Community perspectives on AI/ML and health equity: AIM-AHEAD nationwide stakeholder listening sessions.

Artificial intelligence and machine learning (AI/ML) tools have the potential to improve health equity. However, many historically underrepresented communities have not been engaged in AI/ML training, research, and infrastructure development. Therefore, AIM-AHEAD (Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity) seeks to increase participation and engagement of researchers and communities through mutually beneficial partnerships. The purpose of this paper is to summarize feedback from listening sessions conducted by the AIM-AHEAD Coordinating Center in February 2022, titled the "AIM-AHEAD Community Building Convention (ACBC)." A total of six listening sessions were held over three days. A total of 977 people registered with AIM-AHEAD to attend ACBC and 557 individuals attended the listening sessions across stakeholder groups. Facilitators led the conversation based on a series of guiding questions, and responses were captured through voice and chat via the Slido platform. A professional third-party provider transcribed the audio. Qualitative analysis included data from transcripts and chat logs. Thematic analysis was then used to identify common and unique themes across all transcripts. Six main themes arose from the sessions. Attendees felt that storytelling would be a powerful tool in communicating the impact of AI/ML in promoting health equity, trust building is vital and can be fostered through existing trusted relationships, and diverse communities should be involved every step of the way. Attendees shared a wealth of information that will guide AIM-AHEAD's future activities. The sessions highlighted the need for researchers to translate AI/ML concepts into vignettes that are digestible to the larger public, the importance of diversity, and how open-science platforms can be used to encourage multi-disciplinary collaboration. While the sessions confirmed some of the existing barriers in applying AI/ML for health equity, they also offered new insights that were captured in the six themes.

Genetic and Survey Data Improves Performance of Machine Learning Model for Long COVID.

Over 200 million SARS-CoV-2 patients have or will develop persistent symptoms (long COVID). Given this pressing research priority, the National COVID Cohort Collaborative (N3C) developed a machine learning model using only electronic health record data to identify potential patients with long COVID. We hypothesized that additional data from health surveys, mobile devices, and genotypes could improve prediction ability. In a cohort of SARS-CoV-2 infected individuals (n=17,755) in the All of Us program, we applied and expanded upon the N3C long COVID prediction model, testing machine learning infrastructures, assessing model performance, and identifying factors that contributed most to the prediction models. For the survey/mobile device information and genetic data, extreme gradient boosting and a convolutional neural network delivered the best performance for predicting long COVID, respectively. Combined survey, genetic, and mobile data increased specificity and the Area Under Curve the Receiver Operating Characteristic score versus the original N3C model.

BioEve Search: A Novel Framework to Facilitate Interactive Literature Search.

Background. Recent advances in computational and biological methods in last two decades have remarkably changed the scale of biomedical research and with it began the unprecedented growth in both the production of biomedical data and amount of published literature discussing it. An automated extraction system coupled with a cognitive search and navigation service over these document collections would not only save time and effort, but also pave the way to discover hitherto unknown information implicitly conveyed in the texts. Results. We developed a novel framework (named "BioEve") that seamlessly integrates Faceted Search (Information Retrieval) with Information Extraction module to provide an interactive search experience for the researchers in life sciences. It enables guided step-by-step search query refinement, by suggesting concepts and entities (like genes, drugs, and diseases) to quickly filter and modify search direction, and thereby facilitating an enriched paradigm where user can discover related concepts and keywords to search while information seeking. Conclusions. The BioEve Search framework makes it easier to enable scalable interactive search over large collection of textual articles and to discover knowledge hidden in thousands of biomedical literature articles with ease.