Robot-assisted therapy in patients with neurological disease is an attempt to improve function in a moderate to severe hemiparetic arm. A better understanding of cortical modifications after robot-assisted training could aid in refining rehabilitation therapy protocols for stroke patients. Modifications of cortical activity in healthy subjects were evaluated during voluntary active movement, passive robot-assisted motor movement, and motor imagery tasks performed under unimanual and bimanual protocols.

The major challenge in pre-surgical epileptic patient evaluation is the correct identification of the seizure onset area, especially in MR-negative patients. In this study, we aimed to: (1) assess the concordance between perfusion, from ASL, and metabolism, from (18)F-FDG, acquired simultaneously on PET/MR; (2) verify the utility of a statistical approach as supportive diagnostic tool for clinical readers. Secondarily, we compared (18)F-FDG PET data from the hybrid PET/MR system with those acquired with PET/CT, with the purpose of validate the reliability of (18)F-FDG PET/MR data. Twenty patients with refractory focal epilepsy, negative MR and a defined electro-clinical diagnosis underwent PET/MR, immediately followed by PET/CT. Standardized uptake value ratio (SUVr) and cerebral blood flow (CBF) maps were calculated for PET/CT-PET/MR and ASL, respectively. For all techniques, z-score of the asymmetry index (zAI) was applied for depicting significant Right/Left differences. SUVr and CBF images were firstly visually assessed by two neuroimaging readers, who then re-assessed them considering zAI for reaching a final diagnosis. High agreement between (18)F-FDG PET/MR and ASL was found, showing hypometabolism and hypoperfusion in the same hemisphere in 18/20 patients, while the remaining were normal. They were completely concordant in 14/18, concordant in at least one lobe in the remaining. zAI maps improved readers' confidence in 12/20 and 15/20 patients for (18)F-FDG PET/MR and ASL, respectively. (18)F-FDG PET/CT-PET/MR showed high agreement, especially when zAI was considered. The simultaneous metabolism-perfusion acquisition provides excellent concordance on focus lateralisation and good concordance on localisation, determining useful complementary information.

Explainable artificial intelligence (XAI) elucidates the decision-making process of complex AI models and is important in building trust in model predictions. XAI explanations themselves require evaluation as to accuracy and reasonableness and in the context of use of the underlying AI model. This review details the evaluation of XAI in cardiac AI applications and has found that, of the studies examined, 37% evaluated XAI quality using literature results, 11% used clinicians as domain-experts, 11% used proxies or statistical analysis, with the remaining 43% not assessing the XAI used at all. We aim to inspire additional studies within healthcare, urging researchers not only to apply XAI methods but to systematically assess the resulting explanations, as a step towards developing trustworthy and safe models.

While stroke is one of the leading causes of disability, the prediction of upper limb (UL) functional recovery following rehabilitation is still unsatisfactory, hampered by the clinical complexity of post-stroke impairment. Predictive models leading to accurate estimates while revealing which features contribute most to the predictions are the key to unveil the mechanisms subserving the post-intervention recovery, prompting a new focus on individualized treatments and precision medicine in stroke. Machine learning (ML) and explainable artificial intelligence (XAI) are emerging as the enabling technology in different fields, being promising tools also in clinics. In this study, we had the twofold goal of evaluating whether ML can allow to derive accurate predictions of UL recovery in sub-acute patients, and disentangling the contribution of the variables shaping the outcomes. To do so, Random Forest equipped with four XAI methods was applied to interpret the results and assess the feature relevance and their consensus. Our results revealed increased performance when using ML compared to conventional statistical approaches. Moreover, the features deemed as the most relevant were concordant across the XAI methods, suggesting a good stability of the results. In particular, the baseline motor impairment as measured by simple clinical scales had the largest impact, as expected. Our findings highlight the core role of ML not only for accurately predicting the individual follow-up outcome scores after rehabilitation, but also for making ML results interpretable when associated to XAI methods. This provides clinicians with robust predictions and reliable explanations that are key factors in therapeutic planning/monitoring of stroke patients.

Advanced aging, vascular dysfunction, and nitric oxide (NO) bioavailability are recognized risk factors for Alzheimer's disease (AD). However, the contribution of AD, per se, to this putative pathophysiological mechanism is still unclear. To better answer this point, we quantified cortical perfusion with arterial spin labeling (PVC-CBF), measured ultrasound internal carotid (ICA), and femoral (FA) artery blood flow in a group of patients with similar age (~78 years) but different cognitive impairment (i.e., mild cognitive impairment MCI, mild AD-AD1, moderate AD-AD2, and severe AD-AD3) and compared them to young and healthy old (aged-matched) controls. NO-metabolites and passive leg-movement (PLM) induced hyperemia were used to assess systemic vascular function. Ninety-eight individuals were recruited for this study. PVC-CBF, ICA, and FA blood flow were markedly (range of 9–17%) and significantly (all p < 0.05) reduced across the spectrum from YG to OLD, MCI, AD1, AD2, AD3 subjects. Similarly, plasma level of nitrates and the values of PLM were significantly reduced (range of 8–26%; p < 0.05) among the six groups. Significant correlations were retrieved between plasma nitrates, PLM and PVC-CBF, CA, and FA blood flow. This integrative and comprehensive approach to vascular changes in aging and AD showed progressive changes in NO bioavailability and cortical, extracranial, and peripheral circulation in patients with AD and suggested that they are directly associated with AD and not to aging. Moreover, these results suggest that AD-related impairments of circulation are progressive and not confined to the brain. The link between cardiovascular and the central nervous systems degenerative processes in patients at different severity of AD is likely related to the depletion of NO.