last posts

Primary care needs artificial intelligence to identify and treat metabolic disorders early


Use technology instead of waiting for your population to reach chronic disease.

I’m a fifth-generation western Kentucky native, and I’m told that one of my great-grandfathers was the only person drafted into the Civil War for the Marshall County Union. I did my pediatric training at Washington University at St. Louis Children’s Hospital. I was fascinated during my interview process with remote children’s hospitals like Seattle Children’s. In the end, I contacted my program officer Jim P. Keating and decided to stay close to home around Paducah, Kentucky. It made sense to stay nearby in a large medical specialty group after residency, but after seven years I decided to do a solo home practice in St. Louis, Missouri. Concierge medicine was warming up, but I think the industry found it a bit odd. In 2009, I received a phone call from the Mayo Clinic asking me to present at the Transform Symposium on “Customer Experience”. Shortly after, Brian Dolan of MobiHealthNews called me “the first iPhone doctor” for apparently having my medical practice rigged on my iPhone while pulling e-commerce payments.

Status quo medicine has never been my thing.

I decided to try my hand at rural solo practice in the very county my great-grandfather was from. The return to Kentucky was brutal. I went from doing house calls in many of the wealthiest zip codes in the country, to treating families the least. The thing that impressed me most about the area after being away for so long was the sudden deaths of high school friends in their 40s. Obesity was endemic. Everyone had some chronic illnesses. I did not recognize my friends. Something horrible happened while I was gone.

Patients were arriving, eager and so thrilled that I was even there. I would tell teenagers and their families what to do during their exams. Families who never drink water. Families who don’t like vegetables. A year later, they would only come back for having gained 10 pounds rather than losing any. Then a patient came in and had lost weight using one of the consumer apps. I could see the value, but noticed that I hadn’t really provided that value. Fortunately, Doximity and Healthtap came calling with counseling roles and a full-time telemedicine offer that I couldn’t refuse. Before I knew it, I was recruiting our team to solve this blind spot in healthcare: the time between visits in which patients go from obesity, prediabetes and prehypertension to a chronic disease on their own whole.

Today there is an app for everything. Wearables are ubiquitous. Mobile consumer health programs, employer-run programs, and payer-run programs are available for patients to improve their health. But where is the primary care provider? We drown in problems and struggle with burnout. We are expected to take responsibility for results, but without any prior training (or tools) to influence health behavior change.

Robert Wilson, MD, succinctly laid out his problem in this recent episode of the Startup Health Now podcast. Medical practices are inherently reactive, and the challenge of building proactivity into this system is a top priority:

“Many primary care providers are unhappy with the status quo. We don’t like the fact that we have to wait until someone is sick to really pass on our clinical judgment. So we would like to find ways to integrate prevention and harm reduction and all of those things into our daily practice. Especially family medicine. We take care of the whole family. When we give our advice, it affects the whole family. So if we have a system of apps or integrations that will allow us to deliver that information faster, it will be something much more meaningful. »

I attended a telehealth conference in 2022 led by Eric Thrailkill and his team at the Nashville Entrepreneur Center. I was sitting in the audience trying to dig deeper into the vendor issues highlighted by Nashville medical school leaders. Several themes related to patient-generated data emerged from the noise.

There is a firehose of patient-generated data, but:

  1. It’s not filtered.
  2. It is not actionable.
  3. It doesn’t fit into my workflow. (I am not get this information right time.)

Then there are the patient issues, described succinctly in this infographic from the US Centers for Disease Control and Prevention. Heart disease, cancer, chronic lung disease, stroke, Alzheimer’s disease, diabetes and chronic kidney disease: these are the major drivers of the $4.1 trillion health care costs in our country.

The challenge in primary care is to systematically learn about the entire population, educate the population about their risk, quantify their level of motivation, and then stratify patient populations into groups. Everything must fall together at the right time. You need to deliver actionable data to primary care physicians before their patients leave the office. Then they can implement the provider-led interventions you’ve created to engage patients in that healthcare “blind spot” as chronic conditions progress.

I’m a pediatrician, so the solution to our chronic disease problem has been obvious to me and my colleagues in primary care for a long time. The Affordable Care Act works in reverse impact hospital costs:

  • Waiting for a 74-year-old patient with heart failure to come home from the hospital to enroll in chronic disease management or remote monitoring is too long.
  • Waiting for a 64-year-old patient to be diagnosed with diabetes and then focusing on their medication adherence data and analyzes is too long.
  • Waiting for a 59-year-old obese patient to develop diabetes and hypertension and then “managing his condition” with medication and visits to a specialist is too long.
  • Waiting until a 42-year-old overweight man develops a full picture of metabolic syndrome to then discuss drug therapy is waiting too long.

We need to embed prevention across our entire patient population and automate as many of these processes as possible with algorithms and artificial intelligence to make our days easier, engage our patients, and show them we care.

Patients today are ready to live happily and healthily at home, free from metabolic disease. Now is the time for providers to lead the way by delivering engagement programs and provider-led interventions that will create drastic cost reductions early in our populations at increasing risk.

Natalie Davis, MD, is a pediatrician and Chief Medical Officer of PreventScripts. She is a graduate of Murray State University, University of Kentucky Medical School, and Washington University Pediatrics at St Louis Children’s Hospital. She became obsessed with mobile technology and its potential to change people’s health while serving on the advisory boards of Healthtap and Doximity.




Font Size
lines height