Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
Effective Machine Learning Needs Leadership — Not AI Hype
 Originally published in BigThink, Feb 12, 2024.  Excerpted from The...
Today’s AI Won’t Radically Transform Society, But It’s Already Reshaping Business
 Originally published in Fast Company, Jan 5, 2024. Eric...
Calculating Customer Potential with Share of Wallet
 No question about it: We, as consumers have our...
A University Curriculum Supplement to Teach a Business Framework for ML Deployment
    In 2023, as a visiting analytics professor...
SHARE THIS:

5 years ago
Wise Practitioner – Predictive Analytics Interview Series: Sara Golas, Partners HealthCare Pivot Labs & Jorn op den Buijs, Philips Research

 

By: Jeff Deal, Conference Chair, Predictive Analytics World for Healthcare

In anticipation of their upcoming conference presentation at Predictive Analytics World for Healthcare Las Vegas, June 16-20, 2019, we asked Sara Golas, Senior Data Specialist at Partners HealthCare Pivot Labs & Jorn op den Buijs, Senior Scientist at Philips Research, a few questions about their deployment of predictive analytics. Catch a glimpse of their presentation, Early Identification of Elderly at Risk of Emergency Department Visits, and see what’s in store at the PAW Healthcare conference in Las Vegas.

Q: In your work with predictive analytics, what area of healthcare are you focused on?

A: Sara Golas is the senior data specialist for Partners HealthCare Pivot Labs, a multi-disciplinary research and analytics group focusing on the development, testing, and validation of patient-centric digital health innovations.

A: Jorn op den Buijs is a senior scientist with Philips Research, performing predictive analytics research for the Philips Lifeline Personal Emergency Response System (PERS). This is an emergency pendant with 24/7 connection to a response center that enables elderly to get help fast in case of an incident, such as a fall or breathing problems.

In a joint study, Pivot Labs and Philips are looking for ways to improve outcomes by avoiding stressful and costly emergency care.

Q: What outcomes do your models predict?

A: Our models predict emergent healthcare utilization, such as ambulance transport to the hospital, emergency department visits and hospitalizations.

Q: How does predictive analytics deliver value at your organization(s)? What is one specific way in which it actively drives decisions or impacts operations?

A: Predictive analytics serves to identify patients with high risk for emergency care utilization. High-risk patients are proactively contacted by a dedicated nurse to discuss measures that could prevent an upcoming emergency event. This is not only beneficial for the patient, but could also save tremendous costs by preventing expensive utilization.

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

A: Retrospective validation showed that patients in the top 1% predicted high-risk segment were 12 times more likely to require emergency ambulance transport to the hospital in the next 30 days.

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

A: While personal emergency response service (PERS) programs are traditionally described as fall management services for seniors, our analysis indicates that they are also used for many acute symptoms often related to underlying chronic conditions. Through linkage of clinical EHR data and PERS device data, we found that more than half of hospital admissions just prior to enrolling with PERS are related to chronic conditions. Furthermore, we found that nearly half of the incidents reported via the PERS are related to physical and psychological issues other than falls.

Q: What areas of healthcare do you think have seen the greatest advances or ROI from the use of predictive analytics?

A: With value-based care gaining prominence, predicting avoidable emergency room visits and hospital admissions will be of great importance to healthcare systems. For older adults in particular, this may in turn also help to improve the quality of life of those who wish to age in place.

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

A: Predicting the risk of patients needing ambulance transport in any upcoming period enables the delivery of timely, seamless care and targeted interventions to help reduce avoidable emergency admissions.

—————————–

Don’t miss their presentation, Early Identification of Elderly at Risk of Emergency Department Visits, at PAW Healthcare on Tuesday, June 18, 2019 from 3:55 to 4:40 PM. Click here to register for attendance.

By: Jeff Deal, Conference Chair, Predictive Analytics World for Healthcare

This content is restricted to site members. If you are an existing user, please log in on the right (desktop) or below (mobile). If not, register today and gain free access to original content and industry news. See the details here.

Comments are closed.