Augmented intelligence: The next frontier in health imaging
New imaging techniques are helping radiologists, cardiologists, oncologists and other diagnosticians with greater anatomical and clinical details, highlighting the need for fast access to imaging reports and results and collaborative workflows. Augmented Intelligence can ease the workload on health imaging experts and simultaneously improve their performance. AGFA HealthCare reached out to senior radiologists, surgeons and clinical leaders around the world, and has included their responses in the following perspectives.
Task-based workflow optimization
AI will not replace radiologists or other physicians, but in fact enhance their workflow, helping them to make collaborative and intelligent decisions. Enterprise imaging, powered by AI, will help improve radiology even further with task-based workflow optimization. Physicians will obtain faster access to critical results, helping to reduce wait times and improve referral services for cases that require urgent patient care coordination.
In a recent survey, our respondents emphasized the need for exploring the capabilities of machine learning and AI in addressing certain mistakes and errors that could alert radiographers and radiologists, and automate certain nonessential tasks to ease workload. “We should free our experts to undertake expert work by removing as many nonessential tasks for them as possible,” noted Angie Craig, assistant director of operations and performance, Leeds Teaching Hospitals Trust, National Health Service, United Kingdom. “That’s where artificial intelligence comes in.”
Disseminate DL intelligence with AI
As we break down silos of imaging workflows and enable multidisciplinary consolidation and collaboration, the power of a consolidated platform results in the creation of a vast data lake, ready for analysis by radiologists, diagnosticians, researchers and academics to help improve quality of care by better understanding disease and population health data.
This helps care organizations progress from descriptive to predictive analytics models to improve early detection of diseases, and introduce care plan models that help enforce and improve patient engagement and compliance. During discussions with senior radiologists and diagnosticians, we witnessed a consensus regarding the clinical application of AI to help address screening challenges associated with pressing healthcare problems that include cancers, chronic chest diseases, musculoskeletal conditions, neurological disorders and cardiac conditions as well as the detection of various other clinical conditions. When it comes to oncology, our respondents discussed the significance of AI not only for initial diagnosis but also for follow-up after the treatment in helping track the potential recurrence.
“In my group, we’ve already demonstrated that an AI system for chest X-ray triaging and prioritization can lead to much faster reporting turnaround time,” said Giovanni Montana, professor of data science at the University of Warwick, U.K. “We’ve also shown potential diagnostic benefits in early detection of lung cancer.”
Personalized medicine and smart applications
Care organizations and health authorities across the globe are faced with pressing population health challenges. Whether it comes to detecting cancers or chronic diseases, machine learning and advanced analytics will help radiologists and diagnosticians to focus less on manual repetitive tasks, and more on improving care pathways.
“I think one of the biggest contributions deep learning/artificial intelligence will realistically make to me as a radiologist in the near future is not directly helping with image interpretation, but in bringing the relevant information out of the electronic medical record and presenting it to me in a meaningful way to better inform my clinical judgment,” said Bill Anderson, MD, Edmonton zone medical director for diagnostic imaging at Alberta Health Services. “Incorporating this directly into the report will be how we can really add value as radiologists using deep learning. It not only will streamline my workflow but also will be a major step towards more personalized medicine in radiology.”
As the healthcare IT industry drives the progress of augmented intelligence, new imaging techniques will personalize and streamline workflow, improve multidisciplinary collaboration and increase predictive analytics across the continuum of care. Building an ecosystem of augmented intelligence powered by machine learning, cognitive reasoning and a task-based rules engine will help enable innovative solutions to meet the need for rapid and accurate care delivery.
About the Author:
Anjum M. Ahmed, global director of imaging information systems, AGFA HealthCare