Privacy Analytics enables predictive models for improved renal patient care

Privacy Analytics enables predictive models for improved renal patient care

Kidney disease affects hundreds of millions of people worldwide. Healthcare providers are challenged to deliver the best program of care, at the right time, to help their patients enjoy the highest quality of life possible without putting unnecessary strain on their local healthcare system.

In the U.S. alone, an estimated 37 million people, or about 15 percent of the adult population, suffer from kidney disease according to the most recent data from the National Kidney Foundation. Of these, more than 554,000 people have irreversible kidney failure, also known as end-stage kidney disease (ESKD). As these patients wait for a kidney transplant, they require dialysis to survive – either through home dialysis therapy or an outpatient program that involves several visits a week to an outpatient clinic. There they are connected to a dialysis machine for several hours at a time.

The Background

Working to improve care and patient outcomes

Since 1997, the New York-based Renal Research Institute (RRI) has been working with several national and international academic and research partners to measurably improve patient outcomes through research, technical innovation, implementation of processes, and education.

RRI was originally founded as a joint venture between Fresenius Medical Care (FMC) and Beth Israel Hospital in New York City. FMC provides kidney dialysis products and services through a network of about 4,000 outpatient clinics, serving hundreds of thousands of patients, and has a 38 percent share of the U.S. dialysis market.

“Without Privacy Analytics, we would not have been able to continue with the initiative.”

Len Usvyat

Vice President, Applied Data Science, Biostatistics, and Epidemiology at Fresenius Medical Care

In 2009, RRI, under the leadership of Research Director Peter Kotanko, created the MONitoring Dialysis Outcomes (MONDO) Consortium. MONDO is an international consortium that includes numerous dialysis providers and researchers from the Americas, Europe, Asia, and Africa.

The primary objective of RRI and the members of its MONDO consortium is to advance our understanding of the biology and epidemiology of dialysis patients. All research results are then published in peer-reviewed journals. Such knowledge dissemination is key to raising standards of care for patients, reducing hospitalizations, and driving new operating efficiencies for dialysis outpatient clinics around the world.

FMC is a MONDO participant organization and contributes one of the largest pools of patient data to the consortium. There is no cost and no for-profit agenda associated with MONDO participation. “Participants must simply have a pool of individual, per treatment-level ESKD patient data, and genuine scientific or academic interest in analyzing this data at a holistic level,” said Len Usvyat, FMC’s Vice President, Applied Data Science, Biostatistics, and Epidemiology.

The Challenge

Understanding how to reduce hospitalizations

Analysis of North American patient data had revealed specific trends in outpatient vitals – such as changes in blood pressure or declines in body weight – that preceded an admission to hospital. To better understand if this was a specific North American or a more general observation, RRI, through MONDO, aimed to access and analyze other ESKD patient datasets from elsewhere in the world. Its goal was to determine if predictive models could be created that would enable more proactive, preventative, and cost-effective patient care.

“The chief end goal for everyone is to reduce hospitalizations,” Usvyat said. “Avoiding hospitalization is better for the patient for many reasons. Hospitalizations disrupt patients’ lives, take them away from their loved ones and put them at risk for hospital-acquired infections. Even if the issue that led to their admittance is resolved, by the time they are discharged, they are often weaker and frailer than before.”

The External Factors

Complying with emerging privacy regulations

MONDO participants were mindful from the start about protecting patient privacy. From a regulatory perspective, the arrival of the EU’s General Data Protection Regulation (GDPR) in 2016 raised significant concerns and uncertainty about how MONDO researchers could continue to work with patient data.

“We didn’t know what to do,” Usvyat said. “We were sitting on the data and asking, what could we now do with it? How do we handle different kinds of patient identifiers?”

He and his colleagues realized they needed outside expertise. A recommendation from one of FMC’s leading privacy officers led to a conversation with Privacy Analytics that demonstrated in short order this was the team for the job.

Gain confidence to use and share sensitive data

Find out how our advisory services can help you safely leverage data derived from information about people. Watch this 15-minute webinar.

The Solution

‘White glove’ service and global expertise

“Privacy Analytics was great to work with,” Usvyat said. “They really did walk us through the process of assessing the privacy risks of the data from the very beginning. When dealing with a novel regulatory requirement as blurry as GDPR, we needed, as a group of international partners, expert guidance, and concrete steps on how to manage our database and ensure it was compliant. Without Privacy Analytics, we would not have been able to continue with the initiative.”

It’s very much been about delivering “white glove” treatment, said Privacy Analytics’ Data Scientist Andrew Dickinson.

“When working with a client like RRI that has so many partners across so many jurisdictions and regulatory regimes, no question is out of scope,” he said. “We had many ad hoc meetings and conducted additional research to answer pressing questions related to best practices in achieving the richest possible data while protecting privacy.”

The Result

Continued research and publication drives better patient outcomes

RRI’s work with Privacy Analytics has ensured that the research findings of the MONDO consortium can continue to be shared through publication, in full compliance with regulations.

“We have an obligation to publish because we have so much secured data and so many valuable research findings,” Usvyat said. “We need to publish widely to ensure the dissemination of research findings because access to the MONDO dataset is not granted to anyone who is not part of the consortium.”

Data pooling and analysis among MONDO participants has resulted in the development of new predictive models that have helped to reduce hospitalizations. Reductions in hospital admissions among ESKD patients of up to 10 percent have been observed because of MONDO research.

What’s Next

More data for more insight into kidney disease and COVID-19

RRI’s first engagement with Privacy Analytics for the MONDO database involved the data of some 150,000 patients from dozens of countries. The primary goal of this first engagement was to ensure compliance with GDPR while making the data useable.

The partners are now ramping up on a new project that will have Privacy Analytics addressing the data of some 600,000 patients from around the world. This project will drive compliance with other regulatory regimes in other jurisdictions. The team will apply a single consistent model that protects the privacy of patients, while preserving the utility of their data.

The second project involves more regional data, from more patients, in more countries, including patient-level data pertaining to COVID-19. It also builds on lessons learned by RRI and its MONDO members during the first project with Privacy Analytics.

“There is a lot of interest in understanding COVID data, and dialysis providers are kind of unique in that they see so many of these patients and can say something about them from what we see in the data,” Usvyat said.

Archiving / Destroying

Are you unleashing the full value of data you retain?

Your Challenges

Do you need help...

OUR SOLUTION

Value Retention

Client Success

Client: Comcast

Situation: California’s Consumer Privacy Act inspired Comcast to evolve the way in which they protect the privacy of customers who consent to share personal information with them.

Evaluating

Are you achieving intended outcomes from data?

Your Challenge

Do you need help...

OUR SOLUTION

Unbiased Results

Client Success

Client: Integrate.ai

Situation: Integrate.ai’s AI-powered tech helps clients improve their online experience by sharing signals about website visitor intent. They wanted to ensure privacy remained fully protected within the machine learning / AI context that produces these signals.

Accessing

Do the right people have the right data?

Your Challenges

Do you need help...

OUR SOLUTION

Usable and Reusable Data

Client Success

Client: Novartis

Situation: Novartis’ digital transformation in drug R&D drives their need to maximize value from vast stores of clinical study data for critical internal research enabled by their data42 platform.

 

Maintaining

Are you empowering people to safely leverage trusted data?

Your Challenges

Do you need help...

OUR SOLUTION

Security / compliance efficiency

CLIENT SUCCESS

Client: ASCO’s CancerLinQ

Situation: CancerLinQ™, a subsidiary of American Society of Clinical Oncology, is a rapid learning healthcare system that helps oncologists aggregate and analyze data on cancer patients to improve care. To achieve this goal, they must de-identify patient data provided by subscribing practices across the U.S.

 

Acquiring / Collecting

Are you acquiring the right data? Do you have appropriate consent?

Your Challenge

Do you need help...

OUR SOLUTIONS

Consent / Contracting strategy

Client Success

Client: IQVIA

Situation: Needed to ensure the primary market research process was fully compliant with internal policies and regulations such as GDPR. 

 

Planning

Are You Effectively Planning for Success?

Your Challenges

Do you need help...

OUR SOLUTION

Build privacy in by design

Client Success

Client: Nuance

Situation: Needed to enable AI-driven product innovation with a defensible governance program for the safe and responsible use
of voice-to-text data under Shrems II.

 

Join the next 5 Safes Data Privacy webinar

This course runs on the 2nd Wednesday of every month, at 11 a.m. ET (45 mins). Click the button to register and select the date that works best for you.