Towards an Explainable AI Platform to Study Interruptions in Cancer Radiation Therapy.

Radiation therapy interruptions drive cancer treatment failures; they represent an untapped opportunity for improving outcomes and narrowing treatment disparities. This research reports on the early development of the X-CART platform, which uses explainable AI to model cancer treatment outcome metrics based on high-dimensional associations with our local social determinants of health dataset to identify and explain causal pathways linking social disadvantage with increased radiation therapy interruptions.

Digital Personal Health Coaching Platform for Promoting Human Papillomavirus Infection Vaccinations and Cancer Prevention: Knowledge Graph-Based Recommendation System.

BACKGROUND: Health promotion can empower populations to gain more control over their well-being by using digital interventions that focus on preventing the root causes of diseases. Digital platforms for personalized health coaching can improve health literacy and information-seeking behavior, leading to better health outcomes. Personal health records have been designed to enhance patients' self-management of a disease or condition. Existing personal health records have been mostly designed and deployed as a supplementary service that acts as views into electronic health records. OBJECTIVE: We aim to overcome some of the limitations of electronic health records. This study aims to design and develop a personal health library (PHL) that generates personalized recommendations for human papillomavirus (HPV) vaccine promotion and cancer prevention. METHODS: We have designed a proof-of-concept prototype of the Digital Personal Health Librarian, which leverages machine learning; natural language processing; and several innovative technological infrastructures, including the Semantic Web, social linked data, web application programming interfaces, and hypermedia-based discovery, to generate a personal health knowledge graph. RESULTS: We have designed and implemented a proof-of-the-concept prototype to showcase and demonstrate how the PHL can be used to store an individual's health data, for example, a personal health knowledge graph. This is integrated with web-scale knowledge to support HPV vaccine promotion and prevent HPV-associated cancers among adolescents and their caregivers. We also demonstrated how the Digital Personal Health Librarian uses the PHL to provide evidence-based insights and knowledge-driven explanations that are personalized and inform health decision-making. CONCLUSIONS: Digital platforms such as the PHL can be instrumental in improving precision health promotion and education strategies that address population-specific needs (ie, health literacy, digital competency, and language barriers) and empower individuals by facilitating knowledge acquisition to make healthy choices.

Defining Radiation Treatment Interruption Rates During the COVID-19 Pandemic: Findings From an Academic Center in an Underserved Urban Setting.

PURPOSE: Our purpose was to characterize radiation treatment interruption (RTI) rates and their potential association with sociodemographic variables in an urban population before and during the COVID-19 pandemic. METHODS AND MATERIALS: Electronic health records were retrospectively reviewed for patients treated between January 1, 2015, and February 28, 2021. Major and minor RTI were defined as ≥5 and 2 to 4 unplanned cancellations, respectively. RTI was compared across demographic and clinical factors and whether treatment started before or after COVID-19 onset (March 15, 2020) using multivariate logistic regression analysis. RESULTS: Of 2,240 study cohort patients, 1,938 started treatment before COVID-19 and 302 started after. Patient census fell 36% over the year after COVID-19 onset. RTI rates remained stable or trended downward, although subtle shifts in association with social and treatment factors were observed on univariate and multivariate analysis. Interaction of treatment timing with risk factors was modest and limited to treatment length and minor RTI. Despite the stability of cohort-level findings showing limited associations with race, geospatial mapping demonstrated a discrete geographic shift in elevated RTI toward Black, underinsured patients living in inner urban communities. Affected neighborhoods could not be predicted quantitatively by local COVID-19 transmission activity or social vulnerability indices. CONCLUSIONS: This is the first United States institutional report to describe radiation therapy referral volume and interruption patterns during the year after pandemic onset. Patient referral volumes did not fully recover from an initial steep decline, but local RTI rates and associated risk factors remained mostly stable. Geospatial mapping suggested migration of RTI risk toward marginalized, minority-majority urban ZIP codes, which could not otherwise be predicted by neighborhood-level social vulnerability or pandemic activity. These findings signal that detailed localization of highest-risk communities could help focus radiation therapy access improvement strategies during and after public health emergencies. However, this will require replication to validate and broaden relevance to other settings.

A Digital Personal Health Library for Enabling Precision Health Promotion to Prevent Human Papilloma Virus-Associated Cancers.

Human papillomavirus (HPV) causes the most prevalent sexually transmitted infection (STI) in the United States. Sexually active young adults are susceptible to HPV, accounting for approximately 50% of new STIs. Oncogenic HPV subtypes 16 and 18 are associated with squamous intraepithelial lesions and cancers and are mostly preventable through prophylactic HPV vaccination. Accordingly, this study's objectives are to (1) summarize SDoH barriers and implication for low HPV vaccination rates among young adults (18-26 years), (2) propose a digital health solution that utilizes the PHL to collect, integrate, and manage personalized sexual and health information, and (3) describe the features of the PHL-based app. Through the application of novel techniques from artificial intelligence, specifically knowledge representation, semantic web, and natural language processing, this proposed PHL-based application will compile clinical, biomedical, and SDoH data from multi-dimensional sources. Therefore, this application will provide digital health interventions that are customized to individuals' specific needs and capacities. The PHL-based application could promote management and usage of personalized digital health information to facilitate precision health promotion thereby, informing health decision-making regarding HPV vaccinations, routine HPV/STI testing, cancer screenings, vaccine safety/efficacy/side effects, and safe sexual practices. In addition to detecting vaccine hesitancy, disparities and perceived barriers, this application could address participants' specific needs/challenges with navigating health literacy, technical skills, peer influence, education, language, cultural and spiritual beliefs. Precision health promotion focused on improving knowledge acquisition and information-seeking behaviors, promoting safe sexual practices, increasing HPV vaccinations, and facilitating cancer screenings could be effective in preventing HPV-associated cancers.