Nooshin Abbasi is a post-doctoral research fellow at Brigham and Women's Hospital, Harvard Medical School, and a former research fellow at the Montreal Neurological Institute, McGill University. Her research interests include brain imaging, evidence-based imaging, and bioinformatics, with a focus on applying machine learning tools to large clinical and imaging datasets. Michael Dohopolski is a PGY5 radiation oncology resident. He has worked with Dr. Wang and Dr. Jiang at UT Southwestern on machine learning based clinical decision-making support tools with an emphasis on single prediction uncertainty estimation. She is in the Department of Neurosurgery, University of Pennsylvania, and Division of Neurosurgery, Children's Hospital of Philadelphia.

Radiologists today play a key role in making diagnostic decisions and labeling images for training A.I. algorithms. Low inter-reader reliability (IRR) can be seen between experts when interpreting challenging cases. While teams-based decisions are known to outperform individual decisions, inter-personal biases often creep up in group interactions which limit non-dominant participants from expressing true opinions. To overcome the dual problems of low consensus and inter-personal bias, we explored a solution modeled on biological swarms of bees. Two separate cohorts; three radiologists and five radiology residents collaborated on a digital swarm platform in real time and in a blinded fashion, grading meniscal lesions on knee MR exams. These consensus votes were benchmarked against clinical (arthroscopy) and radiological (senior-most radiologist) observations. The IRR of the consensus votes was compared to the IRR of the majority and most confident votes of the two cohorts.The radiologist cohort saw an improvement of 23% in IRR of swarm votes over majority vote. Similar improvement of 23% in IRR in 3-resident swarm votes over majority vote, was observed. The 5-resident swarm had an even higher improvement of 32% in IRR over majority vote. Swarm consensus votes also improved specificity by up to 50%. The swarm consensus votes outperformed individual and majority vote decisions in both the radiologists and resident cohorts. The 5-resident swarm had higher IRR than 3-resident swarm indicating positive effect of increased swarm size. The attending and resident swarms also outperformed predictions from a state-of-the-art A.I. algorithm. Utilizing a digital swarm platform improved agreement and allows participants to express judgement free intent, resulting in superior clinical performance and robust A.I. training labels.

A recently developed data science pathway for fourth-year radiology residents will help prepare the next generation of radiologists to lead the way into the era of artificial intelligence and machine learning (AI-ML), according to a special report published in Radiology: Artificial Intelligence. AI-ML has the potential to transform medicine by delivering better and more efficient healthcare. Applications in radiology are already arriving at a staggering rate. Yet organized AI-ML curricula are limited to a few institutions and formal training opportunities are lacking. Three senior radiology residents at Brigham and Women's Hospital (BWH) in Boston recently helped devise a data science pathway to provide a well-rounded introductory experience in AI-ML for fourth-year residents.