JMIR Publications

ABSTRACT

Background:

Missingness in healthcare data poses significant challenges in the development and implementation of artificial intelligence (AI) and machine learning (ML) solutions. Identifying and addressing these challenges is critical to ensuring the continued growth and accuracy of these models as well as their equitable and effective use in healthcare settings.

Objective:

This study aims to explore challenges, opportunities, and potential solutions related to missingness in healthcare data for AI applications through the conduct of a virtual conference and thematic analysis of conference proceedings.

Methods:

A virtual conference was held in September 2022, attracting 861 registered participants with 164 attending the live event. The conference featured presentations and panel discussions by experts in AI, ML, and healthcare. Transcripts of the event were analyzed using the stepwise framework of Braun and Clark to identify key themes related to missingness in healthcare data.

Results:

Three principal themes emerged from the analysis: data quality and bias, human input in model development, and trust and privacy. Topics included the accuracy of predictive models, lack of inclusion of underrepresented communities, partnership with physicians and other populations, challenges with sensitive healthcare data, and fostering trust with patients and the healthcare community.

Conclusions:

Addressing the challenges of data quality, human input, and trust is vital when devising and employing machine learning algorithms in healthcare. Recommendations include expanding data collection efforts to reduce gaps and biases, involving medical professionals in the development and implementation of AI models, and developing clear ethical guidelines to safeguard patient privacy. Further research and ongoing discussions are needed to ensure these conclusions remain relevant as healthcare and AI continue to evolve.