Combatting Antimicrobial Resistance through a Data-Driven Approach to Optimize Antibiotic Use and Improve Patient Outcomes: Protocol for a mixed approach study (Preprint)

Abstract

It is projected that drug resistant infections will lead to 10 million deaths annually by 2050, if left unabated. Despite this threat, surveillance data from resource limited settings is scarce and often lacks antimicrobial resistance (AMR)-related clinical outcomes and economic burden. We aim to build an AMR and antimicrobial use (AMU) data warehouse, describe the trends of resistance and antibiotic use, and determine the economic burden of AMR in Uganda and develop a machine learning algorithm for predicting AMR-related clinical outcomes.

The overall objective of the study is to use data-driven approaches to optimize antibiotic use and combat antimicrobial resistant infections in Uganda. We aim to 1)To build a dynamic AMR and Antimicrobial Use and Consumption (AMUC) Data Warehouse to support research in AMR and AMUC to inform AMR related interventions and public health policy, (2) To evaluate the trends in AMR and antibiotic use using annual antibiotic and point prevalence survey data collected at nine regional referral hospitals over a five-year period, (3) To develop a Machine Learning model for predicting the clinical outcomes of patients with bacterial infectious syndromes due to drug resistant pathogens and (4) To estimate the annual economic burden of AMR in Uganda using the cost-of-illness approach.

We will conduct a data curation, machine learning based modelling, and cost of illness analysis study using AMR and AMU data abstracted from procurement, human resources, and clinical records of patients with bacterial infectious syndromes at nine regional referral hospitals in Uganda, collected between 2018 and 2026 We will employ data curation procedures, FLAIR (Findable, Linkable, Accessible, Interactable and Repeatable) principles and role-based access controls (RBAC) to build a robust and dynamic AMR and AMU data warehouse. We will also apply machine learning algorithms to model AMR-related clinical outcomes, advanced statistical analysis to study AMR and AMU trends, and cost of illness analysis to determine AMR-related economic burden.

Once implemented, the expected results from the study will include a robust and dynamic data warehouse, AMR and AMU trends, a machine learning model for predicting AMR-related clinical outcomes (hospital lengthen of stay, time to clinical improvement or negative cultures, medical complications, mortality, and disability), and the cost per AMR case to describe the AMR-related economic burden.

The data warehouse will promote access to rich and interlinked AMR and AMU datasets to answer AMR program and research questions using a wide evidence base. The AMR-related clinical outcomes model and cost data will facilitate improvement in the clinical management of AMR patients and guide resource allocation to support AMR surveillance and interventions.

Infectious Diseases Institute Research Ethic Committee (IDI-REC-2023-67:) & Uganda National Council for Science and Technology (UNCST - HS3690ES).