Prosperdtx Presents Case Study Results at ISPOR 2022

Prosperdtx Presents Case Study Results at ISPOR 2022

Health Economic Research Study Presented at ISPOR, and Published in the Journal Value in Health, Demonstrated Reduction in COVID-19 Mortality Through Causal Inference Analysis

 

SHORT HILLS, NJ -- (BUSINESS WIRE) – May 24, 2022 -- Prosperdtx, a leader in the emerging field of digital therapeutics providing predictive and personalized continuity of care for cancer patients, announced the results of a health economic outcomes study demonstrating the superiority of using causal inference techniques that directly improved health outcomes. The supporting data from the study are being presented at the International Society for Pharmacoeconomics and Outcomes Research (ISPOR) Meeting being held in Washington, DC, or virtually, from May 15 to May 18, 2022. The study is published in the Society’s peer-reviewed journalValue in Health.

For the time-period studied, less than 1% of the U.S. population lived in long-term care facilities, yet this subset of the population accounted for over 100,000 deaths which was 22% of total COVID-19 related deaths.1 As a result of a lack of experimental evidence to treat COVID-19, it is critical to focus on analysis of real-world data to identify causal relationships between treatments and policies to mortality and morbidity among the high-risk individuals. This study implemented causal inference analysis to longitudinal health record data of 4,091 long-term care high-risk patients with COVID-19 to ascertain specific interventions that directly improved health outcomes.

“Our study looked at an analysis of real-world data, using causal inference methodology that provided information with superior characteristics to information collected and analyzed through traditional methods,” said Robert Goldberg, Ph.D., Co-Founder and Chief Strategy Officer. “As a result of this study, we were able to:

  • Identify specific medications that reduced the risk of death
  • Estimated that $4.57 million in hospice care would have been avoided.”

The study showed that from January through October of 2020, predictions of treatment effects using traditional statistical analysis or machine learning techniques are unable to adequately identify actionable causal factors that lead to optimal health. Instead, under dynamic clinical conditions such as COVID-19 patient care, causal inference techniques, as developed by Judea Pearl PhD provided reliable methods for using observational data to prospectively inform treatment optimization.2

The study demonstrated the techniques Pearl has developed, including graphical models of causal relationships and counterfactual evaluation of assumptions can be used identify actionable causal factors of disease and treatment response at a patient level.5  Goldberg noted that, “Our study suggests that causal inference modeling of real-world data can dynamically optimize continuity of care for better health outcomes and lower costs.  And we look forward to working with other researchers and health stakeholders to demonstrate how causal inference can be used to deliver personalized medicine and improve the value of care.”

Details of this study are being presented at the 2022 ISPOR Meeting held from May 15 to May 18. For more information on ISPOR’s program please visit the conference website at https://www.ispor.org/conferences-education/conferences/upcoming-conferences/ispor-2022/program/program

The health economic outcomes poster on the reduction of mortality in COVID-19 patients through causal inference analysis presented at the ISPOR 2022 virtual conference is as follows:

Session title: Studies on COVID-19 Healthcare Impacts

Title:Identifying Interventions That Reduced COVID-19 Mortality in Long-Term Care Facilities: A Causal Inference Analysis 

Authors: Amina Ahmed, MD1, Robert Goldberg, PhD2, Joseph Swiader BS2, Zachery A.P. Wintrob MS MA2, Maggie Yilmaz MS2

Institutions: CareOne Management, LLC, Fort Lee, NJ1, Prosperdtx Inc., Short Hills NJ2

Virtual Session:

Date: Tuesday, May 17

Time: 4:30-5:30 PM ET

Abstract Number: 115871

About Prosperdtx, Inc.

Prosperdtx is a leader in the emerging field of digital therapeutics. Prosperdtx is maximizing the continuity of cancer care so that patients can live longer better lives while reducing the cost of healthcare. Prosperdtx is at the intersection of medical innovation and digital therapeutics which is advancing digital technology platforms developed to help cancer patients along their treatment journey delivering high-value personalized precision cancer care. For more information, visit prosperdtx.com. Follow us on social media @prosperdtx, LinkedIN, Twitter, Facebook, Instagram and YouTube. 

Disclosure Notice

Some of the statements in this press release may be forward-looking statements or statements of future expectations based on currently available information. Such statements are naturally subject to risks and uncertainties. Prosperdtx does not make any representation or warranty, express or implied, as to the accuracy, completeness or updated status of such statements. Therefore, in no case whatsoever will Prosperdtx or its affiliate companies be liable to anyone for any decision made or action taken in conjunction with the information and/or statements in this press release or for any related damages.

1 As of the week ending 07/11/2021 133,443 of the 611,000 (21.8 percent) confirmed deaths due to COVID-19 were nursing home residents. https://data.cms.gov/covid-19/covid-19-nursing-home-data. https://www.kff.org/other/state-indicator/number-of-nursing-facility-residents/?currentTimeframe=0&sortModel=%7B%22colId%22:%22Location%22,%22sort%22:%22asc%22%7D

2 Pearl. Judea, 2018. The Seven Tools of Causal Inference with Reflections on Machine Learning. 1, 1 (November 2018), 6 pages. https://doi.org/10.1145/

3 Ibid.,

4 Miruna Oprescu & Vasilis Syrgkanis & Zhiwei Steven Wu, 2018. "Orthogonal Random Forest for Causal Inference," Papers 1806.03467, arXiv.org, revised Sep 2019

5 Bareinboim E, Pearl J. Causal inference and the data-fusion problem. Proc Natl Acad Sci U S A. 2016 Jul 5; 113(27):7345-52. doi: 10.1073/pnas.1510507113.  

Search our shop