Diabetes is a chronic, metabolic disease characterized by high blood sugar levels. Among the main types of diabetes, type 2 is the most common. Early diagnosis and treatment can prevent or delay the onset of complications. Previous studies examined the application of machine learning techniques for prediction of the pathology, and here an artificial neural network shows very promising results as a possible valuable aid in the management and prevention of diabetes. Additionally, its superior ability for long-term predictions makes it an ideal choice for this field of study. We utilized machine learning methods to uncover previously undiscovered associations between an individual’s health status and the development of type 2 diabetes, with the goal of accurately predicting its onset or determining the individual’s risk level. Our study employed a binary classifier, trained on scratch, to identify potential nonlinear relationships between the onset of type 2 diabetes and a set of parameters obtained from patient measurements. Three datasets were utilized, i.e., the National Center for Health Statistics’ (NHANES) biennial survey, MIMIC-III and MIMIC-IV. These datasets were then combined to create a single dataset with the same number of individuals with and without type 2 diabetes. Since the dataset was balanced, the primary evaluation metric for the model was accuracy. The outcomes of this study were encouraging, with the model achieving accuracy levels of up to 86% and a ROC AUC value of 0.934. Further investigation is needed to improve the reliability of the model by considering multiple measurements from the same patient over time.

Fourier ptychographic microscopy probes label-free samples from multiple angles and achieves super resolution phase-contrast imaging according to a synthetic aperture principle. Thus, it is particularly suitable for high-resolution imaging of tissue slides over a wide field of view. Recently, in order to make the optical setup robust against misalignments-induced artefacts, numerical multi-look has been added to the conventional phase retrieval process, thus allowing the elimination of related phase errors but at the cost of a long computational time. Here we train a generative adversarial network to emulate the process of complex amplitude estimation. Once trained, the network can accurately reconstruct in real-time Fourier ptychographic images acquired using a severely misaligned setup. We benchmarked the network by reconstructing images of animal neural tissue slides. Above all, we show that important morphometric information, relevant for diagnosis on neural tissues, are retrieved using the network output. These are in very good agreement with the parameters calculated from the ground-truth, thus speeding up significantly the quantitative phase-contrast analysis of tissue samples.

The label-free single cell analysis by machine and Deep Learning, in combination with digital holography in transmission microscope configuration, is becoming a powerful framework exploited for phenotyping biological samples. Usually, quantitative phase images of cells are retrieved from the reconstructed complex diffraction patterns and used as inputs of a deep neural network. However, the phase retrieval process can be very time consuming and prone to errors. Here we address the classification of cells by using learning strategies with images coming directly from the raw recorded digital holograms, i.e. without any data processing or refocusing involved. Indeed, in the raw digital hologram the entire complex amplitude information of the sample is intrinsically embedded in the form of modulated fringes. We develop a training strategy, based on deep and feature based machine learning models, in order extract such information by skipping the classical reconstruction process for classifying different neuroblastoma cells. We provided an experimental validation by using the proposed strategy to classify two neuroblastoma cell lines.