Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
Three Best Practices for Unilever’s Global Analytics Initiatives
    This article from Morgan Vawter, Global Vice...
Getting Machine Learning Projects from Idea to Execution
 Originally published in Harvard Business Review Machine learning might...
Eric Siegel on Bloomberg Businessweek
  Listen to Eric Siegel, former Columbia University Professor,...
Effective Machine Learning Needs Leadership — Not AI Hype
 Originally published in BigThink, Feb 12, 2024.  Excerpted from The...
SHARE THIS:

5 years ago
Wise Practitioner – Predictive Analytics Interview Series: Steve Lamb, IPM.ai and Dan Fisher, Swoop

 

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 Steve Lamb, Principal at IPM.ai and Dan Fisher, VP Life Sciences at Swoop, a few questions about their deployment of predictive analytics. Catch a glimpse of their presentation, The Application of Artificial Intelligence in the Rare Disease Market, 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: In the shift towards value-based care, bio-pharma and payers increasingly have aligned interests focused on outcomes. Our focus is in bio-pharma commercial analytics and HEOR, helping our clients to predict patient level outcomes of interest, and facilitate action to expedite.

Q: What outcomes do your models predict?

A: Our models are able to predict many different end events at the patient level. As precision medicine increasingly becomes a reality, patient level predictions can be met with appropriate diagnoses, therapies, treatment regimens, etc. So the most obvious prediction would be a diagnosis with a specific condition, but can be as nuanced as a patient likely to respond well to a given therapy, a patient who is about to progress or relapse, a patient who falls into a specific subset of patients, etc. Anything we can define in our claims data (280M+ de-identified patients, ~8 years of cross-TA history), we can predict more of.

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

A: Predictive analytics allows us to connect our clients to patients who would benefit form a given therapy. This enables patients to get the care they need, and our clients to ensure they are targeting their sales and marketing efforts towards the optimal set of patients in need and their corresponding HCPs.

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

A: We have continuously successfully predicted rare disease diagnoses for patients who have been bouncing around the healthcare system for years without interacting with the correct physician to have their rare disease properly diagnosed. This in turn enables the patients to receive proper treatment for the condition they actually have, rather than continue to receive unnecessary and frustrating testing, and expensive yet ineffective treatment.

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

A: With our supervised machine learning techniques, we can take our clients on an empirical journey into the exploration of the actual patterns of symptomatology and work-up prior to diagnoses. Combinations of Rx claims, Px claims, Mx claims—the magnitude of events, the sequences of events, the time between events—allows our clients the opportunity to cast off what they think they know about the patterns of work-up in the patient journey, and let the data tell its own story.

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

A: Given the shift to value-based care and the increasing alignment of stakeholders (patients, providers, payers, and bio-pharma) in facilitating appropriate diagnosis and treatment, the ability to identify appropriate health interventions has never been more timely. ROI from these collective initiatives is contingent upon appropriate predictions, precision in identifying populations and corresponding pull through by relevant stakeholders.

With that said, any improvement in care delivery and patient outcomes that is enabled by predictive analytics is a great achievement.

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

A: Leveraging real world data and machine learning can enable patients to be diagnosed sooner than they would otherwise be, improving the care they receive and ultimately improving their outcomes.

—————————–

Don’t miss their presentation, The Application of Artificial Intelligence in the Rare Disease Market, at PAW Healthcare on Tuesday, June 18, 2019 from 4:45 to 5:30 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.