Deep Neural Network Regression to Assist Non-Invasive Diagnosis of Portal Hypertension.

Portal hypertension is a complex medical condition characterized by elevated blood pressure in the portal venous system. The conventional diagnosis of such disease often involves invasive procedures such as liver biopsy, endoscopy, or imaging techniques with contrast agents, which can be uncomfortable for patients and carry inherent risks. This study presents a deep neural network method in support of the non-invasive diagnosis of portal hypertension in patients with chronic liver diseases. The proposed method utilizes readily available clinical data, thus eliminating the need for invasive procedures. A dataset composed of standard laboratory parameters is used to train and validate the deep neural network regressor. The experimental results exhibit reasonable performance in distinguishing patients with portal hypertension from healthy individuals. Such performances may be improved by using larger datasets of high quality. These findings suggest that deep neural networks can serve as useful auxiliary diagnostic tools, aiding healthcare professionals in making timely and accurate decisions for patients suspected of having portal hypertension.

CADUCEO: A Platform to Support Federated Healthcare Facilities through Artificial Intelligence.

Data-driven algorithms have proven to be effective for a variety of medical tasks, including disease categorization and prediction, personalized medicine design, and imaging diagnostics. Although their performance is frequently on par with that of clinicians, their widespread use is constrained by a number of obstacles, including the requirement for high-quality data that are typical of the population, the difficulty of explaining how they operate, and ethical and regulatory concerns. The use of data augmentation and synthetic data generation methodologies, such as federated learning and explainable artificial intelligence ones, could provide a viable solution to the current issues, facilitating the widespread application of artificial intelligence algorithms in the clinical application domain and reducing the time needed for prevention, diagnosis, and prognosis by up to 70%. To this end, a novel AI-based functional framework is conceived and presented in this paper.

Frequency and characterization of cognitive impairments in patients diagnosed with paediatric central nervous system tumours: a systematic review.

Background: This systematic review has been conducted with the aim of characterizing cognitive deficits and analyzing their frequency in survivors of paediatric Central Nervous System tumours. Materials and methods: All literature published up to January 2023 was retrieved searching the databases "PubMed", "Cochrane", "APA PsycInfo" and "CINAHL". The following set of pre-defined inclusion criteria were then individually applied to the selected articles in their full-text version: i) Retrospective/prospective longitudinal observational studies including only patients diagnosed with primary cerebral tumours at ≤ 21 years (range 0-21); ii) Studies including patients evaluated for neuro-cognitive and neuro-psychological deficits from their diagnosis and/or from anti-tumoral therapies; iii) Studies reporting standardized tests evaluating patients' neuro-cognitive and neuro-psychological performances; iv) Patients with follow-ups ≥ 2 years from the end of their anti-tumoral therapies; v) Studies reporting frequencies of cognitive deficits. Results: 39 studies were included in the analysis. Of these, 35 assessed intellectual functioning, 30 examined memory domains, 24 assessed executive functions, 22 assessed attention, 16 examined visuo-spatial skills, and 15 explored language. A total of 34 studies assessed more than one cognitive function, only 5 studies limited their analysis on a single cognitive domain. Attention impairments were the most recurrent in this population, with a mean frequency of 52.3% after a median period post-treatment of 11.5 years. The other cognitive functions investigated in the studies showed a similar frequency of impairments, with executive functions, language, visuospatial skills and memory deficits occurring in about 40% of survivors after a similar post-treatment period. Longitudinal studies included in the systematic review showed a frequent decline over time of intellectual functioning. Conclusions: Survivors of paediatric Central Nervous System tumours experience cognitive sequelae characterized by significant impairments in the attention domain (52.3%), but also in the other cognitive functions. Future studies in this research field need to implement more cognitive interventions and effective, but less neurotoxic, tumour therapies to preserve or improve neurocognitive functioning and quality of life of this population.

An Integrated Music and Artificial Intelligence System in Support of Pediatric Neurorehabilitation.

This study aims at the implementation of an Artificial Intelligence approach to the use of music for supporting the neurorehabilitation of children with brain injuries or neurological difficulties.The output of this study will be the implementation of an app for mobile devices with games to be played by pediatric patients, allowing time for their cognitive and motor abilities to recover while enjoying pleasant activities. In particular, a Neural Network Classification approach is proposed in order to automatically adapt the game difficulty to the current cognitive capabilities of the child.

Computer-Based Cognitive Training in Children with Primary Brain Tumours: A Systematic Review.

Background: Late neurocognitive sequelae are common among long-term brain tumour survivors, resulting in significantly worse quality of life. Cognitive rehabilitation through specific APP/software for PC/tablets represents an innovative intervention spreading in recent years. In this study, we aim to review the current evidence and trends regarding these innovative approaches. Methods: A systematic literature review was performed. Inclusion criteria were: (i) Studies recruiting patients diagnosed with any brain tumour before 21 years of age; (ii) studies assessing the role of digital interventions on cognitive outcomes. Case reports, case series, reviews, letters, conference proceedings, abstracts, and editorials were excluded. Results: Overall, nine studies were included; 152 patients (67.8% males) with brain tumours underwent a digital intervention. The mean age at diagnosis and the intervention enrolment ranged from 4.9 to 9.4 years and 11.1 to 13.3 years, respectively. The computer-based software interventions employed were: Cogmed, Captain's Log, Fast ForWord, and Nintendo Wii. Most of these studies assessed the effects of cognitive training on working memory, attention, and performance in daily living activities. Conclusions: The studies suggest that this type of intervention improves cognitive functions, such as working memory, attention, and processing speed. However, some studies revealed only transient positive effects with a significant number of dropouts during follow-up. Trials with greater sample sizes are warranted. Motivating families and children to complete cognitive interventions could significantly improve cognitive outcomes and quality of life.