Breaking News
January 24, 2019 - Cancer Research UK announces £60 million funding to tackle global cancer challenges
January 24, 2019 - SCHILLER AED FRED easyport helped save life of elderly person in Vienna
January 24, 2019 - Pittcon to highlight UHPLC techniques at 30th James L. Waters symposium
January 24, 2019 - Global task force of bone health experts question effectiveness of spinal fusion procedures
January 24, 2019 - Study demonstrates beneficial effects of influenza vaccination on COPD patients
January 24, 2019 - New findings challenge existing strategies for fighting infectious diseases and germs
January 24, 2019 - Study sheds new light on male infertility
January 24, 2019 - Rebound Therapeutics announces FDA 510k clearance of its AURORA Surgiscope System
January 24, 2019 - 3D printing may aid in the treatment of osteoarthritis
January 24, 2019 - Most gay fathers and their kids face stigma despite legal and social advances, finds study
January 24, 2019 - Melanoma Survival Varies Among U.S. States
January 24, 2019 - Migraine – Genetics Home Reference
January 24, 2019 - Is that really a neglected disease?
January 24, 2019 - Study offers new hope for elimination of malaria
January 24, 2019 - Mice transmit brain benefits of enriched upbringing to non-enriched offspring
January 24, 2019 - Researchers demonstrate strong evidence connecting bacterial pathogen and Alzheimer’s pathogenesisis
January 24, 2019 - Overprescribing of antidepressants may occur more often in elderly patients
January 24, 2019 - FDA authorizes marketing of new test to aid in the diagnosis of M. gen. infections
January 24, 2019 - Health Tip: Simple CPR – Drugs.com MedNews
January 24, 2019 - Diabetes in America, 3rd Edition
January 24, 2019 - Bangladesh ‘Tree Man’ returns to hospital as condition worsens
January 24, 2019 - Costs of gun-related hospitalizations, readmissions examined in study
January 24, 2019 - Good health literacy linked to better adherence to blood pressure medications among Hispanics
January 24, 2019 - Only a minority of patients in the U.S. with type 1 diabetes achieve treatment goals
January 24, 2019 - High fat reduces efficiency of the immune system to fight infectious disease
January 24, 2019 - FDA grants clearance to Hologic’s assay for detection of common sexually transmitted infections
January 24, 2019 - Study highlights need for reliable therapeutic targets for prevention, treatment of cardiovascular diseases
January 24, 2019 - Next step toward replacement therapy in type 1 diabetes
January 24, 2019 - “Scientific serendipity” identifies link between type of RNA and autism
January 24, 2019 - Trump Zeroes In On Surprise Medical Bills In White House Chat With Patients, Experts
January 24, 2019 - Unique form of chronic sinusitis found in older patients
January 24, 2019 - NUS researchers make muscle recovery easier for patients with ingenious medical device
January 24, 2019 - Specific cognitive deficits found in individuals with spinal cord injury
January 24, 2019 - An essential reference for diagnostic ultrasonography and biopsy of the thyroid gland
January 24, 2019 - Proteus Digital Health Launches Digital Oncology Medicines to Improve Patient Outcomes
January 24, 2019 - Study looking to prevent type 1 diabetes follows children into adolescence
January 24, 2019 - Nice doctors make a difference
January 23, 2019 - Blood vessel discovery could advance our knowledge of osteoporosis
January 23, 2019 - New esophageal cancer test uses genetic biomarkers to detect changes in esophagal cells
January 23, 2019 - Study evaluates first-ever Robotic Visualization System for neurosurgery
January 23, 2019 - Scientists reveal new mechanism that could lead to specific treatment of strokes and seizures
January 23, 2019 - Both educational level and occupational orientation predict mother’s smoking during pregnancy
January 23, 2019 - How to (gently) get your child to brush their teeth
January 23, 2019 - Short-term hospital readmissions for gun injuries cost $86 million a year | News Center
January 23, 2019 - New certified reference material for testing residual solvents in cannabis
January 23, 2019 - Gene-edited chickens could prevent future flu pandemic
January 23, 2019 - Cardiovascular disease risk begins even before birth
January 23, 2019 - Younger patients receiving kidney transplant more likely to live longer, shows data
January 23, 2019 - Skin samples hold early signs of prion disease, research suggests
January 23, 2019 - Researchers discover how body initiates repair mechanisms that limits damage to myelin sheath
January 23, 2019 - Fecal transplant from certain donors better than others
January 23, 2019 - Risk for Uninsurance in AMI Patients Reduced With Medicaid Expansion
January 23, 2019 - Readmissions reduction program may be associated with increase in patient-level mortality
January 23, 2019 - Fostering translation and communication in medicine and beyond
January 23, 2019 - To Fight Fatty Liver, Avoid Sugary Foods and Drinks
January 23, 2019 - TPU scientists develop new implants that double the rate of bone lengthening in kids
January 23, 2019 - New sessions at Pittcon 2019
January 23, 2019 - Insilico to present latest findings in AI for Drug Discovery at 3rd Annual SABPA FTD Forum
January 23, 2019 - Opioid overdose patients can be safely discharged an hour after administration of naloxone
January 23, 2019 - Scientists find bacterial extracellular vesicles in human blood
January 23, 2019 - Researchers use modified type of flu virus to develop new therapies for prostate cancer
January 23, 2019 - Researchers gain new insights into development of necrotizing enterocolitis in preemies
January 23, 2019 - Medical expert advises people with epilepsy not to stockpile medicines
January 23, 2019 - CDC study explores link between smoking and clinical outcomes of assisted reproductive technology
January 23, 2019 - Study outlines research priorities for improving pediatric patient care and safety
January 23, 2019 - Bedfont to exhibit NObreath FeNO monitor at Arab Health 2019
January 23, 2019 - Nicotinamide riboside supplementation confers significant physiological benefits to mothers and offspring
January 23, 2019 - Increasing temperatures may help preserve crop nutrition
January 23, 2019 - Many Oncologists in the Dark About LGBTQ Health Needs
January 23, 2019 - Epigenetic change causes fruit fly babies to inherit diet-induced heart disease
January 23, 2019 - Erasing memories could reduce relapse rates among drug addicts
January 23, 2019 - African Americans who smoke cigarettes are more likely to develop peripheral artery disease
January 23, 2019 - Unique data combination helps FinnGen researchers to fund links between genetic factors and health
January 23, 2019 - Parents’ mental health problems associated with reactive attachment disorder in children
January 23, 2019 - Graphene Flagship project studies impact of graphene and related materials on our health
January 23, 2019 - The connection between the Pope and contraceptive pills
January 23, 2019 - Prior dengue infection could protect children from symptomatic Zika
January 23, 2019 - Previous dengue virus infection associated with protection from symptomatic Zika
January 23, 2019 - VISTA checkpoint implicated in pancreatic cancer immunotherapy resistance
January 23, 2019 - The Tiny Camera That Could Revolutionize Cardiovascular Surgery
Why predicting suicide is a difficult and complex challenge

Why predicting suicide is a difficult and complex challenge

image_pdfDownload PDFimage_print
Anthony Bourdain, left, and Kate Spade, right. Credit: The Conversation with images from PeabodyAwards/flickr, CC BY-SA

Who is going to die by suicide? This terrible mystery of human behavior takes on particular poignance in the wake of suicides by high-profile and much-beloved celebrities Kate Spade and Anthony Bourdain. It is only natural that people want to know why such tragedies occur. Those closest to those who take their lives are often tormented, wondering if there is something they could have – or should have – known to prevent their loved one’s suicide.

As a scientist who has focused on this question for the past decade, I should have a pretty good idea of who is and isn’t going to die by suicide. But the sad truth is, I don’t. The sadder truth is, neither do any other suicide experts, psychiatrists or physicians. The sum of the research on suicide shows that it does not matter how long we’ve known someone or how much we know about them. In my research, my colleagues and I have shown that we can only predict who is going to die by suicide slightly more accurately than random guessing.

The need for answers

The fact that suicide is so hard to predict unfortunately took about 50 years for most scientists to appreciate. About the same time that this recognition became widespread a few years ago, a new hope emerged: a form of artificial intelligence called machine learning. As several research groups have demonstrated in recent years, machine learning may be able to predict who is going to attempt or die by suicide with up to 90 percent accuracy.

To understand why this is, and why we humans won’t ever be able to accurately predict suicide on our own, one needs to take a step back and understand a little more about the nature of human cognition, suicide and machine learning.

As humans, we love explanations that have two qualities. First, explanations should be simple, meaning that they involve one or a small number of things. For example, depression is a simple explanation for suicide.

Second, explanations should be determinate, meaning that there is one set explanation that accounts for all or most of something. For example, the idea that depression causes most suicides is a determinate explanation. This simple and determinate explanatory style is highly intuitive and very efficient. It’s great for helping us to survive, procreate, and get through our days.

But this style of thinking is terrible for helping us understand nature. This is because nature is not simple and determinate. In recent decades, scientists have come to recognize that nearly everything – from physics to biology to human behavior – is complex and indeterminate. In other words, a very large number of things combined in a complex way are needed to explain most things, and there’s no set recipe for most physical, biological or behavioral phenomena.

I know that this latter idea of indeterminacy is especially counterintuitive, so let me provide a straightforward example of it. The math equation X plus Y equals 1 is indeterminate. As humans, we instinctively try to find one solution to this equation (e.g., X equals 1, Y equals 0). But there is no set recipe for solving this equation; there are nearly infinite solutions to this equation. Importantly, however, this does not mean that “anything goes.” There are also near infinite values for X and Y that do not solve this equation. This indeterminate middle ground between “one solution” and “anything goes” is difficult for most humans to grasp, but it’s how much of nature works.

The sum of our scientific evidence indicates that, just like most other things in nature, the causes and predictors of suicide are complex and indeterminate. Hundreds, and maybe thousands, of things are relevant to suicide, but nothing predicts suicide much more accurately than random guessing. For example, depression is often considered to be an extremely important predictor of suicide. But about 2 percent of severely depressed people eventually die by suicide, which is only slightly higher than the 1.6 percent of people from the general United States population who eventually die by suicide. Such a pattern is consistent with complexity because it suggests that we must put a lot of factors together to account for suicide.

Empathy will always matter

So how should we put all of these factors together? One intuitive solution is to add many of these factors together. But even when summing hundreds of factors, this doesn’t work – prediction is still only slightly more accurate than random guessing.

A much better solution would be to somehow find an optimized combination of tens or even hundreds of factors. How can we do this? One promising answer is machine learning. In short, machine learning programs can process a large amount of data and learn an optimal combination of factors for a given task. For example, most existing machine learning studies have used data from electronic health records, spanning hundreds of factors related to mental health diagnoses, physical health problems, medications, demographics and hospital visit patterns. Results from several groups in recent years have shown that this approach can consistently predict future suicide attempts and death with 80-90 percent accuracy. Multiple groups are currently working on applying these algorithms to actual clinical practice.

One important thing to keep in mind is that there isn’t, and never will be, a single algorithm or recipe for suicide prediction. This is because suicide is indeterminate, much like the X plus Y equals 1 equation. There are likely near-infinite algorithms that could predict suicide with 80-90 percent accuracy, as a number of studies have shown. Research has already demonstrated that no particular factors are necessary for a good algorithm, and many different types of algorithms can produce accurate prediction. But again, this indeterminacy also means that there are near-infinite bad algorithms, too.

All of this research shows that suicide is unfortunately too complex and indeterminate for humans to predict. Neither I nor anyone else can accurately predict who is going to die by suicide or truly explain why a particular person died by suicide (this includes the suicide decedents themselves). Machine learning can do a much better job of approximating the complexity of suicide, but even it falls far short. Although it can accurately predict who will eventually die by suicide, it cannot yet tell us when someone will die by suicide. This “when” dimension of prediction is critical, and we are likely still many years away from accounting for it.

In the meantime, what can we humans do? While we don’t have the ability to know whether someone is going to die by suicide or not, we do have the ability to be supportive and caring. If you believe that someone may be struggling, talk with them and let them know about resources such as the US National Suicide Prevention Lifeline (1-800-273-8255).


Explore further:
Early intervention service cuts suicide rate in schizophrenia

Provided by:
The Conversation

Tagged with:

About author

Related Articles