Premium
Who is More Injury‐Prone? Prediction and Assessment of Injury Risk
Author(s) -
Gupta Ashish,
Wilkerson Gary B.,
Sharda Ramesh,
Colston Marisa A.
Publication year - 2019
Publication title -
decision sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.238
H-Index - 108
eISSN - 1540-5915
pISSN - 0011-7315
DOI - 10.1111/deci.12333
Subject(s) - risk analysis (engineering) , psychological intervention , risk assessment , productivity , human factors and ergonomics , computer science , injury prevention , work (physics) , poison control , business , applied psychology , psychology , medicine , medical emergency , computer security , engineering , nursing , mechanical engineering , economics , macroeconomics
ABSTRACT Injuries are the primary determinant of an individual's mobility, which affect not just their workplace productivity in intensive environments such as manufacturing, but also their decision‐making ability and quality of life. Managers typically assign workers to projects or tasks without having knowledge about their functional capabilities or current state of injury risk as injuries remain highly underreported at workplaces for fear of reprisal and other reasons. Therefore, high‐quality research on injury prevention is nearly nonexistent. Procedures that we use in this study for developing a prediction model for identification of college football players at an elevated injury risk could also be used to quantify injury risk in various occupational settings. Using a number of measurements and models, we arrive at an estimate of an individual's injury likelihood. Our measures include ratings of movement efficiency through physical performance tests, acceleration using Internet of Things (IoT) devices, functional role classifications, and recorded exposures to high‐risk conditions. Findings prescribe several approaches and decision rules for prediction of injury risk and suggest that training programs need to consider an individual's injury risk rather than offer a ‘one‐size‐fits‐all’ approach. The analytics models derived from a combination of injury risk screening and surveillance data can be used for making decisions about targeting employee‐centric risk‐reduction interventions, improved matching of tasks to individuals, or deciding job rotation for improved performance, all while enhancing the quality of life of individuals and reducing the escalating costs of work‐related injuries borne by employers. These models can also be developed for smartphones.