Kadri Medijainen

Background Rare neurological diseases often present with severe cognitive impairment but face significant challenges in access to specialized care. Telemonitoring and telerehabilitation are promising approaches to improve the standard of care in common neurological diseases and could prove even more beneficial to patients with rare neurological diseases. Aim To review the available evidence on the usability and validity of cognitive telemonitoring or telerehabilitation in rare neurological diseases. Methods We performed a scoping review, examining all studies published in the last 25 years on both synchronous and asynchronous cognitive telemonitoring or telerehabilitation approaches in rare neurological diseases of adulthood. Results Active digital cognitive tests show promising feasibility and validity, especially for people with Frontotemporal Dementia and Huntington’s Disease. However, methodological limitations remain, notably the high rate of dropouts for active telemonitoring and limited evidence of cognitive domain-specific sensitivity for passive telemonitoring. Cognitive telerehabilitation is emerging as a feasible and potentially effective approach for primary progressive aphasia. However, other rare neurological diseases still require proper investigation, and the available evidence is still largely preliminary, and is plagued by small sample sizes and heterogeneous methodology, which limits generalizability. Conclusion Our review recognizes the promise of remote approaches in expanding access to both cognitive monitoring and rehabilitation for rare neurological diseases but emphasizes the need for rigorously designed trials to establish clinical utility and best practices. Key unmet needs include improvement of adherence to active telemonitoring, evaluation of clinical validity in reference to gold-standard clinical outcome measures for passive telemonitoring, evaluation of clinical utility via longitudinal studies, evaluation of feasibility across a wider range of disease severity, and technological literacy.

Background/Objectives: Evidence-based practice (EBP) is a core competence in physiotherapy, yet its implementation in routine clinical practice remains inconsistent. This study aimed to describe self-reported EBP competencies among physiotherapists and to examine factors associated with daily EBP and readiness to implement EBP. Methods: A cross-sectional analytic survey was conducted among 337 practicing Estonian physiotherapists (75% female) between 2022 and 2024. EBP competencies were assessed using the Estonian version of the Evidence-Based Practice Questionnaire (EBPQ-E). Two multiple linear regression models examined associations of demographic and professional characteristics and EBP competencies with (1) daily EBP and (2) readiness to implement EBP. Results: The mean total EBPQ-E score was 4.72 (SD = 0.89), with the highest scores in Attitude, followed by Knowledge/Skills, Practice, and Sharing. While physiotherapists strongly endorsed the value of EBP, critical appraisal and knowledge sharing were less frequent. Readiness to implement EBP was associated with supervisory experience, dual employment, and working with colleagues (p < 0.05), explaining 7.5% of the variance. Daily EBP was primarily explained by EBP competencies (40.8% variance), whereas 5–10 years of qualification showed a negative association. Conclusions: While professional and contextual factors support readiness for EBP, sustained implementation relies on continuous competency development and career-long support for practicing physiotherapists, shifting focus away from static background characteristics, workload, and time constraints.

Subject: In this article, convolutional networks of one, two, and three dimensions are compared with respect to their ability to distinguish between the drawing tests produced by Parkinson's disease patients and healthy control subjects. Motivation: The application of deep learning techniques for the analysis of drawing tests to support the diagnosis of Parkinson's disease has become a growing trend in the area of Artificial Intelligence. Method: The dynamic features of the handwriting signal are embedded in the static test data to generate one-dimensional time series, two-dimensional RGB images and three-dimensional voxelized point clouds, and then one-, two-, and three-dimensional CNN can be used to automatically extract features for effective diagnosis. Novelty: While there are many results that describe the application of two-dimensional convolutional models to the problem, to the best knowledge of the authors, there are no results based on the application of three-dimensional models and very few using one-dimensional models. Main result: The accuracy of the one-, two- and three-dimensional CNN models was 62.50%, 77.78% and 83.34% in the DraWritePD dataset (acquired by the authors) and 73.33%, 80.00% and 86.67% in the PaHaW dataset (well known from the literature), respectively. For these two data sets, the proposed three-dimensional convolutional classification method exhibits the best diagnostic performance.

In recent years, deep learning methods have achieved great success in various fields due to their strong performance in practical applications. In this paper, we present a light-weight neural network for Parkinson's disease diagnostics, in which a series of hand-drawn data are collected to distinguish Parkinson's disease patients from healthy control subjects. The proposed model consists of a convolution neural network (CNN) cascading to long-short-term memory (LSTM) to adapt the characteristics of collected time-series signals. To make full use of their advantages, a multilayered LSTM model is firstly used to enrich features which are then concatenated with raw data and fed into a shallow one-dimensional (1D) CNN model for efficient classification. Experimental results show that the proposed model achieves a high-quality diagnostic result over multiple evaluation metrics with much fewer parameters and operations, outperforming conventional methods such as support vector machine (SVM), random forest (RF), lightgbm (LGB) and CNN-based methods.

Introduction: Quality of life (QoL) has been acknowledged as a fundamental concept in the field of health and is favorably improved by physical activity (PA). This systematic review aims to assess the benefits and harms of different types of PA to improve health-related QoL in both community-dwelling and diseased older adults to provide a recommendation for the minimum amount of PA needed to obtain measurable QoL benefits. Methods and analysis: We will search MEDLINE, Cochrane Central Register of Controlled Trials, CINHAL, Epistemonikos, Web of Science and gray literature. Randomized controlled trials enrolling healthy or diseased older adults aged > 65 years, providing any kind of physical activity intervention and having quality of life as an outcome will be included. There will be no language restriction. Two independent reviewers will screen the papers, and a third reviewer will resolve the conflicts. The quality of the included studies will be assessed through the Risk of Bias 2.0 tool. Finally, data will be extracted to create proper meta-analyses of comparisons between the different kinds of physical activity interventions or to control groups. Ethics and dissemination: This review does not require approval from the Ethics Committee. The results will be disseminated in peer-reviewed journals and at international conferences; moreover, the findings will be shared on social media using an accessible language.

BACKGROUND: In the long term, Parkinson’s disease (PD) leads to the development of difficulties in daily functional tasks. There remains a paucity of evidence on the effectiveness of physiotherapy on patient-perceived difficulties regarding basic activities of daily living (ADL). OBJECTIVES: To assess an effect of a versatile physiotherapy intervention on patient-perceived difficulties in basic ADL. METHODS: The study sample included 24 patients (10 men and 14 women) with PD. Participants were randomly assigned into intervention (IG) and control groups (CG). Two assessments were performed with a gap of 10 weeks. Following first assessment, during an 8-week period, IG participants attended sixteen physiotherapy 60-minutes sessions in groups that were divided into five parts to address the core areas recommended by the European Physiotherapy Guideline for PD (EPGPD): gait, transfers, balance, physical capacity, and manual activities. The main assessment tool was the Modified Patients Specific Functional Scale (ModPSFS), which represents a self-assessment rating on difficulties perceived in 17 different commonly occurring activities. RESULTS: IG members reported a significant reduction in self-perceived difficulties as assessed by ModPSFS (effect size 1.39; 95%CI 5.1, 26.6 points, p = 0.005). CONCLUSIONS: 2-months conventional physiotherapy with incorporated core areas recommended in EPGPD for PD reduced patient-perceived difficulties in basic ADL.

BACKGROUND: Gait function is known to be impaired by Parkinson’s disease (PD). The effect of exercise to improve gait has been widely examined, often with special intervention. However, in clinical settings, physiotherapy rarely consists only of gait