| NSF Org: |
IIS Division of Information & Intelligent Systems |
| Recipient: |
|
| Initial Amendment Date: | July 18, 2019 |
| Latest Amendment Date: | July 18, 2019 |
| Award Number: | 1850287 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Wendy Nilsen
wnilsen@nsf.gov (703)292-2568 IIS Division of Information & Intelligent Systems CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | August 1, 2019 |
| End Date: | July 31, 2023 (Estimated) |
| Total Intended Award Amount: | $174,818.00 |
| Total Awarded Amount to Date: | $174,818.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
201 OLD MAIN UNIVERSITY PARK PA US 16802-1503 (814)865-1372 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
E329 Westgate Building University Park PA US 16802-7000 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | Smart and Connected Health |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
Approximately 8 million adults in the United States suffer from Post-traumatic stress disorder (PTSD) in a given year. It causes staggering individual and societal costs including higher mortality risk and significant national health care expenditure. While evidence-based PTSD treatments exist, their dissemination is limited due to logistical issues (e.g., cost and lack of trained professionals). To address these issues, recent studies have used mobile technologies for intervention and treatment delivery. However, ensuring engagement and adherence to these technologies remains a serious challenge. This project aims to address these engagement and adherence issues by developing a finite-state conversational agent (CA) for therapeutic content delivery and day-to-day illness management. Findings from this project can lead to more effective methods for keeping people engaged.
The proposed conversational agent will provide interactive psychoeducation, assessment tools, and personalized illness management strategies to patients with PTSD. It will support turn-taking and interactivity, which will result in active information flow in both ways rather than just passive delivery of information content. The implementation of the CA will involve dialogue management, handling user input for branching, and delivering appropriate message for a given context. For sustaining longitudinal user engagement, it will leverage the Supportive Accountability model with a specific focus on maintaining social presence and process accountability through personalization, goal setting, and contextualized support. The CA will be developed as a stand-alone module that can be incorporated into a mobile app. This will streamline the deployment of the system to patients. The project will collect real-world data to determine domain specific usability issues and information needs. It will also perform a systematic evaluation to understand the causal pathway between a CA and patient engagement. That is, it will assess what components of a CA work for patients, in what contexts, and for how long. Publications and source code resulting from the project will be publicly available.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Post-traumatic stress disorder is a global public health issue impacting millions of individuals. However, there remains a serious treatment gap -- individuals living with PTSD often do not have access to necessary resources. The project aimed to improve intervention delivery in a cost-effective and scalable way for this population. Specifically, the project focused on a conversational agent (CA) to support self-management of individuals living with PTSD. The research activities included designing a highly interactive CA (PTSDialogue) as well as evaluation with both clinical experts and individuals living with PTSD. These activities have resulted in knowledge dissemination to different communities including multiple articles and presentations. We have also made the CA publicly available. Furthermore, I have used the project outcomes for undergraduate and graduate education. The project has also supported training and professional development of students from underrepresented groups.
We designed and implemented PTSDialogue as a finite-state, rule-based CA. It supported the following interaction modules: take assessment, manage symptoms, get support, learn about PTSD, track progress, and daily symptom checker. We adapted these interaction modules from the PTSD Coach -- a mobile phone app developed by the Department of Veterans Affairs. We implemented a rule-based dialogue system to support user interactions. We have also developed two personas reflecting different conversation styles in the CA.
We evaluated the resultant CA in two steps. We first collected data from clinical experts to assess feasibility and identify potential concerns. We integrated feedback from clinical experts to update interactions and features in PTSDialogue. We then conducted semi-structured interviews with individuals living with PTSD to assess the feasibility and acceptance of PTSDialogue. Our findings show high acceptance of the developed CA from the participants. Our findings also identified opportunities and challenges in designing CAs to support longitudinal self-management and complement existing clinical care for PTSD. Furthermore, we have used the data to establish important design features for CAs aiming to provide effective support for this population (e.g., needs for personalization, interactions supporting educational activities, integration with clinical practices). Overall, the outcomes of the project can help to improve conversational interface design as well as reducing treatment gap in mental health care.
=== Product and Dissemination ===
The project activities have resulted in a number of products and steps to disseminate knowledge to different communities. We have made the PTSDialogue prototype publicly available for the community (ptsdialogue.github.io). We have also worked on the following manuscripts and presentations:
- Jingjing Sun. Designing for Supportive Accountability: Using Conversational Agents to Sustain Patient Engagement in PTSD. Poster presented at Penn State Undergraduate Exhibition for Research. 2020.
- Han, Hee Jeong, et al. PTSDialogue: Designing a Conversational Agent to Support Individuals with Post-Traumatic Stress Disorder. Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers. 2021.
- Han, Hee Jeong, et al. Preliminary Evaluation of a Conversational Agent to Support Self-management of Individuals Living With Posttraumatic Stress Disorder: Interview Study With Clinical Experts. JMIR Formative Research 7 (2023): e45894.
- (Under Preparation) Assessing Acceptance and Feasibility of a Conversational Agent to Support Individuals Living with Post-traumatic Stress Disorder.
- (Under Preparation). Conversational User Interfaces for Health and Wellbeing. Foundations and Trends in Human–Computer Interaction. (Monograph)
=== Educational Activities and Mentoring ===
This project supported both undergraduate and graduate training. I have leveraged the project outcomes for an undergraduate course (HCDD 340: Human-Centered Design for Mobile Computing). Students in this class worked on developing chatbots for health interventions. By using the dialogues and prototypes from this project, I was able to provide a hands-on introduction to different methods and tools for designing and developing mobile systems for health intervention. Similarly, I used the project outcomes in CSCW (IST 525) -- a foundational graduate course in our college.
I have also actively trained and mentored both undergraduate and graduate students throughout the project. I supervised an undergraduate student for this project. Following her positive experience in this project, she was interested in exploring a research career. She is currently working on her PhD in a different institute. The project has also supported research training and professional development of two PhD students at Penn State. These students all are from underrepresented groups. I have also shared the project outcomes to an interdisciplinary research group at Penn State that focuses on conversational agents and interactive technologies -- Communication and Human-AI Technology (CHAT). This research group provided opportunities for collaborative work as well as student training and professional development for graduate students and postdocs at Penn State.
Overall, while COVID-19 caused significant disruption to our initial plan, the project team was able to make necessary changes and achieve significant research, education, and mentoring milestones. The resultant outcomes and findings have the potential to advance conversational interface design as well as improving both clinical outcomes and quality of life for individuals with PTSD.
Last Modified: 11/29/2023
Modified by: Saeed Abdullah
Please report errors in award information by writing to: awardsearch@nsf.gov.
