A single Chest X-ray Could Predict 10-Year CVD Risk

Researchers presented in the 2022 RSNA Annual meeting the results of a deep-learning model (AI) based on which a single chest x-ray could predict a patient's 10-year risk of dying from a heart attack or a stroke.

They tested the algorithm against a group of 11,430 outpatients, with an average age 60-years who underwent outpatient chest x-ray and were potentially eligible to receive statins.  Of those patients ,1096 or 9.6% had a major adverse cardiac event in a median 10-year follow up.

There was a significant association of the CVD risk found by chest x-ray and those found with MACE.

This is an example on how AI could detect clinically relevant outcomes with a widely used and low-cost screening test.

The paper was presented at 2022 RSNA meeting, Abstract T#-SSCH04-1

As today is the first of a new year I want to wish you all a happy and healthy 2023.  I would like to thank the 14,000+ who read the 174 posts I published the last 7 years.  

I also want to extend my sincere appreciation to three mentors of mine; my late Chairman Dr. V Capek MD and late Dean B. Siegel MD at UIC and Dean M Tzagournis MD at OSUMC for guiding and supporting me during my academic career. Also the many associates and trainees who daily enriched my experience in our specialty that had an explosive growth in the last 50 years.  

Finally, I want to let you know that starting next month the blog will have a new editor, a talented young radiologist, who with her ideas and knowledge of recent developments and advances in Radiology will make Radiology Monthly better for the benefit of all who read it.

AI Matches Radiologists in Diagnosing Lung Cancer.

 A study published in Radiology found that deep learning artificial intelligence (AI) algorithm diagnosed lung cancer from chest radiographs at a rate similar to radiologists.  The researchers tested it on 10,285 radiographs form 10,202 individuals with 10 radiographs with visible cancer.  The algorithm showed comparable sensitivity 90% to 60% for the radiologists.  In a screening cohort of 100,525 chest x-rays from 50,070 individuals with 47 radiographs with lung cancer, the algorithm's sensitivity was 83% and false positive rate was 3%.  The investigators suggested the algorithm could prove useful especially for clinicians treating healthy persons with lower prevalence of lung cancer.

Chest X-rays Highly Predictive of Covid-19

A paper published in Radiology; Cardiothoracic Imaging reports on a study of 366 patients who had a clinical presentation suspicious for Covid-19.  Radiologists reviewed the patients' chest X-rays along with concurrent reverse polymerase chain reaction (RT-PCR)  virus tests.  The patients mean age was 52.7 (range 17-98 years). RT-PCR tests took an average of 2.5 days until a final diagnosis became available. Radiologists found characteristic X-ray pattern such as confluent, ground glass opacification in the mid and lower lung fields highly specific (96.6%) with a positive predictive value of (83.8%) for making the diagnosis of SARS-CoV-2 viral infection.   

iPad is Accurate in the Diagnosis of Pediatric Pneumonias

In the 51^st annual meeting of the European Society of Pediatric Radiology in Amsterdam, Papaioannou et al from Mitera Hospital in Athens, and Ohio State University in Columbus , Ohio presented their findings regarding the accuracy and usefulness of the iPad in the diagnosis of pneumonias in neonates and infants.

The chest x-rays of 99 consecutive cases were retrospectively evaluated. Findings included consolidation (19), patchy densities/air-space shadowing (7), diffuse air-space shadowing (4), bilateral peribronchial thickening (18), peribronchial thickening and consolidation (4), RLL Hyperinflation (1), patchy hyperlucencies (2) and coarse pattern (2). The images were anonymized and distributed after randomization to two experienced pediatric attending radiologists and two fellows. Diagnostic monitors and a non-retina display iPad2 device were used for viewing the studies.

On the diagnostic monitors, the correct/incorrect ratio was 139/59 for the attendings and 137/61 for fellows. On the iPad, it was 141/57 and 150/48 respectively. In the detection of lung disease, the iPad sensitivity was 79.8%, specificity 64.9%, PPV 5.5% and NPV 70.3%. As a group the attendings and fellows correct/incorrect ratio was 276/120 on the monitors and 291/105 on the iPad. There was no difference in the accuracy of interpretation or the performance depending on the device used among attendings and fellows.

The authors concluded that although diagnostic monitors will continue to be the device of choice in Radiology departments, mobile tablets will play an increasingly important role in the radiographic detection of lung disease in neonates and infants in the intensive care units, emergency department and/or for teleradiology purposes.

John Spigos, BS