RESUMEN
Introduction: Dysarthria, a motor speech disorder caused by muscle weakness or paralysis, severely impacts speech intelligibility and quality of life. The condition is prevalent in motor speech disorders such as Parkinson's disease (PD), atypical parkinsonism such as progressive supranuclear palsy (PSP), Huntington's disease (HD), and amyotrophic lateral sclerosis (ALS). Improving intelligibility is not only an outcome that matters to patients but can also play a critical role as an endpoint in clinical research and drug development. This study validates a digital measure for speech intelligibility, the ki: SB-M intelligibility score, across various motor speech disorders and languages following the Digital Medicine Society (DiMe) V3 framework. Methods: The study used four datasets: healthy controls (HCs) and patients with PD, HD, PSP, and ALS from Czech, Colombian, and German populations. Participants' speech intelligibility was assessed using the ki: SB-M intelligibility score, which is derived from automatic speech recognition (ASR) systems. Verification with inter-ASR reliability and temporal consistency, analytical validation with correlations to gold standard clinical dysarthria scores in each disease, and clinical validation with group comparisons between HCs and patients were performed. Results: Verification showed good to excellent inter-rater reliability between ASR systems and fair to good consistency. Analytical validation revealed significant correlations between the SB-M intelligibility score and established clinical measures for speech impairments across all patient groups and languages. Clinical validation demonstrated significant differences in intelligibility scores between pathological groups and healthy controls, indicating the measure's discriminative capability. Discussion: The ki: SB-M intelligibility score is a reliable, valid, and clinically relevant tool for assessing speech intelligibility in motor speech disorders. It holds promise for improving clinical trials through automated, objective, and scalable assessments. Future studies should explore its utility in monitoring disease progression and therapeutic efficacy as well as add data from further dysarthrias to the validation.
RESUMEN
BACKGROUND: Modern prodromal Alzheimer's disease (AD) clinical trials might extend outreach to a general population, causing high screen-out rates and thereby increasing study time and costs. Thus, screening tools that cost-effectively detect mild cognitive impairment (MCI) at scale are needed. OBJECTIVE: Develop a screening algorithm that can differentiate between healthy and MCI participants in different clinically relevant populations. METHODS: Two screening algorithms based on the remote ki:e speech biomarker for cognition (ki:e SB-C) were designed on a Dutch memory clinic cohort (Nâ=â121) and a Swedish birth cohort (Nâ=â404). MCI classification was each evaluated on the training cohort as well as on the unrelated validation cohort. RESULTS: The algorithms achieved a performance of AUC 0.73 and AUC 0.77 in the respective training cohorts and AUC 0.81 in the unseen validation cohorts. CONCLUSION: The results indicate that a ki:e SB-C based algorithm robustly detects MCI across different cohorts and languages, which has the potential to make current trials more efficient and improve future primary health care.
Asunto(s)
Enfermedad de Alzheimer , Disfunción Cognitiva , Humanos , Habla , Enfermedad de Alzheimer/diagnóstico , Disfunción Cognitiva/diagnóstico , Aprendizaje Automático , Cognición , BiomarcadoresRESUMEN
Introduction: Progressive cognitive decline is the cardinal behavioral symptom in most dementia-causing diseases such as Alzheimer's disease. While most well-established measures for cognition might not fit tomorrow's decentralized remote clinical trials, digital cognitive assessments will gain importance. We present the evaluation of a novel digital speech biomarker for cognition (SB-C) following the Digital Medicine Society's V3 framework: verification, analytical validation, and clinical validation. Methods: Evaluation was done in two independent clinical samples: the Dutch DeepSpA (N = 69 subjective cognitive impairment [SCI], N = 52 mild cognitive impairment [MCI], and N = 13 dementia) and the Scottish SPeAk datasets (N = 25, healthy controls). For validation, two anchor scores were used: the Mini-Mental State Examination (MMSE) and the Clinical Dementia Rating (CDR) scale. Results: Verification: The SB-C could be reliably extracted for both languages using an automatic speech processing pipeline. Analytical Validation: In both languages, the SB-C was strongly correlated with MMSE scores. Clinical Validation: The SB-C significantly differed between clinical groups (including MCI and dementia), was strongly correlated with the CDR, and could track the clinically meaningful decline. Conclusion: Our results suggest that the ki:e SB-C is an objective, scalable, and reliable indicator of cognitive decline, fit for purpose as a remote assessment in clinical early dementia trials.
RESUMEN
Gene set enrichment analysis has become one of the most frequently used applications in molecular biology research. Originally developed for gene sets, the same statistical principles are now available for all omics types. In 2016, we published the miRNA enrichment analysis and annotation tool (miEAA) for human precursor and mature miRNAs. Here, we present miEAA 2.0, supporting miRNA input from ten frequently investigated organisms. To facilitate inclusion of miEAA in workflow systems, we implemented an Application Programming Interface (API). Users can perform miRNA set enrichment analysis using either the web-interface, a dedicated Python package, or custom remote clients. Moreover, the number of category sets was raised by an order of magnitude. We implemented novel categories like annotation confidence level or localisation in biological compartments. In combination with the miRBase miRNA-version and miRNA-to-precursor converters, miEAA supports research settings where older releases of miRBase are in use. The web server also offers novel comprehensive visualizations such as heatmaps and running sum curves with background distributions. We demonstrate the new features with case studies for human kidney cancer, a biomarker study on Parkinson's disease from the PPMI cohort, and a mouse model for breast cancer. The tool is freely accessible at: https://www.ccb.uni-saarland.de/mieaa2.