Multi-centre validation of a flow cytometry method to identify optimal responders to interferon-beta in multiple sclerosis

Predicting disease severity in multiple sclerosis using multimodal data and machine learning

BACKGROUND

Multiple sclerosis patients would benefit from machine learning algorithms that integrates clinical, imaging and multimodal biomarkers to define the risk of disease activity.

METHODS

We have analysed a prospective multi-centric cohort of 322 MS patients and 98 healthy controls from four MS centres, collecting disability scales at baseline and 2 years later. Imaging data included brain MRI and optical coherence tomography, and omics included genotyping, cytomics and phosphoproteomic data from peripheral blood mononuclear cells. Predictors of clinical outcomes were searched using Random Forest algorithms. Assessment of the algorithm performance was conducted in an independent prospective cohort of 271 MS patients from a single centre.

RESULTS

We found algorithms for predicting confirmed disability accumulation for the different scales, no evidence of disease activity (NEDA), onset of immunotherapy and the escalation from low- to high-efficacy therapy with intermediate to high-accuracy. This accuracy was achieved for most of the predictors using clinical data alone or in combination with imaging data. Still, in some cases, the addition of omics data slightly increased algorithm performance. Accuracies were comparable in both cohorts.

CONCLUSION

Combining clinical, imaging and omics data with machine learning helps identify MS patients at risk of disability worsening.

Multicentre Harmonisation of a Six-Colour Flow Cytometry Panel for Naïve/Memory T Cell Immunomonitoring

Background

Personalised medicine in oncology needs standardised immunological assays. Flow cytometry (FCM) methods represent an essential tool for immunomonitoring, and their harmonisation is crucial to obtain comparable data in multicentre clinical trials. The objective of this study was to design a harmonisation workflow able to address the most effective issues contributing to intra- and interoperator variabilities in a multicentre project.

Methods

The Italian National Institute of Health (Istituto Superiore di Sanità, ISS) managed a multiparametric flow cytometric panel harmonisation among thirteen operators belonging to five clinical and research centres of Lazio region (Italy). The panel was based on a backbone mixture of dried antibodies (anti-CD3, anti-CD4, anti-CD8, anti-CD45RA, and anti-CCR7) to detect naïve/memory T cells, recognised as potential prognostic/predictive immunological biomarkers in cancer immunotherapies. The coordinating centre distributed frozen peripheral blood mononuclear cells (PBMCs) and fresh whole blood (WB) samples from healthy donors, reagents, and Standard Operating Procedures (SOPs) to participants who performed experiments by their own equipment, in order to mimic a real-life scenario. Operators returned raw and locally analysed data to ISS for central analysis and statistical elaboration.

Results

Harmonised and reproducible results were obtained by sharing experimental set-up and procedures along with centralising data analysis, leading to a reduction of cross-centre variability for naïve/memory subset frequencies particularly in the whole blood setting.

Conclusion

Our experimental and analytical working process proved to be suitable for the harmonisation of FCM assays in a multicentre setting, where high-quality data are required to evaluate potential immunological markers, which may contribute to select better therapeutic options.