No abstract

Artificial intelligence has been widely used in the field of dentistry in recent years. The present study highlights current advances and limitations in integrating artificial intelligence, machine learning, and deep learning in subfields of dentistry including periodontology, endodontics, orthodontics, restorative dentistry, and oral pathology. This article aims to provide a systematic review of current clinical applications of artificial intelligence within different fields of dentistry. The preferred reporting items for systematic reviews (PRISMA) statement was used as a formal guideline for data collection. Data was obtained from research studies for 2009–2022. The analysis included a total of 55 papers from Google Scholar, IEEE, PubMed, and Scopus databases. Results show that artificial intelligence has the potential to improve dental care, disease diagnosis and prognosis, treatment planning, and risk assessment. Finally, this study highlights the limitations of the analyzed studies and provides future directions to improve dental care.

BackgroundNeurological patients after stroke usually present cognitive deficits that cause dependencies in their daily living. These deficits mainly affect the performance of some of their daily activities. For that reason, stroke patients need long-term processes for their cognitive rehabilitation. Considering that classical techniques are focused on acting as guides and are dependent on help from therapists, significant efforts are being made to improve current methodologies and to use eHealth and Web-based architectures to implement information and communication technology (ICT) systems that achieve reliable, personalized, and home-based platforms to increase efficiency and level of attractiveness for patients and carers.ObjectiveThe goal of this work was to provide an overview of the practices implemented for the assessment of stroke patients and cognitive rehabilitation. This study puts together traditional methods and the most recent personalized platforms based on ICT technologies and Internet of Things.MethodsA literature review has been distributed to a multidisciplinary team of researchers from engineering, psychology, and sport science fields. The systematic review has been focused on published scientific research, other European projects, and the most current innovative large-scale initiatives in the area. A total of 3469 results were retrieved from Web of Science, 284 studies from Journal of Medical Internet Research, and 15 European research projects from Community Research and Development Information Service from the last 15 years were reviewed for classification and selection regarding their relevance.ResultsA total of 7 relevant studies on the screening of stroke patients have been presented with 6 additional methods for the analysis of kinematics and 9 studies on the execution of goal-oriented activities. Meanwhile, the classical methods to provide cognitive rehabilitation have been classified in the 5 main techniques implemented. Finally, the review has been finalized with the selection of 8 different ICT–based approaches found in scientific-technical studies, 9 European projects funded by the European Commission that offer eHealth architectures, and other large-scale activities such as smart houses and the initiative City4Age.ConclusionsStroke is one of the main causes that most negatively affect countries in the socioeconomic aspect. The design of new ICT-based systems should provide 4 main features for an efficient and personalized cognitive rehabilitation: support in the execution of complex daily tasks, automatic error detection, home-based performance, and accessibility. Only 33% of the European projects presented fulfilled those requirements at the same time. For this reason, current and future large-scale initiatives focused on eHealth and smart environments should try to solve this situation by providing more complete and sophisticated platforms.

This paper describes the design of a modular multi-finger haptic device for virtual object manipulation. Mechanical structures are based on one module per finger and can be scaled up to three fingers. Mechanical configurations for two and three fingers are based on the use of one and two redundant axes, respectively. As demonstrated, redundant axes significantly increase workspace and prevent link collisions, which is their main asset with respect to other multi-finger haptic devices. The location of redundant axes and link dimensions have been optimized in order to guarantee a proper workspace, manipulability, force capability, and inertia for the device. The mechanical haptic device design and a thimble adaptable to different finger sizes have also been developed for virtual object manipulation.