A surprising source to identify at-risk patients for early management of chronic disease

  • Small
  • Medium
  • Large

Diagnostic Imaging has the ability to significantly improve healthcare outcomes by looking at data not readily seen by a radiologist, but by a "second set of eyes" from computer algorithms. This technology hasn't yet sent shockwaves through healthcare, but it will.

Seeing the Data
Medical images today are universally stored as digital data comprised of pixels (2D "picture elements"). These pixels are digitally-encoded representations of the physical properties in the underlying 3D slice of biological tissue. Representative shades of gray or color are assigned to and encoded in the pixel.
These digital representations of tissue lend themselves to computations using algorithms (program steps or calculations) specifically designed to extract insights from the images by identifying discriminating, informative features. These algorithms return reliable, repeatable results that produce incidental findings in Imaging. Vastly increased computer processing power allows the algorithms to work in tandem with radiologists to examine all the data in an image, making each image more valuable.

Algorithm Identifies Biomarker for Coronary Heart Disease
Coronary artery calcium is a biomarker of coronary heart disease. Quantification of coronary calcification is a strong predictor for cardiovascular events (heart attack or strokes). Up to now, risk factors such as smoking, obesity, hypertension, and hyperlipidemia were seen as risks and preventive treatment initiated. However, every year approximately 600,000 individuals with no symptoms or warning signs die from a sudden heart attack or stroke.1

From a chest CT scan (performed for any reason), a calcification scoring algorithm can be run in the background and detect the amount of calcium in coronary arteries. Research reported in an article in the February 2017 issue of JAMA Cardiology found that any measureable amount of calcium in middle aged individuals is directly linked to an elevated risk of myocardial infarction, both fatal and nonfatal, within the next decade.2 Even very low calcium scores increased a person's risk of stroke, heart attack and death. If a patient and the person's healthcare provider get this information while the patient is still asymptomatic, they have the opportunity for early, aggressive treatment, regardless of other risk factors.

Other Algorithms for Chronic Disease Management
Chronic diseases are responsible for 7 of 10 deaths each year, and treating people with chronic diseases accounts for 86% of our nation's health care costs, according to the Center for Disease Control and Prevention (CDC). Identifying patients at risk early is critical to improving outcomes and reducing costs.

Another FDA approved algorithm can produce incidental findings for an abnormal fatty liver, which is closely linked to metabolic syndrome, and nonalcoholic fatty liver disease, which is the most common form of chronic liver disease. There is also a strong link with coronary heart disease.

A lung density algorithm can spot low density (areas of trapped air) in the lungs to identify risk of emphysema or COPD. A follow-up inspiration and expiration CT, with an algorithm analysis, can provide a fully automated quantification and visualization of lung structure to more rapidly identify the extent of the disease and for treatment planning.

Bone density can be derived from an algorithm using CT scans of the chest and abdomen. The result is a T-Score equivalent to a DEXA scan to identify osteoporosis. Since osteoporosis is asymptomatic until a bone is fractured, early detection would be unlikely.

Effective Adoption
With any new technology, people and process alignment is key. In healthcare, effective adoption of new technology requires effective organizational leadership, change management, process redesign and participation of all stakeholders. Here are some issues to consider:

Communication. How will the organization communicate these Imaging incidental findings? There needs to be a coordinated effort with the radiologist, primary care physician/team and the patient. The algorithm results can be a separate HL7 transaction link to the EMR, care coordination solution, and/or part of the radiology report.

Education. How and by what means will the organization educate the primary care physician and the patient on the meaning of these findings? Early intervention and management of chronic disease is within the domain of the primary care provider. The facts derived from the algorithms need to be understood by both the primary care team and the patient.

Follow-Up. How will the organization ensure that this information will be acted upon? One tactic is to put the incidental findings in writing for a patient. Follow-up is ultimately influenced by the relationship the patient has with their primary care physician/team, who can put the findings in the context of the patient's current health.

Care Delivery. What process will the organization use with ER patients who have no primary care physician? Most ER's have a referral system for primary care, but it's important to close the loop to ensure the patient and the primary care team are aware of the findings and the need for early intervention.

Driving Quality and Patient Centered Care
Combining early warning information to patients with education to help them understand the meaning of the information provides a unique opportunity to actively engage patients. A patient thus empowered will more likely commit to follow up and make the life style changes needed to optimize their health and well-being.

Diagnostic Imaging algorithms provide definitive, actionable incidental findings for early intervention and management of chronic disease.

The views, opinions and positions expressed within these guest posts are those of the author alone and do not represent those of Becker's Hospital Review/Becker's Healthcare. The accuracy, completeness and validity of any statements made within this article are not guaranteed. We accept no liability for any errors, omissions or representations. The copyright of this content belongs to the author and any liability with regards to infringement of intellectual property rights remains with them.

Copyright © 2021 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.


Featured Whitepapers

Featured Webinars