Breaking News
June 22, 2018 - Osteopathic manual therapy affecting the diaphragm improves chronic low back pain
June 22, 2018 - Researchers create revolutionary model to study pulmonary diseases
June 22, 2018 - Diagnosing Heart Disease Using AI
June 22, 2018 - Increasing biodefense risks posed by synthetic biology
June 22, 2018 - Many Women Report Vasomotor Symptoms in Their 60s
June 22, 2018 - Rare mutation of gene carried by Quebec family gives insight into how the brain is wired
June 22, 2018 - Summer is good time to check for signs of skin cancer
June 22, 2018 - Innovative method can help identify patients with spastic cerebral palsy
June 22, 2018 - Exercise alters characteristics of blood to reduce inflammation in obese people
June 22, 2018 - Researchers examine complications across different types of breast reconstructive surgeries
June 22, 2018 - Rhesus macaque model could be useful to test therapies for congenital Zika virus syndrome
June 22, 2018 - AHA: New Insights Into Sickle Cell and Stroke Risk
June 22, 2018 - Doctors prescribe opioids at high rates to those at increased overdose risk
June 22, 2018 - Reduction in US cigarette smoking rates
June 22, 2018 - Preconception binge drinking may have negative effect on future offspring
June 22, 2018 - FDA expands approval of novel diabetes management device to include younger pediatric patients
June 22, 2018 - Researchers confirm weight loss benefits of the 16:8 diet
June 22, 2018 - FDA approves Eversense CGM system for use in adults with diabetes
June 22, 2018 - State opioid monitoring programs are not created equal
June 22, 2018 - Autistic teens who are bullied have higher rates of depression
June 22, 2018 - Penn Medicine team launches universal stroke awareness program
June 22, 2018 - Scientists discover the molecular trigger of necroptosis
June 22, 2018 - Researchers report unusually high levels of herpesvirus in the brains of people with Alzheimer’s disease
June 22, 2018 - Theoretical models predict how juveniles evolve to be more susceptible than adults to infection
June 22, 2018 - USC study reveals how the cell launches emergency response to repair damaged DNA
June 22, 2018 - $1.9 million grant aims to enhance behavioral health services in community-based settings
June 22, 2018 - New 3D imaging technique could improve arthritis treatment
June 22, 2018 - Cytokinetics Announces Data From Phase 2 Clinical Study of Reldesemtiv in Patients With Spinal Muscular Atrophy
June 22, 2018 - Polarized cells give the heart its fully developed form
June 21, 2018 - Stem cells appear to help fight obesity in animal models
June 21, 2018 - Harnessing Pediatric Cancer Genomic Data in the Cloud
June 21, 2018 - Training nursing students with cost-effective 3D-printed task trainers
June 21, 2018 - Study provides insight into how planned and spontaneous movements are processed in the brain
June 21, 2018 - Suicide Prevention | SAMHSA – Substance Abuse and Mental Health Services Administration
June 21, 2018 - From designer microbes to stem cells, researchers are investigating new strategies to treat bowel disease
June 21, 2018 - Study suggests state-of-the-art genomic testing for routine autopsy of stillbirths
June 21, 2018 - Christiana Care Health System opens first Epilepsy Monitoring Unit in Delaware
June 21, 2018 - CDC: Obesity Prevalence Higher in Non-Metropolitan Counties
June 21, 2018 - Youths Treated for Non-Suicidal Self Harm at Increased Risk of Suicide Within a Year
June 21, 2018 - WVU researchers increase colorectal cancer screening rates in West Virginia
June 21, 2018 - Pediatric kidney recipients often have subclinical inflammation
June 21, 2018 - OHSU Knight Cancer Institute Director wins 2018 Tang Prize in Biopharmaceutical Science
June 21, 2018 - Researchers study broader effects of neonics on wildlife
June 21, 2018 - Study provides new insight on how antibiotics affect the gut microbiome
June 21, 2018 - InHealth Technologies becomes exclusive distributor of RENÚ Voice, RENÚ Gel in the United States
June 21, 2018 - New analysis links higher BMI to lower breast cancer risk for younger women
June 21, 2018 - Interactive preclinical PET-MR workshop demonstrates benefits of multi-modality imaging
June 21, 2018 - Gene signature could improve early diagnosis of TB
June 21, 2018 - Psychiatric Drug Lithium Tied to Birth Defect Risk
June 21, 2018 - Preclinical study suggests ARID1a may be useful biomarker for immunotherapy
June 21, 2018 - Risks of cancer and mortality found to be lowest in light drinkers
June 21, 2018 - Fetal immune cells are fast-acting first responders to microbes in adulthood
June 21, 2018 - Researchers invent medical device for proliferation, differentiation of neural stem cells
June 21, 2018 - Study explores current understanding of human physiology, pathology, trauma and surgery in space
June 21, 2018 - Scientists explore interactions between chromosomes 12 and 17
June 21, 2018 - People with severe obesity constantly try to reduce or control their weight
June 21, 2018 - Relaxing ‘brain tingles’ may have benefits for both mental and physical health
June 21, 2018 - Breakthrough discovery reveals brain metals that may drive progression of Alzheimer’s disease
June 21, 2018 - New methods of fragment-based lead discovery to identify potential antibiotics
June 21, 2018 - Recovery and Treatment | NIH MedlinePlus the Magazine
June 21, 2018 - Study finds cell-free DNA profiling as versatile method to monitor UTIs
June 21, 2018 - ‘Hidden’ driver discovered that helps prime the anti-tumor immune response
June 21, 2018 - Groundbreaking discovery could be key to preventing cancer metastasis
June 21, 2018 - Impulse control disorders found to be more common in people taking Parkinson’s drugs
June 21, 2018 - Study finds possible link between Type 2 diabetes and common white pigment
June 21, 2018 - Most emergency department patients wish to be involved in medical decision-making
June 21, 2018 - Study highlights growing problem of ‘iPad neck’ among young adults and women
June 21, 2018 - UT Southwestern scientists identify gene mutation linked with perplexing brain condition
June 21, 2018 - Probiotics could cut age-related bone loss in elderly women
June 21, 2018 - New study sheds light on role of vitamin D in healthy pregnancy
June 21, 2018 - Teva Provides Update on Clinical Trial of Fremanezumab for Use in Chronic Cluster Headache
June 21, 2018 - Unlocking the secrets of HIV’s persistence
June 21, 2018 - New guidelines recommend newborns with Down’s syndrome to receive leukemia test
June 21, 2018 - BetterYou’s new Magnesium Bone Lotion helps maximize bone health
June 21, 2018 - UH scientist receives grant to examine understudied part of glaucoma
June 21, 2018 - Lifestyle intervention could normalize unhealthy behaviors that lead to cancer, chronic disease
June 21, 2018 - Combining two anti-malarial vaccines could greatly reduce number of infections
June 21, 2018 - By 2030, prostate and lung cancers expected to be most common cancers among HIV population
June 21, 2018 - Researchers evaluate patient satisfaction and well-being after breast reconstruction
June 21, 2018 - Combining stem cell technology and artificial intelligence to diagnose genetic cardiac diseases
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