Search

Abstract Mycobacterium abscessus (MABS) displays differential subspecies susceptibility to macrolides. Thus, identifying MABS's subspecies (M. abscessus, M. bolletii and M. massiliense) is a clinical necessity for guiding treatment decisions. We aimed to assess the potential of Machine Learning (ML)‐based classifiers coupled to Matrix‐Assisted Laser Desorption/Ionization Time‐of‐Flight (MALDI‐TOF) MS to identify MABS subspecies. Two spectral databases were created by using 40 confirmed MABS strains. Spectra were obtained by using MALDI‐TOF MS from strains cultivated on solid (Columbia Blood Agar, CBA) or liquid (MGIT®) media for 1 to 13 days. Each database was divided into a dataset for ML‐based pipeline development and a dataset to assess the performance. An in‐house programme was developed to identify discriminant peaks specific to each subspecies. The peak‐based approach successfully distinguished M. massiliense from the other subspecies for strains grown on CBA. The ML approach achieved 100% accuracy for subspecies identification on CBA, falling to 77.5% on MGIT®. This study validates the usefulness of ML, in particular the Random Forest algorithm, to discriminate MABS subspecies by MALDI‐TOF MS. However, identification in MGIT®, a medium largely used in mycobacteriology laboratories, is not yet reliable and should be a development priority.

Abstract Clostridioides difficile (CD) infections are defined by toxins A (TcdA) and B (TcdB) along with the binary toxin (CDT). The emergence of the ‘hypervirulent’ (Hv) strain PR 027, along with PR 176 and 181, two decades ago, reshaped CD infection epidemiology in Europe. This study assessed MALDI‐TOF mass spectrometry (MALDI‐TOF MS) combined with machine learning (ML) and Deep Learning (DL) to identify toxigenic strains (producing TcdA, TcdB with or without CDT) and Hv strains. In total, 201 CD strains were analysed, comprising 151 toxigenic (24 ToxA+B+CDT+, 22 ToxA+B+CDT+ Hv+ and 105 ToxA+B+CDT−) and 50 non‐toxigenic (ToxA−B−) strains. The DL‐based classifier exhibited a 0.95 negative predictive value for excluding ToxA−B− strains, showcasing accuracy in identifying this strain category. Sensitivity in correctly identifying ToxA+B+CDT− strains ranged from 0.68 to 0.91. Additionally, all classifiers consistently demonstrated high specificity (>0.96) in detecting ToxA+B+CDT+ strains. The classifiers' performances for Hv strain detection were linked to high specificity (≥0.96). This study highlights MALDI‐TOF MS enhanced by ML techniques as a rapid and cost‐effective tool for identifying CD strain virulence factors. Our results brought a proof‐of‐concept concerning the ability of MALDI‐TOF MS coupled with ML techniques to detect virulence factor and potentially improve the outbreak's management.

Abstract This study aimed to evaluate the contribution of Machine Learning (ML) approach in the interpretation of intercalating dye-based quantitative PCR (IDqPCR) signals applied to the diagnosis of mucormycosis. The ML-based classification approach was applied to 734 results of IDqPCR categorized as positive (n = 74) or negative (n = 660) for mucormycosis after combining “visual reading” of the amplification and denaturation curves with clinical, radiological and microbiological criteria. Fourteen features were calculated to characterize the curves and injected in several pipelines including four ML-algorithms. An initial subset (n = 345) was used for the conception of classifiers. The classifier predictions were combined with majority voting to estimate performances of 48 meta-classifiers on an external dataset (n = 389). The visual reading returned 57 (7.7%), 568 (77.4%) and 109 (14.8%) positive, negative and doubtful results respectively. The Kappa coefficients of all the meta-classifiers were greater than 0.83 for the classification of IDqPCR results on the external dataset. Among these meta-classifiers, 6 exhibited Kappa coefficients at 1. The proposed ML-based approach allows a rigorous interpretation of IDqPCR curves, making the diagnosis of mucormycosis available for non-specialists in molecular diagnosis. A free online application was developed to classify IDqPCR from the raw data of the thermal cycler output ( http://gepamy-sat.asso.st/ ).

Mycobacterium abscessus (MABS) displays differential subspecies susceptibility to macrolides. Thus, identifying MABS's subspecies (M. abscessus, M. bolletii and M. massiliense) is a clinical necessity for guiding treatment decisions. We aimed to assess the potential of Machine Learning (ML)‐based classifiers coupled to Matrix‐Assisted Laser Desorption/Ionization Time‐of‐Flight (MALDI‐TOF) MS to identify MABS subspecies. Two spectral databases were created by using 40 confirmed MABS strains. Spectra were obtained by using MALDI‐TOF MS from strains cultivated on solid (Columbia Blood Agar, CBA) or liquid (MGIT®) media for 1 to 13 days. Each database was divided into a dataset for ML‐based pipeline development and a dataset to assess the performance. An in‐house programme was developed to identify discriminant peaks specific to each subspecies. The peak‐based approach successfully distinguished M. massiliense from the other subspecies for strains grown on CBA. The ML approach achieved 100% accuracy for subspecies identification on CBA, falling to 77.5% on MGIT®. This study validates the usefulness of ML, in particular the Random Forest algorithm, to discriminate MABS subspecies by MALDI‐TOF MS. However, identification in MGIT®, a medium largely used in mycobacteriology laboratories, is not yet reliable and should be a development priority. [ABSTRACT FROM AUTHOR]

Abstract The spread of fungal clones is hard to detect in the daily routines in clinical laboratories, and there is a need for new tools that can facilitate clone detection within a set of strains. Currently, Matrix Assisted Laser Desorption-Ionization Time-of-Flight Mass Spectrometry is extensively used to identify microbial isolates at the species level. Since most of clinical laboratories are equipped with this technology, there is a question of whether this equipment can sort a particular clone from a population of various isolates of the same species. We performed an experiment in which 19 clonal isolates of Aspergillus flavus initially collected on contaminated surgical masks were included in a set of 55 A. flavus isolates of various origins. A simple convolutional neural network (CNN) was trained to detect the isolates belonging to the clone. In this experiment, the training and testing sets were totally independent, and different MALDI-TOF devices (Microflex) were used for the training and testing phases. The CNN was used to correctly sort a large portion of the isolates, with excellent (> 93%) accuracy for two of the three devices used and with less accuracy for the third device (69%), which was older and needed to have the laser replaced.

Abstract Objectives Adult-onset Still’s disease (AOSD) is a rare systemic inflammatory disorder. Diagnosing AOSD can be challenging, as disease presentation and clinical course are highly heterogeneous. For unclear reasons, a few patients develop life-threatening complications. Our objective was to determine whether these cases resulted from therapeutic delay or could represent a peculiar AOSD subset. Methods We conducted a multicentre retrospective study of 20 AOSD patients with organ failure requiring intensive care unit admission and 41 control AOSD patients without organ failure. Clinico-biological data at hospital admission were explored using supervised analyses and unsupervised dimension reduction analysis (factor analysis of mixed data, FAMD). Results Disease duration before admission was shorter in patients with life-threatening AOSD (median, 10 vs 20 days, p = 0.007). Disease duration before AOSD therapy initiation also tended to be shorter (median, 24 vs 32 days, p = 0.068). Despite this shorter disease duration, FAMD, hierarchical clustering and univariate analyses showed that these patients exhibited distinctive characteristics at first presentation, including younger age; higher frequency of splenomegaly, liver, cardiac and/or lung involvement; less frequent arthralgia; and higher ferritin level. In multivariate analysis, 3 parameters predicted life-threatening complications: lack of arthralgia, younger age and shorter time between fever onset and hospitalisation. Conclusion This study suggests that life-threatening complications of AOSD occur very early, in a peculiar subset, which we propose to name catastrophic adult-onset Still’s disease (CAOSD). Its exact burden may be underestimated and remains to be clarified through large multicentre cohorts. Further studies are needed to identify red flags and define the optimal therapeutic strategy.

Identifying fungal clones propagated during outbreaks in hospital settings is a problem that increasingly confronts biologists. Current tools based on DNA sequencing or microsatellite analysis require specific manipulations that are difficult to implement in the context of routine diagnosis. Using deep learning to classify the mass spectra obtained during the routine identification of fungi by MALDI-TOF mass spectrometry could be of interest to differentiate isolates belonging to epidemic clones from others. As part of the management of a nosocomial outbreak due to Candida parapsilosis in two Parisian hospitals, we studied the impact of the preparation of the spectra on the performance of a deep neural network. Our purpose was to differentiate 39 otherwise fluconazole-resistant isolates belonging to a clonal subset from 56 other isolates, most of which were fluconazole-susceptible, collected during the same period and not belonging to the clonal subset. Our study carried out on spectra obtained on four different machines from isolates cultured for 24 or 48 h on three different culture media showed that each of these parameters had a significant impact on the performance of the classifier. In particular, using different culture times between learning and testing steps could lead to a collapse in the accuracy of the predictions. On the other hand, including spectra obtained after 24 and 48 h of growth during the learning step restored the good results. Finally, we showed that the deleterious effect of the device variability used for learning and testing could be largely improved by including a spectra alignment step during preprocessing before submitting them to the neural network. Taken together, these experiments show the great potential of deep learning models to identify spectra of specific clones, providing that crucial parameters are controlled during both culture and preparation steps before submitting spectra to a classifier.

Abstract Background The prevalence, prognostic role, and diagnostic value of blood pressure in immune‐mediated thrombotic thrombocytopenic purpura (iTTP) and other thrombotic microangiopathies (TMAs) remain unclear. Methods Using a national cohort of iTTP (n = 368), Shigatoxin‐induced hemolytic uremic syndrome (n = 86), atypical hemolytic uremic syndrome (n = 84), and hypertension‐related thrombotic microangiopathy (n = 25), we sought to compare the cohort’s blood pressure profile to assess its impact on prognosis and diagnostic performances. Results Patients with iTTP had lower blood pressure than patients with other TMAs, systolic (130 [interquartile range (IQR) 118–143] vs 161 [IQR 142–180] mmHg) and diastolic (76 [IQR 69–83] vs 92 [IQR 79–105] mmHg, both p

ABSTRACT Meningitis/encephalitis (ME) syndromic diagnostic assays can be applied for the rapid one-step detection of the most common pathogens in cerebrospinal fluid (CSF). However, the comprehensive performance of multiplex assays is still under evaluation. In our multisite university hospital of eastern Paris, France, ME syndromic testing has been gradually implemented since 2017 for patients with neurological symptoms presenting to an adult or pediatric emergency unit. We analyzed the results from the BioFire FilmArray ME panel versus standard routine bacteriology and virology techniques, together with CSF cytology and clinical data, over a 2.5-year period to compare the diagnostic accuracy of the FilmArray ME panel to that of the reference methods. In total, 1,744 CSF samples from 1,334 pediatric and 336 adult patients were analyzed. False-positive (mostly bacterial) and false-negative (mostly viral) cases were deciphered with the help of clinical data. The performance of the FilmArray ME panel in our study was better for bacterial detection (specificity >99%, sensitivity 100%) than viral detection (specificity >99%, sensitivity 75% for herpes simplex virus 1 [HSV-1] and 89% for enterovirus), our study being one of the largest, to date, concerning enteroviruses. The use of a threshold of 10 leukocytes/mm3 considerably increased the positive agreement between the results of the FilmArray ME panel and the clinical features, especially for bacterial pathogens, for which agreement increased from 58% to 87%, avoiding two-thirds of inappropriate testing. Based on this analysis, we propose an algorithm for the use of both syndromic and specific assays for the optimal management of suspected meningitis/encephalitis in adult and pediatric patients. IMPORTANCE Based on our comparative analysis of performances of the diagnostic assays, we propose an algorithm for the use of both syndromic and specific assays, for an optimal care of the meningitis/encephalitis threat in adult and pediatric patients.

Absolute count of circulating monocytes has been proposed as an independent prognostic factor in diffuse large B-cell lymphoma (DLBCL). However, monocyte nomenclature includes various subsets with pro-, anti-inflammatory, or suppressive functions, and their clinical relevance in DLBCL has been poorly explored. Herein, we broadly assessed circulating monocyte heterogeneity in 91 DLBCL patients. Classical- (cMO, CD14pos CD16neg) and intermediate- (iMO, CD14pos CD16pos) monocytes accumulated in DLBCL peripheral blood and exhibited an inflammatory phenotype. On the opposite, nonclassical monocytes (ncMOSlanpos, CD14low CD16pos Slanneg and ncMOSlanneg, CD14low CD16pos, Slanneg) were decreased in peripheral blood. Tumor-conditioned monocytes presented similarities with ncMO phenotype from DLBCL and were prone to migrate in response to CCL5 and CXCL12, and presented similarities with DLBCL-infiltrated myeloid cells, as defined by mass cytometry. Finally, we demonstrated the adverse value of an accumulation of nonclassical monocytes in 2 independent cohorts of DLBCL.

ABSTRACT Matrix-assisted laser desorption ionization–time of flight mass spectrometry (MALDI-TOF MS) is commonly used by clinical microbiology laboratories to identify pathogens, despite some limitations of the technique. The Enterobacter cloacae complex (ECC) taxonomy has recently been expanded, leading to uncertain identification of some species within the ECC when commercial MALDI-TOF MS is used. This technique is especially unsuited in the case of E. hormaechei, the main species responsible for infections and one of the most prone, within the ECC, to acquire antibiotic resistance. Hence, rapid and reliable identification at the species level could improve patient management. Here, we evaluated the performance of the Bruker Microflex MALDI-TOF MS instrument to identify ECC isolates using two databases and algorithms in comparison to the hsp60 gene sequencing reference method: the Bruker database included in the MALDI Biotyper software and an extensive online database coupled to an original Mass Spectrometric Identification (MSI) algorithm. Among a panel of 94 ECC isolates tested in triplicate, the online database coupled to MSI software allowed the highest rate of identification at the species level (92%) compared to the MALDI Biotyper database (25%), especially for the species E. hormaechei (97% versus 20%). We show that by creating a database of MALDI-TOF reference spectral profiles with a high number of representatives associated with the performant MSI software, we were able to substantially improve the identification of the E. cloacae complex members, with only 8% of isolates misidentified at the species level. This online database is available through a free online MSI application (https://msi.happy-dev.fr/). IMPORTANCE Creation of a database of MALDI-TOF reference spectral profiles with a high number of representatives associated with the performant MSI software enables substantial improvement in identification of E. cloacae complex members. Moreover, this online database is available through a free online MSI application (https://msi.happy-dev.fr/).

Background Immune-mediated thrombotic thrombocytopenic purpura (iTTP) is a rare life-threatening thrombotic microangiopathy requiring urgent therapeutic plasma exchange (TPE). However, the exact impact of a slight delay in TPE initiation on the subsequent patients’ outcome is still controversial. Aim We aimed to study the frequency, short-term neurological consequences, and determinants of diagnostic delay in iTTP. Methods We conducted a retrospective monocentric study including patients with a first acute episode of iTTP (2005–2020) classified into 2 groups: delayed (>24h from first hospital visit, group 1) and immediate diagnosis (≤24h, group 2). Results Among 42 evaluated patients, 38 were included. Eighteen cases (47%) had a delayed diagnosis (median: 5 days). The main misdiagnosis was immune thrombocytopenia (67%). The mortality rate was 5% (1 death in each group). Neurological events (stroke/TIA, seizure, altered mental status) occurred in 67% vs 30% patients in group 1 and 2, respectively (p = 0.04). Two patients in group 1 exhibited neurological sequelae. The hospital length of stay was longer in group 1 (p = 0.02). At the first hospital evaluation, potential alternative causes of thrombocytopenia were more prevalent in group 1 (33% vs 5%, p = 0.04). Anemia was less frequent in group 1 (67% vs 95%, p = 0.04). All patients had undetectable haptoglobin levels. By contrast, 26% of schistocytes counts were Conclusion Diagnostic delay is highly prevalent in iTTP, with a significant impact on short-term neurological outcome. In patients with profound thrombocytopenia, the thorough search for signs of incipient organ dysfunction, systematic hemolysis workup, and proper interpretation of schistocytes count are the key elements of early diagnosis of TTP.

Next-generation sequencing (NGS) is used to investigate the presence of somatic mutations. The utility of incorporating routine sequencing to guide diagnosis and therapeutic decisions remains unclear. We report the findings of an observational, multicenter study that aimed to assess the impact of somatic mutation testing by NGS in a reallife setting of chronic myeloid malignancies. A total of 177 patients were enrolled, partitioned into two overlapping groups. In group A (n=94), the indication was to search for clonal hematopoiesis, in a context of suspected myelodysplastic syndrome or myeloproliferative neoplasia. In group B (n=95), the theranostic impact of somatic mutations was studied. A panel of 34 genes was used on DNA extracted from blood or bone marrow samples. Within group A, the detection of clonal hematopoiesis supported the diagnosis of chronic myeloid malignancies for 31 patients while the absence of clonal hematopoiesis ruled out the suspected diagnosis in 47 patients. Within group B, NGS identified prognostically relevant somatic mutations in 32 patients, which had a therapeutic impact in 18 cases. By determining the presence or absence of somatic mutations, the application of NGS in daily practice was found to be useful for an integrated final diagnosis in 83% of the patients. Moreover, the search for somatic mutations had a prognostic impact that led to treatment modification in 19% of the cases. This study outlines the fact that adequate implementation of new investigations may have a significant positive medico-economic impact by enabling appropriate management of patients.

Abstract Background Adult-onset Still disease (AOSD) is a rare systemic inflammatory disorder. A few patients develop organ complications that can be life-threatening. Our objectives were to describe the disease course and phenotype of life-threatening AOSD, including response to therapy and long-term outcome. Methods A multicenter case series of intensive care medicine (ICU) patients with life-threatening AOSD and a systematic literature review. Results Twenty patients were included. ICU admission mostly occurred at disease onset (90%). Disease manifestations included fever (100%), sore throat (65%), skin rash (65%), and arthromyalgia (55%). Serum ferritin was markedly high (median: 29,110 ng/mL). Acute respiratory failure, shock and multiple organ failure occurred in 15 (75%), 10 (50%), and 7 (35%) cases, respectively. Hemophagocytosis was demonstrated in eight cases. Two patients died. Treatment delay was significant. All patients received corticosteroids. Response rate was 50%. As second-line, intravenous immunoglobulins were ineffective. Anakinra was highly effective. After ICU discharge, most patients required additional treatment. Literature analysis included 79 cases of AOSD with organ manifestations, which mainly included reactive hemophagocytic syndrome (42%), acute respiratory failure (34%), and cardiac complications (23%). Response rate to corticosteroids was 68%. Response rates to IVIgs, cyclosporin, and anakinra were 50%, 80%, and 100%, respectively. Conclusions AOSD should be recognized as a rare cause of sepsis mimic in patients with fever of unknown origin admitted to the ICU. The diagnosis relies on a few simple clinical clues. Early intensive treatment may be discussed. IVIgs should be abandoned. Long-term prognosis is favorable.