Quick computer aided differential diagnostics based on repetitive finger tapping in Parkinson’s disease and atypical parkinsonisms

Development of Neurodegenerative Disease Diagnosis and Monitoring from Traditional to Digital Biomarkers

Monitoring and assessing the progression of symptoms in neurodegenerative diseases, including Alzheimer's and Parkinson's disease, are critical for improving patient outcomes. Traditional biomarkers, such as cerebrospinal fluid analysis and brain imaging, are widely used to investigate the underlying mechanisms of disease and enable early diagnosis. In contrast, digital biomarkers derived from phenotypic changes-such as EEG, eye movement, gait, and speech analysis-offer a noninvasive and accessible alternative. Leveraging portable and widely available devices, such as smartphones and wearable sensors, digital biomarkers are emerging as a promising tool for ND diagnosis and monitoring. This review highlights the comprehensive developments in digital biomarkers, emphasizing their unique advantages and integration potential alongside traditional biomarkers.

Dopaminergic responsiveness and dopaminergic challenge tests of Parkinson's disease: a systematic review and meta-analysis

BACKGROUND AND OBJECTIVE

The assessment and quantification of dopaminergic responsiveness are crucial for the diagnosis and management of Parkinson's disease (PD). This study aimed to summarize and compare motor improvements in patients with PD and atypical parkinsonian syndromes (APS) across three types of dopaminergic challenge tests, as well as evaluate their diagnostic performance.

METHODS

PubMed, Embase, Cochrane Library, and Web of Science were searched to identify eligible studies reporting the improvement rate of the Unified Parkinson's Disease Rating Scale Part III (UPDRS-III) or MDS-UPDRS-III in dopaminergic challenge tests for PD or APS, or diagnostic outcomes in differential diagnosis between PD and APS. A random-effects model was conducted to pool improvement rates and standardized mean differences (SMDs) in patients with PD or APS during dopaminergic challenge tests. Subgroup analysis and meta-regression were used to investigate the sources of heterogeneity. A bivariate mixed-effects model was employed to evaluate the diagnostic performance of these tests.

RESULTS

A total of 58 studies (3641 PD and 711 APS) were included. In the acute levodopa challenge test, patients with PD, APS, and multiple system atrophy (MSA) demonstrated pooled UPDRS-III improvement rates of 41.5% [95% confidence interval (CI) 38.5%-44.5%; I2 = 98.8%], 14.7% (95% CI 6.8%-22.7%; I2 = 96.5%), and 6.3% (95% CI - 4.0% to 16.7%), respectively. Subgroup analyses showed the pooled improvement rate of de novo PD patients (25.9%; 95% CI 15.1%-36.7%) was significantly lower than treated PD patients (42.4%; 95% CI 38.6%-46.2%) (p = 0.005), overlapping with APS patients with off-state H-Y stage ≤ 2.5 (21.2%; 95% CI 14.5%-27.9%). PD patients with off-state H-Y stage ≤ 2.5 (35.4%; 95% CI 31.1%-39.7%) or UPDRS-III score ≤ 30 (30.5%; 95% CI 23.4%-35.7%) had significantly lower improvement rate than PD patients with off-state H-Y stage > 2.5 (44.1%; 95% CI 37.0%-51.3%) (p = 0.041) or UPDRS-III scores > 30 (47.0%; 95% CI 43.7%-50.4%) (p < 0.001). The pooled improvement rate in acute levodopa challenge tests of PD with 100 mg levodopa (17.0%; 95% CI 11.3%-22.8%) was significantly lower than that in tests with 200-250 mg levodopa (34.3%; 95% CI 30.6%-38.0%) (p < 0.001). Meta-regression showed the improvement rate of PD was positively correlated with off-state UPDRS-III scores (p = 0.007). In the acute apomorphine challenge test, PD patients showed a pooled UPDRS-III improvement rate of 40.1% (95% CI 36.9%-43.3%). To differentiate between PD and APS, the pooled sensitivity, specificity, diagnostic odds ratio (DOR), and area under the curve (AUC) for the acute levodopa challenge test were 0.81, 0.77, 13.91, and 0.85; for the acute apomorphine challenge test, they were 0.84, 0.85, 29.94, and 0.91; and for chronic levodopa therapy, they were 0.82, 0.71, 11.54, and 0.72. The pooled sensitivity, specificity, DOR, and AUC of the acute levodopa challenge test for distinguishing PD from MSA were 0.82, 0.78, 15.74, and 0.79; for PD vs. PSP, they were 0.77, 0.78, 11.54, and 0.84; and for PD vs. DLB, they were 0.65, 0.58, 2.65, and 0.64.

CONCLUSIONS

The overall dopaminergic responsiveness is greater in PD patients compared to those with APS. However, there is significant heterogeneity in the pooled motor improvement of dopaminergic responsiveness within PD or APS, with overlap between de novo PD and early-stage APS. All three types of dopaminergic challenge tests demonstrate moderate diagnostic performance in differentiating PD from APS.

The Use of Artificial Intelligence and Wearable Inertial Measurement Units in Medicine: Systematic Review

BACKGROUND

Artificial intelligence (AI) has already revolutionized the analysis of image, text, and tabular data, bringing significant advances across many medical sectors. Now, by combining with wearable inertial measurement units (IMUs), AI could transform health care again by opening new opportunities in patient care and medical research.

OBJECTIVE

This systematic review aims to evaluate the integration of AI models with wearable IMUs in health care, identifying current applications, challenges, and future opportunities. The focus will be on the types of models used, the characteristics of the datasets, and the potential for expanding and enhancing the use of this technology to improve patient care and advance medical research.

METHODS

This study examines this synergy of AI models and IMU data by using a systematic methodology, following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, to explore 3 core questions: (1) Which medical fields are most actively researching AI and IMU data? (2) Which models are being used in the analysis of IMU data within these medical fields? (3) What are the characteristics of the datasets used for in this fields?

RESULTS

The median dataset size is of 50 participants, which poses significant limitations for AI models given their dependency on large datasets for effective training and generalization. Furthermore, our analysis reveals the current dominance of machine learning models in 76% on the surveyed studies, suggesting a preference for traditional models like linear regression, support vector machine, and random forest, but also indicating significant growth potential for deep learning models in this area. Impressively, 93% of the studies used supervised learning, revealing an underuse of unsupervised learning, and indicating an important area for future exploration on discovering hidden patterns and insights without predefined labels or outcomes. In addition, there was a preference for conducting studies in clinical settings (77%), rather than in real-life scenarios, a choice that, along with the underapplication of the full potential of wearable IMUs, is recognized as a limitation in terms of practical applicability. Furthermore, the focus of 65% of the studies on neurological issues suggests an opportunity to broaden research scope to other clinical areas such as musculoskeletal applications, where AI could have significant impacts.

CONCLUSIONS

In conclusion, the review calls for a collaborative effort to address the highlighted challenges, including improvements in data collection, increasing dataset sizes, a move that inherently pushes the field toward the adoption of more complex deep learning models, and the expansion of the application of AI models on IMU data methodologies across various medical fields. This approach aims to enhance the reliability, generalizability, and clinical applicability of research findings, ultimately improving patient outcomes and advancing medical research.

Autism Spectrum Disorder Detection by Hybrid Convolutional Recurrent Neural Networks from Structural and Resting State Functional MRI Images

This study aims to increase the accuracy of autism spectrum disorder (ASD) diagnosis based on cognitive and behavioral phenotypes through multiple neuroimaging modalities. We apply machine learning (ML) algorithms to classify ASD patients and healthy control (HC) participants using structural magnetic resonance imaging (s-MRI) together with resting state functional MRI (rs-f-MRI and f-MRI) data from the large multisite data repository ABIDE (autism brain imaging data exchange) and identify important brain connectivity features. The 2D f-MRI images were converted into 3D s-MRI images, and datasets were preprocessed using the Montreal Neurological Institute (MNI) atlas. The data were then denoised to remove any confounding factors. We show, by using three fusion strategies such as early fusion, late fusion, and cross fusion, that, in this implementation, hybrid convolutional recurrent neural networks achieve better performance in comparison to either convolutional neural networks (CNNs) or recurrent neural networks (RNNs). The proposed model classifies subjects as autistic or not according to how functional and anatomical connectivity metrics provide an overall diagnosis based on the autism diagnostic observation schedule (ADOS) standard. Our hybrid network achieved an accuracy of 96% by fusing s-MRI and f-MRI together, which outperforms the methods used in previous studies.