'In Silicon Valley, some have suggested that the pope doesn't know what he's talking about.' 'In Silicon Valley, some have suggested that the pope doesn't know what he's talking about.' The intelligent and thoughtful encyclical is an important warning of the uses and misuses of a rapidly developing technology. O ften I'm asked if I think that the novels of the future will all be written by AI. Do I worry that a machine can do what I do, only better? I usually say something like: "No algorithm is going to write Anna Karenina!" which is also not a real answer.

Many therapies are effective in treating multiple diseases. We present an approach that leverages methods developed in natural language processing and real-world data to prioritize potential, new indications for a mechanism of action (MoA). We specifically use representation learning to generate embeddings of indications and prioritize them based on their proximity to the indications with the strongest available evidence for the MoA. We demonstrate the successful deployment of our approach for anti-IL-17A using embeddings generated with SPPMI and present an evaluation framework to determine the quality of indication finding results and the derived embeddings.

Dr. Steven Waldren, vice president and chief informatics officer at the American Academy of Family Physicians, right, and Dr. Kamel Sadek, director of informatics at Village Medical, speak at the HIMSS22 conference in Orlando. ORLANDO, Fla. – Even before COVID-19 made the business of healthcare a nightmare for countless physicians and clinicians, burnout was a prevalent issue. And even the slow, still-ongoing emergence into normalcy hasn't been enough to ease this trend: Clerical burdens, including clinical documentation, are a major contributor. But for primary care physicians in particular, a new class of technology, including AI-powered digital assistants, is improving their capacity and capability, while reducing their administrative and cognitive burden. Dr. Steven Waldren, vice president and chief informatics officer at the American Academy of Family Physicians, cited data showing that the average patient visit to a PCP takes about 18 minutes, and of that time, 27% is dedicated to face-to-face time with a patient.

NEW ORLEANS -- Artificial intelligence may be used as a refractive surgery diagnostic tool, according to a speaker at Refractive Surgery Subspecialty Day at the American Academy of Ophthalmology meeting. "A robust [machine learning] process generally includes building new variables, which means feature engineering, choosing the most appropriate algorithm, optimizing its parameters, selecting the most predictive features, and understanding the interconnection and patterns between both existing and created selective variables," Marcony R. Santhiago, MD, PhD, said. "Thus, a better identification of patients at higher risk becomes possible regardless of the cutoff point associated with each one of the features." Santhiago described the use of AI in medicine as "human-computer systems," noting the role people play in useful AI includes creating and maintaining the software, selecting which application to use and fixing problems. To create useful AI, he said researchers should ask two key questions.

SAN FRANCISCO--July 28, 2021-- The American College of Radiology Data Science Institute (ACR DSI) and the American Academy of Ophthalmology today announced a collaboration that will expand ACR DSI's groundbreaking AI-LAB platform to include eye care. Leveraging use cases and data from the Academy, this collaboration will accelerate the use of machine learning in the ophthalmic industry to the benefit of patients across the globe. "We've now made it easier for the ophthalmology community to access real world examples for our own use cases. By working together with ACR, we are leveraging a platform developed for the radiology community to educate our own community about AI development and encouraging new AI to be developed that will benefit our specialty," said Tamara R. Fountain, MD, president of the American Academy of Ophthalmology. The Academy will provide the ophthalmology content and the ACR will provide the IT infrastructure to integrate the use cases and datasets into the landmark AI-LAB.

Datasets in sleep science present challenges for machine learning algorithms due to differences in recording setups across clinics. We investigate two deep transfer learning strategies for overcoming the channel mismatch problem for cases where two datasets do not contain exactly the same setup leading to degraded performance in single-EEG models. Specifically, we train a baseline model on multivariate polysomnography data and subsequently replace the first two layers to prepare the architecture for single-channel electroencephalography data. Using a fine-tuning strategy, our model yields similar performance to the baseline model (F1=0.682 and F1=0.694, respectively), and was significantly better than a comparable single-channel model. Our results are promising for researchers working with small databases who wish to use deep learning models pre-trained on larger databases.

Every afternoon Flora, 9, and Kate, 10, turn on their laptops and iPads to collaborate on a play called "World War III," a futuristic tale of two sisters who try to save the world after being blown back in time by a bomb. The close friends, who live a couple miles apart in St. Paul, Minnesota, used to hang out together to dream up dialogue and plot twists. Now, separated by coronavirus social distancing measures, they Skype on one screen and, on the other, type in a Google doc. No longer able to meet up with friends at the movies or the mall, Flora's brother Brodie, 15, stays in touch on FaceTime and Snapchat and through online games Minecraft and Rainbow Six Siege. He says communicating online with high school pals helps him cope with real-world worries about the coronavirus.

An artificial intelligence software platform is able to provide automated real-time screening for quick detection of diabetic retinopathy, without the help of an expert ophthalmologist. The AI platform, called EyeArt from vendor Eyenuk, was used to screen 893 patients with diabetes at 15 different medical locations as part of a new study. Results of the study, which compared EyeArt against experts using the gold standard for visual acuity testing, were presented on Tuesday at the Annual Meeting of the American Academy of Ophthalmology. What researchers found was that the AI platform accurately detected diabetic retinopathy 95.5 percent of the time, using images of patients' undilated pupils. "The system doesn't require the input of an expert ophthalmologist, and it can provide a reading in 60 seconds, making real-time screening possible for primary care practices and diabetes centers," according to the American Academy of Ophthalmology.

Much attention has been given to automatic sleep staging algorithms in past years, but the detection of discrete events in sleep studies is also crucial for precise characterization of sleep patterns and possible diagnosis of sleep disorders. We propose here a deep learning model for automatic detection and annotation of arousals and leg movements. Both of these are commonly seen during normal sleep, while an excessive amount of either is linked to disrupted sleep patterns, excessive daytime sleepiness impacting quality of life, and various sleep disorders. Our model was trained on 1,485 subjects and tested on 1,000 separate recordings of sleep. We tested two different experimental setups and found optimal arousal detection was attained by including a recurrent neural network module in our default model with a dynamic default event window (F1 = 0.75), while optimal leg movement detection was attained using a static event window (F1 = 0.65). Our work show promise while still allowing for improvements. Specifically, future research will explore the proposed model as a general-purpose sleep analysis model.