Actionable data is key, because it supports decision-making that directly impacts patient outcomes and facilitates collaboration for true “handshake stewardship.” As explained by the authors of this Clinical Infectious Diseases article, “handshake stewardship is distinguished by: (1) lack of restriction and prior authorization, (2) review of all prescribed anti-infectives, (3) a review shared by the physician and the pharmacist, and (4) a daily round-based, in-person approach to supporting providers.”

To make handshake stewardship both efficient and effective, AMS teams need access to data from a range of systems, including laboratory, pharmacy, and electronic health records (EHR). Timely data collection from diverse and siloed hospital systems has often been a challenge, requiring an enormous amount of work on the part of AMS teams. However, recent advances in technology, particularly cloud computing and machine learning used with tools like artificial intelligence (AI), can provide the type of integrated, real-time analysis that clinicians need to track evolving resistance, improve diagnostic utilization, and deliver better patient care.

As noted by the authors in a study published in Antimicrobial Stewardship & Healthcare Epidemiology, “AI algorithms further guide clinicians in determining the likelihood of infection, selecting the most appropriate empiric and targeted regimens, provide dose optimization, and minimize the risk of resistance development.” Better quality data means clinicians can make better treatment decisions, leading to improved patient outcomes.

Real-time analysis is particularly important because AMR is a moving target—microbes are constantly evolving. Antibiograms, which are in-depth, location-specific profiles of microorganisms and their antibiotic susceptibility, are critical tools in clinicians’ fight against AMR. Hospitals typically take months to produce them because of the sheer quantity of data that must be analyzed. By the time the antibiogram is produced, the actual microorganisms and their resistance profiles may have already changed. That’s a problem for clinicians who must make empiric therapy decisions for patients with symptoms of infection. However, integrating disparate data systems and automating the analysis process can help by providing clinicians with up-to-the-moment and even patient-specific antibiograms.

Accessibility to readily available data can be impactful, and research shows that, “machine learning models that predict antibiotic susceptibility have the potential to guide clinicians when choosing antibiotics in a way that maintains or improves patient safety while reducing the overall use of wide acting antibiotics.”
 

Alongside AMS initiatives, diagnostic stewardship has become increasingly important in delivering value-based healthcare. Diagnostics also have a direct impact on antimicrobial stewardship because they provide data that clinicians need to make treatment decisions. Therefore, optimizing the use of diagnostics can contribute to the overall quality of care. Diagnostics are considered an essential weapon in any strategy to combat resistance and they have been shown to reduce mortality, lessen hospital stays, and shrink healthcare costs. With a holistic view of antimicrobial and diagnostic use, stewardship teams can implement new strategies and evaluate their efficacy. Continued technological developments will simultaneously add depth and efficiency to stewardship programs, equipping clinicians to meet the challenges of AMR today and tomorrow.