How New York's largest hospital system is predicting COVID-19 spikes
Northwell Health is using insights from website traffic to forecast COVID-19 hospitalizations two weeks in the future.
Stephen Johnson is a St. Louis-based writer whose work has been published by outlets including PBS Digital Studios, HuffPost, MSN, U.S. News & World Report, Eleven Magazine and The Missourian.
- The machine-learning algorithm works by analyzing the online behavior of visitors to the Northwell Health website and comparing that data to future COVID-19 hospitalizations.
- The tool, which uses anonymized data, has so far predicted hospitalizations with an accuracy rate of 80 percent.
- Machine-learning tools are helping health-care professionals worldwide better constrain and treat COVID-19.
One of the most devastating aspects of the COVID-19 pandemic has been unpredictability. The nation's health systems—especially those in hard-hit areas like New York City—have had to adapt to sudden surges of COVID-19 cases, all while dealing with limited resources, existing patients, and a novel virus that's still not fully understood.
But what if health systems were able to forecast COVID-19 hospitalizations two weeks before they occur? Northwell Health, the largest health care system in New York state, recently deployed a predictive tool that does just that.
Northwell Health's surveillance dashboard is able to predict COVID-19 hospitalizations by using insights from machine learning. In March, Northwell Health's Customer Insights Group developed an algorithm that's been mining data from online traffic to the Northwell.edu website, which has received more than 20 million hits since March.
The algorithm collects data through 15 different indicators, each of which reflects the online behavior of the website's visitors. For example, the tool analyzes metrics such as the length of time users spend on certain pages, searches for emergency department wait times, and specific symptoms users search for. Combined, this information translates into something like the "public mood" of the website on any given day.
Since Northwell Health began using the predictive tool in September, it's predicted COVID-19 hospitalizations with an accuracy of about 80 percent.
To understand how this mood relates to future COVID-19 cases, Northwell Health began comparing its data with a timeline of COVID-19 hospitalizations across 23 hospitals and nearly 800 outpatient facilities and in the metro New York area. This enabled the Customer Insights Group to see patterns of online activity that precede future increases or decreases in hospitalizations.
Since Northwell Health began using the predictive tool in September, it's predicted COVID-19 hospitalizations with an accuracy of about 80 percent.
"This is really the first tool that I've been exposed to that gives me a sort of guestimate of what two weeks from now may look like," said Dr. Eric Cruzen, chief medical informatics officer of Northwell's emergency medicine services and chair of the emergency department at Lenox Health Greenwich Village in Manhattan.
"Even if the data can provide an idea of whether to expect an increase, decrease, or stasis, that's valuable. Because every day we're working to estimate what tomorrow's going to bring. Any tool that's going to shed light on that is a good tool in my book."
The value of forecasting
Northwell emergency departments use the dashboard to monitor in real time.
Credit: Northwell Health
One unique benefit of forecasting COVID-19 hospitalizations is that it allows health systems to better prepare, manage and allocate resources. For example, if the tool forecasted a surge in COVID-19 hospitalizations in two weeks, Northwell Health could begin:
- Making space for an influx of patients
- Moving personal protective equipment to where it's most needed
- Strategically allocating staff during the predicted surge
- Increasing the number of tests offered to asymptomatic patients
The health-care field is increasingly using machine learning. It's already helping doctors develop personalized care plans for diabetes patients, improving cancer screening techniques, and enabling mental health professionals to better predict which patients are at elevated risk of suicide, to name a few applications.
Health systems around the world have already begun exploring how machine learning can help battle the pandemic, including better COVID-19 screening, diagnosis, contact tracing, and drug and vaccine development.
Cruzen said these kinds of tools represent a shift in how health systems can tackle a wide variety of problems.
"Health care has always used the past to predict the future, but not in this mathematical way," Cruzen said. "I think [Northwell Health's new predictive tool] really is a great first example of how we should be attacking a lot of things as we go forward."
Making machine-learning tools openly accessible
Northwell Health has made its predictive tool available for free to any health system that wishes to utilize it.
"COVID is everybody's problem, and I think developing tools that can be used to help others is sort of why people go into health care," Dr. Cruzen said. "It was really consistent with our mission."
Open collaboration is something the world's governments and health systems should be striving for during the pandemic, said Michael Dowling, Northwell Health's president and CEO.
"Whenever you develop anything and somebody else gets it, they improve it and they continue to make it better," Dowling said. "As a country, we lack data. I believe very, very strongly that we should have been and should be now working with other countries, including China, including the European Union, including England and others to figure out how to develop a health surveillance system so you can anticipate way in advance when these things are going to occur."
In all, Northwell Health has treated more than 112,000 COVID patients. During the pandemic, Dowling said he's seen an outpouring of goodwill, collaboration, and sacrifice from the community and the tens of thousands of staff who work across Northwell.
"COVID has changed our perspective on everything—and not just those of us in health care, because it has disrupted everybody's life," Dowling said. "It has demonstrated the value of community, how we help one another."
Cow cuddling is getting ever more popular, but what's the science behind using animals for relaxation?
- An Indian non-profit hopes to help people relax by giving them cuddle sessions with cows.
- This is not the first such center where you can chill out with cattle.
- Like other emotional support animals, the proven health benefits are limited.
Who needs a therapy dog when you can hug a cow?<p> Located outside of the Indian city of Gurugram, the new Cow Cuddling Centre will be run by a non-profit <a href="https://interestingengineering.com/ngo-launches-cow-cuddling-therapy-center-in-india" target="_blank" rel="noopener noreferrer">headed</a> by the former Chairman of the Animal Welfare Board of India, SP Gupta.</p><p>Pitched as a way to escape the stresses of modern life and "forget all your problems," the founders of the establishment have high hopes for it, suggesting that spending time with the cows can cure "respiratory diseases, blood pressure, spinal pain, heart problem, depression but also sadness, anxiety and all kinds of tensions" in a <a href="https://www.indiatimes.com/news/india/cow-science-exam-may-be-postponed-but-an-ngo-is-launching-a-cow-cuddling-centre-in-haryana-535024.html" target="_blank" rel="noopener noreferrer">press statement</a>.</p><p>While you might be thinking that cow cuddling only exists in India because of the cultural importance placed on the animal there, <a href="http://www.bbc.com/travel/story/20201008-is-cow-hugging-the-worlds-new-wellness-trend" target="_blank" rel="noopener noreferrer">the Dutch beat them to it.</a> Cow cuddling farms exist in the United States as <a href="https://www.nytimes.com/2019/07/12/style/self-care/cow-cuddling-therapy.html" target="_blank" rel="noopener noreferrer">well</a>.</p>
Is there any science behind the idea of cuddling with a cow over a more traditional, travel-sized pet?<iframe width="730" height="430" src="https://www.youtube.com/embed/QG3fOOT7xWQ" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe><p> Like many claims about emotional support animals of any kind, there is a limited amount of data on this.</p><p>What studies do exist on emotional support animals are <a href="https://www.tandfonline.com/doi/abs/10.1080/08927936.2015.11435396" target="_blank" rel="noopener noreferrer">small</a>, <a href="https://www.tandfonline.com/doi/abs/10.1080/15228932.2013.765734" target="_blank" rel="noopener noreferrer">limited</a>, and should be considered to be the beginnings of more extensive <a href="https://onlinelibrary.wiley.com/doi/full/10.1111/j.1479-8301.2009.00268.x" target="_blank" rel="noopener noreferrer">studies</a> which will settle the question of how much help these animals can <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5127627/" target="_blank" rel="noopener noreferrer">provide</a>. This is different from work on well-trained service animals, which are <a href="https://content.iospress.com/articles/neurorehabilitation/nre1345" target="_blank" rel="noopener noreferrer">proven</a> to be very <a href="http://www.cf4aass.org/uploads/1/8/3/2/18329873/psd_and_veterans_living_with_ptsd_-_gillett_march_23_2014_2.pdf" target="_blank" rel="noopener noreferrer">helpful</a> when doing the <a href="https://www.sciencedirect.com/science/article/abs/pii/S0965229913002148" target="_blank" rel="noopener noreferrer">tasks</a> they are specially trained for. <br></p><p>Regarding cows, the <a href="http://www.bbc.com/travel/story/20201008-is-cow-hugging-the-worlds-new-wellness-trend" target="_blank" rel="noopener noreferrer">BBC</a> suggests that chilling with cows can cause relaxation by boosting oxytocin levels in humans, though they do not cite a specific study supporting that stance. One often-referenced study from several years back suggests the cows might like and get relaxation out of cuddling <a href="https://www.sciencedirect.com/science/article/abs/pii/S0168159107000445" target="_blank" rel="noopener noreferrer">too</a>.<br></p><p>However, Dr. <a href="https://www.psychologytoday.com/us/contributors/michael-ungar-phd" target="_blank" rel="noopener noreferrer">Michael Ungar</a> suggests in this <a href="https://www.psychologytoday.com/us/blog/nurturing-resilience/202001/cuddle-cow-the-new-psychotherapy" target="_blank" rel="noopener noreferrer">Psychology Today</a> article that cow cuddling might be comparable to equine therapy, which, while also lacking in rigorous scientific support, does seem to provide some people certain benefits.</p><p>The news magazine <a href="https://www.indiatoday.in/india-today-insight/story/cuddling-a-cow-the-latest-wellness-trend-1764558-2021-01-31" target="_blank" rel="noopener noreferrer">India Today </a>featured a brief interview with professor Ritu Dangwal, who also suggests that cow cuddling might have some benefits:</p><p> "As a psychologist and someone who herself experienced it, being with cows is extremely therapeutic. We are stuck in a rat race and our anxiety is at an all-time high. Being with an emotive animal, one that has no judgement and loves unconditionally, does wonders."</p><p>What relaxes some people might be somewhat surprising to others or difficult to generalize in a scientific study. While you might not get prescribed a day in the pasture anytime soon, cow cuddling is an increasingly popular way to relax that gets people back into nature and interacting with animals in a way that many of us rarely get the chance to. While the science isn't quite all there, some people might find it worth the time.</p><p>Just be sure to wear closed-toed shoes if you go.</p>
How does philosophy try to balance having free will with living in a deterministic universe?
- People feel like they have free will but often have trouble understanding how they can have it in a deterministic universe.
- Several models of free will exist which try to incorporate physics into our understanding of our experience.
- Even if physics could rule out free will, there would still be philosophical questions about it.
Hard Determinism<p> Some philosophers have taken the argument of casual determinism mentioned above and used it to say that there is no room for free will at all. This stance, called "hard determinism," maintains that all of our actions are causally necessary and dictated by physics in the same way as a billiard ball's movement. </p><p> The Baron d'Holbach<strong>, </strong>a French philosopher, explained the stance:</p><p style="margin-left: 20px;"> "In short, the actions of man are never free; they are always the necessary consequence of his temperament, of the received ideas and of the notions, either true or false, which he has formed to himself of happiness; of his opinions, strengthened by example, by education, and by daily experience."</p><p> While physics and philosophy have both advanced since the enlightenment era, hard determinism still has supporters.</p>
Indeterminism<iframe width="730" height="430" src="https://www.youtube.com/embed/DMNZQVyabiM" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe><p> As some of you are probably thinking right now, quantum physics, with its uncertainties, probabilities, and general strangeness, might offer a way out of the determinism of classical physics. This idea, sometimes called "<a href="https://plato.stanford.edu/entries/incompatibilism-theories/" target="_blank">indeterminism</a>," occurred to more than a few philosophers too, and variations of it date back to ancient Greece.</p><p> This stance holds that not every event has an apparent cause. Some events might be random, for example. Proponents of the perspective suggest that some of our brain functions might have random elements, perhaps caused by the fluctuations seen in quantum mechanics, that cause our choices to not be fully predetermined. Others suggest that only part of our decision-making process is subject to causality, with a portion of it under what amounts to the control of the individual. </p><p> There are issues with this stance being used to counter determinism. One of them is that having choices made randomly rather than by strict causation doesn't seem to be the kind of free will people think about. From a physical standpoint, brain activity may involve some quantum mechanics, <a href="https://www.newscientist.com/article/mg22830500-300-is-quantum-physics-behind-your-brains-ability-to-think/" target="_blank">but not all of it. </a>Many thinkers incorporate indeterminism into parts of their models of free will, but don't fully rely on the idea. <br><a href="https://www.newscientist.com/article/mg22830500-300-is-quantum-physics-behind-your-brains-ability-to-think/" target="_blank"></a> </p>
Soft Determinism<p> Also called "<a href="https://plato.stanford.edu/entries/compatibilism/" target="_blank">compatibilism</a>," this view agrees with causal determinism but also holds that this is compatible with some kind of free will. This can take on many forms and sometimes operates by varying how "free" that will actually is. </p><p> <a href="https://www.informationphilosopher.com/solutions/philosophers/mill/" target="_blank">John Stuart Mill </a>argued that causality did mean that people will act in certain ways based on circumstance, character, and desires, but that we have some control over these things. Therefore, we have some capacity to change what we would do in a future situation, even if we are determined to act in a certain way in response to a particular stimulus. </p><p> Daniel Dennett goes in another <a href="https://scholar.harvard.edu/files/iphi/files/free_will_2016_01.pdf" target="_blank">direction</a>, suggesting a two-stage model of decision-making involving some indeterminism. In the first stage of making a decision, the brain produces a series of considerations, not all of which are necessarily subject to determinism, to take into account. What considerations are created and not immediately rejected is subject to some level of indeterminism and agent control, though it could be unconscious. In the second step, these considerations are used to help make a decision based on a more deterministic reasoning process. </p><p> In these stances, your decisions are still affected by prior events like the metaphorical billiard balls moving on a table, but you have some control over how the table is laid out. This means you could, given enough time and understanding, have a fair amount of control over how the balls end up moving. </p><p> Critics of stances like this often argue that the free will the agent is left with by these decision-making models is hardly any different from what they'd have under a hard deterministic one. </p>
Libertarian Freedom<iframe width="730" height="430" src="https://www.youtube.com/embed/UZmpUGl6eRc" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe><p> This is the stance with the premium free will people tend to talk about—the idea that you are in full control of your decisions all the time and that casual determinism doesn't apply to your decision-making process. It is "<a href="https://plato.stanford.edu/entries/incompatibilism-theories/" target="_blank">incompatibilist</a>" in that it maintains that free will is not compatible with a deterministic universe. </p><p> People holding this view often take either an "agent-casual" or "event-causal" position. In an agent-casual stance, decision-makers, known as "agents," can make decisions that are not caused by a previous action in the same way that physical events are. They are essentially the "prime movers" of event chains that start with their decisions rather than any external cause. </p><p> Event-casual stances maintain that some elements of the decision-making process are physically indeterminate and that at least some of the factors that go into the final choice are shaped by the agent. The most famous living proponent of such a stance is Robert Kane and his "<a href="https://plato.stanford.edu/entries/incompatibilism-theories/#2.3" target="_blank">effort of will"</a> model.</p><p>In brief, his model supposes an agent can be thought responsible for an action if they helped create the causes that led to it. He argues that people occasionally take "self-forming action" (SFA) that helps shape their character and grant them this responsibility. SFAs happen when the decisions we make would be subject to indeterminism, perhaps a case when two choices are both highly likely- with one being what we want and one being what we think is right, and willpower is needed to cause a choice to be taken. </p><p> At that point, unable to quickly choose, we apply willpower to make a decision that influences our overall character. Not only was that decision freely chosen, but any later, potentially more causally-determined actions, we take rely at least somewhat on a character trait that we created through that previous choice. Therefore, we at least partially influenced them. </p><p>Critics of this stance include Daniel Dennett, who points out that SFAs could be so rare as to leave some people without any real free will at all. <br></p>
Can’t we just outsource free will to physics?<iframe width="730" height="430" src="https://www.youtube.com/embed/R-Nj_rEqkyQ" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe><p> No, the question of free will is much larger than if cause and effect exist and apply to our decisions. Even if that one were fully answered, other questions immediately pop up. <br></p><p>Is the agency left to us, if any, after we learn how much of our decision-making is determined by outside factors enough for us to say that we are free? How much moral responsibility do people have under each proposed understanding of free will? Is free will just the ability to choose otherwise, or do we just have to be responsible for the actions we make, even if we are limited to one choice?<br></p><p> Physics can inform the debate over these questions but cannot end it unless it comes up with an equation for what freedom is.</p><p>Modern debates outside of philosophy departments tend to ignore the differences in the above stances in a way that tends to reduce everything to determinism. This was highlighted by neuroscientist Bobby Azarian in a recent Twitter <a href="https://twitter.com/philipcball/status/1356244216385560581" target="_blank" rel="noopener noreferrer">thread</a>, where he notes there is often a tendency to conflate hard determinism with naturalism—the idea that natural laws, as opposed to supernatural ones, can explain everything in the universe. .</p><p> Lastly, we might wonder if physics is the right department to hand it over to. Daniel Dennett awards evolutionary biology the responsibility for generating consciousness and free will.</p><p> He points out that while physics has always been the same for life on Earth, both consciousness and free will seem to have evolved recently and could be an evolutionary advantage of sorts—not being bound to deterministic decision making could be an excellent tool for staying alive. He considers them to be emergent properties we have and considers efforts to reduce us to our parts, which do function deterministically, to be <a href="https://www.youtube.com/watch?v=joCOWaaTj4A" target="_blank">unsound</a>. </p><p> How to balance our understanding of causal determinism and our subjective experience of seeming to have free will is a problem philosophers and scientists have been discussing for the better part of two thousand years. It is one they'll likely keep going over for a while. While it isn't time to outsource free will to physics, it is possible to incorporate the findings of modern science into our philosophy. </p><p> Of course, we might only do that because we're determined to do so, but that's another problem. </p>
"The Expanse" is the best vision I've ever seen of a space-faring future that may be just a few generations away.
- Want three reasons why that headline is justified? Characters and acting, universe building, and science.
- For those who don't know, "The Expanse" is a series that's run on SyFy and Amazon Prime set about 200 years in the future in a mostly settled solar system with three waring factions: Earth, Mars, and Belters.
- No other show I know of manages to use real science so adeptly in the service of its story and its grand universe building.
Credit: "The Expanse" / Syfy<p>Now, I get it if you don't agree with me. I love "Star Trek" and I thought "Battlestar Galactica" (the new one) was amazing and I do adore "The Mandalorian". They are all fun and important and worth watching and thinking about. And maybe you love them more than anything else. But when you sum up the acting, the universe building, and the use of real science where it matters, I think nothing can beat "The Expanse". And with a <a href="https://www.rottentomatoes.com/tv/the_expanse" target="_blank">Rotten Tomato</a> average rating of 93%, I'm clearly not the only one who feels this way.</p><p>Best.</p><p>Show.</p><p>Ever. </p>
SMARTER FASTER trademarks owned by Freethink Media, Inc. All rights reserved.