Dr. George Aronoff is the Chief Medical Officer at Dosis, and he has over 30 years of experience in nephrology. He was previously Chief of Nephrology & Hypertension at the University of Louisville, where his research with Drs. Brier and Gaweda focused on using AI to dose ESAs in dialysis patients. He received his M.S. in Pharmacology and M.D. from Indiana University.
Dosis’ first product, Strategic Anemia Advisor, is a web-based reference tool that personalizes dosing of ESAs, a class of drugs used to treat chronic anemia.
Could you begin by explaining what is the innovative AI-based dosing platform Strategic Anemia Advisor (SAA)?
Dosis’ Strategic Anemia Advisor (SAA) is an artificial intelligence (AI)-based clinical decision support system that’s been engineered to improve health outcomes of End-Stage Kidney Disease (ESKD) patients and reduce drug costs by an average of 25 percent by personalizing drug dosing. More than 550,000 End-Stage Renal Disease (ESRD) patients in the U.S. are currently undergoing dialysis treatment, and the majority of those patients experience chronic anemia. SAA is based on more than 10 years of research at the University of Louisville and was specifically designed to assist clinical anemia managers with their recommendations for Erythropoiesis Stimulating Agents (ESAs) dosing.
What are some of the benefits of offering personalized dosing recommendations?
AI helps clinicians determine the minimum dose required to achieve the desired therapeutic outcome, which has both clinical and economic benefits. In the case of dosing ESAs, inefficient dosing can result in significantly higher than necessary drug exposure for patients, and correspondingly elevated costs of care. SAA is focused on fine-tuning dose titrations based on a patient’s demonstrated drug response. As dose changes are made regularly, it is in a patient’s best interest to receive the smallest amount of a drug, as greater exposure to ESA is associated with higher risk of heart attack, stroke, thrombosis, and cancer recurrence.
As the leader in this area, Dosis’s SAA delivers a solution that has had proven results, which have allowed it to gain widespread acceptance by top dialysis organizations. To date, SAA has been used to deliver over 2 million dosing recommendations.
Drug dosing driven by AI is gaining ground in many areas of medicine, such as dialysis, cancer and transplant medicine. It is in these areas that increasingly precise dosing plays a critical role in achieving favorable outcomes. AI-powered precision dosing is particularly impactful in the management of drugs used to manage chronic conditions, as both the potential for adverse events and the cost of care increase over the months and years that patients are on these drugs.
How is artificial intelligence used to identify the recommended dosage amount?
SAA uses artificial intelligence to place patients on a spectrum of ESA dose response, from extreme responder (someone who is very sensitive to a drug) to, essentially, non-responder. This estimation is done by evaluating a patient’s historical response to the drug and constructing a unique response profile for each patient. With each subsequent dose and hemoglobin response, SAA refines that estimation to more precisely achieve the target hemoglobin using the lowest possible ESA dose.
What type of reduction in medication utilization have clinics seen from this?
With consistent use of SAA, clinics have seen on average a 25% reduction in ESA utilization with maintained or improved anemia outcomes, as well as a 75% reduction in time spent managing anemia.
Could you discuss how AI-powered precision dosing will likely be the standard of care for chronic disease management in the future?
To inform dosing decisions, doctors have historically relied primarily on their clinical experience, knowledge of the medications they are prescribing, and paper-based recommendations for dosing from drug manufacturers and the FDA. However, these recommendations are often imprecise, as they draw from clinical studies that may or may not accurately reflect an individual patient’s response to the medication.
Precision dosing has been identified as a crucial method to maximize therapeutic safety and efficacy with significant potential benefits for patients and healthcare providers, and AI-powered solutions have so far proven to be among the most powerful tools to actualize precision dosing.
Today, five factors have come together to make AI-powered drug dosing a reality. They include:
- Technological advancements in computing, which allow us to process large, complex datasets quickly, making AI solutions practical.
- Public familiarity with artificial intelligence as an effective tool for solving complex problems, which makes physicians comfortable incorporating such tools in clinical settings.
- Reliable data is now available in electronic medical records and is standardized in a manner that is much more ingestible by algorithms as compared to free-form paper medical records.
- Big data analytics techniques have also made applying artificial intelligence and control algorithms to complex datasets much more practical and efficient. Today, we can draw on data from millions of patients to design and test algorithms in silicon to predict effectiveness and iterate quickly. This is a vast improvement on expert systems that are based on a clinician’s smaller number of patients, possibly in the thousands or hundreds, that are generally only possible to test in much more costly and risky clinical trials.
- Increasingly complex and powerful drugs have been developed that impact basic physiologic processes. Drugs that impact multiple physiologic processes and have a narrow therapeutic window (the “sweet spot” between toxicity and ineffective therapy) have become more prevalent. These are the types of drugs for which AI-powered drug dosing can provide the most benefit.
Taking it a step beyond precision dosing, what are some of your views on the overall future of personalized medicine?
In 10 years, I believe AI-driven dosing models will likely be the standard of care across the healthcare spectrum, used for a wide variety of drugs like warfarin, insulin and immunosuppressives. Basically, any drug that is administered chronically and has a narrow therapeutic range is a good candidate for AI-driven dosing. In addition, as more tools are developed and more opportunities to use those tools are identified, we will see exponential growth in the use of AI to drive therapies, interpret laboratory and radiographic findings, and predict outcomes of therapeutic strategies.
Is there anything else that you would like to share about Dosis?
Dosis is uniquely positioned to implement AI driven decision support and has a track record of translating high level academic research into practical clinical applications at both small and large scale.
Thank you for the great interview, readers who wish to learn more should visit Dosis.
- Removing Objects From Video More Efficiently With Machine Learning
- AI Hardware Technology Imitates Changes in Neural Network Topology
- Stealing Machine Learning Models Through API Output
- NeRF: The Challenge of Editing the Content of Neural Radiance Fields
- Researchers Create Self-Propelled Artificial Cilia