Recent news and commentary covering technology in U.S. healthcare

Claims of burn pit exposure pour in as vets seek PACT Act benefits

“The U.S. Department of Veterans Affairs said it received nearly 113,000 disability claims related to the toxic exposure legislation signed into law less than three months ago, an indication of the potential impact of the measure and the work ahead for the agency. … They include 12 types of cancer and a dozen other respiratory illnesses linked to burn pit exposure in the Gulf War and the wars in Iraq and Afghanistan; hypertension and monoclonal gammopathy of undetermined significance for veterans who served in Vietnam; and radiation-related illnesses for veterans who served in several new locations in the 1960s and early 1970s.”

(Federal Times – October 2022)

Dr. Emily Brigham on the Burden of Climate Change and Urban Lung Health

Urban areas face a concentration of various pollutants that will be exacerbated by the increasing temperatures caused by climate change, and low-income residents likely have fewer resources to withstand negative health impacts, according to Emily Brigham, MD, MHS, of the University of British Columbia.

(The American Journal of Managed Care — October 2022)

Use of Cardiopulmonary Exercise Testing to Evaluate Long COVID-19 Symptoms in Adults

“The findings of this systematic review and meta-analysis study suggest that exercise capacity was reduced more than 3 months after SARS-CoV-2 infection among individuals with symptoms consistent with LC compared with individuals without LC symptoms, with low confidence. Potential mechanisms for exertional intolerance other than deconditioning include altered autonomic function (eg, chronotropic incompetence, dysfunctional breathing), endothelial dysfunction, and muscular or mitochondrial pathology.”

(JAMA Network Open — October 2022)

Pulmonary Dysfunction after Pediatric COVID-19

“Computed tomography has shown persistent damage to the lungs in adults, but CT uses ionizing radiation and has limited diagnostic value in children, where lung changes due to COVID-19 are less pronounced. Both children and adolescents fulfilling the criteria for long COVID disease and those who subjectively had no symptoms after infection showed abnormalities of lung function on MRI [low-field magnetic resonance imaging]. We could see that the regular function of the lungs — which is ventilation and blood circulation — were disturbed in contrast to healthy controls. The changes were still detectable months after first infection.”

(Radiological Society of North America — September 2022)

Contrastive learning and subtyping of post-COVID-19 lung computed tomography images

“For patients dealing with lingering respiratory symptoms from the novel coronavirus, a chest X-ray can reveal only so much. The two-dimensional (2D) scans simply can’t distinguish compromised lung function. For that diagnosis, a more expensive, three-dimensional (3D) technique called a CT scan is necessary. Yet many medical clinics in the United States don’t have CT scanning equipment, leaving so-called long-COVID patients with little information about their lung function. That may change. In a new study, researchers at the University of Iowa have developed what is called a contrastive learning model. This model ‘learns’ from composite 2D images constructed from 3D CT images to detect compromised lung function in long-COVID patients.”

(Frontiers in Physiology – October 2022)

Artificial intelligence applications used in the clinical response to COVID-19: A scoping review

It is relatively easy to develop and test a new AI application and publish the results. It is much harder to deploy that application in clinical practice. The number of machine learning practitioners and journals, together with the availability of data, computing infrastructure, and open-source algorithms, has resulted in a proliferation of academic articles presenting new clinical AI models, including to address COVID-19. However, fewer of these applications have been used in clinical practice, and many of those that have been used are not evaluated in academic literature.

(PLOS Digital Health — October 2022)

The AI Health Care Dilemma

“Although AI is poised to transform business operations across various sectors of the economy, experts agree that it holds heightened potential in the health care industry. … So, why are strides made in health AI met with fear? Health care regulations protect patients from poor quality care, breaches of medical privacy, and inadequate technical standards, but untrustworthy and unregulated AI risks undermining these regulatory safeguards.”

(The Regulatory Review — October 2022)

Challenges to Successful AI Implementation in Healthcare

“The key challenges to successful AI implementation in the healthcare practice are:
1. Ethical & Legal Issues for Data Sharing
2. Training Healthcare Practitioners and Patients to Operate Complex AI Models
3. Managing Strategic Change to Put AI Innovations into Practice”

(TechTarget — October 2022)