Life Sciences Commons^™

Enhancing Timeliness Of Drug Overdose Mortality Surveillance: A Machine Learning Approach, Patrick J. Ward, Peter J. Rock, Svetla Slavova, April M. Young, Terry L. Bunn, Ramakanth Kavuluru

Kentucky Injury Prevention and Research Center Faculty Publications

BACKGROUND: Timely data is key to effective public health responses to epidemics. Drug overdose deaths are identified in surveillance systems through ICD-10 codes present on death certificates. ICD-10 coding takes time, but free-text information is available on death certificates prior to ICD-10 coding. The objective of this study was to develop a machine learning method to classify free-text death certificates as drug overdoses to provide faster drug overdose mortality surveillance.

METHODS: Using 2017–2018 Kentucky death certificate data, free-text fields were tokenized and features were created from these tokens using natural language processing (NLP). Word, bigram, and trigram features were created …

Missed Work Due To Occupational Illness Among Hispanic Horse Workers, Ashley M. Bush, Susan C. Westneat, Steven R. Browning, Jennifer Swanberg

Kentucky Injury Prevention and Research Center Faculty Publications

Occupational illnesses are inadequately reported for agriculture, an industry dominated by a vulnerable Hispanic population and high fatal and nonfatal injury rates. Work-related illnesses can contribute to missed work, caused by a combination of personal and work factors, with costs to the individual, employer, and society. To better understand agricultural occupational illnesses, 225 Hispanic horse workers were interviewed via community-based convenience sampling. Descriptive statistics, bivariate analyses, and log binomial regression modeling were used to: (1) describe the prevalence of missed work due to work-related illnesses among Hispanic horse workers, (2) examine work-related and personal factors associated with missed work, and …