Applying a Chatbot to Geriatric Patients in Psychiatric Clinics: A Pilot Study

This study will use the caring chatbot developed by the Taipei University of Technology team to provide care for participants and use robots to talk to them to collect daily changes in mood, sleep, and activities, and analyze the factors that affect the physical and mental health of the elderly.

Study Overview

• Status: Not yet recruiting
• Conditions: Loneliness; Geriatric Depression
• Intervention / Treatment: Other: caring chatbot

Detailed Description

The prevalence of anxiety and depression in middle-aged and elderly people is quite high. Among the risk factors for illness, "loneliness" is closely related to the physical and mental health of the elderly: the higher the loneliness of the elderly, the more likely to develop unhealthy lifestyle habits and emotional symptoms such as depression and anxiety. Depression and anxiety are often comorbid, and the diagnoses of the two groups have many symptoms that overlap each other. Emotional symptoms that have not been effectively treated have a great impact on the quality of life, and the drug treatment of emotional disorders in the elderly is more difficult. In addition to medication, maintaining a healthy lifestyle is also conducive to the control of emotional disorders.

Information technology has been used in supplementary medical care and maintenance of physical and mental health for decades. However, reviewing the literature, there is less research on applications developed in cooperation between the information field and the field of psychiatric medical care, and there are no applications developed for the mental health of middle-aged and elderly people.

This study will use the caring chatbot developed by the National Taipei University of Technology team to provide care for the participants enrolled from the psychiatric outpatient department, and use the chatbot to talk to them to collect daily changes in mood, sleep, and activities, and analyze the factors that affect the mental health of the elderly.

This research anticipates the following goals:

1. With the chatbot developed, it provides care for subjects every day and collects their daily changes in mood, sleep, and activities.
2. Analyze the relationship between robot interaction and emotional changes, and evaluate the impact of chatbot intervention on the health behavior of the case.

• Study Type: Interventional
• Enrollment (Anticipated): 75
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Ya-Hsin Chou, MD; Phone Number: 2485 (03)3281288; Email: b9302015@cgmh.org.tw

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 55 years to 110 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

Inclusion Criteria:

• with the diagnosis of persistent depressive disorder, major depressive disorder, general anxiety disorder, panic disorder, or agoraphobia
• the condition of their disease is relatively stable (defined as no thought of death and no medication adjustment in the recent 3 months).
• Have a personal mobile phone or communicator that can connect to the Internet

Exclusion Criteria:

• Those who are unwilling to participate in this research
• Those who have poor assessment ability by clinicians and cannot understand the content of the questionnaire; or those who cannot continue to complete the test due to their physical condition
• Comorbid schizophrenia or bipolar disorder
• Patients with dementia, brain injury, substance abuse, and stroke

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: caring chatbot; The investigators will enroll participants aged over 55 in the psychiatric outpatient department. The participants will get a one-month caring chatbot and can interact with the chatbot freely.	Other: caring chatbot; The investigators will use the developed caring chatbot to provide care to the cases and to collect case treatment data and interaction data between the case and the caring chatbot.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
acceptance measured by seven-point Likert scales	Satisfacation (How satisfied were you with Chatbot?), usability (How easy was talking to Chatbot?), continue (How much would you like to continue working with Chatbot?) and adherence (How likely is it that you will follow Chatbot's advice?) were measured by single items on seven-point Likert scales (with 1= "not at all" and 7="very much").	at the end of one-month-intervention of the caring chatbot

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Change from baseline "loneliness" measured by UCLA Loneliness Scale	The UCLA Loneliness Scale (version 3) is a 20-item measure that assesses how often a person feels disconnected from others. Using a 4-point rating scale (1= never; 4 = always), participants answer 20 questions, and researchers later reverse-code the positively worded items so that high values mean more loneliness.	before and at the end of one-month-intervention of the caring chatbot
Change from baseline "depression" measured by Geriatric Depression Scale-Short Form (GDS-15)	Geriatric Depression Scale (GDS) is designed for the older population. A Short Form GDS consisting of 15 questions. Of the 15 items, 10 indicated the presence of depression when answered positively, while the rest indicated depression when answered negatively. Scores of 5-8 indicate mild depression; 9-11 indicate moderate depression; 12-15 indicate severe depression.	before and at the end of one-month-intervention of the caring chatbot
Change from baseline "anxiety" measured by Hospital Anxiety and Depression Scale- Anxiety subscale	Hospital Anxiety and Depression Scale (HADS) is developed for people with physical illnesses. This scale includes a total of 14 questions. There are 7 questions about anxiety and depression, each with a 4-point scoring method (0-3 points). The higher the total score, the greater the anxiety or the greater the depression. Due to the high overlap between the topics of the depression subscale and the GDS, this study only uses the anxiety subscale.	before and at the end of one-month-intervention of the caring chatbot
Change from baseline "quality of life" measured by Short Form Quality Life Sale (SF-12)	Short Form Quality Life Sale (SF-12) is the most commonly used questionnaire in the study of the quality of life of the elderly, with a total score ranging from 13~43. A higher score reflects a better life quality.	before and at the end of one-month-intervention of the caring chatbot
Change from baseline "physical activity" measured by International Physical Activity Questionnaire Self-Administered Short Version (IPAQ-SS)	International Physical Activity Questionnaire Self-Administered Short Version (IPAQ-SS) measures the physical activity of the participant in the past seven days by self-filled method. The questionnaire is consisted of four domains: (1)during transportation, (2) at work, (3) during household and gardening tasks and (4) during leisure time, including exercise and sport participation. In each of the four domains the number of days per week and time per day spent in both moderate and vigorous activity are recorded.	before and at the end of one-month-intervention of the caring chatbot

Collaborators and Investigators

• Sponsor: Chang Gung Memorial Hospital
• Collaborators: National Taipei University of Technology

Study record dates

Study Major Dates

• Study Start (Anticipated): September 27, 2021
• Primary Completion (Anticipated): January 31, 2022
• Study Completion (Anticipated): July 31, 2022

Study Registration Dates

• First Submitted: September 1, 2021
• First Submitted That Met QC Criteria: September 22, 2021
• First Posted (Actual): September 23, 2021

Study Record Updates

• Last Update Posted (Actual): September 23, 2021
• Last Update Submitted That Met QC Criteria: September 22, 2021
• Last Verified: August 1, 2021

More Information

Terms related to this study

• Keywords: chatbot; conversational agent; geriatric psychiatry
• Additional Relevant MeSH Terms: Behavioral Symptoms; Depression
• Other Study ID Numbers: 202001915B0C601

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No