Breaking News
October 23, 2018 - Spectrum Pharmaceuticals Announces Release of Updated Poziotinib Data From MD Anderson Phase 2 Study in Non-Small Cell Lung Cancer Patients
October 23, 2018 - Cancer stem cells use ‘normal’ genes in abnormal ways
October 23, 2018 - Bad Blood: A conversation with investigative reporter John Carreyrou | News Center
October 23, 2018 - As U.S. fertility rates collapse, finger-pointing and blame follow
October 23, 2018 - Researchers develop promising targeted strategy to treat chemo-resistant blood cancer
October 23, 2018 - Pilot clinical trial shows effectiveness of bioelectronic medicine device for lupus
October 23, 2018 - Genentech’s combination therapy improves outcome in patients with non-squamous non-small cell lung cancer
October 23, 2018 - 11th World Stroke Congress examines high stroke impact in low- and middle-income countries
October 22, 2018 - Breast cancer survival could be extended with two new drug combinations
October 22, 2018 - Researchers discover how acne-causing bacteria resist treatment
October 22, 2018 - Cancer trial shows treating the prostate with radiotherapy improves survival
October 22, 2018 - New hope for a drug to treat lymphedema symptoms
October 22, 2018 - Immune-Based Treatment Helps Fight Aggressive Breast Cancer, Study Finds
October 22, 2018 - Takeda announces positive Phase 3 ALTA-1L data in first-line therapy for advanced ALK+ NSCLC
October 22, 2018 - Paternal exercise has significant impact on child’s lifelong metabolic health
October 22, 2018 - Targeting specific genomic mutation in breast cancer improves survival
October 22, 2018 - Loss of tumor protein p53 helps cancer cells grow in hostile environment
October 22, 2018 - IDT to demonstrate CRISPR expertise at European-focused events
October 22, 2018 - Breathing through the nose improves memory consolidation
October 22, 2018 - Recreational Marijuana Now Legal in Canada
October 22, 2018 - Scientists reveal drumming helps schoolchildren diagnosed with autism
October 22, 2018 - A stage IV cancer patient discusses what it means to live well with serious illness
October 22, 2018 - In Kids with Autism, Short Questionnaire May Detect GI Disorders
October 22, 2018 - Merck presents MK-1454 Phase 1 data for treatment of advanced solid tumors or lymphomas
October 22, 2018 - Aspirin may be effective in preventing blood clots after knee replacement
October 22, 2018 - Drug cocktail that increases lifespan discovered
October 22, 2018 - Gilead Sciences presents Phase 3 results of filgotinib in biologic-experienced rheumatoid arthritis at 2018 ACR/ARHP Annual Meeting
October 22, 2018 - Study shows potential positive impact of group prenatal care on birth outcomes
October 22, 2018 - Immunotherapy with pembrolizumab extends survival in metastatic or recurrent head and neck cancer
October 22, 2018 - Health Tip: Keep Ticks Away
October 22, 2018 - Obsessive-compulsive disorder – Genetics Home Reference
October 22, 2018 - Researchers find disrupted functional connectivity in cerebellum of adults with HF-ASD
October 22, 2018 - Deciphera presents Phase 1 clinical results of DCC-2618 in patients with gastrointestinal stromal tumors
October 22, 2018 - Combination of Opdivo and Yervoy shows four-year survival benefits in patients with advanced melanoma
October 22, 2018 - Overcoming bottlenecks in early drug discovery with the power of sound
October 22, 2018 - Scientists discover genes that contribute to ADHD development
October 22, 2018 - Incyte announces Phase 2 FIGHT-202 trial data in patients with cholangiocarcinoma
October 22, 2018 - FDA approves update to Rituxan label to include information on treatment of rare forms of vasculitis
October 22, 2018 - At-home biofeedback therapy effective in relieving difficult-to-treat constipation
October 22, 2018 - Merck presents KEYNOTE-057 trial results for patients with high-risk non-muscle invasive bladder cancer
October 22, 2018 - People with periodontal disease less likely to reach healthy blood pressure ranges
October 22, 2018 - Phase III LONSURF study shows progression-free survival in patients with refractory metastatic gastric cancer
October 22, 2018 - Primary care doctors ‘not doing enough’ to curb STDs
October 22, 2018 - Pfizer announces PALOMA-3 trial results in patients with HR+, HER2- metastatic breast cancer
October 22, 2018 - ImmunoGen announces study results of platinum-resistant ovarian cancer therapy at ESMO 2018 Congress
October 22, 2018 - Study findings could set new standard of care for advanced anal cancer
October 22, 2018 - Erlotinib improves progression-free survival in EGFR mutated NSCLC
October 22, 2018 - Pain, insomnia, and depression often drive osteoarthritis patients to seek medical care
October 22, 2018 - The International Society of Refractive Surgery honors Vivior Chairman with Casebeer Award
October 22, 2018 - Multi-strain probiotic helps reduce chemotherapy-induced diarrhea in cancer patients
October 22, 2018 - Study shows potential of avelumab plus axitinib as new treatment option for patients with advanced RCC
October 22, 2018 - Vertex gets European CHMP positive opinion for KALYDECO to treat patients with cystic fibrosis
October 22, 2018 - Phase III trial reports positive results with HDAC inhibitor in advanced breast cancer patients
October 22, 2018 - Prostate radiotherapy improves survival in men with low burden of metastatic disease
October 22, 2018 - Duration of respiratory disturbances may better predict mortality risk from OSA
October 22, 2018 - Free phone app helps low-income obese patients to lose weight
October 22, 2018 - Immunotherapy with nivolumab and ipilimumab may improve survival in patients with MSI-high metastatic colorectal cancers
October 22, 2018 - FOTIVDA expected to be included in new ESMO guidelines for advanced renal cell carcinoma
October 22, 2018 - Compression Collar May Protect Brain of Female Soccer Players
October 22, 2018 - Technique visualizes neuron communication
October 22, 2018 - Advancement in medical imaging methods for health care
October 22, 2018 - Takeda presents vedolizumab phase 3 VISIBLE 1 trial results for treatment of moderately to severely active ulcerative colitis
October 22, 2018 - Immunotherapy increases survival in some patients with metastatic triple negative breast cancer
October 22, 2018 - Exelixis presents CABOSUN and METEOR trial results in patients with advanced renal cell carcinoma
October 22, 2018 - LYNPARZA Phase III SOLO-1 results show improved outcome for patients with advanced BRCA-mutated ovarian cancer
October 22, 2018 - Brainlab unveils ExacTrac Dynamic at ASTRO meeting in San Antonio, Texas
October 22, 2018 - Not exercising is worse than smoking, diabetes or heart disease finds study
October 22, 2018 - Shorter course of trastuzumab could be an option for women with HER2+ early breast cancer
October 22, 2018 - Map of Mouse Hippocampus Could Be Weapon Against Alzheimer’s
October 22, 2018 - Psychotropic polypharmacy is common in Alzheimer’s disease
October 22, 2018 - Texas A&M and UTA establish Texas Genomics Core Alliance
October 22, 2018 - Analyzing mouse’s potential as animal model of decision-making
October 22, 2018 - Radiotherapy can prolong survival in prostate cancer
October 22, 2018 - A genetic mutation involved in relapse
October 21, 2018 - Report reveals growing impact of cannabis on young people
October 21, 2018 - NSF awards $5 million grant to help scientists magnify societal impact of research
October 21, 2018 - Fertility Rates Down for Each Urbanization Level 2007 to 2017
October 21, 2018 - Genetically engineered 3-D human muscle transplant in a murine model
October 21, 2018 - Moms’ tight work schedules may affect their children’s sleep
October 21, 2018 - AHA: No Direct Link Between Preeclampsia and Cognitive Impairment, Study Finds
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