Understanding and Implementing Diagnostic Stewardship: A Guide for Resident Physicians in the Era of Antimicrobial Resistance

Schinas, Georgios; Dimopoulos, George; Akinosoglou, Karolina

doi:10.3390/microorganisms11092214

Cited by 7 publications

(1 citation statement)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Urinary Tract Infections (UTIs) are among the most common bacterial infections, afflicting individuals across all age brackets and contributing significantly to the global healthcare burden [1], [2], [3]. The complexity of UTI diagnosis, influenced by a broad spectrum of symptoms and causative pathogens, underscores the need for more precise, efficient, and rapid diagnostic methods [4], [5], [6]. While traditional diagnostic techniques rely on microbial cultures and urinalysis, these methods often suffer from delays and variable sensitivity, which can hinder timely and accurate treatment [7], [8], [9].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Machine Learning Models for Urinary Tract Infection Diagnostics: A Comparative Study of Logistic Regression and Random Forest

Airlangga

2024

INFEB

View full text Add to dashboard Cite

Urinary Tract Infections (UTIs) present a significant healthcare challenge due to their prevalence and diagnostic complexity. Timely and accurate diagnosis is critical for effective treatment, yet traditional methods like microbial cultures and urinalysis are often slow and inconsistent. This study introduces machine learning (ML) as a transformative solution for UTI diagnostics, particularly focusing on logistic regression and random forest models renowned for their interpretability and robustness. We conducted a meticulous hyperparameter tuning process using a rich dataset from a clinic in Northern Mindanao, Philippines, incorporating demographic, clinical, and urinalysis data. Our research outlines a detailed methodology for applying and refining these ML models to predict UTI outcomes accurately. Through comprehensive hyperparameter optimization, we enhanced the predictive performance, demonstrating a significant improvement over standard diagnostic practice. The findings reveal a clear superiority of the random forest model, achieving a top testing accuracy of 0.9814, compared to the best-performing logistic regression model's accuracy of 0.7626. This comparative analysis not only validates the efficacy of ML in medical diagnostics but also emphasizes the potential clinical impact of these models in real-world settings. The study contributes to the burgeoning literature on ML applications in healthcare by providing a blueprint for optimizing ML models for clinical use, particularly in diagnosing UTIs. It underscores the promise of ML in augmenting diagnostic precision, thereby potentially reducing the global healthcare burden associated with UTIs.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimizing Machine Learning Models for Urinary Tract Infection Diagnostics: A Comparative Study of Logistic Regression and Random Forest

Airlangga

2024

INFEB

View full text Add to dashboard Cite

show abstract

Diagnostic stewardship for blood cultures in the pediatric intensive care unit: lessons in implementation from the BrighT STAR Collaborative

Woods-Hill,

Koontz,

Xie

et al. 2024

ASHE

View full text Add to dashboard Cite

Objective: BrighT STAR was a diagnostic stewardship collaborative of 14 pediatric intensive care units (PICUs) across the United States designed to standardize and reduce unnecessary blood cultures and study the impact on patient outcomes and broad-spectrum antibiotic use. We now examine the implementation process in detail to understand how sites facilitated this diagnostic stewardship program in their PICUs. Design: A multi-center electronic survey of the 14 BrighT STAR sites, based on qualitative data about the implementation process collected during the primary phase of BrighT STAR. Setting: 14 PICUs enrolled in BrighT STAR. Participants: Site leads at each enrolled site. Methods: An electronic survey guided by implementation science literature and based on data collected during BrighT STAR was administered to all 14 sites after completion of the primary phase of the collaborative. Results: 10 specific tasks appear critical to implementing blood culture diagnostic stewardship, with variability in site-level strategies employed to accomplish those tasks. Sites rated certain tasks and strategies as highly important. Strategies used in top-performing sites were distinct from those used in lower-performing sites. Certain strategies may link to drivers of culture overuse and represent key targets for changing clinician behavior. Conclusions: BrighT STAR offers important insights into the tasks and strategies used to facilitate successful diagnostic stewardship in the PICU. More work is needed to compare specific strategies and optimize stewardship outcomes in this complex environment. Clinical trial registry information: Blood Culture Improvement Guidelines and Diagnostic Stewardship for Antibiotic Reduction in Critically Ill Children (Bright STAR). NCT03441126. https://www.clinicaltrials.gov/study/NCT03441126?term=Bright%20STAR&aggFilters=status:com&checkSpell=false&rank=1

show abstract

The foundation for the microbiology laboratory’s essential role in diagnostic stewardship: an ASM Laboratory Practices Subcommittee report

Dumm,

Marlowe,

Patterson

et al. 2024

J Clin Microbiol

View full text Add to dashboard Cite

Diagnostic stewardship (DxS) has gained traction in recent years as a cross-disciplinary method to improve the quality of patient care while appropriately managing resources within the healthcare system. Clinical microbiology laboratorians have been highly engaged in DxS efforts to guide best practices with conventional microbiology tests and more recently with molecular infectious disease diagnostics. Laboratories can experience resistance to their role in DxS, especially when the clinical benefits, motivations for interventions, and underlying regulatory requirements are not clearly conveyed to stakeholders. Clinical laboratories must not only ensure ethical practices but also meet obligatory requirements to steward tests responsibly. In this review, we aim to support clinical microbiology laboratorians by providing the background and resources that demonstrate the laboratory’s essential role in DxS. The heart of this review is to collate regulatory and accreditation requirements that, in essence, mandate DxS practices as a long-standing, core element of high-quality laboratory testing to deliver the best possible patient care. While examples of the clinical impact of DxS are plentiful in the literature, here, we focus on the operational and regulatory justification for the laboratory’s role in stewardship activities.

show abstract

Understanding and Implementing Diagnostic Stewardship: A Guide for Resident Physicians in the Era of Antimicrobial Resistance

Cited by 7 publications

References 72 publications

Optimizing Machine Learning Models for Urinary Tract Infection Diagnostics: A Comparative Study of Logistic Regression and Random Forest

Optimizing Machine Learning Models for Urinary Tract Infection Diagnostics: A Comparative Study of Logistic Regression and Random Forest

Diagnostic stewardship for blood cultures in the pediatric intensive care unit: lessons in implementation from the BrighT STAR Collaborative

The foundation for the microbiology laboratory’s essential role in diagnostic stewardship: an ASM Laboratory Practices Subcommittee report

Contact Info

Product

Resources

About