Artificial intelligence to empower diagnosis of myelodysplastic syndromes by multiparametric flow cytometry

The diagnosis of myelodysplastic syndromes (MDS) might be challenging and relies on the convergence of cytological, cytogenetic, and molecular factors. Multiparametric flow cytometry (MFC) helps diagnose MDS, especially when other features do not contribute to the decision-making process, but its usefulness remains underestimated, mostly due to a lack of standardization of cytometers. We present here an innovative model integrating artificial intelligence (AI) with MFC to improve the diagnosis and the classification of MDS. We develop a machine learning model through an elasticnet algorithm directed on a cohort of 191 patients, only based on flow cytometry parameters selected by the Boruta algorithm, to build a simple but reliable prediction score with five parameters. Our AI-assisted MDS prediction score greatly improves the sensitivity of the Ogata score while keeping an excellent specificity validated on an external cohort of 89 patients with an Area Under the Curve of 0.935. This model allows the diagnosis of both high- and low-risk MDS with 91.8% sensitivity and 92.5% specificity. Interestingly, it highlights a progressive evolution of the score from clonal hematopoiesis of indeterminate potential (CHIP) to highrisk MDS, suggesting a linear evolution between these different stages. By significantly decreasing the overall misclassification of 52% for patients with MDS and of 31.3% for those without MDS (P=0.02), our AI-assisted prediction score outperforms the Ogata score and positions itself as a reliable tool to help diagnose MDS.

Impact of COVID-19 pandemic on blood culture practices and bacteremia epidemiology

The COVID-19 pandemic has strongly impacted healthcare settings. We assess changes in blood culture practices and results during the COVID-19 era. All blood culture vials processed between January 1, 2017, and December 31, 2020, by 3 clinical laboratories were included. A baseline period from January 1, 2017 to December 31, 2019, was compared to the year 2020. COVID-19 "waves" were defined as follows: "wave 1" from March 16 to May 10, 2020, and "wave 2" from October 29 to December 14, 2020. A mean of 143.5 and 158.6 vials per day were processed in 2019 and 2020 respectively. Up to 300 and 220 vials per day were processed during waves 1 and 2. Among positive vials, a higher rate of contaminant was noticed during wave 1 (55.9% vs 45.0%; P < 0.0001) and interwave (46.0% vs 38.6%; P < 0.0001) in comparison to previous years. The prevalence of contaminants returned to the baseline level during wave 2. Streptococcus pneumonia prevalence fell in 2020 in comparison to the baseline (0.4% vs 1.4%; P < 0.0001). The COVID-19 pandemic was associated with an increase in the number of blood culture vials processed, the rate of contaminants, and a fall in the number of pneumococcal bloodstream infections.

Accurate classification of plasma cell dyscrasias is achieved by combining artificial intelligence and flow cytometry

Monoclonal gammopathy of unknown significance (MGUS), smouldering multiple myeloma (SMM), and multiple myeloma (MM) are very common neoplasms. However, it is often difficult to distinguish between these entities. In the present study, we aimed to classify the most powerful markers that could improve diagnosis by multiparametric flow cytometry (MFC). The present study included 348 patients based on two independent cohorts. We first assessed how representative the data were in the discovery cohort (123 MM, 97 MGUS) and then analysed their respective plasma cell (PC) phenotype in order to obtain a set of correlations with a hypersphere visualisation. Cluster of differentiation (CD)27 and CD38 were differentially expressed in MGUS and MM (P < 0·001). We found by a gradient boosting machine method that the percentage of abnormal PCs and the ratio PC/CD117 positive precursors were the most influential parameters at diagnosis to distinguish MGUS and MM. Finally, we designed a decisional algorithm allowing a predictive classification ≥95% when PC dyscrasias were suspected, without any misclassification between MGUS and SMM. We validated this algorithm in an independent cohort of PC dyscrasias (n = 87 MM, n = 41 MGUS). This artificial intelligence model is freely available online as a diagnostic tool application website for all MFC centers worldwide (https://aihematology.shinyapps.io/PCdyscrasiasToolDg/).

Flow cytometry crossmatching to investigate kidney-biopsy-proven, antibody-mediated rejection in patients who develop de novo donor-specific antibodies

INTRODUCTION

The appearance of de novo donor-specific anti-human leukocyte antigen antibodies (dnDSAs) after kidney transplantation is independently associated with poor long-term allograft outcomes. The objective of the present study was to evaluate the predictive value of a flow cytometry crossmatching (FC-XM) assay after the appearance of dnDSAs related to antibody-mediated allograft rejection (ABMR) after kidney transplantation.

MATERIALS AND METHODS

A total of 89 recipients with dnDSAs after transplantation were included. The crossmatching results were compared with the dnDSA profile (the mean fluorescence intensity (MFI), the complement-binding activity, and the IgG subclass profile) and the biopsy's morphological features.

RESULTS

Of the 89 patients, 59 (66%) were positive in an FC-XM assay, 17 (19%) had complement-binding DSAs, 55 (62%) were positive for IgG1 and/or IgG3 in a solid phase assay, and 45 (51%) had morphological biopsy features linked to ABMR.

CONCLUSION

An FC-XM assay was unable to discriminate between cases with or without ABMR on biopsy findings; it had a low positive predictive value (<70%) and a low negative positive predictive value (<42.9%), taking into account the sensitivity of our assay (limit of detection: DSAs with an MFI >3000). In this context, the height of the MFI of the dnDSAs might be enough for a high positive predictive value for ABMR and additional testing for complement binding activity can remain optional.