AI-Driven Insights Into End-Of-Life Decision-Making: Ethical, Legal, And Clinical Perspectives On Leveraging Machine Learning To Improve Patient Autonomy And Palliative Care Outcomes

Abstract

Rapid advances in the development of machine learning algorithms provide an opportunity to revolutionize treatment decisions at the end of life, particularly for patients who are unable to communicate their own wishes. However, current legal regulation jars with this increased potential and often precludes vital steps from being practically taken in the clinical sphere. The medical sphere is further confined by current incomplete ethical and legal guidance on how predictive algorithms should be deployed in the hospital setting in general. After an analysis of the application of machine learning and deep learning to end-of-life outcomes, our paper outlines how machine learning can be used for principled end-of-life decision-making, tightly drawing the implications of the proposed solutions from pertinent ethical theory and case law.
Historically, the prediction of terminal prognostic outcomes and the formulation of potential competing legal, ethical, and clinical responses to these predictions have taken place in parallel. On the one hand, clinicians have been equipped with a range of prognostic tools to aid estimates of life expectancy for patients approaching the end of their lives. On the other, legal guidance has been developed to codify the timing at which life support can properly be withheld or withdrawn from terminally unwell patients. Nowadays, predictive algorithmic advances have the capacity to revolutionize individualized terminal prognosis. Data analysis significantly improves palliative care outcomes and can ensure that patients — who are traditionally vulnerable to clinicians' well-intentioned overoptimism — can be provided with transparent, personalized information about the end of their lives. With clearer knowledge, the decision to forgo aggressive therapy and move towards a palliative care approach can better correspond to a rational patient's end-of-life preferences.