Developing an NLP-Augmented Support System for Prostate Cancer Patients and Families: An Iterative, User-Centered Approach (Preprint)

Abstract

<sec> <title>BACKGROUND</title> Prostate cancer patients and their families face significant challenges during transitions from diagnosis to treatment and post-treatment self-management. </sec> <sec> <title>OBJECTIVE</title> To develop the Interactive Prostate Cancer Information, Communication, and Support Program (iPICS), an NLP-augmented eHealth platform designed to enhance care continuity, support decision-making, and improve health outcomes for patients and families. </sec> <sec> <title>METHODS</title> This study employed an iterative, user-centered design approach to design, develop, and refine iPICS, guided by Responsible AI principles. The iterative development process involved semi-structured interviews and focus groups with prostate cancer patients and family members (i.e., participants) from diverse sociodemographic backgrounds. Thematic analysis was conducted to identify critical functionalities and content. Participants’ feedback was integrated during the platform’s refinement to ensure iPICS’ usability, accessibility, security, and functionality. </sec> <sec> <title>RESULTS</title> A total of 18 prostate cancer patients and 7 family members participated in two semi-structured interviews and 17 focus groups. Participants identified five major themes relevant to iPICS development: functional requirements, user interface design recommendations, content and visualization needs, program delivery preferences, and privacy and data security concerns. These themes informed the prototype design, development, and refinement of iPICS, which include three core components: Inform, a multimedia health information resource hub; Dialog, a recording and dialogue summarization tool for patient-provider communication; and Snap, a moderated online peer-support forum. Key features of iPICS include evidence-based, guideline-informed Multimedia health information paired with National Institutes of Health sponsored MedlinePlus articles in Inform, keyword extraction and hyperlinking in Dialog, and peer-support functionalities moderated by nurses to ensure safety and reliability in Snap. iPICS development was also compliant with HIPAA standards and aligned with user needs while ensuring usability throughout deployment. </sec> <sec> <title>CONCLUSIONS</title> The NLP-augmented iPICS was developed using an iterative user-centered design approach to support prostate cancer patients and their families. It offers a scalable solution for ethical, transparent, and inclusive supportive survivorship care, particularly during critical care transitions. </sec>

Ähnliche Arbeiten