Citations

Purpose: This study examined whether phoneme-level posterior probabilities generated by an articulatory-informed deep learning model (Phonet) can serve as interpretable and sensitive markers of articulatory impairment in motor speech disorders (MSDs). The goal was to determine whether these features distinguish individuals with and without MSDs and reflect varying severity levels of articulatory impairment. Method: A total of 676 participants (199 with MSDs, 477 without MSDs) completed a remotely captured word repetition task. Speech recordings were phonetically aligned, and posterior probabilities were extracted using a retrained version of the Phonet model, which estimates frame-level probabilities for 23 phonological classes. Segment-level posterior values were computed and compared across groups and severity levels using linear mixed-effects regression models. Results: Posterior probabilities were significantly reduced in the MSD group across all phoneme types. Within the MSD group, posterior probabilities decreased progressively with greater clinical severity, as measured by both perceptual sound distortion ratings and a cumulative articulation error score. Segment-specific analyses revealed systematic differences across phoneme classes, indicating that posterior probabilities capture distinct patterns of articulatory degradation associated with motor speech impairment. Conclusions: Phoneme-level posterior probabilities serve as interpretable, segment-specific indicators of articulatory impairment in MSDs. These features differentiate clinical status and reflect gradations of severity, making them promising tools for augmenting traditional perceptual speech assessments. Their linguistic transparency and scalability support future clinical applications in diagnosis, monitoring, and targeted intervention.

Abstract Purpose To evaluate whether two automated measures of nasality, Nasal Cognate Distinctiveness (NCD) and nasal posterior probability (NPP), provide clinically meaningful markers of hypernasality in speakers with motor speech disorders (MSDs) and to determine whether hypernasality-related information extends beyond stop consonants, which are typically targeted in cognate-based approaches. Method Sentence-level speech recordings were obtained from 561 patients, including 374 neurologically typical controls and 187 individuals with MSDs. NCD was computed for voiceless stops (/p/, /t/, /k/) using likelihood ratios between stops and their nasal cognates. NPP was extracted using a phonological feature-based neural network model and analyzed for stops, consonants, and vowels. Hypernasality severity was rated by speech-language pathologists. Group differences and associations with hypernasality severity were evaluated using linear mixed-effects models and Spearman correlations, and receiver operating characteristic (ROC) analyses were used to evaluate discrimination of absent versus present hypernasality. An additional 20 controls with repeat recordings were used to evaluate test-retest reliability and minimal detectable change (MDC). Results NCD generally decreased and NPP increased with increasing hypernasality severity, with phoneme-specific severity effects observed for NCD. Across stops, NCD and NPP were strongly inversely correlated and showed comparable discrimination of absent versus present hypernasality (AUCs = 0.796 and 0.730, respectively). Consonant and vowel NPP measures were both positively associated with hypernasality severity and demonstrated identical classification performance (AUC = 0.853). No significant differences in ROC performance were observed between NCD and NPP or between consonant and vowel NPP measures. Test-retest change exceeded the MDC threshold in 2 of 20 controls for NCD and 1 of 20 for NPP. Conclusions Both NCD and NPP provide objective markers of hypernasality in speakers with MSDs. The measures capture related aspects of nasalization and demonstrate comparable ability to identify clinically meaningful hypernasality. NPP captures hypernasality-related acoustic information across both consonants and vowels, with similar relationships to severity and classification performance across sound classes. Test-retest findings provide preliminary MDC benchmarks for interpreting longitudinal change.

Assessing balance is crucial in neurological rehabilitation, yet while wearable sensors enable real-world monitoring, identifying reliable digital biomarkers remains challenging. This study utilized a high-fidelity instrumented walkway to determine which gait parameters best predict balance impairment, providing robust targets for future wearable applications. We analyzed 49 steady-state gait metrics from 140 individuals with diverse neurological conditions. Using statistical analysis and machine learning, we evaluated these parameters against objective force plate sway scores and clinical fall-history labels. Group analysis identified 16 parameters significantly distinguishing fallers from non-fallers, and a neural network classified fallers with an area under the curve of 0.75. Across all analytical approaches, overall gait variability, e.g., Stride Width S.D. and the Gait Variability Index, emerged as a universal predictor of balance impairment and fall risk. Furthermore, while traditional linear models emphasized spatial postural control, machine learning classification uniquely identified inter-limb asymmetry as a premier driver of fall prediction. These findings indicate that instrumented gait analysis effectively identifies digital biomarkers for balance deficits. Isolating these specific metrics provides a clear blueprint for meaningful metrics required for continuous objective monitoring and future development of personalized, adaptive rehabilitation strategies.

Abstract Motor speech disorders (MSDs) are early markers of neurological disease, but expert perceptual analysis is rarely available outside specialized centers. Automated speech analysis offers a scalable alternative, yet prior studies have not systematically compared modeling approaches or assessed clinically relevant metrics in independent datasets. This study compared static acoustic features, articulatory informed Phonet features, and self-supervised pretrained models for binary and multi label MSD classification. We trained and evaluated models on 583 speech samples using speaker level splits. Baseline models included logistic regression and Gated Recurrent Units (GRUs) trained on eGeMAPS and MFCCs. We extracted three types of Phonet derived features and evaluated pretrained HuBERT and SSAST models in frozen, partially fine-tuned, and fully fine-tuned configurations. Binary classification distinguished MSDs from controls, while multi label classification identified six MSD subtypes. Models were assessed using validation AUC, and cut points were tested on two independent datasets. Pretrained and Phonet based models substantially outperformed static acoustic features. In binary classification, HuBERT achieved the highest AUC (0.95), while compact Phonet derived GRUs achieved comparable performance (up to 0.94). These models generalized well to independent datasets, maintaining high sensitivity (0.94) and specificity (0.97). In multi label classification, Phonet models achieved the highest macro average AUC (0.86), but threshold-based subtype performance declined on unseen data. Automated MSD detection is feasible and clinically promising. Binary classification generalized well, whereas multi label classification showed limited threshold stability across datasets.

Abstract This study examined the extent to which goodness of pronunciation (GoP) scores and phonological posterior probabilities capture perceptual ratings of speech severity in individuals with motor speech disorders (MSD). Speech recordings of the word catastrophe were obtained from 489 participants, including 333 neurologically typical controls and 156 individuals with MSD. GoP scores were derived using traditional acoustic features and self-supervised speech representations, including WavLM and XLS-R, across multiple modeling approaches, while phonological posterior probabilities were extracted using Phonet. Model performance was evaluated using Kendall’s rank correlations, regression, and receiver operating characteristic analyses against speech-language pathologists’ perceptual ratings of sound distortion and intelligibility. Both GoP and phonological posterior probabilities were significantly associated with perceptual ratings. Self-supervised speech representations substantially outperformed traditional acoustic features, with WavLM-based GoP using k-nearest neighbors achieving the strongest performance. Across correlation, regression, and classification analyses, GoP consistently outperformed phonological posterior probabilities for both sound distortion and intelligibility. Age and gender had minimal influence on model-derived measures or their relationships with perceptual ratings. These findings demonstrate the value of self-supervised GoP as an objective measure of speech impairment while highlighting the complementary role of phonological posterior probabilities in characterizing articulatory aspects of motor speech disorders.

Abstract Background Immunohistochemically detected phosphorylated α‐synuclein (p‐α‐syn) in cutaneous nerves has been found in >95% of patients meeting consensus criteria for dementia with Lewy bodies (DLB); however, its performance in prodromal stages (mild cognitive impairment‐Lewy body [MCI‐LB]) and clinical practice is unknown. Objective We evaluated skin biopsy for p‐α‐syn in a convenience cohort of patients with suspected MCI‐LB or DLB in a tertiary care setting. Methods 53 patients underwent commercially available skin biopsy for skin nerve p‐α‐syn as part of a clinical evaluation for suspected MCI‐LB/DLB. Consensus MCI‐LB/DLB criteria blinded to skin biopsy result were applied through retrospective chart review; those not definitively meeting criteria were considered questionable synucleinopathy (QS). Results Median age at skin biopsy was 70 years (range, 43–87 years) with 81% men. 36 patients (68%) had positive skin biopsies. 32/43 (74%) patients meeting clinical consensus criteria for DLB/MCI‐LB had a positive skin biopsy, with higher frequency in MCI‐LB (87%) compared with DLB (60%). 4/10 (40%) QS had positive biopsies. One patient with a positive skin biopsy had no evidence of central nervous system (CNS) α‐syn on autopsy. Conclusions Positive skin biopsy for p‐α‐syn occurs across the spectrum of cognitive presentations of Lewy body disease including prodromal DLB, albeit at a lower frequency in this retrospective review of atypical cases compared with typical clinical presentations. A positive skin biopsy may not reflect CNS synucleinopathy as the etiology for a patient's symptoms in some cases. Longitudinal studies of skin biopsies for p‐α‐syn in suspected MCI‐LB/DLB with autopsy confirmation are needed. © 2025 International Parkinson and Movement Disorder Society.

Abstract Background To promote equitable access to neurologic diagnostics, our team developed MASTERMIND—the Mobile Assessment of Speech To Evaluate, Recognize, and Monitor Indicators of Neurologic health and Disease. One subtest, the MASTERMIND Assessment of Naming, includes ten pictures randomly selected from a list of 45 words varying in frequency. This study aimed to 1) evaluate the feasibility of a remotely self‐administered naming test for patients with cognitive, linguistic, and/or communication difficulties and 2) assess the sensitivity and specificity of performance measures (accuracy, error type, and response time) for detecting aphasia and cognitive‐communication difficulties. Method The task was remotely administered to 138 controls, 26 cognitively impaired individuals, 15 with motor speech disorders, 8 with cognitive concerns, and 6 with aphasia. Participants named pictures displayed on‐screen, advancing through the task by clicking “Next.” Responses were processed using natural language processing (NLP). Audio was transcribed with Whisper Large‐v3, and responses were matched to stimuli within a 0.4‐second threshold. Errors were categorized by type (semantic, phonemic, or unclear source) through consensus between two raters. Performance metrics (accuracy, error type, response time) were analyzed using Kruskal‐Wallis and Pearson's Chi‐Square tests, with AUROC analysis evaluating diagnostic performance. Results Differences in accuracy, response time, and error type were observed across groups (Table 1). Controls and cognitively impaired participants performed similarly, with longer response times observed in patients with aphasia and motor speech disorders. Accuracy alone was a poor predictor of all patients versus controls (AUROC = 0.468) but prediction was better in distinguishing aphasia patients from 1) controls (AUROC = 0.698), 2) cognitively impaired participants (AUROC = 0.679), and 3) those with MSDs (AUROC = 0.670). Conclusions The MASTERMIND Assessment of Naming is a feasible, scalable, self‐administered diagnostic tool enhanced by automated NLP. It provides critical insights through response time, accuracy, and error analysis. Limitations include potential bias in error classification and fixed processing thresholds. The study highlights MASTERMIND's potential for patient triaging and screening. Future research will evaluate the sensitivity of combined performance metrics to disease progression, expand sample sizes and diversity, and refine usability based on participant feedback.

Abstract Background Neuropathologic evaluation is essential for diagnosing and treating dementia, but definitive diagnoses is only available after post‐mortem brain autopsy. Positron emission tomography (PET) offers a potential in vivo proxy for predicting neuropathology. This study proposes a semi‐supervised learning (SSL) model using a single FDG‐PET image to predict underlying neuropathology. Method The SSL model leverages a self‐organized graph structure based on a patient similarity network (PSN) created from 1,495 FDG‐PET images across the aging and neurodegenerative spectrum. Each patient is represented by a node, with edges indicating image similarity derived from principal component analysis features and cosine similarity weights. The PSN structure connects 20 nearest neighbors. Neuropathologic labels were available for 204 autopsied patients. The Poisson Learning Method was employed to propagate labels from these annotated nodes to unlabeled nodes, guided by the PSN structure. FDG‐PET images were collected from clinical and research participants at the Mayo Clinic and processed using an MRI‐free pipeline. Neuropathologic labels were assigned based on widely accepted diagnostic criteria. Leave‐one‐out cross‐validation (LOOCV) was used to assess model performance. Results The confusion matrix demonstrated high accuracy in predicting Alzheimer's disease, frontotemporal lobar degeneration with tau inclusions, and Lewy body disease pathology. A Sankey diagram and label distribution analysis revealed strong correlations between clinical and predicted neuropathologic labels. Conclusion This study highlights the potential of a graph‐based SSL pipeline to predict neuropathological changes using FDG‐PET imaging data, despite limited pathology labels. The findings underscore the value of SSL in bridging the gap between abundant neuroimaging data and scarce neuropathologic labels, contributing to improved dementia diagnosis and understanding.