Evaluation of PhenoMATRIX and PhenoMATRIX PLUS for the screening of MRSA from nasal and inguinal/perineal swabs using chromogenic media.

The objective of this study was to assess the clinical performances of PhenoMATRIX and PhenoMATRIX PLUS for the screening of methicillin-resistant Staphylococcus aureus (MRSA) from nasal and inguinal/perineal ESwabs using chromogenic media. The automated performances were compared to the manual reading. Additionally, we evaluated PhenoMATRIX PLUS for the automatic release of the negative results to the Laboratory Information System (LIS) and the automatic discharge of the negative plates from the incubators. A total of 6,771 non-duplicate specimens were used by PhenoMATRIX as a machine learning model. The validation of these settings was performed on 17,223 non-duplicate specimens. The MRSA positivity rate was 5% (866/17,223). Validated settings were then used by PhenoMATRIX PLUS on another 1,409 non-duplicate specimens. The sensitivities of PhenoMATRIX and PhenoMATRIX PLUS were 99.8% [95% confidence interval (CI), 99.2%-99.9%] and 100% (95% CI, 92.1%-100%), respectively. The specificities of PhenoMATRIX and PhenoMATRIX PLUS were 99.1% (95% CI, 99.0%-99.2%) and 95.2% (95% CI, 93.8%-96.1%), respectively. All the 1,297 MRSA-negative specimens analyzed by PhenoMATRIX PLUS were automatically released and sent to the LIS immediately after availability of the culture image on the WASPLab (100% accuracy). All negative media plates were automatically discarded. PhenoMATRIX PLUS decreases the time spent by technologists on negative plates and ensures optimal usage of the incubators' capacity.

Potential use of artificial intelligence for vaginal swab analysis in the assessment of common genital disorders: a pilot study.

Genital disorders, such as vulvo-vaginal candidiasis (VVC), bacterial vaginosis (BV), and aerobic vaginitis (AV), are very common among fertile women and negatively impact their reproductive and relational life. Vaginal culture can help in the diagnostic workflow of these conditions. Recently, culture-based techniques have taken advantages of up-front specimen processing units, which also include a digital imaging system to record images of plates at programmable time points. In this proof-of-concept study, we assessed the characteristics of digital plate images of vaginal swabs plated by WASPLab system into different media, in order to detect microbial growth morphotypes specific for each genital disorder. A total of 104 vaginal specimens were included: 62 cases of normal lactobacilli-dominated flora, 12 of BV, 16 of VVC, and 14 of AV were analysed. Vaginal specimens were plated by WASPLab system into different chromogenic media and blood agar plates. Plate images were taken automatically by the digital imager at 38 h post-inoculation. We found that each genital condition was characterized by specific morphotypes in terms of microbial growth and colony colour, thus allowing the potential use of artificial intelligence not only to assess the presence of specific microbial genera/species but also to 'categorize' peculiar clinical conditions.

Performance of PhenoMatrix for the detection of Group B Streptococcus from recto-vaginal swabs.

We assessed the performance of PhenoMatrix digital imaging software in detection of Group B Streptococcus from recto-vaginal swabs plated on a specific chromogenic medium, using the WASP automated processor. PhenoMatrix algorithm showed a sensitivity of 100% and a specificity of 64.5%. False-positive results were mainly due to commensal viridans streptococci.

Use of artificial intelligence for tailored routine urine analyses.

OBJECTIVES: Urine is the most common material tested in clinical microbiology laboratories. Automated analysis is already performed, permitting quicker results and decreasing the laboratory technologist's (LT) workload. These automatic systems have introduced digital imaging concepts. PhenoMATRIX (PHM) is an artificial intelligence software that merges picture algorithms and user rules to provide presumptive results. This study aimed at designing a tailored workflow using PHM, performing its validation and checking its performance in routine practice. METHODS: Two data collections including 96 and 135 urine samples from nephrostomy/ureterostomy and artificial bladder (US), 948 and 1257 urine samples from catheter (UC) and 3251 and 2027 midstream urine (MSU) were used to compare LT results with those obtained using two versions of PHM. Another 19 US, 102 UC and 508 MSU were used to monitor performance level 3 months after routine implementation. RESULTS: Before and after revisions, agreement between the first version of PHM and LT results were 83% (95% confidence interval [CI], 74.3-90.2) and 83% (95% CI, 75.3-90.9) (US), 66.7% (95% CI, 63.5-69.5) and 71.7% (95% CI, 68.8-74.4) (UC) and 65.4% (95% CI, 63.8-67.1) and 76% (95% CI, 74.1-77.1) (MSU). The second version improved results, demonstrating 96.2% (95% CI, 91.6-98.8) and 97% (95% CI, 92.6-99.2) (US), 87.5% (95% CI, 85.5-89.2) and 88.9% (95% CI, 87.0-90.5) (UC) and 91% (95% CI, 89.7-92.1) and 92% (95% CI, 91.1-93.4) (MSU) of agreement with LT results before and after revisions. The reliability of PHM results was confirmed by a routine study demonstrating 92% (95% CI, 90.0-94.2) overall agreement. CONCLUSIONS: PHM showed high performance, with >90% of results in agreement with LT. PHM could help standardize and secure results, prioritize positive plates during analytical workflow and likely save LT time.