Machine learning and Clever Hans, the Calculating Horse

5 November 2018 10:01 AM   •   Greg Simon   •   1 comment

Clever Hans, the Calculating Horse, was a sensation of the early 1900s. He appeared to be able to count, spell, and solve math problems – including fractions! Only after careful investigation did everyone learn that Hans was just responding to unconscious nonverbal cues from his trainer. Hans couldn’t actually calculate, but he could sense the answer his trainer was hoping for.

Gold Standard or Golden Calf?

8 October 2018 07:32 AM   •   Greg Simon   •   0 comments

Most of our measures and measurement tools were created in conference rooms or conference calls dominated by older white men. Over time, those “expert opinion” measures acquire a patina of authority. As time passes, we can start to equate familiarity or habit with accuracy or validity. Our experiences with NCQA/HEDIS measures regarding antidepressant medication adherence illustrate the tendency to over-value the familiar.

What's so funny about dimensionality reduction?

17 September 2018 09:50 AM   •   Greg Simon   •   0 comments

My wife handed me a recent issue of The New Yorker and recommended the Shouts and Murmurs column. It parodied a whistle-blowing data scientist testifying before Parliament. At first read, I didn’t think it was very funny. Then I realized: If you don’t think Shouts and Murmurs is very funny, then it’s probably about you.

Can you see me now?

20 August 2018 08:24 AM   •   Greg Simon   •   1 comment

As our health systems prepare to implement statistical models predicting risk of suicidal behavior, we’ve certainly heard concerns about how that information could be misused. Well-intentioned outreach programs could stray into being intrusive or even coercive. It’s being observed or known that’s the problem, even if nothing is ever said or done about it.

MHRN Blog World Cup Edition: What Soccer Referees Know about Causal Inference

27 June 2018 08:41 AM   •   Greg Simon   •   2 comments

When Nico Lodeiro falls down in the penalty area, I hold my breath waiting for the referee's call. Was it really a foul - or just Nico simulating a foul? I used to be surprised at how often the refs got it right, until a referee friend of mine explained what the refs are looking for.

Suicide Risk Prediction Models: I Like the Warning Light, but I’ll Keep My Hands on the Wheel

4 June 2018 08:30 AM   •   Greg Simon   •   3 comments

Our recent paper about predicting risk of suicidal behavior following mental health visits prompted questions from clinicians and health system leaders regarding practical utility of risk predictions. Our clinical partners asked, “Are machine learning algorithms accurate enough to replace clinicians’ judgement?”

Why I'll Join the All of Us Research Program

7 May 2018 09:39 AM   •   Greg Simon   •   0 comments

NIH’s All of Us Research Program officially launched on Sunday, May 6th. It’s an ambitious national effort to bring together at least one million people from across the U.S. in a long-term study of health across the lifespan.

Advice To Young Researchers: Don't Find Your Niche

6 April 2018 02:33 PM   •   Greg Simon   •   6 comments

Researchers focused on narrower questions are following the standard advice to all young mental health or health services researchers: Find your niche.

When does caring cross over into creepy?

6 March 2018 01:59 PM   •   Greg Simon   •   1 comment

A recent news article about the European Union’s new privacy rules prompted me to think more about population-based suicide prevention programs. Caring outreach that respects privacy is a difficult balance.

Alexa, should I increase my dose of Celexa?

5 February 2018 09:38 AM   •   Greg Simon   •   0 comments

The evolution of depression care management programs can be described in terms of task shifting. Initial Collaborative Care programs actually shifted some tasks up to specialty providers. Our MHRN Automated Outreach pilot project will take that task shifting one step further.