Human-relevant three-dimensional (3D) models of cerebral tissue can be invaluable tools to boost our understanding of the cellular mechanisms underlying brain pathophysiology. Nowadays, the accessibility, isolation and harvesting of human neural cells represents a bottleneck for obtaining reproducible and accurate models and gaining insights in the fields of oncology, neurodegenerative diseases and toxicology. In this scenario, given their low cost, ease of culture and reproducibility, neural cell lines constitute a key tool for developing usable and reliable models of the human brain. Here, we review the most recent advances in 3D constructs laden with neural cell lines, highlighting their advantages and limitations and their possible future applications.
This article aims to provide a thorough overview of the use of Artificial Intelligence (AI) techniques in studying the gut microbiota and its role in the diagnosis and treatment of some important diseases. The association between microbiota and diseases, together with its clinical relevance, is still difficult to interpret. The advances in AI techniques, such as Machine Learning (ML) and Deep Learning (DL), can help clinicians in processing and interpreting these massive data sets. Two research groups have been involved in this Scoping Review, working in two different areas of Europe: Florence and Sarajevo. The papers included in the review describe the use of ML or DL methods applied to the study of human gut microbiota. In total, 1109 papers were considered in this study. After elimination, a final set of 16 articles was considered in the scoping review. Different AI techniques were applied in the reviewed papers. Some papers applied ML, while others applied DL techniques. 11 papers evaluated just different ML algorithms (ranging from one to eight algorithms applied to one dataset). The remaining five papers examined both ML and DL algorithms. The most applied ML algorithm was Random Forest and it also exhibited the best performances.
The application of machine learning (ML) techniques could facilitate the identification of predictive biomarkers of somatostatin analog (SSA) efficacy in patients with neuroendocrine tumors (NETs). We collected data from 74 patients with a pancreatic or gastrointestinal NET who received SSA as first-line therapy. We developed three classification models to predict whether the patient would experience a progressive disease (PD) after 12 or 18 months based on clinic-pathological factors at the baseline. The dataset included 70 samples and 15 features. We initially developed three classification models with accuracy ranging from 55% to 70%. We then compared ten different ML algorithms. In all but one case, the performance of the Multinomial Naïve Bayes algorithm (80%) was the highest. The support vector machine classifier (SVC) had a higher performance for the recall metric of the progression-free outcome (97% vs. 94%). Overall, for the first time, we documented that the factors that mainly influenced progression-free survival (PFS) included age, the number of metastatic sites and the primary site. In addition, the following factors were also isolated as important: adverse events G3–G4, sex, Ki67, metastatic site (liver), functioning NET, the primary site and the stage. In patients with advanced NETs, ML provides a predictive model that could potentially be used to differentiate prognostic groups and to identify patients for whom SSA therapy as a single agent may not be sufficient to achieve a long-lasting PFS.
Understanding how neuronal circuits generate complex activity patterns and perform computations remains a significant challenge in neuroscience. In vitro neuronal models provide controlled environments to investigate brain microcircuits, their responses to stimuli, and dysfunctions in pathological conditions. While invaluable for direct observation and manipulation, these experiments are also resource-intensive and raise ethical concerns, particularly when involving human-derived neurons. In silico models offer a cost-effective, scalable complementary alternative. They integrate multi-scale data, enabling high-throughput investigations and the exploration of mechanisms that may be beyond the reach of experimental methods. These computational approaches support hypothesis generation, data interpretation, and theoretical insight. When combined with in vitro studies, they create a synergistic framework that advances our understanding of neuronal function and dysfunction in ways neither method could achieve alone. This review examines computational models developed since 2000 to support in vitro neuronal investigations, with a focus on their contributions to understanding network dynamics. This includes topics such as neuronal activity, stem-cell-derived neurons, network topology, and metabolism. We highlight key applications, from predicting mechanisms of neuropathy to exploring network learning and memory. We offer an overview of a corner problem for the development of computational models, that is parameter estimation, and discuss implementation strategies emphasizing accessibility through public repositories. By synthesizing these developments, this review aims to inspire new approaches in computational neuroscience, advancing the study of brain function and dysfunction.