Research map / Architectures and efficiency / RNNs and normalization
PhoneMD: Learning to Diagnose Parkinson’s Disease from Smartphone Data
Patrick Schwab, Walter Karlen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Aggregate multiple test predictions with EAM and add age and gender | PhoneMD · mPower test set | AUC: 0.74 -> 0.85 | Improved |
| Use EAM instead of mean aggregation | Neural-network test predictions · mPower test set | AUC: 0.64 -> 0.71 | Improved |
| Combine neural-network and expert-feature test models | EAM · mPower test set | AUC: 0.71 -> 0.70 | Mixed |
| Add age and gender to the EAM (ablation) | EAM (Both) · mPower test set | AUC: 0.70 -> 0.85 | Improved |
| Train one end-to-end network to assess tests and aggregate them jointly (ablation) | PhoneMD · mPower test set | AUC: 0.50 (0.50, 0.56) | Hurt |
| Add timing information to the EAM metadata (ablation) | EAM · mPower test set | predictive performance | No clear effect |
| Add a segment-level neural attention mechanism to the voice CNN (ablation) | Voice CNN · Voice | predictive performance | Hurt |
| Downsample walking, voice, and tapping signals (ablation) | Specialised test models · Walking, voice, and tapping | predictive performance | No clear effect |
| Use the CNN rather than expert features for tapping | Tapping test model · Tapping | AUC: 0.62 vs 0.59 | Hurt |
| Use expert features rather than the RNN for memory | Memory test model · Memory | AUC: 0.52 vs 0.65 | Hurt |
Closest papers by meaning
- Accessible, At-Home Detection of Parkinson’s Disease via Multi-Task Video Analysis (AAAI 2025 · similarity 0.88)
- YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis (NeurIPS 2023 · similarity 0.87)
- TULIP: Multi-camera 3D Precision Assessment of Parkinson's Disease (CVPR 2024 · similarity 0.86)
- Care-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson’s Disease Gait Assessment (NeurIPS 2025 · similarity 0.85)
- Breaking Data Silos in Parkinson’s Disease Diagnosis: An Adaptive Federated Learning Approach for Privacy-Preserving Facial Expression Analysis (AAAI 2025 · similarity 0.84)
- DECT: Harnessing LLM-assisted Fine-Grained Linguistic Knowledge and Label-Switched and Label-Preserved Data Generation for Diagnosis of Alzheimer’s Disease (AAAI 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
