Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
Podcast: Four Things the Machine Learning Industry Must Learn from Self-Driving Cars
    Welcome to the next episode of The Machine...
A Refresher on Continuous Versus Discrete Input Variables
 How many times have I heard that the most...
Podcast: Why Deep Learning Could Expedite the Next AI Winter
  Welcome to the next episode of The Machine Learning...
PAW Preview Video: Evan Wimpey, Director of Strategic Analytics at Elder Research
 In anticipation of his upcoming presentation at Deep Learning...
SHARE THIS:

5 months ago
Wise Practitioner – Predictive Analytics Interview Series: Dohyeong Kim, PhD, at University of Texas at Dallas

 

In anticipation of his upcoming presentation at Predictive Analytics World for Healthcare, Las Vegas, June 19-24, 2022, we asked Dohyeong Kim, PhD, Professor and Associate Dean of Graduation Education Public Policy at University of Texas at Dallas, a few questions about their deployment of predictive analytics. Catch a glimpse of his presentation, Ambient PM Concentrations as a Precursor of Emergency Visits for Respirator Complaints: Roles of Deep Learning and Multi-Point Real Time Monitoring, and see what’s in store at the PAW for Healthcare conference.

Q: In your work with predictive analytics, what behavior or outcome do your models predict?

A: Daily counts of emergency room visits or individual asthmatic symptoms.

Q: How does predictive analytics deliver value at your organization – what is one specific way in which it actively drives decisions or operations?

A: Our predictive analytic tools help patients take necessary action to mitigate adverse symptoms or guide policymakers to design evidence-based environmental and health interventions.

Q: Can you describe a quantitative result, such as the predictive lift of your model or the ROI of an analytics initiative?

A: The predictive accuracy of our model is as good as the RMSE of 0.79.

Q: What surprising discovery or insight have you unearthed in your data?

A: Our results reveal evidence that accuracy in predicting emergency visit counts is improved substantially when spatial variations of air pollutants from multi-point stations are incorporated in the algorithm as a 9-day time window.

Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.

A: Our study explored the feasibility of deep learning algorithms to improve the accuracy of predicting daily emergency hospital visits by tracking their spatiotemporal association with PM concentrations. Our findings suggest guidelines on how environmental and health policymakers can arrange limited resources for emergency care and design ambient air monitoring and prevention strategies.

Don’t miss Dohyeong’s presentation, Ambient PM Concentrations as a Precursor of Emergency Visits for Respirator Complaints: Roles of Deep Learning and Multi-Point Real Time Monitoring, at PAW for Healthcare, on Wednesday, June 22, 2022, from 3:30 pm to 4:15 pm. Click here to register for attendance.

Leave a Reply