Deep learning classification of drug-related problems from pharmaceutical interventions issued by hospital clinical pharmacists during medication prescription review: a large-scale descriptive retrospective study in a French university hospital.

Objectives Pharmaceutical interventions are proposals made by hospital clinical pharmacists to address sub-optimal uses of medications during prescription review. Pharmaceutical interventions include the identification of drug-related problems, their prevention and resolution. The objective of this...

Descripción completa

Detalles Bibliográficos
Publicado en:European Journal of Hospital Pharmacy Vol. 32; no. 4; pp. 324 - 329
Autores principales: Alkanj, Ahmad, Godet, Julien, Johns, Erin, Gourieux, Benedicte, Michel, Bruno
Formato: research tables/charts Journal Article
Publicado: BMJ Publishing Group Jul2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=187586542&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 187586542
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        20479956
        FD0Y
      jtl: European Journal of Hospital Pharmacy
      issn: 20479956
      maglogo: N
    pubinfo:
      dt: Jul2025
      vid: 32
      iid: 4
      pid: 8280
      pub: BMJ Publishing Group
    artinfo:
      ui:
        187586542
        187586542
        187586542
        10.1136/ejhpharm-2024-004139
        187586542
      ppf: 324
      ppct: 5
      formats:
      tig:
        atl: Deep learning classification of drug-related problems from pharmaceutical interventions issued by hospital clinical pharmacists during medication prescription review: a large-scale descriptive retrospective study in a French university hospital.
      aug:
        au:
          Alkanj, Ahmad
          Godet, Julien
          Johns, Erin
          Gourieux, Benedicte
          Michel, Bruno
        affil: Laboratoire de Pharmacologie et Toxicologie NeuroCardiovasculaire UR7296, Strasbourg, France
      sug:
        subj:
          Deep Learning France
          Neural Networks (Computer)
          Medication Errors Classification
          Adverse Drug Event Classification
          Pharmacists
          Prescriptions, Drug
          Medication Review
          Human
          Descriptive Research
          Retrospective Design
          Academic Medical Centers
          France
          Software
          Algorithms
          Descriptive Statistics
          Nonexperimental Studies
          Data Analysis Software
      ab: Objectives Pharmaceutical interventions are proposals made by hospital clinical pharmacists to address sub-optimal uses of medications during prescription review. Pharmaceutical interventions include the identification of drug-related problems, their prevention and resolution. The objective of this study was to exploit a newly developed deep neural network classifier to identify drug-related problems from pharmaceutical interventions and perform a large retrospective descriptive analysis of them in a French university hospital over a 3-year period. Methods Data were collected from prescription support software from 2018 to 2020. A classifier running in Python 3.8 and using Keras library was then used to automatically categorise drug-related problems from pharmaceutical interventions according to the coding of the French Society of Clinical Pharmacy. Results 2 930 656 prescription lines were analysed for a total of 119 689 patients. Among these prescription lines, 1 53 335 (5.2%) resulted in pharmaceutical interventions (n=48 202 patients; 40.2%). Pharmaceutical interventions were predominantly observed in patients aged 65 years or older (n=26 141 patients out of 53 186; 49.1%) and in patients taking five or more medications (44 702 patients out of 93 419; 47.8%). The most frequently identified types of drug-related problems associated with pharmaceutical interventions were 'Nonconformity to guidelines or contra-indication' (n=88 523; 57.7%), 'Overdosage' (16 975; 11.1%) and 'Improper administration' (13 898; 9.1%). The most frequently encountered drugs were: paracetamol (n=10 585; 6.9%), esomeprazole (6031; 3.9%), hydrochlorothiazide (2951; 1.9%), enoxaparin (2191; 1.4%), tramadol (1879; 1.2%), calcium (2073; 1.3%), perindopril (1950; 1.2%), amlodipine (1716; 1.1%), simvastatin (1560; 1.0%) and insulin (1019; 0.7%). Conclusions The deep neural network classifier used met the challenge of automatically classifying drug-related problems from pharmaceutical interventions from a large database without mobilising significant human resources. The use of such a classifier can lead to alerting caregivers about certain risky practices in prescription and administration, and triggering actions to improve patients' therapeutic outcomes.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N