We propose a novel approach for interpreting deep embeddings in the context of patient clustering. We evaluate our approach on a dataset of participants with type 2 diabetes from the UK Biobank, and demonstrate clinically meaningful insights into disease progression patterns.

A novel artificial intelligence-based tool predicted treatment failure with … Their next study showed that a deep learning approach using 2D MRI …

He also mentioned the following five general steps for the use of machine learning in cancer and thrombosis: Start by defining venous thromboembolism …

Artificial intelligence is exactly that — it would recognize patterns that you might not otherwise recognize if you relied only on your small …

The US Food and Drug Administration (FDA) has authorized marketing of artificial intelligence (AI) software to help pathologists detect prostate cancer. The program, called Paige Prostate, is the first approved AI system in pathology. "We really believe this product can make a huge difference," Paige CEO Leo Grady, PhD, told Medscape Medical News. The program was approved as an adjunct to pathologist review, not a replacement. Grady explained that "for a second opinion today, you ship a glass slide to somebody else or you do another stain that's really expensive or you do another molecular test."

As far back as the 1970s, doctors have pondered whether one day, as medical technology barrels ahead, the patient history and physical examination (H&P) would eventually become obsolete. And yet, we were all told in medical school that a proper history is enough to make X percent of diagnoses, which increases further when you work in physical findings. But today we are on the brink of the era of multiomics, a term encompassing the numerous data available for patients, from genomics, epigenomics, proteomics, microbiomics, metabolomics, and an array of other omics. These days, a health dataset from a single patient can be immense, to be sure. Advances in artificial intelligence and machine learning, however, are making it possible to organize and filter multiomic data from a patient in ways that make them useful to physicians--ways that can personalize diagnosis and care, and bypass the often imperfect recollections of patients and patients' families obtained during a history.

In the past several years, I have prepared a "top 10" list of biomedical advances. For 2018, I am instead highlighting a few areas that are fast- moving, are attracting considerable attention, and have transformative potential. Those three areas are genome editing, artificial intelligence, and the gut microbiome. There has been steady progress with illumination of biology using CRISPR (among other editing tools, such as transcription activator-like effector nucleases [TALENs] and zinc finger nucleases). One example was taking the BRCA1 gene and systematically editing its nucleotides and assessing functional changes.[1] In just one study, we could ascertain functional effects of hundreds of mutations that took more than a decade for a genomics company (Myriad Genetics; Salt Lake City, Utah) to determine via family studies.