Helping GPs to extrapolate guideline recommendations to patients for whom there are no explicit recommendations, through the visualization of drug properties. The example of AntibioHelp® in bacterial diseases

Abstract

IntroductionClinical decision support systems (CDSS) implementing clinical practice guidelines (CPGs) have 2 main limitations: they target only patients for whom CPGs provide explicit recommendations, and their rationale may be difficult to understand. These 2 limitations result in poor CDSS adoption. We designed AntibioHelp® as a CDSS for antibiotic treatment. It displays the recommended and nonrecommended antibiotics, together with their properties, weighted by degree of importance as outlined in the CPGs. The aim of this study was to determine whether AntibioHelp® could increase the confidence of general practitioners (GPs) in CPG recommendations and help them to extrapolate guidelines to patients for whom CPGs provide no explicit recommendations.Materials and MethodsWe carried out a 2-stage crossover study in which GPs responded to clinical cases using CPG recommendations either alone or with explanations displayed through AntibioHelp®. We compared error rates, confidence levels, and response times.ResultsWe included 64 GPs. When no explicit recommendation existed for a particular situation, AntibioHelp® significantly decreased the error rate (−41%, P value = 6x10−13), and significantly increased GP confidence (+8%, P value = .02). This CDSS was considered to be usable by GPs (SUS score = 64), despite a longer interaction time (+9–22 seconds). By contrast, AntibioHelp® had no significant effect if there was an explicit recommendation.Discussion/ConclusionThe visualization of weighted antibiotic properties helps GPs to extrapolate recommendations to patients for whom CPGs provide no explicit recommendations. It also increases GP confidence in their prescriptions for these patients. Further evaluations are required to determine the impact of AntibioHelp® on antibiotic prescriptions in real clinical practice.

A usability study to improve a clinical decision support system for the prescription of antibiotic drugs

“…It is a relative quick and easy instrument to use and it covers areas such as user satisfaction, efficiency of use and system effectiveness [31]. This method has already been used for assessing the usability of a CDSS for antibiotic prescription [24, 32]. We did not use this survey instrument, because it does not provide insight in details or causes of identified problems.…”

“…Most of these systems however focus on antimicrobial prescribing [15, 22, 23]. It has been shown that CDSS can increase confidence of general practitioners in their antibiotic prescriptions [24]. The systems that are designed to support antimicrobial prescribing in secondary care tend to focus more on a broader population than in primary care, where the systems are often focused on specific syndrome presentation in adults [15].…”

Explainable decision support through the learning and visualization of preferences from a formal ontology of antibiotic treatments

“…In a recent study [23], we investigated whether displaying the weighted preference properties could increase the confidence of General Practitioners (GPs) in CPG recommendations, and help them to extrapolate recommendations to patients for whom CPGs provide no explicit recommendations (e.g. because the recommended antibiotic cannot be prescribed due to allergies or contraindications).…”

“…Our approach is implemented in AntibioHelp® [23,60], a CDSS for antibiotic prescriptions. However, this approach could also be useful during the process of CPG formulation.…”

“…The ontology of antibiotic treatments was used as input for learning the implicit preference models used by medical experts in the writing of CPGs. The resulting CDSS [23] provides a visual display of the various antibiotics available on the market and their properties, weighted according to the preference model learned from the expert recommendations found in CPGs.…”