MedCity Influencers, Artificial Intelligence

Hospital precision dosing is ramping up

Artificial intelligence and predictive models are making it increasingly easier for physicians and pharmacists to select the right treatment for the right patient at the right time.

Artificial intelligence (AI) and emerging technologies are bringing exciting changes to hospitals and health systems. With technology advances in recent years, healthcare organizations are increasingly adopting digital health solutions to improve patient care. Clinical decision support (CDS) platforms, for example, are being used by providers to optimize treatment to help make sure drugs work as intended. Precision dosing CDS platforms incorporate AI to give hospitals the ability to reduce medication errors, elevate care quality, and boost cost savings in 2021 and beyond.

Precision dosing specific to hospital settings

Precision dosing is defined as the process of individualizing medication doses by taking into account patient-specific factors such as demographics, clinical characteristics, and genetic data. Precision dosing CDS platforms are critical tools for reducing adverse drug events (ADEs), which are some of the costliest medical complications and add more than $30 billion annually to the U.S. healthcare system. ADEs also result in 1.3 million annual trips to the ED, according to the CDC. Ultimately, ADEs cause numerous negative downstream effects for patients, including longer hospital stays, increased emergency department visits, and higher rates of admissions and readmissions.

Many patients are put at risk for an ADE because drugs are typically developed with the average patient in mind. Drugs are often studied in a few thousand patients during a clinical development program. As a result, many types of patients are not adequately studied in clinical trials, including geriatric patients, pediatric patients, and those who have end organ dysfunction. This has downstream implications since once the drug is approved, it is typically administered more broadly in patient populations not well characterized in clinical trials. These patient groups are at a higher risk of experiencing poor clinical outcomes. In fact, the FDA has reported that medications across a range of therapeutic areas are only effective in 25% to 62% of patients. Precision dosing has the ability to address these two problems through individualized dosing.

Precision dosing is especially beneficial for drugs with a narrow therapeutic window (i.e., drugs with a toxic dose that is very close to the minimum dose needed for the drug to be effective). The approach can also be beneficial for drugs with high inter-patient variability in drug response. Key therapeutic areas for precision dosing include infectious diseases, oncology, blood and marrow transplant, solid organ transplant, and inflammatory bowel disease. For example, precision dosing has worked well when individualizing dosing for vancomycin, an antibiotic prescribed for bacterial infections that can cause acute kidney injury if the dose is too high, leading to longer hospital stays and higher costs.

Today, hospital physicians and pharmacists are incorporating precision dosing into their clinical practices to ensure patients receive the right dose of complicated medications, from intravenous antibiotics to chemotherapy. Hospital clinicians can access precision dosing guidance through an EHR-integrated application that is integrated within their clinical workflow, or through standalone web-based applications.

Sponsored Post

Physician Targeting Using Real-time Data: How PurpleLab’s Alerts Can Help

By leveraging real-time data that offers unprecedented insights into physician behavior and patient outcomes, companies can gain a competitive advantage with prescribers. PurpleLab®, a healthcare analytics platform with one of the largest medical and pharmaceutical claims databases in the United States, recently announced the launch of Alerts which translates complex information into actionable insights, empowering companies to identify the right physicians to target, determine the most effective marketing strategies and ultimately improve patient care.

Modern precision dosing support platforms employ pharmacology models and machine learning, operating on patient-specific data (including demographic, clinical, lab, and genetic information) to help clinicians understand a patient’s individual pharmacological profile to guide dosing decisions. The goal is to make sure each patient receives the right dose at the right time. Precision dosing can be applied to numerous medications and improve patient outcomes by ensuring the patient receives the maximum effective dose while reducing the likelihood of an adverse drug event.

What’s ahead for 2021 and beyond?
We see healthcare continuing its shift from a fixed-dosing mindset to one that embraces individualized dosing, as AI and machine learning advances and precision dosing technology becomes more available at the point of care. We also expect to see an increase in precision dosing and monitoring of specialty drugs as well as conditioning regimens for gene therapy and cellular therapy.

Individualized treatment at the point of care with precision dosing and drug monitoring is also gaining momentum on the tailwinds of the recently revised vancomycin dosing consensus guidelines. The new guidelines call for a shift in monitoring vancomycin based on serum trough levels alone to area-under-the-curve (AUC)-guided dosing with the assistance of Bayesian dosing software, which adapts to varying regimens and changes in individual patients’ physiology during courses of therapy.

In addition to precision dosing at the point of care, we will see greater utility during the drug development process. Biopharmaceutical companies are increasingly incorporating precision dosing into clinical trials and are motivated to bundle precision dosing with new medications used to treat both rare and common diseases in order to maximize the effectiveness of new therapies. This means that once the drug has been approved, clinicians may benefit from immediate availability of a CDS tool that assists in determining an individualized dosing regimen for the newly approved drug.

At the same time, larger hospitals and health systems may also benefit from the ability to tailor pharmacology models to their specific patient populations. Currently, precision dosing platforms use pharmacokinetic models derived from general population data to guide dosing decisions. A health system with a patient population that does not closely resemble the general population that a model is based on may find that the dosing regimens suggested by these models are less accurate, potentially increasing the time taken for patients to reach a target drug exposure.

In the near future, provider organizations will be able to use retrospective data from their patient populations to develop a tailored predictive model unique to their patient demographics, allowing more accurate dosing across their populations. Use of more accurate, population-specific precision dosing models will help organizations improve care quality and reduce costs as they increasingly transition to value-based care and risk-based contracting.

As AI moves into more areas of healthcare delivery, precision medicine will be redefined, and its benefits expanded to more patients. No longer will precision medicine only mean the selection of targeted drugs for patients with a specific genomic profile—an approach that, in oncology, is thought to benefit only ~5% of cancer patients. Precision medicine will grow to include individualized dosing of a broad range of medications already in widespread use across many therapeutic areas. Precision medicine, including precision dosing, not only has positive implications for the patient, but also holds promise for improving hospital and health system operational business models, reducing payer costs, and improving clinical research and drug development.

Photo: Stas_V, Getty Images

Sirj Goswami is the CEO and co-founder of InsightRX, which provides a cloud-based precision dosing platform to help guide treatment decisions. He holds a PhD from the Department of Bioengineering and Therapeutic Sciences at the University of California San Francisco.

This post appears through the MedCity Influencers program. Anyone can publish their perspective on business and innovation in healthcare on MedCity News through MedCity Influencers. Click here to find out how.