DTDhaval Trivedi

Dhaval Trivedi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Dhaval Trivedi has a total of 59 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    An agile co-creation approach for designing a comprehensive digital motor assessment test for Parkinson's Disease patients

    by Beatriz Alves, Ghada Alhussein, Filomena Carnide, Nikolaos Grammalidis, Kosmas Dimitropoulos, Dhaval Trivedi, Mónica Kurtis Urra, Stelios Hadjidimitriou, Leontios Hadjileontiadis, Sofia B. Dias


  • Top Cited Papers
    Open Access

    Parkinson’s Disease Detection Based on Running Speech Data From Phone Calls

    by Christos Laganas, Dimitrios Iakovakis, Stelios Hadjidimitriou, Vasileios Charisis, Sofia B. Dias, Sevasti Bostantzopoulou, Zoe Katsarou, Lisa Klingelhoefer, Heinz Reichmann, Dhaval Trivedi, et al.

    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.


  • Open Access

    Screening of Parkinsonian subtle fine-motor impairment from touchscreen typing via deep learning

    by Dimitrios Iakovakis, K. Ray Chaudhuri, Lisa Klingelhoefer, Sevasti Bostantjopoulou, Zoe Katsarou, Dhaval Trivedi, Heinz Reichmann, Stelios Hadjidimitriou, Vasileios Charisis, Leontios J. Hadjileontiadis

    Fine-motor impairment (FMI) is progressively expressed in early Parkinson’s Disease (PD) patients and is now known to be evident in the immediate prodromal stage of the condition. The clinical techniques for detecting FMI may not be robust enough and here, we show that the subtle FMI of early PD patients can be effectively estimated from the analysis of natural smartphone touchscreen typing via deep learning networks, trained in stages of initialization and fine-tuning. In a validation dataset of 36,000 typing sessions from 39 subjects (17 healthy/22 PD patients with medically validated UPDRS Part III single-item scores), the proposed approach achieved values of area under the receiver operating characteristic curve (AUC) of 0.89 (95% confidence interval: 0.80–0.96) with sensitivity/specificity: 0.90/0.83. The derived estimations result in statistically significant ( $$p<0.05$$ p < 0.05 ) correlation of 0.66/0.73/0.58 with the clinical standard UPDRS Part III items 22/23/31, respectively. Further validation analysis on 9 de novo PD patients vs. 17 healthy controls classification resulted in AUC of 0.97 (0.93–1.00) with 0.93/0.90. For 253 remote study participants, with self-reported health status providing 252.000 typing sessions via a touchscreen typing data acquisition mobile app (iPrognosis), the proposed approach predicted 0.79 AUC (0.66–0.91) with 0.76/0.71. Remote and unobtrusive screening of subtle FMI via natural smartphone usage, may assist in consolidating early and accurate diagnosis of PD.


  • Restless legs syndrome - the under-recognised non-motor burden: a questionnaire-based cohort study

    by Anna Sauerbier, Chaamanti Sivakumar, Lisa Klingelhoefer, Pablo Martinez-Martin, Lauren Perkins, Rona Inniss, Alexandra Rizos, Dhaval Trivedi, Valentina Leta, Yi Min Wan, et al.

    Objectives: Non-motor symptoms (NMS) range from neuropsychiatric to pain and are an important but underexplored feature of restless legs syndrome (RLS). There are currently no tools available which enable the holistic assessment of NMS in RLS in clinical practice. The primary aim of this study was to systematically assess NMS prevalence and burden in patients with RLS using the NMS Questionnaire (NMSQuest) validated for Parkinson’s disease. Methods: Patients with idiopathic RLS according to the criteria of the international RLS study group (IRLSSG) were included. Patients underwent a physical examination and clinical interview as well as completed the NMS Questionnaire and the international restless legs syndrome study group (IRLSSG) rating scale. Results: Seventy-four patients with primary RLS were included (mean age 64.6 ± 14.4 years, 62.2% female, mean disease duration 23.5 ± 17.8 years, mean Levodopa equivalent daily dose 63.3 ± 67.4 mg). On average patients reported an IRLSSG rating scale score of 24.8 ± 8.2 (maximum 40) and NMSQuest score of 9.9 ± 5.0 (maximum 30). Patients reported a minimum of two NMS with the majority (39.2%) reporting a moderate NMS burden, followed by severe (28.4%) and very severe (17.6%) burden. The most frequent NMS were insomnia (89.2%) followed by nocturia (70.3%), feeling sad (59.5%), forgetfulness (54.1%), urgency (47.3%), feeling anxious (43.2%), unexplained pain (41.9%), difficulty concentrating (40.5%) and dizziness (40.5%). There were no significant differences in NMSQuest total scores according to disease duration and gender (p = 0.739, p = 0.849). Conclusion: In conclusion, this study is one of the first to address NMS in RLS systematically and the data underlines the need to holistically assess NMS in RLS in order to deliver true value-based healthcare for these patients.


  • Open Access

    On Exploring Design Elements in Assistive Serious Games for Parkinson’s Disease Patients: The i-PROGNOSIS Exergames Paradigm

    by S. B. Dias, J. A. Diniz, D. Trivedi, E. Konstantinidis, T. Savvidis, P. Bamidis, S. Bostantzopoulou, H. Jaeger, M. Stadtschnitzer, V. Charisis, et al.

    Serious Games (SGs) design couples learning design with game logic. Moreover, it can result in SGs with beneficial effects in sustaining and/or improving the (physical, cognitive) functionality in older adults. In this vein, the design elements in assistive SGs for Parkinson's Disease (PD) patients are explored here. The Game-Based Learning (GBL) design framework is adopted and its main game-design parameters are combined in a test case of Exergames design, drawn from the i-PROGNOSIS Personalized Game Suite (http://www.i-prognosis.eu). Data from a GBL-related Web-survey, completed by 104 participants, were subjected to linear regression analysis, so to identify an adapted GBL framework with the most significant game-design parameters, which efficiently predict the transferability of the Exergames beneficial effect to real-life, addressing functional PD symptoms. The findings of the proposed analysis can assist game designers to focus on the use of significant parameters during the designing process of Exergames for PD patients and maximize the positive effect of the SGs in their quality of daily life.


  • Open Access

    Active and healthy ageing for Parkinson's disease patients' support: A user's perspective within the i-PROGNOSIS framework

    by S. Hadjidimitriou, V. Charisis, K. Kyritsis, E. Konstantinidis, A. Delopoulos, P. Bamidis, S. Bostantjopoulou, A. Rizos, D. Trivedi, R. Chaudhuri, et al.

    In this paper, the user requirements, along with the methodology adopted towards their identification within the i-PROGNOSIS framework (www.i-prognosis.eu), are presented. The latter are placed within the concept of active and healthy ageing (AHA), focusing on the case of Parkinson's Disease (PD) patients' support. The bases for the user requirements identification were face-to-face sessions, focus groups and a large scale Web-survey. Towards the efficient user requirements identification and i-PROGNOSIS components development, exemplified usage scenarios and related business processes the stakeholders of i-PROGNOSIS can perform, are discussed. Overall, 122 functional and non-functional requirements were identified, serving as a basis for the spiral development model of i-PROGNOSIS, revealing the beneficial role of the users in designing solutions within the AHA concept.