and better patient outcomes. “Mayo Clinic is committed to putting patients first, and we have long believed AI can help transform health care. Seven years ago, we launched Mayo Clinic Platform to move healthcare from a pipeline to a platform model through a safe, trusted, patient-centric de-identified data foundation designed to accelerate innovation, breakthroughs, and cures,” Mayo Clinic President and CEO Gianrico Farrugia, M.D., said in a news release. “Now, by combining our clinical expertise and data foundation with Microsoft’s engineering and AI capabilities, we are once again building something new in healthcare and bringing more of Mayo Clinic to more patients.”

Mining data for discoveries

Physicians and other clinicians use systems to collect data — lots and lots of data, some specialized, some routine. There could be new health discoveries awaiting when those facts and figures are analyzed by AI. But having lots of something does not necessarily make it inherently valuable, and making a deep dive into data presents significant challenges. Standards for collecting and using data, and ways to mitigate bias and errors, all could be part of new strategies to improve explanations and predictions, whether generated by classic statistical analysis or AI. Here’s “Using routinely collected data for research purposes: challenges and mitigation strategies,” an article proposing such improvements, in The BMJ.