Psychomotor function measured via online activity predicts motor vehicle fatality risk

Tim Althoff,Ryen W White,Eric Horvitz

doi:10.1038/s41746-017-0003-3

Tim Althoff, Ryen W White + Show 1 more

Open Access

https://doi.org/10.1038/s41746-017-0003-3

Copy DOI

Abstract

Impaired psychomotor performance severely increases the risk of fatal and non-fatal car accidents. However, we currently lack methods to continuously and non-intrusively monitor psychomotor performance. We show we can estimate psychomotor function at population scale from 16 billion observations of typing speeds during the input of web search queries. We show that these estimates exhibit diurnal variation with a substantial increase during typical sleep times, matching published accident risk rates. Further, we show that psychomotor impairment, as measured by keystroke timing, predicts motor vehicle fatality risk on a population level (Spearman ρ = 0.61; p « 10−10). The methods and results highlight a promising direction of harnessing ambient streams of data, such as patterns of interactions with devices, as large-scale sensors to continuously and non-intrusively monitor human psychomotor performance at population scale.

Highlights

Motor vehicle crashes are responsible for 1.25 million deaths annually and are the leading cause of death for people of ages 15–29.1 The risk of car crashes based on operator error increases significantly with insufficient sleep.[2,3] Recent advances in inferring psychomotor function using measures of typing speed of queries during web search enable population-scale estimation of psychomotor impairment.[4]
County-level average keystroke timing is strongly correlated with motor vehicle fatalities across 2723 counties (Spearman ρ = 0.61; p « 10−10; Fig. 1a)
Search queries and accident risk data were collected during different time periods and included subjects do not necessarily overlap

Summary

Introduction

Motor vehicle crashes are responsible for 1.25 million deaths annually and are the leading cause of death for people of ages 15–29.1 The risk of car crashes based on operator error increases significantly with insufficient sleep.[2,3] Recent advances in inferring psychomotor function using measures of typing speed of queries during web search enable population-scale estimation of psychomotor impairment.[4] We examine whether psychomotor performance as indicated by slower typing speeds during web search predicts population-level motor vehicle fatalities by locale

Methods

Results

Conclusion