Cargando…

1242. Advanced Automated Analysis System for Antimicrobial Stewardship Programs Including Clinician-focused Features Developed with Artificial Intelligence tools in a Resource-Limited Setting.

BACKGROUND: Antimicrobial Stewardship Programs (ASP) are a priority for the control of bacterial resistance. Artificial intelligence (AI) provides tools that can enable the development and optimization of strategies to optimize ASPs. This abstract describes the experience of improving ASP using AI t...

Descripción completa

Detalles Bibliográficos
Autores principales: Gutierrez-Tobar, Ivan Felipe, BRAVO, J U A N, HERNANDEZ, M A R T H A, TURMEQUE, N I D I A, Londono-Ruiz, Juan Pablo, ALVAREZ, C A R L O S
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10679402/
http://dx.doi.org/10.1093/ofid/ofad500.1082
_version_ 1785150582647947264
author Gutierrez-Tobar, Ivan Felipe
BRAVO, J U A N
HERNANDEZ, M A R T H A
TURMEQUE, N I D I A
Londono-Ruiz, Juan Pablo
ALVAREZ, C A R L O S
author_facet Gutierrez-Tobar, Ivan Felipe
BRAVO, J U A N
HERNANDEZ, M A R T H A
TURMEQUE, N I D I A
Londono-Ruiz, Juan Pablo
ALVAREZ, C A R L O S
author_sort Gutierrez-Tobar, Ivan Felipe
collection PubMed
description BACKGROUND: Antimicrobial Stewardship Programs (ASP) are a priority for the control of bacterial resistance. Artificial intelligence (AI) provides tools that can enable the development and optimization of strategies to optimize ASPs. This abstract describes the experience of improving ASP using AI tools, including a component that facilitates the analysis of antibiotic prescriptions to the ASP and a component to provide real-time feedback and training to clinicians. METHODS: AI tools were used to develop code that integrated a centralized prescription database with local recommendations for automatic analysis. Combination of AI tools, Excel, Google Sites, Apps Script, Google Forms, and Data Studio, were used to optimize ASP technologies to develop real-time ASP analysis visualization and feedback dashboards for prescribers. (Graph 1) [Figure: see text] RESULTS: A control panel was created in Google Sites to access various ASP visualization sections. Different dashboards were developed for ASP analysis, including daily prescription analysis, analysis by service, pathology, prescriber profile, and by the most prevalent infections. Interfaces and forms were created to register ASP analysis and interventions. Broad-spectrum and daily prescribed antibiotics dashboards allow the identification of prescription characteristics and the results of the automated evaluation (adherence to guidelines and dosages). A specific dashboard allows for real-time analysis of the main ASP metrics. Additionally, dashboards were created for clinicians to provide real-time automated recommendations for switching to oral administration, duration according to guidelines, and other factors based on the registered diagnosis, antibiotics, dosage, and days. (Graph 2-3) [Figure: see text] Google site that aggregates all available generated visualization dashboards to facilitate access for the Antimicrobial Stewardship Program. [Figure: see text] This dashboard allows filtering by month and day to immediately identify ALL prescriptions, including patient location, diagnosis, dosage, and the results of the automatic analysis of adherence to the guide and dosage, allowing the ASP to intervene immediately if required. Conclusions [Figure: see text] A tool for systematizing an ASP using AI strategies can optimize ASPs in institutions with limited resources and can be adapted for use in other scenarios. CONCLUSION: Use of AI tools in ASP automation has led to the development of a systematic tool for analyzing antibiotic prescriptions. This innovative approach provides a practical solution for developing and optimizing ASP in resource-limited environments. Additionally, it incorporates a new element that includes visualization dashboards for clinicians to receive real-time feedback and suggestions about antimicrobial prescriptions. This tool could be replicable and scalable for possible use in other scenarios. (Graph 4) DISCLOSURES: All Authors: No reported disclosures
format Online
Article
Text
id pubmed-10679402
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-106794022023-11-27 1242. Advanced Automated Analysis System for Antimicrobial Stewardship Programs Including Clinician-focused Features Developed with Artificial Intelligence tools in a Resource-Limited Setting. Gutierrez-Tobar, Ivan Felipe BRAVO, J U A N HERNANDEZ, M A R T H A TURMEQUE, N I D I A Londono-Ruiz, Juan Pablo ALVAREZ, C A R L O S Open Forum Infect Dis Abstract BACKGROUND: Antimicrobial Stewardship Programs (ASP) are a priority for the control of bacterial resistance. Artificial intelligence (AI) provides tools that can enable the development and optimization of strategies to optimize ASPs. This abstract describes the experience of improving ASP using AI tools, including a component that facilitates the analysis of antibiotic prescriptions to the ASP and a component to provide real-time feedback and training to clinicians. METHODS: AI tools were used to develop code that integrated a centralized prescription database with local recommendations for automatic analysis. Combination of AI tools, Excel, Google Sites, Apps Script, Google Forms, and Data Studio, were used to optimize ASP technologies to develop real-time ASP analysis visualization and feedback dashboards for prescribers. (Graph 1) [Figure: see text] RESULTS: A control panel was created in Google Sites to access various ASP visualization sections. Different dashboards were developed for ASP analysis, including daily prescription analysis, analysis by service, pathology, prescriber profile, and by the most prevalent infections. Interfaces and forms were created to register ASP analysis and interventions. Broad-spectrum and daily prescribed antibiotics dashboards allow the identification of prescription characteristics and the results of the automated evaluation (adherence to guidelines and dosages). A specific dashboard allows for real-time analysis of the main ASP metrics. Additionally, dashboards were created for clinicians to provide real-time automated recommendations for switching to oral administration, duration according to guidelines, and other factors based on the registered diagnosis, antibiotics, dosage, and days. (Graph 2-3) [Figure: see text] Google site that aggregates all available generated visualization dashboards to facilitate access for the Antimicrobial Stewardship Program. [Figure: see text] This dashboard allows filtering by month and day to immediately identify ALL prescriptions, including patient location, diagnosis, dosage, and the results of the automatic analysis of adherence to the guide and dosage, allowing the ASP to intervene immediately if required. Conclusions [Figure: see text] A tool for systematizing an ASP using AI strategies can optimize ASPs in institutions with limited resources and can be adapted for use in other scenarios. CONCLUSION: Use of AI tools in ASP automation has led to the development of a systematic tool for analyzing antibiotic prescriptions. This innovative approach provides a practical solution for developing and optimizing ASP in resource-limited environments. Additionally, it incorporates a new element that includes visualization dashboards for clinicians to receive real-time feedback and suggestions about antimicrobial prescriptions. This tool could be replicable and scalable for possible use in other scenarios. (Graph 4) DISCLOSURES: All Authors: No reported disclosures Oxford University Press 2023-11-27 /pmc/articles/PMC10679402/ http://dx.doi.org/10.1093/ofid/ofad500.1082 Text en © The Author(s) 2023. Published by Oxford University Press on behalf of Infectious Diseases Society of America. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Abstract
Gutierrez-Tobar, Ivan Felipe
BRAVO, J U A N
HERNANDEZ, M A R T H A
TURMEQUE, N I D I A
Londono-Ruiz, Juan Pablo
ALVAREZ, C A R L O S
1242. Advanced Automated Analysis System for Antimicrobial Stewardship Programs Including Clinician-focused Features Developed with Artificial Intelligence tools in a Resource-Limited Setting.
title 1242. Advanced Automated Analysis System for Antimicrobial Stewardship Programs Including Clinician-focused Features Developed with Artificial Intelligence tools in a Resource-Limited Setting.
title_full 1242. Advanced Automated Analysis System for Antimicrobial Stewardship Programs Including Clinician-focused Features Developed with Artificial Intelligence tools in a Resource-Limited Setting.
title_fullStr 1242. Advanced Automated Analysis System for Antimicrobial Stewardship Programs Including Clinician-focused Features Developed with Artificial Intelligence tools in a Resource-Limited Setting.
title_full_unstemmed 1242. Advanced Automated Analysis System for Antimicrobial Stewardship Programs Including Clinician-focused Features Developed with Artificial Intelligence tools in a Resource-Limited Setting.
title_short 1242. Advanced Automated Analysis System for Antimicrobial Stewardship Programs Including Clinician-focused Features Developed with Artificial Intelligence tools in a Resource-Limited Setting.
title_sort 1242. advanced automated analysis system for antimicrobial stewardship programs including clinician-focused features developed with artificial intelligence tools in a resource-limited setting.
topic Abstract
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10679402/
http://dx.doi.org/10.1093/ofid/ofad500.1082
work_keys_str_mv AT gutierreztobarivanfelipe 1242advancedautomatedanalysissystemforantimicrobialstewardshipprogramsincludingclinicianfocusedfeaturesdevelopedwithartificialintelligencetoolsinaresourcelimitedsetting
AT bravojuan 1242advancedautomatedanalysissystemforantimicrobialstewardshipprogramsincludingclinicianfocusedfeaturesdevelopedwithartificialintelligencetoolsinaresourcelimitedsetting
AT hernandezmartha 1242advancedautomatedanalysissystemforantimicrobialstewardshipprogramsincludingclinicianfocusedfeaturesdevelopedwithartificialintelligencetoolsinaresourcelimitedsetting
AT turmequenidia 1242advancedautomatedanalysissystemforantimicrobialstewardshipprogramsincludingclinicianfocusedfeaturesdevelopedwithartificialintelligencetoolsinaresourcelimitedsetting
AT londonoruizjuanpablo 1242advancedautomatedanalysissystemforantimicrobialstewardshipprogramsincludingclinicianfocusedfeaturesdevelopedwithartificialintelligencetoolsinaresourcelimitedsetting
AT alvarezcarlos 1242advancedautomatedanalysissystemforantimicrobialstewardshipprogramsincludingclinicianfocusedfeaturesdevelopedwithartificialintelligencetoolsinaresourcelimitedsetting