Research map / Video / Video segmentation and tracking
MedSat: A Public Health Dataset for England Featuring Medical Prescriptions and Satellite Imagery
Sanja Scepanovic, Ivica Obadic, Sagar Joglekar, Laura GIUSTARINI, Cristiano Nattero, Daniele Quercia, Xiao Xiang Zhu
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 |
|---|---|---|---|
| combine environmental and sociodemographic features instead of environmental only (ablation) | LightGBM · opioids | R2: 0.52 -> 0.6 | Improved |
| combine environmental and sociodemographic features instead of sociodemographic only (ablation) | LightGBM · diabetes | R2: 0.26 -> 0.35 | Improved |
| combine environmental and sociodemographic features instead of environmental only (ablation) | LightGBM · diabetes | R2: 0.19 -> 0.35 | Improved |
| add environmental features over image-only features (ablation) | LightGBM · opioids | R2: 0.19 -> 0.52 | Improved |
| use image features only (no env/soc) (ablation) | LightGBM · diabetes | R2: 0.35 -> 0.02 | Hurt |
| use sociodemographic instead of environmental features (ablation) | LightGBM · depression | R2: 0.42 -> 0.41 | No clear effect |
| use environmental instead of sociodemographic features (ablation) | LightGBM · total prescriptions | R2: 0.22 -> 0.26 | Improved |
| use sociodemographic instead of environmental features (ablation) | LightGBM · diabetes | R2: 0.19 -> 0.26 | Improved |
| use Spatial Lag Model with sociodemographic features instead of image features (ablation) | SLM · opioids | variance explained: 28% -> 52% | Improved |
| use LightGBM instead of FNN | LightGBM · prescription prediction | R2 | Improved |
| predict mental condition prescriptions versus other conditions | LightGBM · depression vs diabetes | R2: 0.35 -> 0.50 | Improved |
Closest papers by meaning
- How Your Location Relates to Health: Variable Importance and Interpretable Machine Learning for Environmental and Sociodemographic Data (AAAI 2025 · similarity 0.88)
- GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding (NeurIPS 2025 · similarity 0.81)
- SpaCE: The Spatial Confounding Environment (ICLR 2024 · similarity 0.81)
- Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth (NeurIPS 2024 · similarity 0.80)
- SPATIALEPIBENCH: Benchmarking Spatial Information and Epidemic Priors in Forecasting (NeurIPS 2026 · similarity 0.80)
- Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial Associations (NeurIPS 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.
