Health IT

Healthcare information (HIT) systems are designed to connect all the elements together for patient data, reports, medical imaging, billing, electronic medical record (EMR), hospital information system (HIS), PACS, cardiology information systems (CVIS)enterprise image systemsartificial intelligence (AI) applications, analytics, patient monitors, remote monitoring systems, inventory management, the hospital internet of things (IOT), cloud or onsite archive/storage, and cybersecurity.

Charles E. Kahn, Jr., MD, MS, editor of the the RSNA journal Radiology: Artificial Intelligence, and professor and vice chair of radiology at the University of Pennsylvania Perelman School of Medicine. He discusses the need to validate artificial intelligence (AI) algorithms with your own patient population to determine if it is accurate for a specific institutions patients. He also explains how bias can be inadvertently added into a algorithm, and how the AI may take learning shortcuts. #AI

VIDEO: Assessing radiology AI and understanding programatic bias 

Charles E. Kahn, Jr., MD, MS, editor of the the RSNA  journal Radiology: Artificial Intelligence, and professor and vice chair of radiology at the University of Pennsylvania Perelman School of Medicine, discusses the need to validate AI algorithms with your own patient population data.  

Google Cloud intros ambitious branch dedicated to medical imaging

A Big Four tech company has launched a platform it hopes will accelerate data interoperability and AI adoption in, specifically, medical imaging.

Thumbnail

Transplanted lungs react to COVID in a distinctive way

Clinicians treating COVID-19 patients who have transplanted lungs and lower airway infection should order molecular testing in addition to, or regardless of, imaging findings.

Monique Rasband from KLAS Research shares trends in PACS and radiology informatics.

VIDEO: 6 key trends in PACS and radiology informatics observed by KLAS

Monique Rasband, vice president of imaging, cardiology and oncology, KLAS Research, shares some of technology trends observed in radiology PACS and and imaging informatics since 2019.

Validation and testing of all artificial intelligence (AI) algorithms is needed to eliminate any biases in the data used to train the AI, according to HIMSS.

VIDEO: Understanding biases in healthcare AI

Validation and testing of all algorithms is needed to eliminate any biases in the data used to train the AI, according to Julius Bogdan, vice president and general manager of the HIMSS Digital Health Advisory Team for North America.

Thumbnail

For monitoring purposes, AI-aided MRI does what liver biopsy does with less risk, lower cost

Patients with autoimmune hepatitis may be better monitored across disease stages by AI-augmented multiparametric MRI than by liver biopsy, as the imaging has proven less costly and is inherently less risky due to its noninvasiveness. 

On review, popular imaging decision aid earns 1 thumbs-up—with caveats

With 91% sensitivity but only 25% specificity, the tool is worthwhile for clinicians who remain wary of frequent false positives that would send patients with no fractures for unneeded imaging.

Self-supervised AI ‘reads’ radiology reports to speed algorithm development

A machine learning system has come along that needs no human labeling of data for training yet matches radiologists at classifying diseases on chest X-rays—including some that the model was not specifically taught to detect.

Around the web

The patient, who was being cared for in the ICU, was not accompanied or monitored by nursing staff during his exam, despite being sedated.

The nuclear imaging isotope shortage of molybdenum-99 may be over now that the sidelined reactor is restarting. ASNC's president says PET and new SPECT technologies helped cardiac imaging labs better weather the storm.

CMS has more than doubled the CCTA payment rate from $175 to $357.13. The move, expected to have a significant impact on the utilization of cardiac CT, received immediate praise from imaging specialists.