Conventional and unconventional T-cell responses contribute to the prediction of clinical outcome and causative bacterial pathogen in sepsis patients.

Sepsis is characterized by a dysfunctional host response to infection culminating in life-threatening organ failure that requires complex patient management and rapid intervention. Timely diagnosis of the underlying cause of sepsis is crucial, and identifying those at risk of complications and death is imperative for triaging treatment and resource allocation. Here, we explored the potential of explainable machine learning models to predict mortality and causative pathogen in sepsis patients. By using a modelling pipeline employing multiple feature selection algorithms, we demonstrate the feasibility of identifying integrative patterns from clinical parameters, plasma biomarkers, and extensive phenotyping of blood immune cells. While no single variable had sufficient predictive power, models that combined five and more features showed a macro area under the curve (AUC) of 0.85 to predict 90-day mortality after sepsis diagnosis, and a macro AUC of 0.86 to discriminate between Gram-positive and Gram-negative bacterial infections. Parameters associated with the cellular immune response contributed the most to models predictive of 90-day mortality, most notably, the proportion of T cells among PBMCs, together with expression of CXCR3 by CD4+ T cells and CD25 by mucosal-associated invariant T (MAIT) cells. Frequencies of Vδ2+ γδ T cells had the most profound impact on the prediction of Gram-negative infections, alongside other T-cell-related variables and total neutrophil count. Overall, our findings highlight the added value of measuring the proportion and activation patterns of conventional and unconventional T cells in the blood of sepsis patients in combination with other immunological, biochemical, and clinical parameters.

GeoWaVe: geometric median clustering with weighted voting for ensemble clustering of cytometry data.

MOTIVATION: Clustering is an unsupervised method for identifying structure in unlabelled data. In the context of cytometry, it is typically used to categorize cells into subpopulations of similar phenotypes. However, clustering is greatly dependent on hyperparameters and the data to which it is applied as each algorithm makes different assumptions and generates a different 'view' of the dataset. As such, the choice of clustering algorithm can significantly influence results, and there is often not one preferred method but different insights to be obtained from different methods. To overcome these limitations, consensus approaches are needed that directly address the effect of competing algorithms. To the best of our knowledge, consensus clustering algorithms designed specifically for the analysis of cytometry data are lacking. RESULTS: We present a novel ensemble clustering methodology based on geometric median clustering with weighted voting (GeoWaVe). Compared to graph ensemble clustering methods that have gained popularity in single-cell RNA sequencing analysis, GeoWaVe performed favourably on different sets of high-dimensional mass and flow cytometry data. Our findings provide proof of concept for the power of consensus methods to make the analysis, visualization and interpretation of cytometry data more robust and reproducible. The wide availability of ensemble clustering methods is likely to have a profound impact on our understanding of cellular responses, clinical conditions and therapeutic and diagnostic options. AVAILABILITY AND IMPLEMENTATION: GeoWaVe is available as part of the CytoCluster package https://github.com/burtonrj/CytoCluster and published on the Python Package Index https://pypi.org/project/cytocluster. Benchmarking data described are available from https://doi.org/10.5281/zenodo.7134723. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

CytoPy: An autonomous cytometry analysis framework.

Cytometry analysis has seen a considerable expansion in recent years in the maximum number of parameters that can be acquired in a single experiment. In response to this technological advance there has been an increased effort to develop new computational methodologies for handling high-dimensional single cell data acquired by flow or mass cytometry. Despite the success of numerous algorithms and published packages to replicate and outperform traditional manual analysis, widespread adoption of these techniques has yet to be realised in the field of immunology. Here we present CytoPy, a Python framework for automated analysis of cytometry data that integrates a document-based database for a data-centric and iterative analytical environment. In addition, our algorithm-agnostic design provides a platform for open-source cytometry bioinformatics in the Python ecosystem. We demonstrate the ability of CytoPy to phenotype T cell subsets in whole blood samples even in the presence of significant batch effects due to technical and user variation. The complete analytical pipeline was then used to immunophenotype the local inflammatory infiltrate in individuals with and without acute bacterial infection. CytoPy is open-source and licensed under the MIT license. CytoPy is available at https://github.com/burtonrj/CytoPy, with notebooks accompanying this manuscript (https://github.com/burtonrj/CytoPyManuscript) and software documentation at https://cytopy.readthedocs.io/.

Zoledronate rescues immunosuppressed monocytes in sepsis patients.

Severe sepsis is often accompanied by a transient immune paralysis, which is associated with enhanced susceptibility to secondary infections and poor clinical outcomes. The functional impairment of antigen-presenting cells is considered to be a major hallmark of this septic immunosuppression, with reduced HLA-DR expression on circulating monocytes serving as predictor of mortality. Unconventional lymphocytes like γδ T-cells have the potential to restore immune defects in a variety of pathologies including cancer, but their use to rescue sepsis-induced immunosuppression has not been investigated. Our own previous work showed that Vγ9/Vδ2+ γδ T-cells are potent activators of monocytes from healthy volunteers in vitro, and in individuals with osteoporosis after first-time administration of the anti-bone resorption drug zoledronate in vivo. We show here that zoledronate readily induces upregulation of HLA-DR, CD40 and CD64 on monocytes from both healthy controls and sepsis patients, which could be abrogated by neutralising the pro-inflammatory cytokines interferon (IFN)-γ and tumour necrosis factor (TNF)-α in the cultures. In healthy controls, the upregulation of HLA-DR on monocytes was proportional to the baseline percentage of Vγ9/Vδ2 T-cells in the peripheral blood mononuclear cell population. Of note, a proportion of sepsis patients studied here did not show a demonstrable response to zoledronate, predominantly patients with microbiologically confirmed bloodstream infections, compared with sepsis patients with more localised infections marked by negative blood cultures. Taken together, our results suggest that zoledronate can, at least in some individuals, rescue immunosuppressed monocytes during acute sepsis and thus may help improve clinical outcomes during severe infection.

Using artificial intelligence to reduce diagnostic workload without compromising detection of urinary tract infections.

BACKGROUND: A substantial proportion of microbiological screening in diagnostic laboratories is due to suspected urinary tract infections (UTIs), yet approximately two thirds of urine samples typically yield negative culture results. By reducing the number of query samples to be cultured and enabling diagnostic services to concentrate on those in which there are true microbial infections, a significant improvement in efficiency of the service is possible. METHODOLOGY: Screening process for urine samples prior to culture was modelled in a single clinical microbiology laboratory covering three hospitals and community services across Bristol and Bath, UK. Retrospective analysis of all urine microscopy, culture, and sensitivity reports over one year was used to compare two methods of classification: a heuristic model using a combination of white blood cell count and bacterial count, and a machine learning approach testing three algorithms (Random Forest, Neural Network, Extreme Gradient Boosting) whilst factoring in independent variables including demographics, historical urine culture results, and clinical details provided with the specimen. RESULTS: A total of 212,554 urine reports were analysed. Initial findings demonstrated the potential for using machine learning algorithms, which outperformed the heuristic model in terms of relative workload reduction achieved at a classification sensitivity > 95%. Upon further analysis of classification sensitivity of subpopulations, we concluded that samples from pregnant patients and children (age 11 or younger) require independent evaluation. First the removal of pregnant patients and children from the classification process was investigated but this diminished the workload reduction achieved. The optimal solution was found to be three Extreme Gradient Boosting algorithms, trained independently for the classification of pregnant patients, children, and then all other patients. When combined, this system granted a relative workload reduction of 41% and a sensitivity of 95% for each of the stratified patient groups. CONCLUSION: Based on the considerable time and cost savings achieved, without compromising the diagnostic performance, the heuristic model was successfully implemented in routine clinical practice in the diagnostic laboratory at Severn Pathology, Bristol. Our work shows the potential application of supervised machine learning models in improving service efficiency at a time when demand often surpasses resources of public healthcare providers.

Examining the utility of extended laboratory panel testing in the emergency department for risk stratification of patients with COVID-19: a single-centre retrospective service evaluation.

BACKGROUND: The role of specific blood tests to predict poor prognosis in patients admitted with infection from SARS-CoV-2 remains uncertain. During the first wave of the global pandemic, an extended laboratory testing panel was integrated into the local pathway to guide triage and healthcare resource utilisation for emergency admissions. We conducted a retrospective service evaluation to determine the utility of extended tests (D-dimer, ferritin, high-sensitivity troponin I, lactate dehydrogenase and procalcitonin) compared with the core panel (full blood count, urea and electrolytes, liver function tests and C reactive protein). METHODS: Clinical outcomes for adult patients with laboratory-confirmed COVID-19 admitted between 17 March and 30 June 2020 were extracted, alongside costs estimates for individual tests. Prognostic performance was assessed using multivariable logistic regression analysis with 28-day mortality used as the primary endpoint and a composite of 28-day intensive care escalation or mortality for secondary analysis. RESULTS: From 13 500 emergency attendances, we identified 391 unique adults admitted with COVID-19. Of these, 113 died (29%) and 151 (39%) reached the composite endpoint. 'Core' test variables adjusted for age, gender and index of deprivation had a prognostic area under the curve of 0.79 (95% CI 0.67 to 0.91) for mortality and 0.70 (95% CI 0.56 to 0.84) for the composite endpoint. Addition of 'extended' test components did not improve on this. CONCLUSION: Our findings suggest use of the extended laboratory testing panel to risk stratify community-acquired COVID-19 positive patients on admission adds limited prognostic value. We suggest laboratory requesting should be targeted to patients with specific clinical indications.