ChatGPT-assisted diagnosis: Is the future suddenly here?

I have been framing the future of health care as diagnosis through face-to-face interactions for making a diagnosis (and getting the patient to buy-in to the treatment plan) and ongoing maintenance or surveillance using telemedicine with supporting technologies. This article has forced me to reconsider how we might deploy artificial intelligence to support patients and clinicians during the triage and diagnosis stages of a medical journey. “Symptom checkers serve two main functions: they facilitate self-diagnosis and assist with self-triage. They typically provide the user with a list of potential diagnoses and a recommendation of how quickly they should seek care, … Read More

The New Hospital at Home Movement: Opportunity or Threat for Patient Care?

Select Key Findings Policy Issues Debating the Future: Does H@H Save Costs and Improve Patient Care? “[..] Recent studies of cost savings from H@H programs range from 20 percent (Reese 2021) to 40 percent (Brigham and Women’s Hospital in Boston, Levine et al. 2020). But these findings are not generalizable as they are based entirely on single case studies of highly structured programs involving small samples of very carefully selected patients. For example, the study of Brigham and Women’s program examined 91 adults who were admitted to the hospital’s ED and randomly assigned to the hospital vs home for treatment. [..] While … Read More

Telehealth Best Practices: Dr Geoff Rutledge Of HealthTap On How To Best Care For Your Patients When They Are Not Physically In Front Of You

“[Authority Magazine’s Jake Frankel] can you articulate for our readers a few of the main benefits of having a patient in front of you? [Co-founder and CMO of HealthTap Geoff Rutledge] The most important point to emphasize is that the essential physician–patient interaction is direct face-to-face communication that allows a doctor to connect with their patient, engage with them, and enable them to share in detail what is going on with their lives and their health. And that this critical face-to-face communication can occur equally well either in an in-person, in-office setting or via high-resolution video and audio consultation. It’s … Read More

Internal Memo: Amazon Care to shut down, ‘not a complete enough offering’ for corporate customers

Excerpt – Amazon will stop offering its Amazon Care primary health-care services at the end of this year, according to an internal memo, after determining that it wasn’t “the right long-term solution for our enterprise customers.” The surprise move Wednesday is a major course correction in Amazon’s broader foray into healthcare. Amazon says the decision impacts only Amazon Care, and not its other health-care initiatives. “This decision wasn’t made lightly and only became clear after many months of careful consideration,” said Neil Lindsay, Amazon Health Services senior vice president, in the email to Amazon Health Services employees. “Although our enrolled … Read More

Smartphone apps promised to help combat the pandemic. How well did they work?

“A new review paper, published Monday in Nature Biotechnology, explores the wide range of apps rolled out to combat the pandemic [..]. Here are four questions that still need to be answered about how apps can combat Covid. [1] How do you get broad swaths of the public to adopt an app? “Contact tracing had a lot of problems,” said [physician and Director of Digital Medicine at Scripps Research Translational Institute and a co-author of the new paper Jay] Pandit. [..] The initial goal for the U.K. National Health Service’s Covid-19 app was to reach a 60% adoption rate. [..] … Read More

Intravenous Fluids—A Test Case for Learning Health Systems

“Explanatory trials evaluating the efficacy and safety of adding a new drug or device to current clinical care (A vs A-plus) are traditionally powered to detect the smallest difference in clinical outcomes that would justify incorporating the new treatment into care, considering its added risks, costs, and burdens. For example, the median minimal clinically important difference in mortality targeted by acute care trials has been approximately 8%, implying that smaller differences in mortality might not justify incorporation of the new treatments into care. These types of trials ask, “is this new treatment better than current care by enough to offset … Read More

The Telehealth Era is Just Beginning: More gains in quality, affordability, and accessibility are on the way

“Having analyzed health outcomes data from the independent National Committee for Quality Assurance, health plan member satisfaction surveys from J.D. Power, and internal data from our own organizations, we are confident that full implementation of five opportunities would improve clinical quality nationwide by 20%, increase access to care by 20%, and reduce health care spending by 15% to 20%. Reduce Expensive and Unnecessary Trips to the ER Reverse America’s Chronic-Disease Crisis – For members of large multispecialty medical groups such as Kaiser Permanente [KP], high blood pressure is a much more manageable problem [outside of KP, control rates hover around … Read More

Developing a shared sepsis data infrastructure: a systematic review and concept map to FHIR

“There is an urgent need to improve diagnostic excellence in sepsis1. One potential solution is the development of a flexible, scalable, and interoperable data infrastructure to screen and identify sepsis patients across health systems using real-time, granular clinical data available within electronic health records (EHRs). Despite clinical data for millions of sepsis or pre-sepsis patients routinely collected in EHRs, the healthcare enterprise has accessed only a small fraction of these data to improve the clinical understanding of sepsis. The development of a sepsis data backbone could be extended to meet diverse needs, including sepsis translational research, clinical care delivery, machine … Read More

Preventing Delayed and Missed Care by Applying Artificial Intelligence to Trigger Radiology Imaging Follow-up

“[..] artificial intelligence (AI) is well suited to the detection and reporting of follow-up recommendations because of the large volume of imaging studies requiring screening and the relatively standardized language employed by radiologists in preparing reports. Natural language processing (NLP) methods, including text pattern-matching and traditional machine-learning techniques, have been developed for this task. In this article, we use the term traditional machine learning to refer to all machine-learning methods that are not deep learning, and these terms will be defined in detail in the sections that follow. More recently, novel deep-learning methods for NLP have shown great promise for … Read More

Experiences of Health Centers in Implementing Telehealth Visits for Underserved Patients During the COVID-19 Pandemic

“Before the pandemic, most health centers did not offer telehealth visits for primary care or behavioral health, in large part because of reimbursement policy. In spring 2020, dramatic policy changes removed many of the restrictions on telehealth delivery, and health centers responded by standing up large telehealth programs. This sudden and dramatic change in health care delivery posed numerous challenges. Health centers had to quickly make changes to technology, workflows, and staffing to accommodate telehealth visits. To support health centers in these efforts, the California Health Care Foundation established the Connected Care Accelerator (CCA) program, a quality improvement initiative that … Read More