Data-Driven Subtyping of Parkinson’s Using Acoustic Analysis of Sustained Vowels and Cluster Analysis: Findings in the Parkinson’s Voice Initiative Study
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract People diagnosed with Parkinson’s (PwP) exhibit a diverse manifestation of heterogeneous symptoms which likely reflect different subtypes. However, there is no widely accepted consensus on the criteria for subtype membership assignment. We explored clustering PwP using a data-driven approach mining speech signals. We used data from the three English-speaking cohorts (Boston, Oxford, Toronto) in the Parkinson’s Voice Initiative (PVI), where speech and basic demographic information were collected over the standard telephone network. We acoustically characterized 2097 sustained vowel /a/ recordings from 1138 PwP (Boston cohort) using 307 dysphonia measures. We applied unsupervised feature selection to select a concise subset of the dysphonia measures and hierarchical clustering combined with 2D-data projections using t-distributed stochastic neighbor embedding (t-SNE) to facilitate visual exploration of PwP groups. We assessed cluster validity and consistency using silhouette plots and the cophenetic correlation coefficient. We externally validated cluster findings on the Oxford and Toronto PVI cohorts ( n = 285 and 107 participants, respectively). We selected 21 dysphonia measures and found four main clusters which provide tentative insights into different dominating speech-associated characteristics (cophenetic coefficient = 0.72, silhouette score = 0.67). The cluster findings were consistent across the three PVI cohorts, strongly supporting the generalization of the presented methodology towards PwP subtype assignment, and were independently visually verified in 2D projections with t-SNE. The presented methodology with mining sustained vowels and clustering may provide an objective and streamlined approach towards informing PwP subtype assignment. This may have important implications towards developing more personalized clinical management of symptoms for PwP.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.010 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it