Precision Medicine Using AI-Powered Dosing Provides Innovative Way for Hospitals to Reduce Medication Expenses

Hospitals see financial benefits from using AI-powered precision medicine to personalize medication dosing

The number of Medicare beneficiaries with chronic kidney disease (CKD) has increased by 89% over the past decade. It’s one of the reasons why CKD is in the range of precision medicine initiatives for hospitals. Starting January 1, 2022, a new Kidney Care Choices (KCC) model will offer strong financial incentives for healthcare providers to manage kidney care for Medicare beneficiaries.

Along with financial incentives for managing kidney care for different patient populations, related innovations will be of interest to nephrologists and hospital administrators of healthcare systems that offer nephrology services.

Among innovations in kidney care is a new type of precision medicine artificial intelligence (AI)-powered medication dosing technology for chronic conditions, among them chronic anemia and CKD. The precision medication technology comes from a little-known company called Dosis, which was founded in 2017.

Dosis’ initial technological product, the Strategic Anemia Advisor, has been used in over 15 million treatments, according to the company. Strategic Anemia Advisor personalizes the dosing of medications used to stimulate the synthesis of red blood cells in dialysis patients who normally have low red blood cell levels.

This AI-driven medication dosage product comes as researchers have been making progress in the application of such computer-driven methods to serve patients with anemia resulting from chronic kidney disease.

Using AI to Recommend Personalized Medication Doses for Chronic Conditions

By using AI to recommend personalized doses for individual patients, patients are able to reach therapeutic red blood cell levels more quickly and by using less medication. This saves dialysis centers or hospitals administering dialysis the costs associated with the medications while simultaneously creating therapeutic conditions that should lead to better outcomes.

A new AI-driven tool may prove value in preventing negative effects of long-term incorrect medication dosing, explains Shivrat Chhabra (above), CEO of Dosis Inc. (Photo: LinkedIn)

“One-size-fits-all recommendations are typically imprecise because they tend to be based on data from clinical trials that may or may not accurately reflect the results that a particular patient may experience,” Shivrat Chhabra, CEO of Dosis, said in a recent interview. “They also cannot easily be adapted to reflect a patient’s actual response. AI-based precision dosing approaches, on the other hand, use an individual’s actual demonstrated response history to calculate optimal dosing, which allows for much greater precision.”

Adverse Events Related to Incorrect Dosing

Precision-dosing techniques today focus on increasing and decreasing dosage depending on a patient’s actual response to a drug. “In most instances, it is in a patient’s best interest to receive the smallest amount of a drug required to achieve the desired therapeutic effect,” Chhabra said, “as greater exposure to some drugs may be associated with higher risk of serious adverse events.”

By providing a patient-specific dosing regimen, Chhabra believes hospitals and other clinical providers can help patients to avoid the long-term consequences of incorrect dosing. “When patients are on medication regimens to manage chronic conditions for months and years, the consequences of getting the dosing wrong build significantly over time,” Chhabra said. “Conversely, the benefits of getting the dosing right and managing the condition well also grow over time. These increased stakes make artificial intelligence an especially important tool in the management of chronic conditions.”

Ultimately, Chhabra believes that AI-directed precision medicine is the future of medical treatment. An algorithm that leads to fewer complications and reduces medication use has the potential to reduce treatment expenses.

“I believe AI-powered dosing algorithms will be accepted as the standard of care,” Chhabra emphasized. “In five to 10 years, we have good reason to believe that the majority of therapeutic drugs for chronic diseases will be dosed using AI-enabled precision techniques. Precision dosing already is being proven to be able to provide significant improvements in dose efficiencies and ease of dosing.”

FDA Supports Piloting of Real-World Performance Monitoring of AI in Healthcare

As precision medicine becomes a more essential component of medical treatment in the United States, AI-driven tools for chronic condition management will find their place in personalized treatments. The U.S. Food and Drug Administration has been weighing in on it. In January 2021, the FDA released an action plan for artificial intelligence/machine learning (AI/ML)-based software as a medical device (SaMD). It is relevant for all stakeholders.

Advancing real-world performance pilots in coordination with stakeholders and other FDA programs will provide additional clarity on what a real-world evidence generation program could look like for AI/ML-based SaMD, according to the FDA. Ultimately, the work will contribute to the knowledge base and clinical validation around the value of specific precision medicine approaches.

Regardless, a tool that safely and effectively assists physicians, clinicians, and nurses with making decisions around personalized drug dosages, in ways that align with better health outcomes and high-value healthcare for patients, may enable practical application of precision medicine in the clinical setting.

—Caleb Williams

Related Information:

Healthcare Expenditures for Persons with CKD

Kidney Care Choices (KCC) Model first performance year


Personalized Anemia Management and Precision Medicine in ESA and Iron Pharmacology in End-Stage Kidney Disease

Dosis Develops Artificial Intelligence Powered Personalized Dosing Platform

AI-powered precision drug dosing can boost outcomes and cost efficiency

Artificial Intelligence/Machine Learning (AI/ML) Software as a Medical Device Action Plan

Setting the Foundation for a Best-in-Class Precision Medicine Program: Four Steps to Guide Hospital and Health System Leaders