Performance evaluation of machine-assisted interpretation of Gram stains from positive blood cultures.

Manual microscopy of Gram stains from positive blood cultures (PBCs) is crucial for diagnosing bloodstream infections but remains labor intensive, time consuming, and subjective. This study aimed to evaluate a scan and analysis system that combines fully automated digital microscopy with deep convolutional neural networks (CNNs) to assist the interpretation of Gram stains from PBCs for routine laboratory use. The CNN was trained to classify images of Gram stains based on staining and morphology into seven different classes: background/false-positive, Gram-positive cocci in clusters (GPCCL), Gram-positive cocci in pairs (GPCP), Gram-positive cocci in chains (GPCC), rod-shaped bacilli (RSB), yeasts, and polymicrobial specimens. A total of 1,555 Gram-stained slides of PBCs were scanned, pre-classified, and reviewed by medical professionals. The results of assisted Gram stain interpretation were compared to those of manual microscopy and cultural species identification by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS). The comparison of assisted Gram stain interpretation and manual microscopy yielded positive/negative percent agreement values of 95.8%/98.0% (GPCCL), 87.6%/99.3% (GPCP/GPCC), 97.4%/97.8% (RSB), 83.3%/99.3% (yeasts), and 87.0%/98.5% (negative/false positive). The assisted Gram stain interpretation, when compared to MALDI-TOF MS species identification, also yielded similar results. During the analytical performance study, assisted interpretation showed excellent reproducibility and repeatability. Any microorganism in PBCs should be detectable at the determined limit of detection of 105 CFU/mL. Although the CNN-based interpretation of Gram stains from PBCs is not yet ready for clinical implementation, it has potential for future integration and advancement.

Comparison of phenotypic methods for the detection of penicillinase in Staphylococcus aureus and proposal of a practical diagnostic approach.

Objectives: Disc diffusion is a cost-efficient, low-complexity, reliable method for detection of blaZ -mediated benzylpenicillin resistance in Staphylococcus aureus if the zone edge is inspected. EUCAST breakpoints cannot fully separate ß-lactamase-positive from ß-lactamase-negative strains, and EUCAST recommends the zone edge test. Literature on nitrocefin-based testing and the zone edge test is scarce with wide variations in reported assay performance. Methods: This study compared two different nitrocefin-based commercial and in-house tests and the EUCAST-based zone edge test for penicillinase detection in S. aureus applying a PCR-based gold standard. Results: In total, 215 non-duplicate clinical S. aureus isolates were included in the study, of which 127 (59.1%) did not harbour a blaZ gene, whereas 88 (40.9%) were blaZ positive. This study showed that for blaZ detection the zone edge test is more sensitive (96.6%) than nitrocefin tests independent of using nitrocefin discs (87.5% sensitivity) or solution (89.8% sensitivity), and that the significant inter-person variations of the zone edge test are probably related to the training level of the individual investigators (individual sensitivity ranging from 68.2% to 96.6%, specificity ranging from 89.8% to 100%). Conclusions: In addition to continued and strict training of investigators, we propose mandatory checking of benzylpenicillin zone edges, particularly in an investigation zone from 26 to 30 mm, which can result in improved specificity/positive predictive value of the zone edge test (from 98.4% to 100%) but retains the high sensitivity/negative predictive value of the method.

Burkholderia pseudomallei misidentified by automated system.

After returning from Thailand, a 35-year-old man from Switzerland was hospitalized with an abscess of the head. Material cultured from the abscess and adjacent bone grew a gram-negative rod, which was misidentified by an automated microbiology system as Burkholderia cepacia. The organism was eventually identified by molecular methods as B. pseudomallei.