Depression is one of the most common and disabling mental disorders that has a relevant impact on society. Semiautomatic and/or automatic health monitoring systems could be crucial and important to improve depression detection and follow-up. Sentiment Analysis refers to the use of natural language processing and text mining methodologies aiming to identify opinion or sentiment. Affective Computing is the study and development of systems and devices that can recognize, interpret, process, and simulate human affects. Sentiment Analysis and Affective Computing methodologies could provide effective tools and systems for an objective assessment and monitoring of psychological disorders and, in particular, of depression. In this paper, the application of sentiment analysis and affective computing methodologies to depression detection and monitoring are presented and discussed. Moreover, a preliminary design of an integrated multimodal system for depression monitoring, that includes sentiment analysis and affective computing techniques, is proposed. Specifically, the paper outlines the main issues and challenges relative to the design of such a system.

Through an adequate survey of the history of the disease, Narrative Medicine (NM) aims to allow the definition and implementation of an effective, appropriate, and shared treatment path. In the present study different topic modeling techniques are compared, as Latent Dirichlet Allocation (LDA) and topic modeling based on BERT transformer, to extract meaningful insights in the Italian narration of COVID-19 pandemic. In particular, the main focus was the characterization of Post-acute Sequelae of COVID-19, (i.e., PASC) writings as opposed to writings by health professionals and general reflections on COVID-19, (i.e., non-PASC) writings, modeled as a semi-supervised task. The results show that the BERTopic-based approach outperforms the LDA-base approach by grouping in the same cluster the 97.26% of analyzed documents, and reaching an overall accuracy of 91.97%.

Sentiment Analysis can help to extract knowledge related to opinions and emotions from user generated text information. It can be applied in medical field for patients monitoring purposes. With the availability of large datasets, deep learning algorithms have become a state of the art also for sentiment analysis. However, deep models have the drawback of not being non human-interpretable, raising various problems related to model's interpretability. Very few work have been proposed to build models that explain their decision making process and actions. In this work, we review the current sentiment analysis approaches and existing explainable systems. Moreover, we present a critical review of explainable sentiment analysis models and discussed the insight of applying explainable sentiment analysis in the medical field.

The management of the COVID-19 pandemic presents several unprecedented challenges in different fields, from medicine to biology, from public health to social science, that may benefit from computing methods able to integrate the increasing available COVID-19 and related data (e.g., pollution, demographics, climate, etc.). With the aim to face the COVID-19 data collection, harmonization and integration problems, we present the design and development of COVID-WAREHOUSE, a data warehouse that models, integrates and stores the COVID-19 data made available daily by the Italian Protezione Civile Department and several pollution and climate data made available by the Italian Regions. After an automatic ETL (Extraction, Transformation and Loading) step, COVID-19 cases, pollution measures and climate data, are integrated and organized using the Dimensional Fact Model, using two main dimensions: time and geographical location. COVID-WAREHOUSE supports OLAP (On-Line Analytical Processing) analysis, provides a heatmap visualizer, and allows easy extraction of selected data for further analysis. The proposed tool can be used in the context of Public Health to underline how the pandemic is spreading, with respect to time and geographical location, and to correlate the pandemic to pollution and climate data in a specific region. Moreover, public decision-makers could use the tool to discover combinations of pollution and climate conditions correlated to an increase of the pandemic, and thus, they could act in a consequent manner. Case studies based on data cubes built on data from Lombardia and Puglia regions are discussed. Our preliminary findings indicate that COVID-19 pandemic is significantly spread in regions characterized by high concentration of particulate in the air and the absence of rain and wind, as even stated in other works available in literature.

The diagnosis of psychogenic nonepileptic seizures (PNES) by means of electroencephalography (EEG) is not a trivial task during clinical practice for neurologists. No clear PNES electrophysiological biomarker has yet been found, and the only tool available for diagnosis is video EEG monitoring with recording of a typical episode and clinical history of the subject. In this paper, a data-driven machine learning (ML) pipeline for classifying EEG segments (i.e., epochs) of PNES and healthy controls (CNT) is introduced. This software pipeline consists of a semiautomatic signal processing technique and a supervised ML classifier to aid clinical discriminative diagnosis of PNES by means of an EEG time series. In our ML pipeline, statistical features like the mean, standard deviation, kurtosis, and skewness are extracted in a power spectral density (PSD) map split up in five conventional EEG rhythms (delta, theta, alpha, beta, and the whole band, i.e., 1–32 Hz). Then, the feature vector is fed into three different supervised ML algorithms, namely, the support vector machine (SVM), linear discriminant analysis (LDA), and Bayesian network (BN), to perform EEG segment classification tasks for CNT vs. PNES. The performance of the pipeline algorithm was evaluated on a dataset of 20 EEG signals (10 PNES and 10 CNT) that was recorded in eyes-closed resting condition at the Regional Epilepsy Centre, Great Metropolitan Hospital of Reggio Calabria, University of Catanzaro, Italy. The experimental results showed that PNES vs. CNT discrimination tasks performed via the ML algorithm and validated with random split (RS) achieved an average accuracy of 0.97 ± 0.013 (RS-SVM), 0.99 ± 0.02 (RS-LDA), and 0.82 ± 0.109 (RS-BN). Meanwhile, with leave-one-out (LOO) validation, an average accuracy of 0.98 ± 0.0233 (LOO-SVM), 0.98 ± 0.124 (LOO-LDA), and 0.81 ± 0.109 (LOO-BN) was achieved. Our findings showed that BN was outperformed by SVM and LDA. The promising results of the proposed software pipeline suggest that it may be a valuable tool to support existing clinical diagnosis.