This study explores the innovative application of a nearable solution (i.e., mattress) based on fiber Bragg grating (FBG) technology for continuously monitoring of critical sleep-related biomarkers. Based on biocompatible silicone compounds, the mattress embeds thirteen strategically positioned FBG sensors to detect bed occupancy, sleeping posture, respiratory rate (RR), and heart rate (HR). Our experimental protocol involves ten participants who underwent simulated sleeping conditions to evaluate the mattress's performance across different postures and respiratory patterns. Employing traditional machine learning algorithms, including decision tree, support vector machine (SVM), and Naïve-Bayes classifiers, the mattress achieves 100% accuracy in bed occupancy detection. It also effectively distinguishes between axial and lateral sleeping positions, with SVM achieving the highest accuracy of 78.4% for axial versus lateral differentiation and convolutional neural networks achieving 75.9% in distinguishing left from right positions. Additionally, for most participants, the system successfully estimates RR and HR with mean absolute errors of less than 0.7 breaths per minute and 4 bpm, respectively, across various breathing patterns in terms of frequencies and amplitudes employing different algorithms (frequency and time-domain approaches). The promising findings highlight the potential of the proposed system for a comprehensive evaluation of sleep-related breathing disorders in clinical and home settings.

Recent advancements in Natural Language Processing (NLP) have substantially enhanced language understanding. However, non-English languages, especially in specialized and low-resource domains like biomedicine, remain largely underrepresented. Bridging this gap is essential for promoting inclusivity and expanding the global applicability of NLP technologies. This study presents a cross-lingual knowledge distillation framework that utilizes sentence transformers to improve domain-specific NLP capabilities in non-English languages. Specifically, the framework focuses on biomedical text classification tasks. By aligning sentence embeddings between a teacher model trained on English biomedical corpora and a multilingual student model, the proposed method effectively transfers both domain-specific and task-specific knowledge. This alignment allows the student model to efficiently process and adapt to biomedical texts in Spanish, French, and German, particularly in low-resource settings with limited tuning data. Extensive experiments with domain-adapted models like BioBERT and multilingual BERT with machine-translated text pairs demonstrate substantial performance improvements in downstream biomedical NLP tasks. The proposed framework proves highly effective in scenarios characterized by limited training data availability. The results highlight the scalability and effectiveness of this approach, facilitating the development of robust multilingual models tailored to the biomedical domain, thus advancing global accessibility and impact in biomedical NLP applications.

In this study, we delve into the adaptation and effectiveness of Transformer-based, pre-trained Large Language Models (LLMs) within the biomedical domain, a field that poses unique challenges due to its complexity and the specialized nature of its data. Building on the foundation laid by the transformative architecture of Transformers, we investigate the nuanced dynamics of LLMs through a multifaceted lens, focusing on two domain-specific tasks, i.e., Natural Language Inference (NLI) and Named Entity Recognition (NER). Our objective is to bridge the knowledge gap regarding how these models’ downstream performances correlate with their capacity to encapsulate task-relevant information. To achieve this goal, we probed and analyzed the inner encoding and attention mechanisms in LLMs, both encoder- and decoder-based, tailored for either general or biomedical-specific applications. This examination occurs before and after the models are fine-tuned across various data volumes. Our findings reveal that the models’ downstream effectiveness is intricately linked to specific patterns within their internal mechanisms, shedding light on the nuanced ways in which LLMs process and apply knowledge in the biomedical context. The source code for this paper is available at https://github.com/agnesebonfigli99/LLMs-in-the-Biomedical-Domain . • Comparison between encoder/decoder LLMs and their domain-adapted versions. • Assessment of the impact of different data volumes on Fine-Tuning. • Probing and analysis of LLMs’ internal representations and attention mechanisms. • Identification of key internal patterns linked to LLMs’ performances.

The rapid increase in the number and variety of smart devices connected to the Internet has increased the need to ensure resilience, reliability, and traceability when transferring data within the current Internet of Things (IoT) network. The adoption of Distributed Ledger Technologies (DLT) can provide data with the above-mentioned features, but the low scalability and high cost related to the adoption of classical DLTs, like the blockchains, results in ineffective integration with most of IoT systems. Conversely, other DLTs, DAGs (Directed Acyclic Graph), possess benefits comparable to those of blockchains without presenting most of the limitations that prevent their application in the IoT domain. Therefore we present dRAIN: a distributed Reliable Architecture for IoT Networks. The adoption of this architecture can grant the communication, management, supervision, and updating of distributed IoT devices, guaranteeing the resilience of the system and the reliability and traceability of exchanged data. In order to test the scalability potential and to assess the actual limitation of the proposed architecture, we developed both a physical and virtual (simulated) Proof of Concept. The results of our analysis show adequate execution times for the operations, guaranteeing high levels of security with acceptable performance, and prove the architecture suitable for most IoT applications that do not require to process external data in real-time.

Current management of Type 1 Diabetes mellitus (T1D) resorts to manual meal announcements from the patient to manage postprandial glycemia; nevertheless, suboptimal glycemic control is observed in real data, with the presence of many hypoglycemic and hyperglycemic events. The utilization of Continuous Glucose Monitoring (CGM) sensors and Artificial Intelligence (AI) is paving the way for improved and automated glycemic control. A step in this direction is represented by the automation of meal detection, which would not require patients to perform tasks such as carbohydrate estimation and meal announcement that are error-prone, especially for children and elderly patients.In this work, we investigate several AI models for meal detection from in silico data of 10 adults, 10 adolescents, and 10 children with T1D using only CGM data, and compare them to the standard detection method based on the glycemic threshold. We generate 30 days of data per patient that include 5 meals per day and introduce human error on carbohydrate estimation to make data more similar to the real ones. The AI models can detect more than 81% of meals from any cohort of patients while producing a relatively small amount of false positives. The feedforward neural network, the support vector machine, and the threshold method are the most promising meal detection strategies for adult, adolescent, and child populations, respectively, and may improve patients’ health and disease management.

Prostate cancer is the most common form of cancer in Western countries and there is the need to develop clinical decision support systems able to support physicians in the diagnosis of clinical relevant prostate cancer and avoid useless invasive prostate biopsies. In this respect, this paper introduces a radiomic approach that classifies the prostate cancer aggressiveness by combining Three Orthogonal Planes-Local Binary Pattern (TOP - LBP) with other texture measures. Furthermore, to combat the skewed nature of class priors, our proposal employs a data augmentation technique. The results achieved on 99 samples are up-and-coming, they favorably compare against conventional PI-RADS-based approach, and they show also the benefit given by the introduction of TOP-LBP in the radiomic signature.

The hospital is a center of healthcare services that, nowadays, can be considered as a highly technological corporation. In this work we introduce the Hospital 4.0 frame-work, discussing the innovation it would bring both at the methodological and technological level. Transforming the hospital organization from a multi-functional center where the patient is treated by different therapeutic units to an integrated center able to provide the patient with a personal care service, involving the patient as an active subject, represents the innovative challenge for the forthcoming years.

Chronic Obstructive Pulmonary Disease (COPD) is a preventable, treatable, and slowly progressive disease, whose course is aggravated by a periodic worsening of symptoms and lung function lasting for several days. The development of home telemonitoring systems has made possible to collect symptoms and physiological data in electronic records, boosting the development of decision support systems (DSSs). Current DSSs work with physiological measurements collected by means of several measuring and communication devices as well as with symptoms gathered by questionnaires submitted to COPD subjects. However, this contrasts with the advices provided by the World Health Organization and the Global initiative for chronic Obstructive Lung Disease that recommend to avoid invasive or complex daily measurements. For these reasons this manuscript presents a DSS detecting the onset of worrisome events in COPD subjects. It uses the hearth rate and the oxygen saturation, which can be collected via a pulse oximeter. The DSS consists in a binary finite state machine, whose training stage allows a subject specific personalization of the predictive model, triggering warnings, and alarms as the health status evolves over time. The experiments on data collected from 22 COPD patients tele-monitored at home for six months show that the system recognition performance is better than the one achieved by medical experts. Furthermore, the support offered by the system in the decision-making process allows to increase the agreement between the specialists, largely impacting the recognition of the worrisome events.

The development of computer-aided diagnosis (CAD) systems for antinuclear autoantibodies tests in indirect immunofluorescence using HEp-2 cells has attracted growing research efforts in the last years. Although in this field many CAD solutions extract information from objects detected within the images, cell segmentation is an issue far from being solved. This work introduces a segmentation pipeline based on an active contour method, as none in the literature on HEp-2 cell segmentation does. Our proposal can detect objects whose boundaries are not necessarily defined by gradient, and this choice plays a relevant role for HEp-2 images with different fluorescence intensities and different staining patterns. The performances of the approach is tested not only on a public benchmark dataset with 18 images, but also on other 24 images that we made publicly available. Furthermore, its performances are compared with those provided by other state-of-the-art segmentation methods.

Chronic obstructive pulmonary disease (COPD) is a slowly progressive disease characterized by airway obstruction. Patients suffering from COPD could report exacerbations, which are deteriorations in respiratory health that worsen the course of the disease. The prompt recognition of an exacerbation from daily variations and its early treatment reduces the healing time and the risk of hospitalization. Using a pulse oximeter connected to a mobile phone, we remotely collect the values of heart rate and of the oxygen saturation on a cohort of seven elderly patients affected by severe COPD. We analyze if a score given by the weighted composition of these signals permits to detect the worrisome events prefiguring an exacerbation onset. A cross validation-based evaluation allows us to assess how the results generalize to an independent data set. We found that the tested score does not provide satisfactory results in terms of sensitivity and specificity, suggesting that it is not able to disambiguate between exacerbation onset and other COPD related events.