{"id":2231,"title":"Using algorithms to predict death: Lessons learned","link":"https:\/\/www.reframetech.de\/en\/2018\/09\/20\/using-algorithms-to-predict-death-lessons-learned\/","date":"09\/20\/2018","date_unix":1537427020,"date_modified_unix":1649928089,"date_iso":"2018-09-20T07:03:40+00:00","content":"

Animals are extraordinary beings. Oscar the cat, for example. Adopted as a kitten by the staff at a nursing home in the United States, he grew up surrounded by people with end-stage dementia. At some point staff members noticed something unusual: Oscar did not interact much with people, but when he made himself comfortable next to one of the residents, that person invariably died within a few hours. After a while the nurses started informing family members that they saw Oscar curled up beside a patient. What sounds like an urban legend was in fact documented in\u00a0an article<\/a><\/strong>\u00a0in the respected New England Journal of Medicine <\/em>in 2007. Oscar soon made headlines around the world. Even a book<\/a><\/strong>\u00a0<\/strong>has been written about the unusual feline.<\/p>\n

That makes Oscar very good at something that challenges doctors and nurses every day:<\/a><\/strong> predicting when a person will die. Moreover, he\u2019s amazingly accurate. Animals also sense when humans have illnesses such as tumors.\u00a0Dogs, for example, can be trained to detect lung cancer by sniffing a patient\u2019s breath<\/a><\/strong>.<\/strong>\u00a0And the results are better than those provided by conventional diagnostics.<\/p>\n

Researchers are now trying to discover how they do it. Presumably the animals can smell certain molecules in the patient\u2019s breath or on various parts of the body. Although the actual mechanism is not yet known, what is clear is that the animals\u2019 brains absorb and process complex information and then come to the relevant conclusion. That describes how algorithms work as well.<\/p>\n

It was only a matter of time before researchers developed algorithmic systems that are capable, like Oscar, of predicting death. Two types are now generally used:<\/p>\n

    \n
  1. Algorithms that analyze a patient\u2019s vital signs, such as heart rate and blood oxygen levels, to predict the probability of death within a few hours<\/strong><\/a>\u2013 in order to save the patient\u2019s life.<\/li>\n
  2. Algorithms that use a pool of patient data, such as medical diagnoses, treatments or prescribed medications, to predict the probability of death within 3 to 12 months<\/strong><\/a>\u2013 allowing terminally ill patients to benefit from at-home palliative care.<\/li>\n<\/ol>\n

    In both cases, it is generally acknowledged that algorithm-based systems will be able to produce, on average, better predictions than humans can. And even if hospital staff use special scoring systems to assess risk or the probability of death, the scores\u2019 accuracy still leaves a lot to be desired, which is why doctors and nurses generally rely on their own professional experience.<\/p>\n

    Over the course of their careers, medical practitioners treat thousands of patients. Yet it\u2019s hard to pinpoint the exact knowledge they use as the basis for choosing one therapy over another. That is not the case with software, however, which runs on a dataset that is always accessible and constantly growing.<\/p>\n

    Whether it\u2019s a matter of predicting avoidable problems early on and thus saving lives or accurately foreseeing the unavoidable and helping the seriously ill die in a dignified manner, algorithms can help doctors make decisions based not only on their subjective experiences, but on objective parameters as well. In addition, using algorithms can help medical staff to systematize decision-making processes, for example in hospitals.<\/p>\n

    Yet as useful as such systems might be, many people feel uncomfortable when they discover that software is being used to foretell a death. This is particularly true in the second example given above: when death is more or less inevitable and there is little that can be done to save the patient\u2019s life. The oncologist and author Siddhartha Mukherjee describes exactly this feeling of discomfort in one of his essays. In other words, there are many questions that must still be answered and many aspects that require public discussion before such algorithms become widely used.<\/p>\n

    Algorithmic decision-making processes must be transparent<\/strong><\/p>\n

    Two such \u201cdeath algorithms\u201d are currently the subject of discussion in the United States which are being deployed to predict if seriously ill patients will die within the next 3 to 12 months (see our blog entry \u201c<\/strong>Optimizing palliative care: When algorithms predict a patient\u2019s death<\/strong><\/a>\u201d<\/strong>). One is still being developed and has been published in a study by researchers at Stanford University; the other is the property of private US-based palliative-care provider Aspire Health.<\/p>\n

    In contrast to the Stanford researchers, Aspired Health is a for-profit enterprise that specializes in home-based end-of-life care. That means it earns money when people with serious illnesses no longer receive curative care. The greater the number of people who use the palliative services provided by Aspire, the greater the company\u2019s profit. The conflict of interest is readily apparent. To make things more problematic, no one outside of the company knows how the algorithm used by Aspire works, since it\u2019s a trade secret. It thus remains unclear how the system decides when the company\u2019s palliative services are the better choice for a patient.<\/p>\n

    One could easily presume that Aspire Health has optimized the algorithm to identify as many patients as possible who would benefit from palliative care. Yet increasing the sensitivity generally results in lower specificity. That means the algorithm would misidentify too many of those patients who will actually live longer than one year, the upper limit for palliative care.<\/p>\n

    An algorithm must be transparent if outsiders are to understand how it has been optimized. And when it comes to systems that predict the probability of death, optimization parameters should not be the purview of commercial businesses alone. The system\u2019s developers must instead publicly disclose which goals are being pursued with the algorithm and under what conditions it is being used. Both of these aspects must be subject to a public social, political and ethical debate. Moreover, it must be possible to verify the algorithm\u2019s performance.<\/p>\n

    Algorithms must be thoroughly validated on an ongoing basis<\/strong><\/p>\n

    It must be possible to validate algorithms if they are to be considered transparent. And an algorithm must be publicly accessible if it is to be publicly validated. Furthermore, a number of questions must be asked when it comes to algorithms of this type, such as:<\/p>\n