Assessment of a hybrid decision support system using machine learning with artificial intelligence to safely rule out prescriptions from medication review in daily practice

Levivien, Clara; Cavagna, Pauline; Grah, Annick; Buronfosse, A.; Courseau, Romain; Bézie, Yvonnick; Corny, Jennifer

doi:10.1007/s11096-021-01366-4

Cited by 19 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average time to carry out medication reconciliation when using the computerized system was shorter than the average time for manual evaluation by the pharmacist. In this regard, other studies corroborate this nding 15,20 . The applied computerized system also found a greater number of discrepancies than the manual system performed by the pharmacist.…”

Section: Discussionsupporting

confidence: 74%

Development and Application of a Computerized System for Medication Reconciliation in a Hospital Environment

Soares,

Espindola,

Rosa

et al. 2023

Preprint

View full text Add to dashboard Cite

Introduction: The World Health Organization (WHO) is concerned with ensuring patient safety in all health services. Thousands of people suffer from errors and adverse events related to medications2. Hospitals lack financial conditions, human resources, infrastructure, and computerized support systems for the implementation of clinical pharmacy, pharmacovigilance and medication reconciliation services. The introduction of systems that help the rational use of medicines (RMU), which is one of the pillars of safety in health services, is very relevant, especially for patients and pharmacists. Objective: To develop and apply a computerized pharmaceutical decision support system for the medication reconciliation in a general hospital. Method: Study of the development and application of a digital tool, with a cross-sectional design, for the comparison between manual medication reconciliation performed by the pharmacist and medication reconciliation performed with a computerized support system. Results: In the medication reconciliation process, the computerized system reduced the time for analyzing prescriptions by eight minutes per patient. Of the 392 patients who were part of the sample, 97.7% used continuous medication at home. Among the list of home medications that were not prescribed in hospital prescriptions and identified through the system are: losartan (9.1%), levothyroxine (4.4%), metformin (3.6%), and medication for mental disorders. depression and anxiety such as: sertraline (2.9%), clonazepam (2.4%) fluoxetine (1.6%). Conclusion: The developed computerized system proved to be superior to the pharmacist's manual search during medication reconciliation and clinical pharmacy and can be a valuable tool in pharmaceutical care.

show abstract

Section: Discussionsupporting

confidence: 74%

Development and Application of a Computerized System for Medication Reconciliation in a Hospital Environment

Soares,

Espindola,

Rosa

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The discussion on electronic prescription alerts is only mapped to two impacts, namely reducing prescribing errors and improving compliance with protocols. [6], [7], [18], [24], [26], [29], [30], [35], [39], [43]- [46], [48], [49], [55] [31], [42] [2], [40], [41], [53] [5], [8], [19] CDSS and EHR (or other system) integration [34], [50], [52] [17], [47], [51] [33] [25] Electronic prescription alert [6], [11], [14], [18], [28], [32], [35], [36], [37], [38], [43], [46], [48], [49] [27], [54] --DDI [11], [14], [36], [37] ---…”

Section: Performance Indicatorsmentioning

confidence: 99%

Do clinical decision support systems for prescribing improve patient safety? a systematic literature review

Kusumadewi

Miladiyah

2023

IJEECS

View full text Add to dashboard Cite

Clinical decision support systems (CDSS) are developed independently or connected to the electronic health record (EHR) or other computerized systems. The study begins with identification by searching the literature through the Google Scholar, PubMed and ScienceDirect databases. The search results obtained 5,595 articles. Forty-two articles were obtained, which were used further. Most of the research focus is on "CDSS development and evaluation". In terms of impacts, the most common is "reduce prescribing errors". One of the biggest problems reported was the presence of "alert fatigue," which was felt to be disturbing to doctors and pharmacists. CDSS must be supported by a method that is able to indicate the presence of drug-drug interactions (DDI). The use of alerts indicating the presence of a DDI should be interpreted using clinical judgment to determine the risks and benefits of a particular drug for a specific patient. The performance of CDSS is mostly reported to have been able to reduce prescribing errors, which in turn will improve patient safety. However, increased adherence to clinical protocols has not been widely reported. Complaints that are still quite a lot reported are the presence of "alert fatigue", which can interfere with effectiveness.

show abstract

“…With the advent of artificial intelligence (AI) models, for use by the public dominating the headlines in 2023, a fierce debate ensued about their "appropriate and inappropriate use" in academic research [1]. While the discussions mainly centre around the ethical implications of the academic writing skills of such generative AI models, it raises the question what novel opportunities generative AI presents for clinical pharmacy research [2]. As clinical pharmacy practice operates in a complex interdisciplinary healthcare system, clinical pharmacy practice research is equally complex and transdisciplinary, potentially opening up a lot of opportunity for bridging the disciplines using artifical intelligence in new ways [3].…”

Section: Introductionmentioning

confidence: 99%

Novel opportunities for clinical pharmacy research: development of a machine learning model to identify medication related causes of delirium in different patient groups

Weidmann,

Watson

2024

Int J Clin Pharm

View full text Add to dashboard Cite

The advent of artificial intelligence (AI) technologies has taken the world of science by storm in 2023. The opportunities of this easy to access technology for clinical pharmacy research are yet to be fully understood. The development of a custom-made large language model (LLM) (DELSTAR) trained on a wide range of internationally recognised scientific publication databases, pharmacovigilance sites and international product characteristics to help identify and summarise medication related information on delirium, as a proof-of-concept model, identified new facilitators and barriers for robust clinical pharmacy practice research. This technology holds great promise for the development of much more comprehensive prescribing guidelines, practice support applications for clinical pharmacy, increased patient and prescribing safety and resultant implications for healthcare costs. The challenge will be to ensure its methodologically robust use and the detailed and transparent verification of its information accuracy.

show abstract

Assessment of a hybrid decision support system using machine learning with artificial intelligence to safely rule out prescriptions from medication review in daily practice

Cited by 19 publications

References 14 publications

Development and Application of a Computerized System for Medication Reconciliation in a Hospital Environment

Development and Application of a Computerized System for Medication Reconciliation in a Hospital Environment

Do clinical decision support systems for prescribing improve patient safety? a systematic literature review

Novel opportunities for clinical pharmacy research: development of a machine learning model to identify medication related causes of delirium in different patient groups

Contact Info

Product

Resources

About