A Robust Machine Learning Model for Diabetic Retinopathy Classification

Ensemble learning is a process that belongs to the artificial intelligence (AI) field. It helps to choose a robust machine learning (ML) model, usually used for data classification. AI has a large connection with image processing and feature classification, and it can also be successfully applied to analyzing fundus eye images. Diabetic retinopathy (DR) is a disease that can cause vision loss and blindness, which, from an imaging point of view, can be shown when screening the eyes. Image processing tools can analyze and extract the features from fundus eye images, and these corroborate with ML classifiers that can perform their classification among different disease classes. The outcomes integrated into automated diagnostic systems can be a real success for physicians and patients. In this study, in the form image processing area, the manipulation of the contrast with the gamma correction parameter was applied because DR affects the blood vessels, and the structure of the eyes becomes disorderly. Therefore, the analysis of the texture with two types of entropies was necessary. Shannon and fuzzy entropies and contrast manipulation led to ten original features used in the classification process. The machine learning library PyCaret performs complex tasks, and the empirical process shows that of the fifteen classifiers, the gradient boosting classifier (GBC) provides the best results. Indeed, the proposed model can classify the DR degrees as normal or severe, achieving an accuracy of 0.929, an F1 score of 0.902, and an area under the curve (AUC) of 0.941. The validation of the selected model with a bootstrap statistical technique was performed. The novelty of the study consists of the extraction of features from preprocessed fundus eye images, their classification, and the manipulation of the contrast in a controlled way.

Correlation of XMAP and ELISA cytokine profiles; development and validation for immunotoxicological studies in vitro

There is an emerging trend in immunotoxicological studies to use the multiplex technologies for testing the safety and the efficacy of new pharmaceuticals by using cytokines profiling as biomarker. The Luminex 200 xMAP (multi-analyte profiling) technology provides simultaneous measurement of multiple cytokines in small sample volumes, expressing rapidly the differences between various test compounds. The aim is to develop and validate the Luminex 200 multiplex immunoassays by correlation with ELISA (enzyme-linked immunosorbent assays) for implementation in evaluating cytokine profiling in immunotoxicological studies in vitro.

METHODS

Human peripheral whole blood from healthy subject diluted 1+4 with RPMI 1640 was cultured 48 hours in 28 experimental variants: control, in presence of mitogens, bioflavonoid extracts (from Crataegus monogyna and Echinacea purpurea) as cytoprotectors and with a toxic compound [Pb(NO3)2]), separately or variously combined. IL-1beta and IL-2 were comparatively performed by xMAP and ELISA immunoassays from the same sample to initialize validation of multiplex cytokine panel: IL-1beta, IL-2, IL-4, IL-6, IL-8, IL-10, TNF-alpha, IFN-gamma, usually performed by Luminex 200 system in our immunotoxicological studies. The results indicate similarly typed trends of cytokine values obtained by both methods, with comparable relative changes in presence of mitogens, bioflavonoids and toxic, respectively. Although xMAP absolute cytokine values were higher than ELISA values, the correlation between multiplexed assay and ELISA was good for IL-1beta and IL-2 with positive correlation coefficients near to 1. Conclusions. Quantitative differences between absolute values for IL-1beta and IL-2 obtained by xMAP and ELISA assays are found, but the relative values are comparable and the two methods keep similar trends in similar exposure conditions. The performance parameters of the xMAP assay and the good correlation coefficients with the "gold standard" ELISA recommend to validate the multiplex assay for analyzing cytokine profiles in immunotoxicological studies in vitro.