Though algorithms are chosen to eliminate bias in the Learning Health Systems (LHS) that support medical decision making, we are left with unconscious bias present in data due to lack of representation for marginalized populations, particularly in palliative care. Medical practitioners often lack historical foundations for decision making for patients in underrepresented populations, which lead to palliative patients being subjected to uneven quality of care and an absence of treatment goals due to a lack of advocacy and other challenges.

Data Ethics and Digital Privacy in Learning Health Systems for Palliative Medicine reviews the ethical foundations that drive our approach, data collection (public data, private data and data privacy), data stratification methodologies to support marginalized and intersectional populations, analysis techniques, algorithmic development to maintain privacy, survival analysis, result interpretation, LHS development, and LHS implementation. These methodologies address the HIPAA Privacy Rule, which clearly establishes the standard to protect digitally held health care data.

Informing both research and practice, Data Ethics and Digital Privacy in Learning Health Systems for Palliative Medicine brings attention to an important issue that lies at the intersection of medicine, science, and digital technology and communication.