Interpretable Machine Learning Models for the Digital Clock Drawing Test
This work addresses the need for more accurate and interpretable tools in neuropsychological screening for cognitive conditions, representing an incremental improvement over current clinical practices.
The researchers tackled the problem of automating the scoring of the Digital Clock Drawing Test (dCDT) for cognitive screening by developing machine learning models that analyze pen stroke data, resulting in systems that substantially outperformed existing clinician scoring methods in accuracy while maintaining interpretability.
The Clock Drawing Test (CDT) is a rapid, inexpensive, and popular neuropsychological screening tool for cognitive conditions. The Digital Clock Drawing Test (dCDT) uses novel software to analyze data from a digitizing ballpoint pen that reports its position with considerable spatial and temporal precision, making possible the analysis of both the drawing process and final product. We developed methodology to analyze pen stroke data from these drawings, and computed a large collection of features which were then analyzed with a variety of machine learning techniques. The resulting scoring systems were designed to be more accurate than the systems currently used by clinicians, but just as interpretable and easy to use. The systems also allow us to quantify the tradeoff between accuracy and interpretability. We created automated versions of the CDT scoring systems currently used by clinicians, allowing us to benchmark our models, which indicated that our machine learning models substantially outperformed the existing scoring systems.