Question and Answer with Jeremy Orr, Chief Medical Officer, Medial EarlySign

43

Healthcare Business Today: Can you tell us about Medial EarlySign?

Jeremy Orr: Medial EarlySign identifies as a clinical solutions company, helping health care systems and primary care providers with early detection and prevention challenges. We develop post-analytical models that can provide personalized insights on a variety of chronic and acute medical conditions, such as cancers, diabetes and associated complications. 

At Medial EarlySign, the emphasis is placed on the solution, rather than the mode of how we get there. This means that we study at great length the products that we produce and place clinical efficacy at the center of what we do. We look at a clinical challenge from the perspective of health systems and providers in order to determine what would help them most. 

Healthcare Business Today: Can you give an example of one of Medial EarlySign’s solutions that has been successfully implemented?

Jeremy Orr: One of our algorithmic solutions, LGI flag, utilizes routine EHR data to identify individuals at high risk of serious lower GI conditions. When a patient is identified at risk for LGI disease, this can be due to several LGI conditions mostly associated with bleeding such as inflammations, ulcers, adenomas and colorectal cancer. We help our clients find these conditions through surveying routine lab data, in this case blood counts, to detect subtle changes – even within the normal range – that may be signs of occult gastrointestinal bleeding. Patients that have those signals are flagged for further intervention, often a colonoscopy. Studies have shown that patients flagged by our system in the top 3% risk level are six times more likely to have serious lower GI conditions than those not flagged. 

Another example is our diabetes algorithm which looks at hemoglobin A1c and glucose testing, both of which are very common in screening and routine care. In looking at a population with prediabetes, our algorithm can determine which subset is most likely to become fully diabetic within 12 months. Approximately one-third of the U.S. adult population are prediabetic, with some 3% expected to become diabetic within one year without intervention. For a health system, the ability to determine which patients to prioritize for intervention and lifestyle changes would prove invaluable.  

Healthcare Business Today: How do you differentiate from your competitors?

Jeremy Orr: One key differentiator is that we ensure not only the technological effectiveness of our solutions, but also that they are easily integrated into our customers’ existing workflow. For a fully effective solution, multiple factors must be considered aside from the technical component. Before implementation, the first step is delving into a client’s workflow to understand their existing processes, including who the clinical stakeholders are, how the client communicates with patients, how patients are scheduled for appropriate interventions, and how messaging is achieved.  

We also measure the effectiveness of our technology once it is implemented, comparing the number of patients contacted, how many are scheduled for intervention and the results of the interventions.  Each client serves as a mini-study of effectiveness. 

Healthcare Business Today: Can you tell us about some of the challenges of implementing your solutions?

Jeremy Orr: Prediction models have been around for decades in various forms. Artificial intelligence is only the latest, most powerful version of this. However, the most challenging component of any implementation is how much attention a system gives to ensuring that the solution succeeds. In the past, models have failed due to a healthcare system’s complexity. Work processes tend to be complicated and employees, comfortable with their current systems, are often opposed to change. Physicians and nurses, already overburdened with numerous daily duties, will tend to eschew additional responsibilities due to the limited resources they have available to devote to it. 

When a new system is implemented, it often fails from a lack of follow up or measurement of effectiveness over time. This creates a landscape of failed predictors simply because of poor implementation and lack of follow up. Medial EarlySign focuses on some key factors to overcome this challenge: we find out what clients are currently doing to detect and predict for a given condition, how patients are being contacted for screening, and what efforts are in place to address care gaps.  With this simple information, we understand where our clients are and therefore can complement what they are currently doing, rather than disrupting the existing system.  

Additionally, we engage stakeholders early on, to understand the behavioral psychology of each party. From care managers to physicians and clinicians to the patient, we understand the process of how a patient is encouraged to have a screening they should be having anyway. By understanding each stakeholder, we can explain our system and ensure that each party is comfortable with the technology and care plan, directing conversations with the client and ensuring that proper screenings are taking place. 

Dr. Jeremy Orr, Chief Medical Officer for Medial EarlySign, has more than 20 years of clinical medical practice, population health, and healthcare IT experience. A practicing, board-certified family physician, Dr. Orr was named a “Top 100 Physician” during his time with Kaiser Permanente, and then went on to launch a medical practice that became part of Centura Health. While an Assistant Professor at the University of Colorado, he was selected as Teacher of the Year by residents. Prior to joining EarlySign, Jeremy served as the CMO of Boston-based clinical data analytics firm Humedica (later Optum Analytics) and as CMO of Los Angeles based clinical decision support company Stanson Health. Jeremy earned his MD at University at Buffalo and his MPH at Tulane.

LEAVE A REPLY

Please enter your comment!
Please enter your name here

four × 1 =

This site uses Akismet to reduce spam. Learn how your comment data is processed.