Designing a Digital Health Solution: A Platform for Automated Surveillance of Fungal Infection.

Surveillance of invasive fungal infection (IFI) requires laborious review of multiple sources of clinical information, while applying complex criteria to effectively identify relevant infections. These processes can be automated using artificial intelligence (AI) methodologies, including applying natural language processing (NLP) to clinical reports. However, developing a practically useful automated IFI surveillance tool requires consideration of the implementation context. We employed the Design Thinking Framework (DTF) to focus on the needs of end users of the tool to ensure sustained user engagement and enable its prospective validation. DTF allowed iterative generation of ideas and refinement of the final digital health solution. We believe this approach is key to increasing the likelihood that the solution will be implemented in clinical practice.

Detecting evidence of invasive fungal infections in cytology and histopathology reports enriched with concept-level annotations.

Invasive fungal infections (IFIs) are particularly dangerous to high-risk patients with haematological malignancies and are responsible for excessive mortality and delays in cancer therapy. Surveillance of IFI in clinical settings offers an opportunity to identify potential risk factors and evaluate new therapeutic strategies. However, manual surveillance is both time- and resource-intensive. As part of a broader project aimed to develop a system for automated IFI surveillance by leveraging electronic medical records, we present our approach to detecting evidence of IFI in the key diagnostic domain of histopathology. Using natural language processing (NLP), we analysed cytology and histopathology reports to identify IFI-positive reports. We compared a conventional bag-of-words classification model to a method that relies on concept-level annotations. Although the investment to prepare data supporting concept annotations is substantial, extracting targeted information specific to IFI as a pre-processing step increased the performance of the classifier from the PR AUC of 0.84 to 0.92 and enabled model interpretability. We have made publicly available the annotated dataset of 283 reports, the Cytology and Histopathology IFI Reports corpus (CHIFIR), to allow the clinical NLP research community to further build on our results.

Introduction to the updated Australasian consensus guidelines for the management of invasive fungal disease and use of antifungal agents in the haematology/oncology setting, 2021.

This article introduces the fourth update of the Australian and New Zealand consensus guidelines for the management of invasive fungal disease and use of antifungal agents in the haematology/oncology setting. These guidelines are comprised of nine articles as presented in this special issue of the Internal Medicine Journal. This introductory chapter outlines the rationale for the current update and the steps taken to ensure implementability in local settings. Given that 7 years have passed since the previous iteration of these guidelines, pertinent contextual changes that impacted guideline content and recommendations are discussed, including the evolution of invasive fungal disease (IFD) definitions. We also outline our approach to guideline development, evidence grading, review and feedback. Highlights of the 2021 update are presented, including expanded scope to provide more detailed coverage of common and emerging fungi such as Aspergillus and Candida species, and emerging fungi, and a greater focus on the principles of antifungal stewardship. We also introduce an entirely new chapter dedicated to helping healthcare workers convey important concepts related to IFD, infection prevention and antifungal therapy, to patients.

Consensus guidelines for antifungal stewardship, surveillance and infection prevention, 2021.

Invasive fungal diseases (IFD) are serious infections associated with high mortality, particularly in immunocompromised patients. The prescribing of antifungal agents to prevent and treat IFD is associated with substantial economic burden on the health system, high rates of adverse drug reactions, significant drug-drug interactions and the emergence of antifungal resistance. As the population at risk of IFD continues to grow due to the increased burden of cancer and related factors, the need for hospitals to employ antifungal stewardship (AFS) programmes and measures to monitor and prevent infection has become increasingly important. These guidelines outline the essential components, key interventions and metrics, which can help guide implementation of an AFS programme in order to optimise antifungal prescribing and IFD management. Specific recommendations are provided for quality processes for the prevention of IFD in the setting of outbreaks, during hospital building works, and in the context of Candida auris infection. Recommendations are detailed for the implementation of IFD surveillance to enhance detection of outbreaks, evaluate infection prevention and prophylaxis interventions and to allow benchmarking between hospitals. Areas in which information is still lacking and further research is required are also highlighted.

Antimicrobial stewardship in Australia: the role of qualitative research in programme development.

Antimicrobial stewardship (AMS) in Australia is supported by a number of factors, including enabling national policies, sectoral clinical governance frameworks and surveillance programmes, clinician-led educational initiatives and health services research. A One Health research programme undertaken by the National Centre for Antimicrobial Stewardship (NCAS) in Australia has combined antimicrobial prescribing surveillance with qualitative research focused on developing antimicrobial use-related situational analyses and scoping AMS implementation options across healthcare settings, including metropolitan hospitals, regional and rural hospitals, aged care homes, general practice clinics and companion animal and agricultural veterinary practices. Qualitative research involving clinicians across these diverse settings in Australia has contributed to improved understanding of contextual factors that influence antimicrobial prescribing, and barriers and facilitators of AMS implementation. This body of research has been underpinned by a commitment to supplementing 'big data' on antimicrobial prescribing practices, where available, with knowledge of the sociocultural, technical, environmental and other factors that shape prescribing behaviours. NCAS provided a unique opportunity for exchange and cross-pollination across the human and animal health programme domains. It has facilitated synergistic approaches to AMS research and education, and implementation of resources and stewardship activities. The NCAS programme aimed to synergistically combine quantitative and qualitative approaches to AMS research. In this article, we describe the qualitative findings of the first 5 years.

Improving sepsis care for hospital inpatients using existing medical emergency response systems.

BACKGROUND: Sepsis is a medical emergency; timely management has been shown to reduce mortality. We aimed to improve the care of inpatients who developed sepsis after hospital admission by integrating a sepsis bundle with an existing medical emergency team (MET). METHODS: We performed a before-and-after study at an Australian institution. A multimodal intervention was implemented including formation of a working group, development of a guideline, standard documentation, education, audit and feedback. The primary outcome was the proportion of MET calls where there was compliance with the sepsis resuscitation bundle within one hour of MET call. RESULTS: There was an improvement in completion of the entire resuscitation bundle (OR 2.33, 95%, CI: 1.23 - 4.41) and lactate measurement (OR 2.72, CI: 1.53, 4.84) within one hour of MET call. There was a non-significant reduction in the median time to antibiotic administration in patients where antibiotics were initiated or changed at the MET call (60 mins vs. 44 mins, p = 0.8). In hospital mortality was observed to fall from 22.1% to 11.4%, but after adjusting for age and baseline illness severity this differences was not statistically significant (OR 0.52, CI: 0.23, 1.19, p = 0.12). CONCLUSION: The implementation of a multimodal sepsis bundle and the utilisation of an existing MET call system demonstrated an increase in the overall uptake of a sepsis bundle. This was associated with an observed reduction in all-cause in-hospital mortality, although this difference was not statistically significant after adjustment for confounders. Further interventions with a focus on nursing education and engagement may improve timely antibiotic administration.