Fig. 6: The COBRA score exploits clinically-relevant structure.
From: Quantifying impairment and disease severity using AI models trained on healthy subjects
a The first row show scatterplots of the clinical Fugl-Meyer assessment and the proposed COBRA score, obtained from wearable-sensor data. In the left graph, the COBRA score is computed only using data identified as clinically relevant (i.e. corresponding to motion actions). In the middle graph, the score is computed using the remaining data. In the right graph, it is computed using all of the data. The second row shows the same scatterplots, with the only difference that the COBRA score is obtained from video data. The COBRA score based on clinically-relevant data achieves a higher correlation with the clinical assessment in both cases. b The graphs show scatterplots of the Kellgren-Lawrence grade and the proposed COBRA score, obtained from knee MRI scans. In the left graph, the COBRA score is computed only using data identified as clinically relevant (i.e. corresponding to cartilage tissue). In the middle graph, the score is computed using the remaining data. In the right graph, it is computed using all of the data. The COBRA score using clinically relevant data again achieves a higher correlation with the clinical assessment.
