Logi-PAR: Logic-Infused Patient Activity Recognition via Differentiable Rule
This work addresses the critical need for explainable and auditable patient activity recognition in clinical settings, which is crucial for improving patient safety and quality of care by providing explicit logical reasoning beyond mere classification.
This paper introduces Logi-PAR, a framework for Patient Activity Recognition that integrates contextual fact fusion and neural-guided differentiable rules to infer not only what activity is occurring but also why. It achieves state-of-the-art performance on clinical benchmarks (VAST and OmniFall), outperforming Vision-Language Models and transformer baselines, and can provide auditable explanations and counterfactual interventions (e.g., a 65% risk reduction with assistance).
Patient Activity Recognition (PAR) in clinical settings uses activity data to improve safety and quality of care. Although significant progress has been made, current models mainly identify which activity is occurring. They often spatially compose sub-sparse visual cues using global and local attention mechanisms, yet only learn logically implicit patterns due to their neural-pipeline. Advancing clinical safety requires methods that can infer why a set of visual cues implies a risk, and how these can be compositionally reasoned through explicit logic beyond mere classification. To address this, we proposed Logi-PAR, the first Logic-Infused Patient Activity Recognition Framework that integrates contextual fact fusion as a multi-view primitive extractor and injects neural-guided differentiable rules. Our method automatically learns rules from visual cues, optimizing them end-to-end while enabling the implicit emergence patterns to be explicitly labelled during training. To the best of our knowledge, Logi-PAR is the first framework to recognize patient activity by applying learnable logic rules to symbolic mappings. It produces auditable why explanations as rule traces and supports counterfactual interventions (e.g., risk would decrease by 65% if assistance were present). Extensive evaluation on clinical benchmarks (VAST and OmniFall) demonstrates state-of-the-art performance, significantly outperforming Vision-Language Models and transformer baselines. The code is available via: https://github.com/zararkhan985/Logi-PAR.git}