Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 2 appraisals
Journal of clinical microbiology
Identification of Aspergillus at section and species levels by artificial intelligence-based microscopic morphology image recognition
Rapid and accurate identification of Aspergillus species in clinical microbiology laboratories is crucial for aspergillosis diagnosis and antifungal therapy. However, traditional methods still face challenges in distinguishing phylogenetically related species due to their morphological similarities. This study presents FungalNet, a deep learning model integrating ResNet-50 architecture with Focal Loss algorithm, specifically designed to enhance feature extraction for Aspergillus identification. A total of 12,000 high-resolution images were obtained from lactophenol cotton blue-stained slide preparations under a 100× oil immersion objective, among which 311 images were excluded through a novel quality control approach combining fivefold cross-validation and expert manual review. The performance of four deep learning models (FungalNet and three established models) for identifying Aspergillus species and sections was evaluated using the remaining 11,689 qualified images. FungalNet demonstrated superior classification performance, achieving overall accuracies of 98.45% and 97.85% at the section and species levels, respectively. These results indicate that FungalNet shows significant promise for rapid and accurate identification of Aspergillus species. With further optimization and multicenter validation, this tool could potentially be integrated into routine diagnostic workflows to enhance the efficiency and reliability of fungal identification in clinical settings.IMPORTANCEThis study integrates microscopic morphology identification with deep learning to address the challenge of accurate Aspergillus species identification. Twelve clinically isolated Aspergillus species belonging to eight different sections were included. From touch-tape slide preparations with lactophenol cotton blue staining under a 100× oil immersion objective, 11,689 qualified images were collected and analyzed using FungalNet (our proposed model) along with three established models (GoogLeNet, ResNet-50, and Xception). The results showed that FungalNet demonstrated superior performance in Aspergillus identification, achieving the highest classification accuracy at both section (98.45%) and species (97.85%) levels. Given its rapid turnaround time and cost-effectiveness, this AI-based image analysis approach shows promising potential for the rapid and accurate identification of Aspergillus species in clinical microbiology laboratories.
9 Apr 2026
Read appraisal →Intensive Care Med
Invasive candidiasis in intensive care medicine: shaping the future of diagnosis and therapy
BACKGROUND: Invasive candidiasis (IC) remains one of the most challenging infections in critical care, contributing significantly to morbidity, prolonged organ support, and mortality among intensive care unit (ICU) patients. The clinical landscape of IC is evolving, with increasing recognition of Candida non-albicans species and other yeasts formerly classified as Candida spp., alongside emerging multidrug resistance and growing complexity in host immune profiles. OBJECTIVES: This contemporary, multidisciplinary narrative review-authored by intensivists, infectious diseases specialists, clinical microbiologists, and pharmacologists-aims to provide ICU clinicians with practical, up-to-date insights into the diagnosis and management of IC. To maintain clinical focus, the review excludes non-IC fungal infections and non-ICU patient populations. METHODS: Relevant literature and expert consensus were critically reviewed to summarize current diagnostic and therapeutic approaches for IC in critically ill patients. Emphasis was placed on pragmatic clinical application, diagnostic limitations, antifungal stewardship, and personalized therapeutic decision-making. RESULTS: Despite the availability of novel antifungal agents with improved pharmacokinetic properties, treatment success in IC depends equally on timely and accurate diagnosis and individualized, context-aware therapy. Blood cultures continue to demonstrate limited sensitivity (~40%). Non-culture assays, including β-D-glucan and molecular diagnostics, provide faster detection and high negative predictive value but suffer from low positive predictive value and inconsistent adoption in clinical practice. The absence of validated host-derived biomarkers further limits risk stratification, antifungal discontinuation decisions, and personalized care. CONCLUSIONS: Emerging antifungal agents, stewardship strategies, and multidisciplinary care models are essential to improve clinical outcomes and reduce antifungal resistance. This review underscores the need for integrated, team-based diagnostic and therapeutic approaches to close persistent gaps in IC management, ultimately promoting more effective, timely, and individualized care for critically ill patients with Candida spp.
1 Nov 2025
Read appraisal →