Framework to implement a pharmaceutical decision support system: Detecting and resolving drug-related problems
Potier, Arnaud
Framework to implement a pharmaceutical decision support system: Detecting and resolving drug-related problems - 2023.
63
Goals. To present the framework for implementing a pharmaceutical decision support system (PDSS) that improves the detection and resolution of drug-related problems (DRP). The aim is to improve the relevance of the patient’s drug management. Methods. Over 4 years, in 2 health care facilities, pharmacists and IT professionals, supported by the company Keenturtle (France), formalized the PDSS, based on the active triangulation of a clinical decision support system (CDSS). Guidelines for representing knowledge in pharmaceutical algorithms, including human supervision, were defined. A glossary of terms, particularly related to AI-pharmacy, was made available to train PDSS users. Results. The PDSS is operational since 2018; it associates patient health data to pharmacotherapy knowledge in the software Pharmaclass®. A 12-step guideline helps the pharmacist transpose clinical recommendations into 201 pharmaceutical algorithms that model patient situations integrated into the PDSS. A dedicated framework for these pharmaceutical algorithms facilitates the detection and resolution of DRPs. Additionally, 41 terms are defined in a glossary. Conclusion. Defining a framework for implementing and using a PDSS reduces its complexity. The knowledge representation enhances pharmacists’ expertise through its pedagogical aspect, making it a central element of the PDSS. The symbolic artificial intelligence approach will support pharmacists in their practice.
Framework to implement a pharmaceutical decision support system: Detecting and resolving drug-related problems - 2023.
63
Goals. To present the framework for implementing a pharmaceutical decision support system (PDSS) that improves the detection and resolution of drug-related problems (DRP). The aim is to improve the relevance of the patient’s drug management. Methods. Over 4 years, in 2 health care facilities, pharmacists and IT professionals, supported by the company Keenturtle (France), formalized the PDSS, based on the active triangulation of a clinical decision support system (CDSS). Guidelines for representing knowledge in pharmaceutical algorithms, including human supervision, were defined. A glossary of terms, particularly related to AI-pharmacy, was made available to train PDSS users. Results. The PDSS is operational since 2018; it associates patient health data to pharmacotherapy knowledge in the software Pharmaclass®. A 12-step guideline helps the pharmacist transpose clinical recommendations into 201 pharmaceutical algorithms that model patient situations integrated into the PDSS. A dedicated framework for these pharmaceutical algorithms facilitates the detection and resolution of DRPs. Additionally, 41 terms are defined in a glossary. Conclusion. Defining a framework for implementing and using a PDSS reduces its complexity. The knowledge representation enhances pharmacists’ expertise through its pedagogical aspect, making it a central element of the PDSS. The symbolic artificial intelligence approach will support pharmacists in their practice.
Réseaux sociaux