Machine learning to predict antimicrobial resistance: future applications in clinical practice?

INTRODUCTION

Machine learning (ML) is increasingly being used to predict antimicrobial resistance (AMR). This review aims to provide physicians with an overview of the literature on ML as a means of AMR prediction.

METHODS

References for this review were identified through searches of MEDLINE/PubMed, EMBASE, Google Scholar, ACM Digital Library, and IEEE Xplore Digital Library up to December 2023.

RESULTS

Thirty-six studies were included in this review. Thirty-two studies (32/36, 89 %) were based on hospital data and four (4/36, 11 %) on outpatient data. The vast majority of them were conducted in high-resource settings (33/36, 92 %). Twenty-four (24/36, 67 %) studies developed systems to predict drug resistance in infected patients, eight (8/36, 22 %) tested the performances of ML-assisted antibiotic prescription, two (2/36, 6 %) assessed ML performances in predicting colonization with carbapenem-resistant bacteria and, finally, two assessed national and international AMR trends. The most common inputs were demographic characteristics (25/36, 70 %), previous antibiotic susceptibility testing (19/36, 53 %) and prior antibiotic exposure (15/36, 42 %). Thirty-three (92 %) studies targeted prediction of Gram-negative bacteria (GNB) resistance as an output (92 %). The studies included showed moderate to high performances, with AUROC ranging from 0.56 to 0.93.

CONCLUSION

ML can potentially provide valuable assistance in AMR prediction. Although the literature on this topic is growing, future studies are needed to design, implement, and evaluate the use and impact of ML decision support systems.

Explainable and Interpretable Machine Learning for Antimicrobial Stewardship: Opportunities and Challenges

There is growing interest in exploiting the advances in artificial intelligence and machine learning (ML) for improving and monitoring antimicrobial prescriptions in line with antimicrobial stewardship principles. Against this background, the concepts of interpretability and explainability are becoming increasingly essential to understanding how ML algorithms could predict antimicrobial resistance or recommend specific therapeutic agents, to avoid unintended biases related to the "black box" nature of complex models. In this commentary, we review and discuss some relevant topics on the use of ML algorithms for antimicrobial stewardship interventions, highlighting opportunities and challenges, with particular attention paid to interpretability and explainability of employed models. As in other fields of medicine, the exponential growth of artificial intelligence and ML indicates the potential for improving the efficacy of antimicrobial stewardship interventions, at least in part by reducing time-consuming tasks for overwhelmed health care personnel. Improving our knowledge about how complex ML models work could help to achieve crucial advances in promoting the appropriate use of antimicrobials, as well as in preventing antimicrobial resistance selection and dissemination.

Optimizing artificial intelligence in sepsis management: Opportunities in the present and looking closely to the future

Sepsis remains a major challenge internationally for healthcare systems. Its incidence is rising due to poor public awareness and delays in its recognition and subsequent management. In sepsis, mortality increases with every hour left untreated. Artificial intelligence (AI) is transforming worldwide healthcare delivery at present. This review has outlined how AI can augment strategies to address this global disease burden. AI and machine learning (ML) algorithms can analyze vast quantities of increasingly complex clinical datasets from electronic medical records to assist clinicians in diagnosing and treating sepsis earlier than traditional methods. Our review highlights how these models can predict the risk of sepsis and organ failure even before it occurs. This gives providers additional time to plan and execute treatment plans, thereby avoiding increasing complications associated with delayed diagnosis of sepsis. The potential for cost savings with AI implementation is also discussed, including improving workflow efficiencies, reducing administrative costs, and improving healthcare outcomes. Despite these advantages, clinicians have been slow to adopt AI into clinical practice. Some of the limitations posed by AI solutions include the lack of diverse data sets for model building so that they are widely applicable for routine clinical use. Furthermore, the subsequent algorithms are often based on complex mathematics leading to clinician hesitancy to embrace such technologies. Finally, we highlight the need for robust political and regulatory frameworks in this area to achieve the trust and approval of clinicians and patients to implement this transformational technology.

Mapping the Bibliometrics Landscape of AI in Medicine: Methodological Study

BACKGROUND

Artificial intelligence (AI), conceived in the 1950s, has permeated numerous industries, intensifying in tandem with advancements in computing power. Despite the widespread adoption of AI, its integration into medicine trails other sectors. However, medical AI research has experienced substantial growth, attracting considerable attention from researchers and practitioners.

OBJECTIVE

In the absence of an existing framework, this study aims to outline the current landscape of medical AI research and provide insights into its future developments by examining all AI-related studies within PubMed over the past 2 decades. We also propose potential data acquisition and analysis methods, developed using Python (version 3.11) and to be executed in Spyder IDE (version 5.4.3), for future analogous research.

METHODS

Our dual-pronged approach involved (1) retrieving publication metadata related to AI from PubMed (spanning 2000-2022) via Python, including titles, abstracts, authors, journals, country, and publishing years, followed by keyword frequency analysis and (2) classifying relevant topics using latent Dirichlet allocation, an unsupervised machine learning approach, and defining the research scope of AI in medicine. In the absence of a universal medical AI taxonomy, we used an AI dictionary based on the European Commission Joint Research Centre AI Watch report, which emphasizes 8 domains: reasoning, planning, learning, perception, communication, integration and interaction, service, and AI ethics and philosophy.

RESULTS

From 2000 to 2022, a comprehensive analysis of 307,701 AI-related publications from PubMed highlighted a 36-fold increase. The United States emerged as a clear frontrunner, producing 68,502 of these articles. Despite its substantial contribution in terms of volume, China lagged in terms of citation impact. Diving into specific AI domains, as the Joint Research Centre AI Watch report categorized, the learning domain emerged dominant. Our classification analysis meticulously traced the nuanced research trajectories across each domain, revealing the multifaceted and evolving nature of AI's application in the realm of medicine.

CONCLUSIONS

The research topics have evolved as the volume of AI studies increases annually. Machine learning remains central to medical AI research, with deep learning expected to maintain its fundamental role. Empowered by predictive algorithms, pattern recognition, and imaging analysis capabilities, the future of AI research in medicine is anticipated to concentrate on medical diagnosis, robotic intervention, and disease management. Our topic modeling outcomes provide a clear insight into the focus of AI research in medicine over the past decades and lay the groundwork for predicting future directions. The domains that have attracted considerable research attention, primarily the learning domain, will continue to shape the trajectory of AI in medicine. Given the observed growing interest, the domain of AI ethics and philosophy also stands out as a prospective area of increased focus.

Using Machine Learning to Predict Antimicrobial Resistance-A Literature Review

Machine learning (ML) algorithms are increasingly applied in medical research and in healthcare, gradually improving clinical practice. Among various applications of these novel methods, their usage in the combat against antimicrobial resistance (AMR) is one of the most crucial areas of interest, as increasing resistance to antibiotics and management of difficult-to-treat multidrug-resistant infections are significant challenges for most countries worldwide, with life-threatening consequences. As antibiotic efficacy and treatment options decrease, the need for implementation of multimodal antibiotic stewardship programs is of utmost importance in order to restrict antibiotic misuse and prevent further aggravation of the AMR problem. Both supervised and unsupervised machine learning tools have been successfully used to predict early antibiotic resistance, and thus support clinicians in selecting appropriate therapy. In this paper, we reviewed the existing literature on machine learning and artificial intelligence (AI) in general in conjunction with antimicrobial resistance prediction. This is a narrative review, where we discuss the applications of ML methods in the field of AMR and their value as a complementary tool in the antibiotic stewardship practice, mainly from the clinician's point of view.

Learning meaningful latent space representations for patient risk stratification: Model development and validation for dengue and other acute febrile illness

Background

Increased data availability has prompted the creation of clinical decision support systems. These systems utilise clinical information to enhance health care provision, both to predict the likelihood of specific clinical outcomes or evaluate the risk of further complications. However, their adoption remains low due to concerns regarding the quality of recommendations, and a lack of clarity on how results are best obtained and presented.

Methods

We used autoencoders capable of reducing the dimensionality of complex datasets in order to produce a 2D representation denoted as latent space to support understanding of complex clinical data. In this output, meaningful representations of individual patient profiles are spatially mapped in an unsupervised manner according to their input clinical parameters. This technique was then applied to a large real-world clinical dataset of over 12,000 patients with an illness compatible with dengue infection in Ho Chi Minh City, Vietnam between 1999 and 2021. Dengue is a systemic viral disease which exerts significant health and economic burden worldwide, and up to 5% of hospitalised patients develop life-threatening complications.

Results

The latent space produced by the selected autoencoder aligns with established clinical characteristics exhibited by patients with dengue infection, as well as features of disease progression. Similar clinical phenotypes are represented close to each other in the latent space and clustered according to outcomes broadly described by the World Health Organisation dengue guidelines. Balancing distance metrics and density metrics produced results covering most of the latent space, and improved visualisation whilst preserving utility, with similar patients grouped closer together. In this case, this balance is achieved by using the sigmoid activation function and one hidden layer with three neurons, in addition to the latent dimension layer, which produces the output (Pearson, 0.840; Spearman, 0.830; Procrustes, 0.301; GMM 0.321).

Conclusion

This study demonstrates that when adequately configured, autoencoders can produce two-dimensional representations of a complex dataset that conserve the distance relationship between points. The output visualisation groups patients with clinically relevant features closely together and inherently supports user interpretability. Work is underway to incorporate these findings into an electronic clinical decision support system to guide individual patient management.

Machine learning and synthetic outcome estimation for individualised antimicrobial cessation

The decision on when it is appropriate to stop antimicrobial treatment in an individual patient is complex and under-researched. Ceasing too early can drive treatment failure, while excessive treatment risks adverse events. Under- and over-treatment can promote the development of antimicrobial resistance (AMR). We extracted routinely collected electronic health record data from the MIMIC-IV database for 18,988 patients (22,845 unique stays) who received intravenous antibiotic treatment during an intensive care unit (ICU) admission. A model was developed that utilises a recurrent neural network autoencoder and a synthetic control-based approach to estimate patients' ICU length of stay (LOS) and mortality outcomes for any given day, under the alternative scenarios of if they were to stop vs. continue antibiotic treatment. Control days where our model should reproduce labels demonstrated minimal difference for both stopping and continuing scenarios indicating estimations are reliable (LOS results of 0.24 and 0.42 days mean delta, 1.93 and 3.76 root mean squared error, respectively). Meanwhile, impact days where we assess the potential effect of the unobserved scenario showed that stopping antibiotic therapy earlier had a statistically significant shorter LOS (mean reduction 2.71 days, p -value <0.01). No impact on mortality was observed. In summary, we have developed a model to reliably estimate patient outcomes under the contrasting scenarios of stopping or continuing antibiotic treatment. Retrospective results are in line with previous clinical studies that demonstrate shorter antibiotic treatment durations are often non-inferior. With additional development into a clinical decision support system, this could be used to support individualised antimicrobial cessation decision-making, reduce the excessive use of antibiotics, and address the problem of AMR.

Investigating pharmacy students' therapeutic decision-making with respect to antimicrobial stewardship cases

BACKGROUND

Antimicrobial stewardship programs (ASPs) play a big role in minimizing antimicrobial resistance. Pharmacists are essential members of the health care team and in order for them to fulfill roles on ASP teams and become antimicrobial stewards, they must be prepared adequately by pharmacy schools prior to entry into actual practice. Although programming has been implemented into entry-to-practice programs worldwide, little is known about how students interpret antimicrobial stewardship (AMS) data and arrive at clinical decisions. We aimed to explore students' cognitive processes and determine how they formulate therapeutic decisions when presented with AMS cases.

METHODS

This was a qualitative study conducted using a case study approach, in which a sample (n=20) of pharmacy students was recruited to interpret AMS cases. Semi-structured 1-on-1 interviews were arranged with each participant. A think-aloud procedure with verbal protocol analysis was adopted to determine students' decision-making processes. Thematic analysis was used to interpret themes from the interview data.

RESULTS

Two themes were interpreted from the data: students' focus and students' approach to case interpretation. Students' focus relates to external factors students consider when interpreting AMS case data and use to make and justify therapeutic decisions including patient-centered factors, drug-related factors, AMS interventions, and pharmacist's role. Students' clinical reasoning describes the approach that students use to interpret the data and the decision-making processes they employ to arrive at a clinical decision including a systematic approach versus non-systematic approach.

CONCLUSIONS

Students vary in their focus and the cognitive strategies used to interpret AMS cases. Findings support the notion that clinical reasoning and decision-making should be explicitly taught in pharmacy curricula, in order to help students become aware of their own cognitive processes and decision-making abilities.

Optimizing antibiotic therapies to reduce the risk of bacterial resistance

The incidence of infections caused by bacteria that are resistant to antibiotics is constantly increasing. In Europe alone, it has been estimated that each year about 33'000 deaths are attributable to such infections. One important driver of antimicrobial resistance is the use and abuse of antibiotics in human medicine. Inappropriate prescribing of antibiotics is still very frequent: up to 50% of all antimicrobials prescribed in humans might be unnecessary and several studies show that at least 50% of antibiotic treatments are inadequate, depending on the setting. Possible strategies to optimize antibiotic use in everyday clinical practice and to reduce the risk of inducing bacterial resistance include: the implementation of rapid microbiological diagnostics for identification and antimicrobial susceptibility testing, the use of inflammation markers to guide initiation and duration of therapies, the reduction of standard durations of antibiotic courses, the individualization of antibiotic therapies and dosing considering pharmacokinetics/pharmacodynamics targets, and avoiding antibiotic classes carrying a higher risk for induction of bacterial resistance. Importantly, measures to improve antibiotic prescribing and antibiotic stewardship programs should focus on facilitating clinical reasoning and improving prescribing environment in order to remove any barriers to good prescribing.

How to use new antibiotics in the therapy of ventilator-associated pneumonia

PURPOSE OF REVIEW

Ventilator-associated pneumonia (VAP) is a common nosocomial infection in critically ill patients requiring endotracheal intubation and mechanical ventilation. Recently, the emergence of multidrug-resistant Gram-negative bacteria, including carbapenem-resistant Enterobacterales, multidrug-resistant Pseudomonas aeruginosa and Acinetobacter species, has complicated the selection of appropriate antimicrobials and contributed to treatment failure. Although novel antimicrobials are crucial to treating VAP caused by these multidrug-resistant organisms, knowledge of how to optimize their efficacy while minimizing the development of resistance should be a requirement for their use.

RECENT FINDINGS

Several studies have assessed the efficacy of novel antimicrobials against multidrug-resistant organisms, but high-quality studies focusing on optimal dosing, infusion time and duration of therapy in patients with VAP are still lacking. Antimicrobial and diagnostic stewardship should be combined to optimize the use of these novel agents.

SUMMARY

Improvements in diagnostic tests, stewardship practices and a better understanding of dosing, infusion time, duration of treatment and the effects of combining various antimicrobials should help optimize the use of novel antimicrobials for VAP and maximize clinical outcomes while minimizing the development of resistance.

The Diagnosis of Dengue in Patients Presenting With Acute Febrile Illness Using Supervised Machine Learning and Impact of Seasonality

Background

Symptomatic dengue infection can result in a life-threatening shock syndrome and timely diagnosis is essential. Point-of-care tests for non-structural protein 1 and IgM are used widely but performance can be limited. We developed a supervised machine learning model to predict whether patients with acute febrile illnesses had a diagnosis of dengue or other febrile illnesses (OFI). The impact of seasonality on model performance over time was examined.

Methods

We analysed data from a prospective observational clinical study in Vietnam. Enrolled patients presented with an acute febrile illness of <72 h duration. A gradient boosting model (XGBoost) was used to predict final diagnosis using age, sex, haematocrit, platelet, white cell, and lymphocyte count collected on enrolment. Data was randomly split 80/20% into a training and hold-out set, respectively, with the latter not used in model development. Cross-validation and hold out set testing was used, with performance over time evaluated through a rolling window approach.

Results

We included 8,100 patients recruited between 16th October 2010 and 10th December 2014. In total 2,240 (27.7%) patients were diagnosed with dengue infection. The optimised model from training data had an overall median area under the receiver operator curve (AUROC) of 0.86 (interquartile range 0.84-0.86), specificity of 0.92, sensitivity of 0.56, positive predictive value of 0.73, negative predictive value (NPV) of 0.84, and Brier score of 0.13 in predicting the final diagnosis, with similar performances in hold-out set testing (AUROC of 0.86). Model performances varied significantly over time as a function of seasonality and other factors. Incorporation of a dynamic threshold which continuously learns from recent cases resulted in a more consistent performance throughout the year (NPV >90%).

Conclusion

Supervised machine learning models are able to discriminate between dengue and OFI diagnoses in patients presenting with an early undifferentiated febrile illness. These models could be of clinical utility in supporting healthcare decision-making and provide passive surveillance across dengue endemic regions. Effects of seasonality and changing disease prevalence must however be taken into account-this is of significant importance given unpredictable effects of human-induced climate change and the impact on health.

A Risk-Based Clinical Decision Support System for Patient-Specific Antimicrobial Therapy (iBiogram): Design and Retrospective Analysis

Background

There is a pressing need for digital tools that can leverage big data to help clinicians select effective antibiotic treatments in the absence of timely susceptibility data. Clinical presentation and local epidemiology can inform therapy selection to balance the risk of antimicrobial resistance and patient risk. However, data and clinical expertise must be appropriately integrated into clinical workflows.

Objective

The aim of this study is to leverage available data in electronic health records, to develop a data-driven, user-centered, clinical decision support system to navigate patient safety and population health.

Methods

We analyzed 5 years of susceptibility testing (1,078,510 isolates) and patient data (30,761 patients) across a large academic medical center. After curating the data according to the Clinical and Laboratory Standards Institute guidelines, we analyzed and visualized the impact of risk factors on clinical outcomes. On the basis of this data-driven understanding, we developed a probabilistic algorithm that maps these data to individual cases and implemented iBiogram, a prototype digital empiric antimicrobial clinical decision support system, which we evaluated against actual prescribing outcomes.

Results

We determined patient-specific factors across syndromes and contexts and identified relevant local patterns of antimicrobial resistance by clinical syndrome. Mortality and length of stay differed significantly depending on these factors and could be used to generate heuristic targets for an acceptable risk of underprescription. Combined with the developed remaining risk algorithm, these factors can be used to inform clinicians’ reasoning. A retrospective comparison of the iBiogram-suggested therapies versus the actual prescription by physicians showed similar performance for low-risk diseases such as urinary tract infections, whereas iBiogram recognized risk and recommended more appropriate coverage in high mortality conditions such as sepsis.

Conclusions

The application of such data-driven, patient-centered tools may guide empirical prescription for clinicians to balance morbidity and mortality with antimicrobial stewardship.

Resistance Trend Estimation Using Regression Analysis to Enhance Antimicrobial Surveillance: A Multi-Centre Study in London 2009-2016

In the last years, there has been an increase of antimicrobial resistance rates around the world with the misuse and overuse of antimicrobials as one of the main leading drivers. In response to this threat, a variety of initiatives have arisen to promote the efficient use of antimicrobials. These initiatives rely on antimicrobial surveillance systems to promote appropriate prescription practices and are provided by national or global health care institutions with limited consideration of the variations within hospitals. As a consequence, physicians' adherence to these generic guidelines is still limited. To fill this gap, this work presents an automated approach to performing local antimicrobial surveillance from microbiology data. Moreover, in addition to the commonly reported resistance rates, this work estimates secular resistance trends through regression analysis to provide a single value that effectively communicates the resistance trend to a wider audience. The methods considered for trend estimation were ordinary least squares regression, weighted least squares regression with weights inversely proportional to the number of microbiology records available and autoregressive integrated moving average. Among these, weighted least squares regression was found to be the most robust against changes in the granularity of the time series and presented the best performance. To validate the results, three case studies have been thoroughly compared with the existing literature: (i) Escherichia coli in urine cultures; (ii) Escherichia coli in blood cultures; and (iii) Staphylococcus aureus in wound cultures. The benefits of providing local rather than general antimicrobial surveillance data of a higher quality is two fold. Firstly, it has the potential to stimulate engagement among physicians to strengthen their knowledge and awareness on antimicrobial resistance which might encourage prescribers to change their prescription habits more willingly. Moreover, it provides fundamental knowledge to the wide range of stakeholders to revise and potentially tailor existing guidelines to the specific needs of each hospital.

Leapfrogging laboratories: the promise and pitfalls of high-tech solutions for antimicrobial resistance surveillance in low-income settings

The scope and trajectory of today’s escalating antimicrobial resistance (AMR) crisis is inadequately captured by existing surveillance systems, particularly those of lower income settings. AMR surveillance systems typically collate data from routine culture and susceptibility testing performed in diagnostic bacteriology laboratories to support healthcare. Limited access to high quality culture and susceptibility testing results in the dearth of AMR surveillance data, typical of many parts of the world where the infectious disease burden and antimicrobial need are high. Culture and susceptibility testing by traditional techniques is also slow, which limits its value in infection management. Here, we outline hurdles to effective resistance surveillance in many low-income settings and encourage an open attitude towards new and evolving technologies that, if adopted, could close resistance surveillance gaps. Emerging advancements in point-of-care testing, laboratory detection of resistance through or without culture, and in data handling, have the potential to generate resistance data from previously unrepresented locales while simultaneously supporting healthcare. Among them are microfluidic, nucleic acid amplification technology and next-generation sequencing approaches. Other low tech or as yet unidentified innovations could also rapidly accelerate AMR surveillance. Parallel advances in data handling further promise to significantly improve AMR surveillance, and new frameworks that can capture, collate and use alternate data formats may need to be developed. We outline the promise and limitations of such technologies, their potential to leapfrog surveillance over currently available, conventional technologies in use today and early steps that health systems could take towards preparing to adopt them.

Artificial Intelligence for Clinical Decision Support in Sepsis

Sepsis is one of the main causes of death in critically ill patients. Despite the continuous development of medical technology in recent years, its morbidity and mortality are still high. This is mainly related to the delay in starting treatment and non-adherence of clinical guidelines. Artificial intelligence (AI) is an evolving field in medicine, which has been used to develop a variety of innovative Clinical Decision Support Systems. It has shown great potential in predicting the clinical condition of patients and assisting in clinical decision-making. AI-derived algorithms can be applied to multiple stages of sepsis, such as early prediction, prognosis assessment, mortality prediction, and optimal management. This review describes the latest literature on AI for clinical decision support in sepsis, and outlines the application of AI in the prediction, diagnosis, subphenotyping, prognosis assessment, and clinical management of sepsis. In addition, we discussed the challenges of implementing and accepting this non-traditional methodology for clinical purposes.

Best practice: antibiotic decision-making in ICUs

PURPOSE OF REVIEW

A major challenge in the ICU is optimization of antibiotic use. This review assesses current understanding of core best practices supporting and promoting astute antibiotic decision-making.

RECENT FINDINGS

Limiting exposure to the shortest effective duration is the cornerstone of antibiotic decision-making. The decision to initiate antibiotics should include assessment of risk for resistance. This requires synthesis of patient-level data and environmental factors to determine whether delayed initiation could be considered in some patients with suspected sepsis until sensitivity data is available. Until improved stratification scores and clinically meaningful cut-off values to identify MDR are available and externally validated, decisions as to which empiric antibiotic is used should rely on syndromic antibiograms and institutional guidance. Optimization of initial and maintenance doses is another enabler of enhanced outcome. Stewardship practices must be streamlined by re-assessment to minimize negative effects, such as a potential increase in duration of therapy and increased risk of collateral damage from exposure to multiple, sequential antibiotics that may ensue from de-escalation.

SUMMARY

Multiple challenges and research priorities for antibiotic optimization remain; however, the best stewardship practices should be identified and entrenched in daily practice. Reducing unnecessary exposure remains a vital strategy to limit resistance development.

Bacterial and Fungal Coinfection in Individuals With Coronavirus: A Rapid Review To Support COVID-19 Antimicrobial Prescribing

BACKGROUND

To explore and describe the current literature surrounding bacterial/fungal coinfection in patients with coronavirus infection.

METHODS

MEDLINE, EMBASE, and Web of Science were searched using broad-based search criteria relating to coronavirus and bacterial coinfection. Articles presenting clinical data for patients with coronavirus infection (defined as SARS-1, MERS, SARS-CoV-2, and other coronavirus) and bacterial/fungal coinfection reported in English, Mandarin, or Italian were included. Data describing bacterial/fungal coinfections, treatments, and outcomes were extracted. Secondary analysis of studies reporting antimicrobial prescribing in SARS-CoV-2 even in absence of coinfection was performed.

RESULTS

1007 abstracts were identified. Eighteen full texts reporting bacterial/fungal coinfection were included. Most studies did not identify or report bacterial/fungal coinfection (85/140; 61%). Nine of 18 (50%) studies reported on COVID-19, 5/18 (28%) on SARS-1, 1/18 (6%) on MERS, and 3/18 (17%) on other coronaviruses. For COVID-19, 62/806 (8%) patients were reported as experiencing bacterial/fungal coinfection during hospital admission. Secondary analysis demonstrated wide use of broad-spectrum antibacterials, despite a paucity of evidence for bacterial coinfection. On secondary analysis, 1450/2010 (72%) of patients reported received antimicrobial therapy. No antimicrobial stewardship interventions were described. For non-COVID-19 cases, bacterial/fungal coinfection was reported in 89/815 (11%) of patients. Broad-spectrum antibiotic use was reported.

CONCLUSIONS

Despite frequent prescription of broad-spectrum empirical antimicrobials in patients with coronavirus-associated respiratory infections, there is a paucity of data to support the association with respiratory bacterial/fungal coinfection. Generation of prospective evidence to support development of antimicrobial policy and appropriate stewardship interventions specific for the COVID-19 pandemic is urgently required.

Antimicrobial use, drug-resistant infections and COVID-19

Coronavirus disease 2019 may have a complex long-term impact on antimicrobial resistance (AMR). Coordinated strategies at the individual, health-care and policy levels are urgently required to inform necessary actions to reduce the potential longer-term impact on AMR and on access to effective antimicrobials.