Fractal dimension (FD) calculated on oral radiographs has been proposed as a useful tool to screen for osteoporosis. This systematic review and meta-analysis firstly aimed at assessing the reliability of FD measures in distinguishing osteoporotic patients (OP) from healthy controls (HC), and secondly, to identify a standardized procedure of FD calculation in dental radiographs for the possible use as a surrogate measure of osteoporosis. A comprehensive search was conducted up to September 2020 using PubMed, Web of Science, and SCOPUS databases. The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) statement was followed. Meta-analysis was performed on FD values calculated for HC and OP. Overall, 293 articles were identified. After a three steps screening, 19 studies were included in the qualitative appraisal and 12 were considered for meta-analysis. The methodological quality of the retrieved studies was generally low. Most of the studies included used White and Rudolph and box counting to process the images and to calculate FD, respectively. Overall, 51% of the studies found a meaningful difference between HC and OP groups. Meta-analyses showed that to date, FD measures on dental radiographs are not able to distinguish the OP from HC group significantly. From the current evidence, the use of FD for the identification of OP is not reliable, and no clear conclusion can be drawn due to the heterogeneity of studies. The present review revealed the need for further studies and provided the fundamentals to design them in order to find a standardized procedure for FD calculation (regions for FD assessment; images processing technique; methods for FD measurement). More effort should be made to identify osteoporosis using dental images which are cheap and routinely taken during periodic dental examinations.

In Mild Cognitive Impairment (MCI), identifying a high risk of conversion to Alzheimer's Disease Dementia (AD) is a primary goal for patient management. Machine Learning (ML) algorithms are widely employed to pursue data-driven diagnostic and prognostic goals. An agreement on the stability of these algorithms -when applied to different biomarkers and other conditions- is far from being reached. In this study, we compared the different prognostic performances of three supervised ML algorithms fed with multimodal biomarkers of MCI subjects obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Random Forest, Gradient Boosting, and eXtreme Gradient Boosting algorithms predict MCI conversion to AD. They can also be simultaneously employed -with the voting procedure- to improve predictivity. AD prediction accuracy is influenced by the nature of the data (i.e., neuropsychological test scores, cerebrospinal fluid AD-related proteins and APOE ε4, cerebral structural MRI (sMRI) data). In our study, independent of the applied ML algorithms, sMRI data showed the lowest accuracy (0.79) compared to other classes. Multimodal data were helpful in the algorithms' performances by combining clinical and biological measures. Accordingly, using the three ML algorithms, the highest accuracy (0.90) was reached by employing neuropsychological and AD-related biomarkers. Finally, the feature selection procedure indicated that the most critical variables in the respective classes were the ADAS-Cog-13 scale, the medial temporal lobe and hippocampus atrophy, and the ratio between phosphorylated Tau and Aβ42 proteins. In conclusion, our data support the notion that using multiple ML algorithms and multimodal biomarkers helps make more accurate and solid predictions.

Autoscopic phenomena are psychic illusory visual experiences consisting of the perception of the image of one's own body or face within space, either from an internal point of view, as in a mirror or from an external point of view. Descriptions based on phenomenological criteria distinguish six types of autoscopic experiences: autoscopic hallucination, he-autoscopy or heautoscopic proper, feeling of a presence, out of body experience, negative and inner forms of autoscopy. We report a case of a patient with he-autoscopic seizures. EEG recordings during the autoscopic experience showed a right parietal epileptic focus. This finding confirms the involvement of the temporo-parietal junction in the abnormal body perception during autoscopic phenomena. We discuss and review previous literature on the topic, as different localization of cortical areas are reported suggesting that out of body experience is generated in the right hemisphere while he-autoscopy involves left hemisphere structures.