Objective: Parkinson’s Disease (PD) is a progressive neurodegenerative disorder, manifesting with subtle early signs, which, often hinder timely and early diagnosis and treatment. The development of accessible, technology-based methods for longitudinal PD symptoms tracking in daily living, offers the potential for transforming disease assessment and accelerating diagnosis. Methods: A privacy-aware method for classifying patients and healthy controls (HC), on the grounds of speech impairment present in PD, is proposed. Voice features from running speech signals were extracted from passively-captured recordings over voice calls. Language-aware training of multiple- and single-instance learning classifiers was employed to fuse and predict on voice features and demographic data from a multilingual cohort of 498 subjects (392/106 self-reported HC/PD patients). Results: By means of leave-one-subject-out cross-validation, the best-performing models yielded 0.69/0.68/0.63/0.83 area under the Receiver Operating Characteristic curve (AUC) for the binary classification of PD patient vs. HC in sub-cohorts of English/Greek/German/Portuguese-speaking subjects, respectively. Out-of sample testing of the best performing models was conducted in an additional dataset, generated by 63 clinically-assessed subjects (24/39 HC/early PD patients). Testing has resulted in 0.84/0.93/0.83 AUC for the English/Greek/German-speaking sub-cohorts, respectively. Conclusions: The proposed approach outperforms other methods proposed for language-aware PD detection considering the ecological validity of the voice data. Significance: This paper introduces for the first time a high-frequency, privacy-aware and unobtrusive PD screening tool based on analysis of voice samples captured during routine phone calls.
AI-based software applications for personalized nutrition have recently gained increasing attention to help users follow a healthy lifestyle. In this paper, we present a knowledge-based recommendation framework that exploits an explicit dataset of expert-validated meals to offer highly accurate diet plans spanning across ten user groups of both healthy subjects and participants with health conditions. The proposed advisor is built on a novel architecture that includes (a) a qualitative layer for verifying ingredient appropriateness, and (b) a quantitative layer for synthesizing meal plans. The first layer is implemented as an expert system for fuzzy inference relying on an ontology of rules acquired by experts in Nutrition, while the second layer as an optimization method for generating daily meal plans based on target nutrient values and ranges. The system’s effectiveness is evaluated through extensive experiments for establishing meal and meal plan appropriateness, meal variety, as well as system capacity for recommending meal plans. Evaluations involved synthetic data, including the generation of 3000 virtual user profiles and their weekly meal plans. Results reveal a high precision and recall for recommending appropriate ingredients in most user categories, while the meal plan generator achieved a total recommendation accuracy of 92% for all nutrient recommendations.
In recent years, an innovative method has been developed for the non-invasive observation of the gastrointestinal tract (GT), namely Wireless Capsule Endoscopy (WCE). WCE especially enables a detailed inspection of the entire small bowel and identification of its clinical lesions. However, the foremost disadvantage of this technological breakthrough is the time consuming task of reviewing the vast amount of images produced. To address this, a novel technique for distinguishing pathogenic endoscopic images related to ulcer, the most common disease of GT, is presented here. Towards this direction, the Bidimensional Ensemble Empirical Mode Decomposition was applied to RGB color images of the small bowel acquired by a WCE system in order to extract their Intrinsic Mode Functions (IMFs). The IMFs reveal differences in structure from their finest to their coarsest scale, providing a new analysis domain. Additionally, lacunarity analysis was employed as a method to quantify and extract the texture patterns of the ulcer regions and the normal mucosa, respectively, in order to discriminate the abnormal from the normal images. Experimental results demonstrated promising classification accuracy (>95%), exhibiting a high potential towards WCE-based analysis.
The shift from traditional to technology-based diagnosis and management of psoriatic arthritis (PsA) represents a significant evolution in patient care. Traditionally, PsA was diagnosed and managed through clinical evaluations, physical examinations, and basic imaging techniques. With the evolution of digital technologies, the PsA care is transforming, giving rise to the field of digital rheumatology. In this vein, Europe has invested in research initiatives, like iPROLEPSIS, that could accelerate this transformation and redefine PsA care within a digital world. In this Viewpoint we present the current clinical PsA landscape, highlight the PsA patients' interaction with the digital world, and showcase the novel iPROLEPSIS digital offerings. The latter scaffold digital rheumatology by identifying PsA key drivers. Moreover, they support personalized PsA risk prediction and improve early PsA detection. Furthermore, they enable precise PsA treatment strategies and digital therapeutics within a novel digital health ecosystem.
Enhanced Ulcer Recognition from Capsule Endoscopic Images Using Texture Analysis | InTechOpen, Published on: 2012-04-18. Authors: Vasileios Charisis, Leontios Hadjileontiadis and George Sergiadis