Leveraging Action Unit Derivatives for Early-Stage Parkinson's Disease Detection
Bibliographic record
Abstract
Hypomimia is a symptom of Parkinson's disease (PD), involving a decrease in facial movements and a loss of emotional expressions on the face. The objective of this study is to identify hypomimia in individuals in the early stage of PD by analyzing facial action units (AUs). Our study included video recordings from 109 PD subjects and 45 healthy control (HC) subjects with an average of two videos per person (294 videos in total). The participants were requested to perform rapid syllable repetitions. For the purpose of discriminating between normal facial muscle movements and those specific to PD subjects experiencing hypomimia, we calculate the derivatives of the AUs. We derive global features based on the AUs intensities and their derivatives, and utilize XGBoost and Random Forest to perform the classification between PD and HC. We achieve subject-level classification scores of up to 73.7% for balanced accuracy (BA) and an area under the curve (AUC) of 81.39% using XGBoost, and a BA of 79.1% and an AUC of 83.7% with Random Forest. These findings show potential in identifying hypomimia during the early phases of PD. Moreover, this research could facilitate the continuous monitoring of hypomimia beyond hospital settings, enabled by telemedicine. • We propose a new method to detect early-stage Parkinson's disease from face videos. • Facial movement is quantified using the derivatives of facial action units (AUs). • Good discrimination Parkinson's disease vs. healthy controls is shown with XGBoost. • Clinical interpretation of the classifier's output is proposed.
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.
How this classification was reachedexpand
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".