Enhancing agriculture, forestry, and fishing injury surveillance using free text data.

Details

• Personal Author:
  Hirabayashi L ; Scott E
• Description:
  Background: Access to free text in existing administrative databases has proved useful in identifying and characterizing agricultural, forestry, and fishing (AFF) related injuries. Particularly, narratives from pre-hospital care reports (PCRs) provide specific details of the injury event directly from the scene and from interviewing the patient. These narratives, which are retained by a number of states, are systematically searched for AFF specific keywords and verified for AFF relatedness. The Occupational Injury and Illness Classification System (OIICS) is then applied to the dataset by a team of coders. To enhance this process, researchers are applying Bayesian methodologies to speed up text review and ultimately, reduce the cost of the surveillance system. Methods: The process described above has been applied to PCRs from Maine and New Hampshire for a three-year period to create a confirmed injury dataset. Agriculture, forestry and fishing records were identified by industry, and by the certainty of the injury report (e.g. true case, suspected case) This dataset was then split, along with non AFF records, into a training and validation datasets to build and test Bayesian algorithms for the determination of AFF records. Results: Maine and New Hampshire had 767,060 pre-hospital care report records for 2008-2010. Of these, 28,341 contained one or more of 161 AFF keywords (searched either by character string or exact word). Of the keyword containing records, 1,203 were determined to be AFF related. Results of the Bayesian methodology are currently being testing and will be presented at the conference. Discussion: Pre-hospital care reports are a rich source of occupational injury data, especially for agriculture, forestry and fishing. These injuries are able to be identified and coded using the OIICS classification scheme, making them comparable to other industries. Pre-hospital care reports have the potential to be a useful source of research data, beyond AFF, but for other industries and for public health in general. Conclusions on the success of using Bayesian methods to enhance coding of AFF cases will be discussed at the conference.
• Subjects:
  Accidents, Occupational Environmental Monitoring Epidemiology Health Surveys Metal Workers Occupational Health Preceptorship Safety Surveys And Questionnaires
• Keywords:
  Agriculture Fishing Forestry Injuries Surveillance
• Publisher:
  National Institute for Occupational Safety and Health
• Document Type:
  Text
• Funding:
  Cooperative Agreement
• Genre:
  Abstract
• Place as Subject:
  Maine ; New Hampshire ; New York ; OSHA Region 1 ; OSHA Region 2
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  77-78
• NIOSHTIC Number:
  nn:20069988
• Citation:
  National Occupational Injury Research Symposium 2018, (NOIRS 2018), October 16-18, 2018, Morgantown, West Virginia. Morgantown, WV: U.S. Department of Health and Human Services, Public Health Service, Centers for Disease Control and Prevention, National Institute for Occupational Safety and Health, 2018 Oct; :77-78
• Contact Point Address:
  Erika E. Scott, PhD, Deputy Director, Northeast Ctr for Occup Health & Safety in Agriculture, Forestry & Fishing, One Atwell Rd, Cooperstown, NY 13326
• Email:
  Erika.Scott@bassett.org
• Federal Fiscal Year:
  2019
• NORA Priority Area:
  Agriculture, Forestry and Fishing
• Performing Organization:
  Mary Imogene Bassett Hospital, Cooperstown, New York
• Peer Reviewed:
  False
• Start Date:
  20010930
• Source Full Name:
  National Occupational Injury Research Symposium 2018, (NOIRS 2018), October 16-18, 2018, Morgantown, West Virginia
• End Date:
  20270831
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:cfed4de96cff937d04442e98dfea8017e95feab4624458308e81aaf28ed346d58e6a384f955985e7e6b3ae73508ebd1291d8bbf400bbb97fe6c873957e614371
• Download URL:
  https://stacks.cdc.gov/view/cdc/181993/cdc_181993_DS1.pdf
• File Type:
  [PDF - 609.35 KB ]