Can Big Data and AI Improve End-of-Life Care?

Bioethics in the News logoThis post is a part of our Bioethics in the News series

By Tom Tomlinson, PhD

A recently reported study claims to more accurately predict how much longer patients will live. Researchers at Stanford University assigned a neural network computer the task of training itself to develop an artificial intelligence model that would predict if a patient would die within 3-12 months of any given date. The computer trained on the EMR records of 177,011 Stanford patients, 12,587 of whom had a recorded date of death. The model was validated and tested on another 44,273 patient records. You can find the wonky details here.

The model can predict with 90% accuracy whether a patient will die within the window.

Now this is a lot better than individual physicians typically do. It’s not just that such predictions are fraught with uncertainty, given how many complex, interacting factors are at work that only a computer can handle. If uncertainty were the only factor, one would expect physicians’ prognostic errors to be randomly distributed. But they are not. Clinicians overwhelmingly err on the optimistic side, so the pessimists among them turn out to be right more often.

The study takes accurately predicting death to be a straightforwardly useful thing. It gives patients, families and clinicians more reliable, trustworthy information that is of momentous significance, better informing critical questions. Will I be around for my birthday? Is it time to get palliative or hospice care involved?

The study’s authors are particularly hopeful that the use of this model will prompt more timely use of palliative care services, and discourage overuse of chemotherapy, hospitalization, and admission to intensive care units in the last months of life—all well-documented problems in the care of terminally ill people, especially those dying of cancer. So this is a potentially very significant use of “big data” AI research methods to address major challenges in end-of-life care.

But making real progress toward these goals will take a lot more than this model can deliver.

36302888621_ad3b5fc2e1_h

Image description: A graphic on a blue gradient background shows the silhouette of an individual in the foreground containing colorful computer motherboard graphics. In the background are silhouettes of twelve more individuals standing in a line and containing black and white computer motherboard graphics. Image source: Maziani Sabudin/Flickr Creative Commons.

The first question is how it could inform decisions about what to do next. The limitation here is that the model uses events from my medical history occurring prior to the time it’s asked to predict my survival. Perhaps the decision I’m facing is whether to go for another round of chemotherapy for metastatic cancer; or whether instead to enter a Phase 3 clinical trial for a new therapeutic agent. The question (one might think) is what each option will add to my life expectancy.

Now if the training database had some number of patients who took that particular chemotherapy option, then that factor would have somehow been accounted for when the computer built the model. Assuming the model reliably predicted the mortality of those earlier patients, all we’d need to do is add that factor to my medical record as a hypothetical, run the model again, and see whether the prognosis changed.

But is there something about the chemotherapy being offered that is different than the regimens on which the computer trained? Then the model will not be able to assess the significance of that difference for the patient’s survival. Obviously, this limitation will be even more radical for the experimental treatment option. So in the individual case, the model’s helpfulness in making prospective treatment decisions could be quite limited. It would have to be supplemented, or even supplanted, by old-fashioned clinical judgment, or alternative algorithmic prognostic tools.

This may be one reason the study authors imagine a different use: identify patients with 3-12 months life expectancy and refer them for a palliative care consultation. The idea is to push against the tendency already noted for physicians to wait too long in making palliative care or hospice referrals. Assuming the model is running all the time in the background, it could trigger an alert to the attending physician, or even an automatic palliative care referral for all those the model flagged.

Now, in my ethics consultation experience, getting an appropriate palliative care or hospice referral only one month preceding death would be a stunning accomplishment, let alone three months prior. But the key word here is “appropriate,” since the need for palliative care is not dictated by life-expectancy alone, but more importantly, by symptoms. Not every patient with a projected life expectancy between 3 and 12 months will be suffering from symptoms requiring palliative care expertise to manage. Automatic referrals requiring palliative care evaluations could overwhelm thinly-staffed palliative care services, drawing time and resources away from patients in greater need.

Part of the problem here is the imprecision of the model, and the effects this may have on patient and provider acceptance of the results. A 90% chance of death within 3-12 months sounds ominous, but it leaves plenty of wiggle-room for unrealistic optimism: lots of patients will be confident that they are going to fall at the further end of that range, or that they will be among the 10% of cases the model got wrong altogether. And it’s not just patients who will be so affected. Their treating physicians will also be reluctant to conclude that there is nothing left to do, and that everything they did to the patient before has been in vain. Patients aren’t the only ones prone to denial.

And the nature of the AI-driven prognosis will make it more difficult to respond to patient skepticism with an explanation anyone can understand. As the authors point out, all we really know is that the model can predict within some range of probability. We don’t know why or how it’s done so. The best we can do is remove a feature of interest from the data (e.g., time since diagnosis), rerun the model, and see what effect it has on the probability for the patient’s prognosis. But the model offers no reasons to explain why there was a change, or why it was of any particular magnitude. The workings of Artificial Intelligence, in other words, are not always intelligible. Acceptable explanations will still be left to the clinician and their patient.

Tom Tomlinson photoTom Tomlinson, PhD, is Director and Professor in the Center for Ethics and Humanities in the Life Sciences, College of Human Medicine, and Professor in the Department of Philosophy at Michigan State University.

Join the discussion! Your comments and responses to this commentary are welcomed. The author will respond to all comments made by Thursday, March 8, 2018. With your participation, we hope to create discussions rich with insights from diverse perspectives.

You must provide your name and email address to leave a comment. Your email address will not be made public.

Click through to view references

Posted in Bioethics in the News, Uncategorized | Tagged , , , , , , , , , , | 1 Comment

Article from Dr. Cabrera in February issue of ‘The Lancet Neurology’

Laura Cabrera photoCenter Assistant Professor Dr. Laura Cabrera and co-author Judy Illes (University of British Columbia) have a comment article in the February 2018 issue of The Lancet Neurology. Their article is titled “Balancing ethics and care in disorders of consciousness.”

Summary: Neuromodulatory interventions that rely on the premise that stimulation activates or promotes brain circuit signals are being applied to a wide range of therapeutic targets in neurological and psychiatric disorders. The numbers of patients with whom these interventions are being tested, the range of approaches, and the variety of methods are all on the rise. Paralleling these trends are the increasing numbers of countries doing clinical trials, and the coverage of them in the press.  

The full text is available online through The Lancet (MSU Library or other institutional access may be required to view this article).

Posted in Articles, Center News, Publications, Uncategorized | Tagged , , , , ,

March webinar to address pain as a social construct

bbag-blog-image-logoPain But No Gain: Pain as a Problematic and Useless Concept?

Event Flyer

References to the human experience of “pain” are common, but those references are often ambiguous and vague. Such ambiguity creates conceptual and practical challenges, especially in the work of clinical ethics consultation. Conceptual challenges arise, for example, from the distinction between pain and suffering. Practical challenges arise from tensions between objective and subjective components of pain, and clinical ethical challenges arise in cases like Charlie Gard’s. Here, on the one hand, the court argued that Charlie was in such extreme pain and suffering, he should be allowed to die. Alternatively, others stated that we could not truly know about the experience of his pain, and that treatment therefore should be made available. While pain is a relevant clinical problem, it is also a social construct shaped by culture, environment and gender. These distinctions however get lost in a simple “pain” reference. With several clinical ethics scenarios, Dr. Eijkholt will ask if references to pain help us with anything, or if we should perhaps abandon pain as a “useless concept.”

March 14 calendar iconJoin us for Dr. Eijkholt’s lecture on Wednesday, March 14, 2018 from noon until 1 pm in person or online.

Marleen Eijkholt, JD, PhD, is and Assistant Professor in the Center for Ethics and Humanities in the Life Sciences and the Department of Obstetrics, Gynecology and Reproductive Biology at the Michigan State University College of Human Medicine. Dr. Eijkholt focuses on a wide range of Ethical, Legal and Social Implications (ELSI) in health care ethics, including neurotechnology, reproductive medicine, clinical medicine and clinical research. Her work is eclectic like her background, including projects on pain, placebos, and reproductive rights, or deep brain stimulation, and experimental treatments like stem cells. She combines ethical, legal and philosophical theories in her research and scholarship. Additionally, she engages these in her professional life as an ethics consultant at Spectrum Health System. Dr. Eijkholt also contributes her expertise to the College of Human Medicine’s Shared Discovery Curriculum.

In person: This lecture will take place in C102 East Fee Hall on MSU’s East Lansing campus. Feel free to bring your lunch! Beverages and light snacks will be provided.

Online: Here are some instructions for your first time joining the webinar, or if you have attended or viewed them before, go to the meeting!

Can’t make it? All webinars are recorded! Visit our archive of recorded lecturesTo receive reminders before each webinar, please subscribe to our mailing list.

Posted in Bioethics Events, Brownbag & Webinar Series, Center News, Outreach, Uncategorized | Tagged , , , , , , ,

Dr. Cabrera presents neuroscience research at Herrenhausen Conference in Germany

Laura Cabrera photoCenter Assistant Professor Dr. Laura Cabrera recently returned from Germany, where she presented research at the Herrenhausen Conference held in Hanover. The conference, “Lost in the Maze? Navigating Evidence and Ethics in Translational Neuroscience,” focused on major scientific and ethical challenges of novel neurological interventions and how they can be overcome.

Dr. Cabrera was one of the young researchers selected to present her research on “Responsible Translation of Contemporary Neuroscientific Advances: A Critical Appraisal of the Recent U.S. FDA Approval for Earlier DBS Intervention in Parkinson Disease” as a flash talk and a poster.

Posted in Center News, International, Research, Uncategorized | Tagged , , , , ,

Bioethics for Breakfast: Medicaid Work Requirements: Blood, Sweat and Tears Too?

Bioethics for Breakfast Seminars in Medicine, Law and SocietyAdrianne Haggins, MD, presented at the Bioethics for Breakfast event on February 8, 2018, offering perspective and insight on the topic, “Medicaid Work Requirements: Blood, Sweat and Tears Too?” Leonard Fleck, PhD, moderated this session.

The Trump administration has proposed giving states permission to attach work requirements for Medicaid eligibility. So far, ten states are seeking that permission. Is this a good idea, either from an ethical perspective or a policy perspective? Our speaker, Dr. Adrianne Haggins, is part of a research team at the University of Michigan that evaluated the impact of Michigan’s Medical expansion on employment—as reported in JAMA Internal Medicine (Dec. 11, 2017)—as well as health, and healthcare utilization.

A researcher at Kaiser Health News has added, “States will have to figure out how to define the work requirement and alternative options, such as going to school or volunteering in some organizations; how to enforce the new rules; how to pay for new administrative costs; and how to handle the millions of enrollees likely to seek exemptions.” Dr. Haggins also discussed some of her own research regarding health disparities and emergency department utilization.

Audience participants questioned such things as the administrative costs associated with implementation as well as the value and accuracy of labeling individuals as able-bodied with its attendant underlying stigma of deserving/undeserving of medical care. It was noted that much of the national conversation is linked to racialized assumptions that those utilizing Medicaid benefits are largely persons of color. Finally, many audience members argued the point that all people unconditionally deserve access to health care and some observed how that point too often gets lost in the semantics.

Related Reading:

Adrianne Haggins, MD
Adrianne Haggins is a clinical assistant professor in emergency medicine at the University of Michigan Medical School, and alumnus of the MSU College of Human Medicine class of 2007. She is a member of a research team at the University of Michigan evaluating the impact of Michigan’s Medicaid expansion, the Healthy Michigan Plan, using a mixed-methods approach. This evaluation provides rich data on enrollee and health care provider experiences with the Michigan Medicaid program, as well as health care utilization. Dr. Haggins’ specific interests are related to examining the impact of health care reform on emergency department utilization.

About Bioethics for Breakfast:
In 2010, Hall, Render, Killian, Heath & Lyman invited the Center for Ethics to partner on a bioethics seminar series. The Center for Ethics and Hall Render invite guests from the health professions, religious and community organizations, political circles, and the academy to engage in lively discussions of topics spanning the worlds of bioethics, health law, business, and policy. For each event, the Center selects from a wide range of controversial issues and provides two presenters either from our own faculty or invited guests, who offer distinctive, and sometimes clashing, perspectives. Those brief presentations are followed by a moderated open discussion.
Posted in Bioethics Events, Friends of the Center, Outreach, Uncategorized | Tagged , , , , , , , ,

Episode 6: Medical Workforce Diversity and the Professional Entry Tax

No Easy Answers in Bioethics logoEpisode 6 of No Easy Answers in Bioethics is now available! This episode features guests Libby Bogdan-Lovis, Assistant Director of the Center for Ethics and Humanities in the Life Sciences, and Dr. Karen Kelly-Blake, Assistant Professor in the Center for Ethics and the Department of Medicine at the Michigan State University College of Human Medicine. As leaders of a multi-institutional research team, they were interested in examining strategies and associated rationales for expanding underrepresented minority presence in U.S. undergraduate medical education. In this episode, they provide insight on what their scoping review has revealed, focusing on the notion that underrepresented minorities in medicine are often expected to pursue a service track—an expectation not placed on their white majority peers.

Ways to Listen

This episode was produced and edited by Liz McDaniel in the Center for Ethics. Music: “While We Walk (2004)” by Antony Raijekov via Free Music Archive, licensed under a Attribution-NonCommercial-ShareAlike License. Full transcript available.

About: No Easy Answers in Bioethics is a podcast series from the Center for Ethics and Humanities in the Life Sciences in the Michigan State University College of Human Medicine. Each month Center for Ethics faculty and their collaborators discuss their ongoing work and research across many areas of bioethics—clinical ethics, evidence-based medicine, health policy, medical education, neuroethics, shared decision-making, and more. Episodes are hosted by H-Net: Humanities and Social Sciences Online.

Posted in Center News, Outreach, Podcasts, Uncategorized | Tagged , , , , , , , , ,

Dr. Stahl explores how we see illness in new book ‘Imaging and Imagining Illness’

Devan Stahl photoCenter Assistant Professor Dr. Devan Stahl has a new book available from Cascade BooksImaging and Imagining Illness: Becoming Whole in a Broken Body. Edited by Dr. Stahl with a foreword from Rosemarie Garland-Thomson, the collection of essays draws from the disciplines of medical humanities, literature, visual culture, philosophy, and theology.

'Imaging and Imagining Illness' book cover

The cover of Imaging and Imagining Illness. Image courtesy of the author.

From Dr. Stahl:

Imaging and Imagining Illness explores the effects of imaging technologies on patients’ body image and self-understanding as well as the ways they influence our cultural understandings of illness. The project began as a collaboration between my sister Darian Goldin Stahl and myself. After I was diagnosed with multiple sclerosis, I shared my stories of living with MS as well as my MRIs with Darian. As a print artist, Darian began using my scans in her artwork as a way to give a more complete picture of what it is like to live with illness. Darian’s art had a profound effect on how I saw myself and inspired me to open our collaboration to others. We invited four other scholars to build on our work from their unique disciplines and shed light on the meaning of illness and the impact medical imaging can have on our cultural imagination. Drs. Therese Jones and Kirsten Ostherr offer reflections from their disciplines of medical humanities and visual culture and media studies. Having read all of the previous chapters, Drs. Ellen T. Armour and Jeff P. Bishop build on previous insights and add reflections from theology and philosophy. By engaging illness through multiple disciplines, the book represents the many ways we can understand and represent illness.

Posted in Books, Center News, Publications, Uncategorized | Tagged , , , , , ,