On 30 April 2025, the CAMO-Net Uganda hub convened a Knowledge Exchange and Sharing Workshop on Antimicrobial Resistance (AMR), which took place in Kampala. The event brought together researchers, healthcare practitioners, policymakers and academicians to share findings from studies under the CAMO-Net Project and to define clear, practical steps for strengthening Uganda’s response to AMR.

Dr Olaro Charles, Director General, Ministry of Health Uganda, opened the workshop by commending the CAMO-Net Uganda hub for its consistent efforts in the AMR space. He emphasised the important role of government support in ensuring responsible antibiotic use, reliable supply chains and robust antimicrobial stewardship. Dr Charles noted that without sustained public investment, any progress on AMR risks will be short-lived. He therefore called on all stakeholders to advocate for dedicated budget lines and to integrate AMR activities within broader health sector plans.

Hon. Dr Charles Ayume, Guest of Honour and Founding Chair of the Parliamentary Forum on AMR, followed with remarks on the importance of political leadership. He traced the Forum’s origins to early collaborations with the CAMO-Net Uganda hub, emphasising that the parliamentary forum exists to translate scientific evidence into legislation and policy. Dr Ayume stressed that strong political will is the foundation upon which all other interventions rest, and he urged colleagues to maintain AMR as a standing agenda item in committee meetings.

Professor Alison Holmes, CAMO-Net global lead, then addressed participants on the need to move beyond project-based thinking. Drawing on examples from other regions, she illustrated how short-term initiatives often yield limited impact unless they are embedded in national systems. Professor Holmes highlighted Uganda’s achievements in standardising data collection and in piloting community engagement models. She encouraged attendees to leverage these experiences to build lasting partnerships, to invest in local laboratory capacity and to champion evidence translation at every level of the health system.

The workshop’s research presentations formed the core of the day’s proceedings. Four studies were summarised:

• Antibiotic usage trends at regional referral hospitals
  Researchers analysed pharmacy and ward records to identify patterns of inpatient antibiotic consumption. Preliminary results indicate frequent use of broad-spectrum agents and occasional deviations from national treatment guidelines.
• Prescription patterns among people living with HIV
  This study examined outpatient prescription data to assess appropriateness of antibiotic courses. Findings suggest a need for targeted training among clinicians to reduce unnecessary prescriptions.
• Clinical profiles of patients with resistant infections in tertiary centres
  Clinical teams presented demographic and outcome data for patients diagnosed with antibiotic-resistant infections. Mortality rates and length of hospital stay were discussed as key indicators for measuring the burden of resistance.
• Economic burden of AMR in Uganda
  An economic analysis estimated the annual cost of AMR at USD 25 million, accounting for extended hospital stays, additional drug costs and productivity losses.

Each presentation was followed by a focused question-and-answer session, during which participants explored diagnostic gaps, reflected on prescribing behaviours and discussed potential policy responses.

In the afternoon, delegates split into four breakout groups to draft action matrices around distinct themes aligned with the studies.  Each group presented its matrix to the plenary, receiving feedback from parliamentarians and policy leads. Common themes included the need for measurable indicators, timelines for implementation and alignment with existing national policies.

In her closing remarks, Dr Hope Mackline reflected on the collaborative spirit evident throughout the day, noting that the workshop had succeeded in aligning diverse stakeholder perspectives around a shared agenda. Dr Andrew Kambugu then urged participants to translate the matrices into concrete work plans and to report progress at the next meeting.

As CAMO-Net Uganda moves into the final year of its current project cycle, stakeholders expressed a clear commitment to translating the workshop’s strategies into lasting, evidence-informed approaches to address AMR.

CAMO-Net Uganda has secured significant new funding to scale up its groundbreaking work on antimicrobial resistance (AMR), with a focus on using machine learning (ML) to improve health outcomes.

The successful project, titled Data-Driven Infrastructure for Combating Antimicrobial Resistance IN UGanda (DARING) will receive $282,705.09 USD over 18 months from the Lacuna Fund to generate much-needed clinical outcome data and support equitable AI development in low- and middle-income countries (LMICs).

The project is funded by the Wellcome Trust and Google through the Lacuna Fund, which is the world’s first collaborative effort to provide data scientists, researchers, and social entrepreneurs in LMICs with the resources they need to produce labelled datasets that address urgent problems in their communities. The aim of the fund is to address a key data gap: robust, representative clinical datasets that reflect the realities of LMICs and can strengthen AMR surveillance, prediction, and policy interventions.

CAMO-Net Uganda is one of five national hubs within the Centres for Antimicrobial Optimisation Network (CAMO-Net), a global collaboration working to improve antimicrobial use and outcomes through interdisciplinary research, innovation, and collaboration. Based at the Infectious Diseases Institute at Makerere University, the Uganda hub is pioneering work on AMR surveillance, gender-sensitive data analysis, and the application of AI in infectious disease management. Recent projects have included presenting economic burden data to Uganda’s Parliament and exploring antibiotic use patterns in HIV care.

The DARING project, led by Dr Ronald Galiwango at CAMO-Net Uganda, builds on findings from CAMO-Net Uganda’s machine learning work, which collected data on clinical outcomes for 599 patients with resistant and susceptible infections. While this was a major step forward, the team identified the dataset as insufficient for training reliable ML models. With this new funding, the Uganda team will collect additional clinical outcome data from nine Regional Referral Hospitals across the country. The enhanced dataset will significantly improve model training and accuracy, supporting efforts to predict AMR-related risks and improve treatment decisions.

Dr Galiwango is a highly experienced researcher in health informatics and data science, and a key member of the CAMO-Net Uganda team. His work focuses on sustainable digital health infrastructure and equitable data access, with a strong emphasis on public health impact across sub-Saharan Africa.

“This grant allows us to expand our data infrastructure in a way that can meaningfully shift how we understand and respond to antimicrobial resistance in Uganda,” said Dr Galiwango. “By collecting richer, more representative clinical data, we are laying the foundation for machine learning models that can support clinicians, inform policy, and ultimately improve patient outcomes.”

The new and existing datasets will be integrated into CAMO-Net Uganda’s expanding data warehouse, ensuring they are accessible to researchers, policymakers, and global partners. This work continues CAMO-Net’s commitment to ethical data governance, public access, and equitable knowledge-sharing. With the DARING project now officially awarded and due to begin at the end of April 2025, CAMO-Net Uganda continues to push boundaries in the global response to AMR by ensuring the data that powers policy and research reflects the populations most affected.

A groundbreaking portable molecular diagnostic platform, Dragonfly, developed by researchers at the Centres for Antimicrobial Optimisation Network (CAMO-Net) in collaboration with the Centre for Bio-inspired Technology (CBIT) and commercialised by Imperial spin-out ProtonDx, now allows for the rapid detection of mpox and other skin-tropic viral infections directly at the point-of-care. This advancement is crucial in enhancing timely diagnosis and effective outbreak management, especially in resource-limited settings.

The research, led by Dr Jesus Rodriguez-Manzano, details Dragonfly’s development and validation and has been published in the science journal Nature Communications. Dr Rodriguez-Manzano, who spearheaded the development of the original Dragonfly diagnostic platform along with first authors Dr Matthew L Cavuto and Dr Kenny Malpartida-Cardenas, is a Senior Lecturer in Diagnostics for Infectious Diseases at Imperial College London’s Department of Infectious Disease. He also serves as Deputy Director and Chief Scientist at the Centre for Antimicrobial Optimisation (CAMO), Research Strategy Advisor for Diagnostics & Innovation at the Fleming Initiative, and is a key member of CAMO-Net UK.

The new diagnostic platform demonstrated high accuracy in diagnosing mpox and other skin-tropic viral infections. The device achieved a sensitivity of 96.1% and specificity of 100% for orthopoxviruses (OPXV), and 94.1% sensitivity and 100% specificity for the mpox virus (MPXV). This means it correctly identified nearly all positive cases while ensuring no false positives, making it a highly reliable diagnostic tool. Its design also eliminates the need for bulky laboratory equipment, making it particularly suitable for decentralised healthcare environments.

Skin-tropic viral infections are viruses that primarily affect the skin, often causing rashes, lesions, or blisters. These include MPXV, herpes simplex virus (HSV), and varicella-zoster virus (VZV), which can present with similar symptoms, making rapid and accurate diagnosis essential for appropriate treatment and infection control.

Overview of the complete mobile Dragonfly testing kit, reconfigured for the simultaneous extraction and detection of OPXV and MPXV from two patient samples

The resurgence of mpox, following the World Health Organization’s (WHO) designation of the virus as a Public Health Emergency of International Concern for the second time in 2024, has underscored the urgent need for effective, decentralised diagnostic solutions. Traditional molecular testing methods, such as quantitative PCR (qPCR), are often confined to centralised laboratories, limiting timely detection and outbreak control efforts. Dragonfly bridges this gap by integrating a power-free nucleic acid extraction method (based on SmartLid technology) with lyophilised colourimetric loop-mediated isothermal amplification (LAMP) chemistry, enabling sample-to-result molecular grade diagnostics in under 40 minutes.

Unlike conventional molecular diagnostic platforms, Dragonfly does not require a thermocycler or complex optical detection systems. Instead, it relies on a colour-based readout designed to simplify result interpretation and ensure compatibility with colour-blind users. The system consists of a single-use sample extraction kit, a lyophilised test panel, and a low-cost isothermal heat block, which can be powered by batteries or solar energy, further enhancing its field usability.

In close collaboration with Dr Marcus Pond from North West London Pathology laboratories, Dragonfly’s efficacy was assessed using 164 clinical samples, including 51 mpox-positive cases, benchmarked against gold-standard qPCR testing. The platform demonstrated robust differentiation between mpox and other viruses with similar skin manifestations, such as HSV and VZV. Its diagnostic accuracy offers a significant advancement in early case detection, infection management, and outbreak surveillance.

Dr Rodriguez-Manzano highlighted the importance of this development: “Dragonfly represents a crucial step in making molecular diagnostics more accessible. By eliminating the need for specialised equipment and trained personnel, we are enabling rapid and accurate detection of mpox and other infectious diseases in settings where it is needed most.”

This innovation is a key output of CAMO-Net and represents its key objective of fighting infectious diseases by addressing the underlying causes of antimicrobial resistance (AMR). CAMO-Net is a Wellcome-funded, multidisciplinary global collaboration of established research institutions addressing AMR. CAMO-Net operates across 13 sites in 11 countries, predominantly in the global south, where communities are disproportionately affected by AMR. The network focuses on producing contextually relevant tools, technologies, guidelines, and practices to optimise antimicrobial use in humans, supported by equitable availability and accessibility.

With mpox cases rising and the WHO’s strategic framework emphasising improved diagnostic capabilities, Dragonfly provides a timely and effective solution. Its potential applications extend beyond mpox, offering a versatile platform adaptable to other emerging infectious diseases. As global health systems continue to address the challenges posed by viral outbreaks, innovations like Dragonfly will play a critical role in strengthening diagnostic resilience worldwide.

You can read the full paper here.

At the end of March 2025, Uganda reaffirmed its national commitment to addressing antimicrobial resistance (AMR) through a high-level quarterly meeting of the Uganda National Antimicrobial Resistance Subcommittee (UNAMRSC). The meeting convened a wide range of stakeholders from human health, veterinary, agricultural, and environmental sectors to evaluate progress and refine strategies aligned with Uganda’s National AMR Action Plan.

Researchers from CAMO-Net Uganda, based at Makere University’s Infectious Diseases Institute (IDI) presented updated findings from its recent study on the economic burden of antibiotic resistance. The presentation, delivered by Health Economist Elly Nuwamanya, shed new light on the scale and social dimensions of AMR-related costs in Uganda. The data revealed that women bear a significantly greater economic burden due to higher informal care and lost productivity costs, prompting discussions around the importance of gender-responsive AMR policies.

“Our findings highlight the urgent need for gender-sensitive planning within Uganda’s AMR response,” Mr Nuwamanya said. “Without targeted interventions, the impact of antibiotic resistance will continue to deepen existing health and economic inequalities.”

This focus on gender reflects a growing emphasis across CAMO-Net on understanding how AMR intersects with broader social and environmental determinants. Research from CAMO-Net South Africa and CAMO-Net India has explored how climate-related stressors and gender norms shape access to healthcare, antibiotic use, and vulnerability to drug-resistant infections. These insights are helping CAMO-Net partners design interventions that are not only evidence-based but also socially equitable – recognising that sustainable AMR responses must be inclusive of the diverse realities individuals face.

The meeting in Uganda also examined national surveillance data and identified key challenges in antimicrobial susceptibility testing (AST), particularly in rural and underserved areas. Participants called for improved data quality and coverage, highlighting that accurate surveillance is critical for guiding effective antimicrobial stewardship and ensuring the equitable delivery of care.

During the meeting, the CAMO-Net Uganda hub also met with Professor Damalie Nakanjako, Principal of the Makerere University College of Health Sciences, to discuss future collaboration opportunities with CAMO-Net and the wider IDI team. The discussion focused on strengthening AMR research capacity, expanding training programmes, and improving diagnostic systems through investment in laboratory infrastructure and workforce development.

This alignment with the wider Makerere University community builds on one of the key pillars of Uganda’s National AMR Action Plan: enhancing research and innovation to inform evidence-based decision-making. As Uganda progresses into the next phase of implementation, such partnerships between academia, research institutions, and government bodies are seen as critical drivers of sustainable impact. This also plays an important part of CAMO-Net’s mission – playing its part in shaping policies that directly address AMR both locally and around the world.

The UNAMRSC meeting concluded with renewed commitments to:

• Scale up AST coverage across all regions,
• Prioritise cross-sectoral data sharing,
• Strengthen governance and accountability frameworks, and
• Expand awareness and capacity-building initiatives in line with a One Health approach.

With its strong evidence base and collaborative ethos, the CAMO-Net Uganda hub continues to play a central role in supporting national efforts to monitor, understand, and respond to AMR. As Uganda navigates the complex challenges of AMR containment, cross-sectoral partnerships remain essential to protect public health, reduce economic losses, and build a resilient healthcare system.

Researchers from CAMO-Net Uganda recently attended Uganda’s Parliament for a high-level forum on antimicrobial resistance (AMR). The session brought together Members of Parliament, health policymakers, and national stakeholders to address the growing challenge of AMR.

The CAMO-Net Uganda hub was invited to the forum to contribute evidence and insights on AMR in the country. The forum, which was chaired by Hon. Dr Charles Ayume, Chair of the Parliamentary Health Committee, explored the legislative and policy measures needed to mitigate AMR’s health and economic impact.

The session marked a significant milestone in CAMO-Net’s mission to bring local evidence to the heart of national policy. The Uganda hub, hosted by the Infectious Diseases Institute (IDI) at Makerere University, presented the findings of a newly completed study on the economic burden of antibiotic resistance (ABR) across nine regional referral hospitals. The results painted a stark picture: Uganda is losing approximately UGX 64 billion (USD 17.7 million) annually due to the wide-ranging costs of AMR.

These include:

• Direct health system costs of over USD 12 million, including hospital stays, treatment, and personnel
• Informal care costs totalling over USD 4 million, reflecting time and support provided by family and community caregivers
• Lost productivity costs of more than USD 1.4 million, stemming from prolonged illness and premature deaths

“Without immediate, coordinated action, the economic strain on our health system will only worsen,” warned Elly Nuwamanya, Research Health Economist at CAMO-Net Uganda, and the study’s lead researcher. “The cost of inaction is far greater than the investment needed to strengthen AMR surveillance and stewardship.”

The policy brief distributed at the forum highlighted additional insights. Notably, the data revealed that women bear a disproportionate share of the economic burden, with informal care and productivity loss costs 44% and 52% higher, respectively, than those for men. This gendered dimension underscores the importance of inclusive, equitable AMR interventions.

The findings also pointed to a 30% shortfall in the annual budget allocation for regional referral hospitals due to AMR, illustrating how resistant infections are not only a clinical issue but a systemic economic challenge. The most significant contributors to direct costs were hospital personnel and antibiotic use, suggesting that tackling AMR could also reduce pressure on frontline staff and improve the efficiency of health service delivery.

Dr Francis Kakooza, Head of Global Health Security at IDI and Co-Principal Investigator of the CAMO-Net Uganda hub, welcomed the forum as a moment of real political traction.

“This is a timely and reassuring step,” he said. “For years, researchers have spoken about the health threat of AMR. Now, with these findings, we can show its economic toll in Uganda—and give policymakers the data they need to act.”

Members of Parliament responded with a strong call for enhanced regulation and enforcement. Hon. Dr Ayume reaffirmed the Health Committee’s commitment to reviewing existing drug dispensation laws and working across ministries to develop a legislative framework that prioritises AMR containment. MPs also stressed the importance of public education, diagnostic capacity, and responsible prescribing in both public and private healthcare settings.

The forum concluded with a shared recognition of the need for:

• Stronger AMR surveillance and data sharing between sectors
• Stewardship programmes to guide appropriate antimicrobial use
• Enhanced training for healthcare workers
• Greater investment in infection prevention and control measures
• Clear legislative pathways to support these priorities

The session was widely covered by national media and commended by stakeholders for bridging the gap between evidence and policymaking. CAMO-Net will continue to work closely with Uganda’s AMR Coordination Committee and relevant ministries to support the development of an integrated national response.

This forum is an example of how CAMO-Net’s model—supporting country-led research, building capacity, and connecting data to policy—can strengthen systems and promote sustainable solutions to the AMR challenge.

Read more

Read more about this story:

• https://african.business/2025/03/apo-newsfeed/uganda-members-of-parliament-mps-call-for-stringent-enforcement-of-laws-on-drug-dispensation
• https://ubc.go.ug/2025/03/25/legislators-push-for-stronger-drug-prescription-and-antimicrobial-resistance-measures/
• https://wallnetnews.com/mps-urge-government-to-strengthen-enforcement-against-antimicrobial-resistance/
• https://www.parliament.go.ug/news/3647/mps-call-stringent-enforcement-laws-drug-dispensation

Learn more about Elly Nuwamanya

A recent mixed-method study from CAMO-Net Brazil has provided valuable insights into the barriers and enablers of implementing antimicrobial stewardship (AMS) in primary healthcare settings in São Caetano do Sul, Brazil.

The study, published in the American Journal of Infection Control, was conducted between August and December 2023, combined quantitative data from 208 healthcare workers and qualitative interviews with 16 patients and 12 healthcare workers. The aim was to understand the local context of antimicrobial use and inform the development of targeted AMS strategies.

Led by Dr Letícia Britto Costa from the Institute of Tropical Medicine, University of São Paulo, where CAMO-Net Brazil is located, the study revealed that professionals with higher education, such as physicians, nurses, and pharmacists, demonstrated higher confidence and knowledge in antimicrobial use. However, healthcare workers with intermediate educational backgrounds, such as community health agents and nurse technicians, reported limited training and felt uncertain about their roles in AMS.

A significant finding was the physician-centred decision-making process, which often excluded other healthcare workers from contributing to antimicrobial management. This led to frustration and anxiety among non-prescribing professionals, who felt ill-equipped to support patients with complex infections.

The study also highlighted critical breaks in the continuity of care, with patients frequently navigating between multiple health services without adequate follow-up. Additionally, patients demonstrated limited understanding of antibiotics, with some confusing them with painkillers or self-medicating inappropriately.

Building on CAMO-Net Brazil’s work

This research builds on CAMO-Net Brazil’s ongoing efforts to enhance antimicrobial stewardship. Notably, it complements the recent launch of guidelines on antimicrobial use in São Caetano do Sul, which aim to standardise prescribing practices and support healthcare workers in optimising antimicrobial use.

Recommendations for AMS implementation

Dr Letícia Britto Costa emphasised the importance of addressing these gaps through targeted educational programmes. “To successfully implement antimicrobial stewardship, we must invest in comprehensive training for all healthcare workers and establish clear guidelines for antimicrobial use, such as those recently published by CAMO-Net Brazil. By empowering our teams and engaging patients and caregivers, we can optimise antimicrobial use and reduce the burden of resistance.”

The study recommends:

• Tailored training sessions for all healthcare worker categories, focusing on infection management and communication with patients.
• Development of local guidelines for antimicrobial prescribing.
• Improved coordination between health services to enhance continuity of care.
• Educational campaigns for patients and caregivers on the appropriate use of antibiotics.

This study highlights the need for a multifaceted approach to AMS in Brazil’s primary healthcare settings. By leveraging healthcare workers’ willingness to learn and addressing training disparities, the CAMO-Net Brazil team aims to bridge the gap between scientific evidence and clinical practice. These efforts are essential for addressing antimicrobial resistance and safeguarding public health, not only in Brazil but also as a model for strengthening stewardship in primary healthcare settings worldwide.

You can read the full study here.

CAMO-Net Pakistan, based at Dow University of Health Sciences, is actively addressing antimicrobial resistance (AMR) through a One Health lens, recognising the interconnectedness of human, animal, and environmental health. While CAMO-Net’s research is currently focused on optimising antimicrobial use in humans, its members are deeply engaged in broader AMR challenges, including those in the poultry industry and environmental drivers of resistance.

During the recent CAMO-Net Capacity Strengthening Workshop, Dr Nida Baig, Assistant Professor at Dow University of Health Sciences and CAMO-Net Pakistan researcher, presented her research on AMR in Pakistan’s poultry sector, highlighting critical concerns and the urgent need for action.

Pakistan is the world’s 11th largest poultry producer, with production rising from 1.16 to 1.94 million tonnes of broiler chicken across more than 15,000 farms. However, alongside this growth, there is widespread misuse of antibiotics, including their use as growth promoters and hygiene alternatives. Dr Baig’s research has identified multidrug-resistant bacteria in poultry, including E. coli, Staphylococcus spp., Salmonella, Klebsiella spp., and Pseudomonas, many of which form strong biofilms that enhance their resistance. “The unchecked use of antibiotics in poultry farming is not just a risk to animal health but a direct threat to public health,” Dr Baig explained. “If we do not take urgent steps to regulate antibiotic use in food production, we risk accelerating the spread of AMR beyond control.”

A key concern is the movement of antibiotic resistance genes rather than just resistant bacterial strains, which increases the risk of resistance spreading to human infections. This highlights the urgent need for policies to regulate antimicrobial use in agriculture and strengthen surveillance to track resistance trends across human, animal, and environmental sectors.

Beyond poultry, CAMO-Net Pakistan is also examining the role of water and wastewater in AMR transmission. This research is informed by similar work undertaken by CAMO-Net Brazil, which is investigating the presence of resistant bacteria and antimicrobial residues in urban water supplies. In Pakistan, past outbreaks of extensively drug-resistant (XDR) typhoid in the southern Sindh province have been linked to contaminated sewage, demonstrating the urgent need to monitor and mitigate antibiotic pollution. Future initiatives will explore the selective pressure exerted by antibiotics in wastewater, their potential to drive resistance mutations, and the role of environmental contamination in the spread of AMR.

By engaging in research across multiple sectors, CAMO-Net Pakistan is contributing to a more comprehensive understanding of AMR in the region. The team’s work underscores the importance of a One Health approach, integrating human health with agriculture and environmental considerations to develop effective interventions. As the global AMR crisis intensifies, collaborations across sectors and countries will be essential in identifying sustainable solutions and safeguarding public health.

A recent study by CAMO-Net Uganda, based in the the Infectious Diseases Institute (IDI), Makerere University, has shown that resistance to antibiotics is rising in Uganda.

As part of our efforts to address this trend, the CAMO-Net Uganda national hub is developing machine learning (ML) models designed to address antimicrobial resistance (AMR) in the region. These models, led at IDI by Dr Ronald Galiwango, are designed to predict clinical outcomes in patients with drug-resistant infections and will improve patient management, support AMR surveillance in the region, and optimise resource allocation for AMR interventions.

Antimicrobial resistance is a growing global health crisis, rendering existing treatments ineffective and leading to increased mortality, prolonged hospital stays, and rising healthcare costs. If left unaddressed, AMR could cause 1.91 million direct deaths and contribute to 8.22 million deaths globally by 2050. AMR occurs when bacteria, viruses, fungi, and parasites develop resistance to antimicrobial drugs, largely due to the misuse and overuse of antibiotics in human, animal, and environmental settings.

Uganda faces significant challenges in tackling AMR. An IDI study, led by Dr Jonathan Mayito, CAMO-Net researcher and internal medicine physician, and conducted across nine Regional Referral Hospitals (RRHs), revealed rising resistance across all drug categories, including the Access, Watch, and Reserve (AWaRe) classification. One of the main contributors to AMR in Uganda is the widespread availability of over-the-counter antibiotics, leading to self-medication, incomplete treatment courses, and misuse for non-bacterial infections.

Additionally, delays in antimicrobial susceptibility testing (AST) force healthcare providers to rely on empirical treatment, increasing the misuse of broad-spectrum antibiotics and accelerating resistance. Weak data systems further hinder AMR surveillance and effective decision-making. Addressing these issues—reducing AST turnaround times, improving antibiotic stewardship, and strengthening data systems—is critical for optimising antimicrobial use, improving patient outcomes, and curbing resistance.

Machine learning and AMR

Machine learning (ML) is gaining traction as a promising approach to addressing AMR, driven by advancements in computational power, algorithm performance, and expanding clinical datasets. Unlike traditional methods, which are often slow, expensive, and labour-intensive, ML can rapidly process vast datasets—including genomic sequences, clinical records, and molecular structures—to generate accurate predictions and insights. ML models are dynamic and adaptive, making them well-suited for tackling the constantly evolving nature of AMR.

ML is a branch of artificial intelligence (AI) that enables computers to learn patterns from data and make predictions without explicit programming. There are two primary approaches:

1. Supervised learning, where the model is trained on labelled data with known outcomes.

2. Unsupervised learning, where the model detects patterns in unlabelled data, identifying clusters and relationships.

Applications of ML in addressing AMR

1. Drug discovery and design

Traditional antibiotic discovery is slow and costly, often taking over a decade and billions of dollars to develop new drugs. ML accelerates this process by screening vast chemical libraries and predicting antimicrobial compounds with desirable properties. Deep learning techniques, such as neural networks, enhance drug-target interaction modelling, aiding in the development of new antibiotics. ML also integrates with tools like AlphaFold and molecular docking to predict how drugs interact with bacterial proteins, facilitating more effective treatment options.

Combination therapy, which uses multiple drugs to combat infections, is a crucial strategy against AMR. Identifying effective drug combinations is challenging due to the vast number of possible interactions. ML simplifies this process by analysing millions of potential drug pairings and identifying synergistic effects, improving treatment efficacy and reducing resistance development.

2. Predicting resistance patterns

ML algorithms analyse genomic and epidemiological data to predict bacterial resistance patterns with high precision. By detecting genetic mutations linked to resistance, these models help researchers anticipate emerging resistance trends. This proactive approach enables public health authorities to guide antibiotic stewardship and implement effective infection control strategies. By forecasting resistance mechanisms, ML supports better decision-making to curb AMR at both national and global levels.

3. Optimising treatment strategies

Machine learning enhances clinical decision-making by analysing patient-specific data—such as medical history, microbiology results, and demographics—to recommend the most effective antibiotics and dosages. By predicting the likelihood of resistance and optimising treatment plans, ML-powered clinical decision support tools help reduce unnecessary antibiotic use, minimise side effects, and improve patient outcomes.

Challenges in Applying ML to AMR

Despite its potential, machine learning faces several challenges in AMR research:

• Model Interpretability: Many ML models operate as “black boxes,” making it difficult to understand how they generate predictions. Clinicians need transparency to trust and adopt these models.
• Data Availability and Quality: ML models require large, high-quality datasets, but healthcare data is often fragmented, inconsistent, and error-prone, limiting model accuracy.
• Bias and Generalisability: If training data does not represent the target population, the models may develop biases, reducing their real-world applicability

The CAMO-Net Uganda national hub is working to provide solutions to these problems. Machine learning offers transformative potential in our efforts to address AMR by accelerating drug discovery, predicting resistance patterns, and optimising treatment strategies.

Dr Ronald Galiwango, who leads the machine learning research at CAMO-Net Uganda said, “Machine learning has the potential to transform how we address antimicrobial resistance by providing faster, more precise insights into resistance patterns and treatment outcomes. By harnessing vast datasets, we can move beyond reactive approaches and develop proactive, data-driven strategies that optimise antibiotic use and improve patient care. Our work at CAMO-Net Uganda is focused on building ML models that not only predict resistance trends but also support clinicians in making more informed decisions—helping to slow the spread of resistance and safeguard the effectiveness of existing treatments.”

Ongoing investment in data infrastructure, workforce training, and policy integration is essential for realising machine learning’s full potential in the global effort to address AMR. By leveraging these capabilities, Uganda and other regions disproportionately affected by AMR can enhance its management, ensuring more effective antibiotic use and better patient outcomes.

Dr Conrad Tumwine of CAMO-Net Uganda reports back after attending the inaugural East African Regional Global Health Security Summit 2025.

The inaugural East African Regional Global Health Security Summit 2025, held in Mombasa from 28–30 January, provided a platform for experts to discuss pressing health security challenges. One of the most pivotal breakout sessions, ‘Antimicrobial Resistance and Healthcare-Associated Infections: Countering an Emerging Threat’, examined the escalating global and regional crisis of antimicrobial resistance (AMR) and its profound impact on healthcare systems. The session brought together leading experts to explore strategies for surveillance, prevention, and control of AMR in East Africa.

The panel featured Evelyn Wesangula – Senior AMR Control Specialist at the East, Central, and Southern Africa Health Community (ECSA-HC), Dr Dathan Byonanebye – Deputy Head of the Global Health Security Department at the Infectious Diseases Institute, Rogers Kisame – Fleming Fund Programme Manager at Baylor Foundation, and Prof Samuel Kariuki – Continental Lead for Africa and Eastern Africa Director at the Drugs for Neglected Diseases initiative (DNDi).

Discussions underscored the growing threat of AMR, highlighting how the misuse of antibiotics in both human and veterinary medicine has accelerated resistance. Panellists emphasised that AMR is not a distant concern but an urgent crisis, with drug-resistant infections already contributing to rising mortality rates. Strengthening AMR surveillance was identified as a critical priority, as many East African countries lack comprehensive data on resistance patterns. Without effective tracking systems, policymakers and healthcare providers struggle to implement targeted interventions.

Healthcare-associated infections (HAIs) were also recognised as a key driver of AMR, particularly in hospitals with inadequate infection prevention and control (IPC) measures. The session reinforced the need for improved hygiene standards, proper sterilisation of medical equipment, and robust antimicrobial stewardship programmes to limit the spread of drug-resistant infections in healthcare settings. Additionally, panellists stressed the importance of policy and innovation in addressing AMR, calling for greater investment in rapid diagnostic tools and alternative treatments, supported by private sector engagement.

Another key focus of the discussion was the role of research and academia in developing solutions to tackle AMR. Dr Dathan Byonanebye highlighted that data-driven policies and regional collaboration are essential for addressing the crisis. He stressed that research institutions must work alongside governments to invest in studies assessing AMR trends and evaluating the effectiveness of interventions. Panellists urged governments to enforce stricter regulations on antibiotic use, integrate AMR control into national health policies, and foster global partnerships to drive innovation.

The session reinforced the urgency of action. Addressing AMR requires a coordinated approach combining education, diagnostics, and infrastructure investments with stronger partnerships and multisectoral collaboration. With public and private sector stakeholders committed to this effort, the path from discussion to meaningful action has never been clearer.

This blog comes directly from our CAMO-Net Uganda team, featuring the words of Reuben Kiggundu, Mackline Hope, Brian Otaalo, Barbara Castelnuovo.

Antibiotics are a cornerstone of modern medicine, saving millions of lives each year. However, their inappropriate use poses a serious public health challenge, contributing to the growing threat of antimicrobial resistance (AMR). Among people living with HIV (PLHIV), who are often more vulnerable to infections due to compromised immunity, antibiotic misuse can have particularly severe consequences. The Centres for Antimicrobial Optimisation Network (CAMO-Net), a Wellcome-funded, multidisciplinary global collaboration addressing the impact of AMR on human health, is conducting studies across 11 countries to optimise antimicrobial use.

As part of this work, a retrospective study is being conducted to assess antibiotic prescribing for PLHIV. Researchers have been reviewing data from the Infectious Diseases Institute clinic in Kampala over the past 10 years to evaluate the appropriateness of prescriptions.

Preliminary analysis of antibiotic prescription data from 778 PLHIV, with a mean age of 49 years and 71.2% female participants, has identified concerning trends. Nearly half of the cohort were in advanced stages of HIV (WHO Stage III & IV), and the majority (68.9%) had been on antiretroviral therapy (ART) for over a decade. Early findings suggest significant antibiotic misuse within this population.

Only 38.8% of patients had a documented indication for antibiotic use, and just 38.5% underwent diagnostic investigations to guide treatment decisions. Overall, 77.3% of prescriptions were deemed inappropriate. Of these, 31.9% were issued without confirmed or suspected bacterial infection. Even when antibiotics were prescribed in response to a suspected or confirmed bacterial infection, more than half (54.2%) were of the incorrect class. Among prescriptions where the correct antibiotic class was selected, inappropriate dosing (29.3%), frequency (59.6%), and duration (65.6%) were common, alongside unnecessary combination therapy in 79% of cases. Inappropriate prescribing was particularly frequent for cephalosporins (54.5%) and fluoroquinolones (52.8%).

These findings highlight a critical issue of antibiotic overuse among PLHIV, which could further exacerbate the burden of AMR, particularly in Uganda and other low-income settings with a high HIV prevalence. This not only threatens to increase morbidity and mortality within this population but also results in the inefficient use of essential healthcare resources. Additionally, unnecessary antibiotic use can lead to drug-drug interactions with ART, potentially reducing treatment effectiveness.

To address these concerns, CAMO-Net is conducting therapeutic drug monitoring studies for antibiotics among PLHIV attending the ART clinic in Kampala, Uganda. By strengthening antimicrobial stewardship, enhancing diagnostic capacity, and promoting evidence-based prescribing, healthcare systems can mitigate the risks of AMR and improve outcomes for PLHIV. The findings from this study are already informing efforts to strengthen antimicrobial stewardship, with additional controls on antibiotic prescribing planned. The final analysis is expected by the end of Q1 2025 and will be published in a peer-reviewed journal.