Implementation of Pharmacogenomics and Artificial Intelligence Tools for Chronic Disease Management in Primary Care Setting

Abstract

Chronic disease management often requires use of multiple drug regimens that lead to polypharmacy challenges and suboptimal utilization of healthcare services. While the rising costs and healthcare utilization associated with polypharmacy and drug interactions have been well documented, effective tools to address these challenges remain elusive. Emerging evidence that proactive medication management, combined with pharmacogenomic testing, can lead to improved health outcomes and reduced cost burdens may help to address such gaps. In this report, we describe informatic and bioanalytic methodologies that integrate weak signals in symptoms and chief complaints with pharmacogenomic analysis of ~90 single nucleotide polymorphic variants, CYP2D6 copy number, and clinical pharmacokinetic profiles to monitor drug-gene pairs and drug-drug interactions for medications with significant pharmacogenomic profiles. The utility of the approach was validated in a virtual patient case showing detection of significant drug-gene and drug-drug interactions of clinical significance. This effort is being used to establish proof-of-concept for the creation of a regional database to track clinical outcomes in patients enrolled in a bioanalytically-informed medication management program. Our integrated informatic and bioanalytic platform can provide facile clinical decision support to inform and augment medication management in the primary care setting.

Keywords: artificial intelligence; chronic disease; electronic medical record; medication management; pharmacogenomics; polypharmacy.

Figure 1

Interprofessional Pharmacogenomics (IPGx) Model. 1. Referral of polypharmacy patient to the IPGx clinic. 2. Interprofessional team collects relevant medical history with an emphasis on information related to chief complaints, which also includes a transition of care history from primary care to the IPGx. This information is analyzed using the Clinical Semantic Network to identify complaints of possible pharmacological root cause. 3a. When warranted, pharmacogenomic profiling is performed. 3b. When warranted, pharmacokinetic profiling is performed. 4. A medication management report citing complaints of potential pharmacological root causes and suggested alternative medications or adjustments to drug regimen is provided to the referring physician. 5. If patient chooses to give informed consent, all clinical data, bioanalytic data and biological specimens are entered into a pharmacogenomic research registry (clinical-genomic database).

Figure 2

Side Effects Dashboard. List of symptoms indicating potential pharmacological origin.

Figure 3

Medication and Pharmacokinetic Pathway Summary. The green rectangles are a few salient transporters, and the light blue box represents anticholinergic burden. The left most vertical column denotes the patient’s medications. Vertically, the column beneath named alleles in red indicates that the respective pathway could be overloaded. Panel B Key.

Figure 3

Medication and Pharmacokinetic Pathway Summary. The green rectangles are a few salient transporters, and the light blue box represents anticholinergic burden. The left most vertical column denotes the patient’s medications. Vertically, the column beneath named alleles in red indicates that the respective pathway could be overloaded. Panel B Key.