Can an Algorithm be My Healthcare Proxy?

Planning for death is not a process in which everyone participates. Yet a lack of planning can have vast impacts on a patient's well-being, the well-being of her family, and the medical community as a whole. Advance Care Planning (ACP) has been a field in the United States for a half-century. Many modern techniques prompting patients to think about end of life (EOL) involve short surveys or questionnaires. Different surveys are targeted to different populations (based off of likely disease progression or cultural factors, for instance), are designed with different intentions, and are administered in different ways. There has been recent work using technology to increase the number of people using advance care planning tools. However, modern techniques from machine learning and artificial intelligence could be employed to make additional changes to the current ACP process. In this paper we will discuss some possible ways in which these tools could be applied. We will discuss possible implications of these applications through vignettes of patient scenarios. We hope that this paper will encourage thought about appropriate applications of artificial intelligence in ACP as well as implementation of AI in order to ensure intentions are honored.

[1]  D. Schillinger,et al.  Engaging Diverse English- and Spanish-Speaking Older Adults in Advance Care Planning: The PREPARE Randomized Clinical Trial , 2018, JAMA internal medicine.

[2]  H. Mcdonald,et al.  Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: a systematic review. , 2005, JAMA.

[3]  C. Sabatino.  Advance Care Planning Tools That Educate, Engage, and Empower , 2014 .

[4]  Nir Ailon,et al.  An Active Learning Algorithm for Ranking from Pairwise Preferences with an Almost Optimal Query Complexity , 2010, J. Mach. Learn. Res..

[5]  D. Patrick,et al.  Shared priorities for the end-of-life period. , 2009, Journal of pain and symptom management.

[6]  E.H. Shortliffe,et al.  Knowledge engineering for medical decision making: A review of computer-based clinical decision aids , 1979, Proceedings of the IEEE.

[7]  S. H. Regli,et al.  Machine Learning Approaches to Predict 6-Month Mortality Among Patients With Cancer , 2019, JAMA network open.

[8]  WangWei,et al.  Recommender system application developments , 2015 .

[9]  D. Waldrop,et al.  Decisions by Default: Incomplete and Contradictory MOLST in Emergency Care. , 2017, Journal of the American Medical Directors Association.

[10]  C Lovis,et al.  Attitude of Physicians Towards Automatic Alerting in Computerized Physician Order Entry Systems , 2012, Methods of Information in Medicine.

[11]  S. Halpern,et al.  Approximately One In Three US Adults Completes Any Type Of Advance Directive For End-Of-Life Care. , 2017, Health affairs.

[12]  Ryan Calo,et al.  There is a blind spot in AI research , 2016, Nature.

[13]  S. Tamang,et al.  Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data , 2018, JAMA internal medicine.

[14]  H. Llewellyn-Thomas,et al.  Decision Support for Patients , 2013, Medical care research and review : MCRR.

[15]  Y. Lee,et al.  Exploring Patient Values in Medical Decision Making: A Qualitative Study , 2013, PloS one.

[16]  Craig Boutilier,et al.  A POMDP formulation of preference elicitation problems , 2002, AAAI/IAAI.

[17]  Nick Hanley,et al.  Using conjoint analysis to quantify public preferences over the environmental impacts of wind farms. An example from Spain , 2002 .

[18]  L. Anderson,et al.  Completion of advance directives among U.S. consumers. , 2014, American journal of preventive medicine.

[19]  P. Bomba,et al.  POLST: An improvement over traditional advance directives , 2012, Cleveland Clinic Journal of Medicine.

[20]  Vincent Conitzer,et al.  Artificial Artificial Intelligence: Measuring Influence of AI 'Assessments' on Moral Decision-Making , 2020, AIES.

[21]  L. Winter.  Patient values and preferences for end-of-life treatments: are values better predictors than a living will? , 2013, Journal of palliative medicine.

[22]  H. Glick.  The right-to-die: state policymaking and the elderly. , 1991, Journal of aging studies.

[23]  Andrew Y. Ng,et al.  Improving palliative care with deep learning , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[24]  Dimitrios I. Fotiadis,et al.  Machine learning applications in cancer prognosis and prediction , 2014, Computational and structural biotechnology journal.

[25]  Wei Wang,et al.  Recommender system application developments: A survey , 2015, Decis. Support Syst..

[26]  J. Savulescu,et al.  Patient values informing medical treatment: a pilot community and advance care planning survey , 2017, BMJ Supportive & Palliative Care.

[27]  R. Kane,et al.  Decision Aids for Advance Care Planning: An Overview of the State of the Science , 2014, Annals of Internal Medicine.

[28]  R. Gramling,et al.  End-of-Life Preferences, Length-of-Life Conversations, and Hospice Enrollment in Palliative Care: A Direct Observation Cohort Study among People with Advanced Cancer. , 2019, Journal of palliative medicine.

[29]  Kevin M. Heard,et al.  Implementation of a real-time computerized sepsis alert in nonintensive care unit patients* , 2011, Critical care medicine.

[30]  J. Curtis,et al.  Psychometric characteristics of a quality of communication questionnaire assessing communication about end-of-life care. , 2006, Journal of palliative medicine.

[31]  S. Hickman,et al.  The Quality of Physician Orders for Life-Sustaining Treatment Decisions: A Pilot Study. , 2017, Journal of palliative medicine.

[32]  R. Fine,et al.  Early Experience with Digital Advance Care Planning and Directives, a Novel Consumer-Driven Program , 2016, Proceedings.

[33]  Ming Yin,et al.  Understanding the Effect of Accuracy on Trust in Machine Learning Models , 2019, CHI.

[34]  C. E. Kahn.  Decision aids in radiology. , 1996, Radiologic clinics of North America.