Towards a symbiotic relationship between big data, artificial intelligence, and hospital pharmacy

Abstract

The digitalization of health and medicine and the growing availability of electronic health records (EHRs) has encouraged healthcare professionals and clinical researchers to adopt cutting-edge methodologies in the realms of artificial intelligence (AI) and big data analytics to exploit existing large medical databases. In Hospital and Health System pharmacies, the application of natural language processing (NLP) and machine learning to access and analyze the unstructured, free-text information captured in millions of EHRs (e.g., medication safety, patients' medication history, adverse drug reactions, interactions, medication errors, therapeutic outcomes, and pharmacokinetic consultations) may become an essential tool to improve patient care and perform real-time evaluations of the efficacy, safety, and comparative effectiveness of available drugs. This approach has an enormous potential to support share-risk agreements and guide decision-making in pharmacy and therapeutics (P&T) Committees.

Keywords: Electronic health records; Machine learning; Natural language processing; Pharmacovigilance.

Fig. 1

Electronic health records (EHRs) contain a large amount of patient-centered clinical data. EHRs are generated and stored in virtually all healthcare departments, including primary care and specialized care settings, emergency rooms, and hospital pharmacies. Most of the information captured in EHRs is unstructured (red shade), including imaging results/signals and free-text narratives jotted down by health professionals (clinical notes). Hospital pharmacists’ documentation of their interventions generate a vast amount of important clinical data, including patients’ medication history, adverse drug reactions (ADRs), discharge plans, changes in prescription (Rx) orders, disease management, drug–drug and other interactions, and pharmacokinetic consultations

Fig. 2

Using natural language processing (NLP) and artificial intelligence (AI) to perform research studies with EHRs. Adopting a multicenter approach, the free-text unstructured information (e.g., clinical notes in any digital format) in millions of de-identified EHRs can be organized in aggregated databases using NLP and AI. These tools are currently being used to answer important clinical questions in Hospital Pharmacy settings in real time, such as drug efficacy/safety and comparative effectiveness; these can be used to guide share-risk agreements and decision-making in pharmacy and therapeutics (P&T) committees