AIHce EXP Rebroadcast: The Future of Machine Learning in IH - Modern Predictive Modeling Approaches

Date: Thursday, Mar. 18, 2021 - Thursday, Mar. 18, 2021
Time: 1:00 p.m. - 2:00 p.m.

Add to Calendar: Ical Google Yahoo

Thursday March 18, 2021

1:00 - 2:00 pm ET

Earn 1 Contact Hour

Member $49 | Nonmember $59 | Student $25

Industrial hygienists are using an increasingly diverse set of data streams to facilitate decision-making in the workplace. Due to expanding analytical capabilities, more detailed information can be obtained for a wider range of potential hazards simultaneously. The constant expansion of available data necessitates the use of modern data analysis techniques to effectively translate the stream of data into actionable intelligence. One such approach involved Bayesian statistical analysis techniques. Recent advances in these techniques will soon allow practitioners to use existing data to produce predictive models using a combination of machine learning, or artificial intelligence. The purpose of the educational session is to discuss recent advances in machine learning that leverage modern data analysis techniques to produce risk prediction models(e.g,Bayesian Belief Networks) that can be used by IH professionals to design effective risk prevention programs. Finally, the role of citizen scientists in the collection of data for predictive modeling will be discussed. In addition to the history and recent developments in the field, attendees at the session will be engaged in an interactive session to provide feedback on applications in their field.

Learning Outcomes

Upon completion, the participant will be able to:
• Define the operational meaning of machine learning and predictive models.
• Discuss the history and applications of machine learning techniques.
• Determine how predictive models like Bayesian Belief Networks are developed.
• Outline applications of machine learning and predictive models in EHS.
• Determine the role of citizen scientists and practitioners in the development of predictive models.
• Recognize data quality challenges and limitations to machine learning use in occupational settings.
• Utilize resources for processing and analyzing data and developing predictive models.
• Identify knowledge gaps in the application of predictive models to IH settings.