Aug 14 – 18, 2023
Europe/Berlin timezone

[P52-LH/BS]OCD Cognitive Therapy Game Using ERP(Exposure and Response Prevention)

Not scheduled
20m
Poster Poster(Thu)

Speaker

Ms Juhyeon Lee (ChungbukNationalUniversity)

Description

Obsessive-compulsive disorder is known for characteristics of repetitive-intrusive obsessive thought and persistent-repetitive behaviors that are intended to neutralize thoughts in order to reduce anxiety.
[1] The lifetime prevalence of obsessive-compulsive disorder is 2-3%. Obsessive-compulsive disorder is known to make patients waste time, cause severe distress, and impair their occupational and social functioning. [2]
Therapy for obsessive-compulsive disorder involves applying cognitive therapy and behavioral therapy techniques such as Exposure and Response Prevention (ERP). Treatment begins with patients acknowledging that they have obsessive-compulsive disorder and resulting symptoms are irrational beliefs. Subsequently, they are encouraged to overcome the situation on their own.
According to [3], case studies on cognitive-behavioral therapy, patients show improvement in their symptoms as the program progresses. It was important to encourage their voluntary participation to increase the continuity of treatment.

This game uses exposure and response prevention as a form of treatment. Patients are exposed to situations that cause anxiety and encouraged to avoid engaging in compulsive behavior. The game continuously observes patients to provide the appropriate form of exposure. When they overcome their anxiety, they get appropriate psychological rewards. In this way, patients can feel a sense of accomplishment and willpower, which can lead to the effectiveness of treatment.

  1. Symmetry compulsions: "Asymmetry Maker“
    In this game, the user must create asymmetry by moving only the symmetrical objects.
    If the user touches any asymmetrical objects, the score will be deducted. The difficulty level is adjusted by the degree of asymmetry and the number of objects.

  2. Checking compulsions: "Remembering actions"
    At the beginning of the game, the user performs everyday tasks that they would normally do when leaving their home. When the user reaches the destination after overcoming all obstacles, the game asks about one of the actions they did at home. The score is determined by how many "check" hints the user has used. The difficulty level is adjusted by the number of tasks to be done outside and the level of the questions.

  3. Hoarding compulsions: "Getting rid of unnecessary items"
    The user needs to throw away unnecessary items in the given situation. the score is reduced by the number of unnecessary items left. The difficulty level is adjusted by the ambiguity and quantity of the items to be discarded.

  4. Contamination compulsions: "Washing hands appropriately"
    The user needs to clean their house, and every time they clean, their hands gradually get more contaminated. If the user washes their hands too frequently, the score will be reduced. The difficulty level is adjusted by the number of objects and the degree of dirtiness.

Before starting the game, a survey is conducted to collect data on the level of the patient's OCD symptoms and their type to provide direction for the game. During the game, two types of data are collected. The first is the score data, which is used to visualize the user's score and show the degree of improvement. The second is the data on the factors that lead to point deduction in each game. These deduction factors are displayed as indicators, which help users understand and recognize their main OCD-related behaviors.
Both types of data are preprocessed and then trained with machine learning for each game. After that, the system predicts the next score and expected deduction factors, and recommends the difficulty and the type of next game accordingly.
System preprocesses the collected data for data analysis and stores it in a database using Firebase for management. The stored data is then utilized with the TensorFlow framework to predict the next outcomes of the user and recommend the difficulty level for the next game.

References

[1] Hwang, S., Noh, D., & Kim, C. (2010). The Meaning of Emotional Abnormalities in Obsessive-Compulsive Disorder. Journal of the Korean Academy of Anxiety and Mood Disorders, 6(1), 10-16.(kor)
[2] Oh, S., Kim, S., Han, J., Lee, J., Lee, T., Shin, M., & Kwon, J. (2017). Neurocognitive Dysfunction According to Untreated Duration of Obsessive-Compulsive Disorder: A Preliminary Study. Journal of Korean Neuropsychiatric Association, 24(2), 75-81.(kor)
[3] Park, J., & Kim, S. (2016). A Qualitative Case Study on the Experience of Participation in Cognitive-Behavioral Therapy Program for Patients with Obsessive-Compulsive Disorder. Qualitative Research, 2(1), 67-96.(kor)

Keywords OCD, Cognitive Therapy, ERP, Habituation Mechanism, Machine Learning

Primary authors

Mr Jintaek Lee (ChungbukNationalUniversity) Ms Jiyang Moon (WonKwangUniversity) Ms Juhyeon Lee (ChungbukNationalUniversity) Mr Mingon Kim (InJeUniversity)

Presentation materials

There are no materials yet.