Category: Obsessive Compulsive and Related Disorders
Keywords: Hoarding | Assessment
Presentation Type: Symposium
The prevalence rates of hoarding disorder (HD), adverse effects, limited treatment engagement, and challenges with clutter reduction speak to the need to enhance HD assessment and CBT treatment approaches. Hoarding symptoms are typically assessed using self-and/or assessor report as well as clinical interview instruments. To address the visual aspect of HD, the paper-based Clutter Image Rating (CIR) scale includes sets of 9 “clutter-equidistant” photos for each of 3 rooms (i.e., bedroom, living room, kitchen) that are used to rate clutter severity. Ratings may be provided by clients, family members, clinicians, and human service personnel. While the CIR has been validated, it can be subjective (requiring image rating by a human), potentially biased by the assessor’s perception, and costly, if a clinician performs a home-based assessment. This project aims to leverage the recent success of machine learning in visual recognition, to develop an automatic, computer-based rating of room clutter.
To date, we have collected a set of 1332 on-line images of hoarded rooms rated by a trained assessor using the CIR. We applied machine learning to automatically assess CIR values. In particular, we applied the support vector machine (SVM) as a classifier to either the histogram of oriented gradients (HOG) or convolutional neural network (CNN) features. Analysis of the dataset of 1332 on-line images resulted in a high correct classification rate within ±1 of the CIR rating. Large errors existed for some images.
Results are promising, and relatively consistent with ratings by trained professionals. Next steps include continuing to seek more accurate algorithms for rating CIR values. Automated real-time CIR assessment would remove human bias from CIR scoring, thus leading to a better precision and consistency across venues and time. Such an objective HD measure would also enhance the scalability of HD assessment, enable real-time monitoring and feedback, and facilitate the coordination of response among clinical and community providers.
Friday, November 17
3:30 PM – 5:00 PM
Saturday, November 18
8:30 AM – 10:00 AM
The asset you are trying to access is locked. Please enter your access key to unlock.