The September issue of the Texas Medical Association’s magazine, Texas Medicine Magazine, featured the efforts of C. Turner Lewis, III, MD, Medical Director of Children’s Medical Clinics of East Texas, to mitigate the harmful effects of pediatric asthma and alergies. Dr. Lewis employed a pilot program that included elements of PCCI’s predictive modeling to help reduce emergency department visits to zero over the course of a two-month period.
Click on the image below to read the entire article:
PCCI’s collaboration with a healthcare services coalition in Gregg County designed to improve support for mental health in the region was highlighted in the Longview News-Journal. Click the headline below to see the full article:
The Parkland Center for Clinical Innovation is a Dallas-based collaborative team of data scientists and healthcare professionals who use data and social determinants of health to better support under-served communities, and it has agreed to help with data analysis, Williams said.
A video from Parkland Center for Clinical Innovation (PCCI) highlights its Women in Data Science and Technology Summer Internship program, with members of the program sharing their valuable experiences.
PCCI’s 2019 summer intern program is made up of area students from Dallas Independent School District high schools, SMU’s Statistics Department as well as students from the University of Texas at Dallas and Creighton University.
This internship program has become one of the most prestigious internship programs in North Texas with a mission to expand opportunities for women in an industry that significantly lacks gender diversity.
At the Texas Hospital Association’s (THA) Quality and Patient Safety Conference this week in Austin, Texas, Aida Somun, PCCI’s Chief Operating Officer, shared the organization’s vision for leveraging social determinants of health to help under-served populations in our communities.
Aida’s presentation, “Building a Framework to Address Social Determinants of Health” gave insights into how providers and payers can identify socioeconomic needs and develop interventions that reach outside the walls of the clinic.
Attending the presentation were THA leaders, Dr. Bob Hendler, THA’s chief medical officer, Lindsay Thompson, THA’s Senior Director of Education and Governance Programs and Shirley Lavergne, THA’s Manager Education Programs.
Dr. Anjum Khurshid, Director of Data Integration and Assistant Professor of Population Health at Dell Medical School, was also in attendance along with large and small progressive health care organizations who exchanged ideas on how to incorporate these learnings into their population health strategies to improve quality of patient care.
D CEO Healthcare features PCCI’s work with the Parkland Community Health Plan and Parkland Hospital on pre-term birth prevention. The results of this work show how PCCI and Parkland are working together to develop innovative ways to improve healthcare for the under-served in our community.
##
At the Parkland Center for Clinical Innovation, data analytics and technology are improving outcomes for underserved pregnant women in Dallas. One significant way to reduce maternal and infant mortality is to avoid pre-term birth, and in 2017, Texas had a 10.4 percent pre-term birth rate – earning a D in the annual ranking from March of Dimes.
The women were enrolled in the Parkland health plan, which reached out to them to get the women signed up for the texting system. Pre-term birth can be a difficult thing to predict, says Dr. Joseph Chang, Associate Chief Medical Officer for Outpatient and Ambulatory Services at Parkland. Traditionally, the only way to know if a women was going to have a pre-term birth was if she had a past pre-term birth. But he says that a couple of interventions, including progesterone shots, can make a huge difference.
“Adherence to medicine is the biggest factor,” Chang says. “If we really were able to identify the right people, use a platform for today’s young parents, maybe that would really work.”
Because Parkland is both the health plan and the healthcare provider, PCCI was able to access both sides of the payer relationship in a way that can be difficult to access in traditional healthcare systems. Their system brought the electronic health record together with behavioral health information to identify the women, and yielded impressive results.
Appointments were closely monitored, with PCCI measuring data along the way to adjust the text messaging and tailor it to the patients’ needs. After just one year, women in the program increased prenatal visit attendance by 24 percent, reduced pre-term birth by 27 percent. The program also reduced post-delivery cost by 54 percent in the first year. The 679 women who enrolled saved the system $1 million in the first year.
Fighting healthcare battles before the patient arrives at the doctor is important for PCCI CEO Steve Miff. “Health begins where we work, live, learn, play, and pray,” he says. “We are moving upstream, because if they are not addressed it will have a negative impact on health.”
Politico covered PCCI’s efforts to reduce frequent flyers by targeting patients who lacked many of the supports needed after they left the hospital. Their software connected social service agencies to the healthcare system to refer patients to get those services outside of the hospital, which would be cheaper and more efficient than seeing patients return again and again because they lacked food or housing. The impact was significant. The pre-term birth program is another way to head off medical costs before they happen.
Looking ahead, PCCI hopes to continue to fight social isolation to provide access to services, improving many of the behavioral and environmental factors that negatively impact health. “How do we use digital tech and bring women together, create clusters of similar individuals, customize behavioral therapy?” Miff says. “We can do that via a digitally provided environment, we can do it from home, and bridge the gap via telemedicine.”
Chang sees this technology being applied to any number of ailments, but sees a massive opportunity in addressing diabetes treatment. There are apps for measuring and taking glucose, but the texting might be more effective because it doesn’t require another application. “The biggest problem is taking their medicine – taking it and taking it correctly.”
Mobile Health Times reports on PCCI contributing to the HHS health kidney initiative. Read below:
Read Dallas Innovates’ coverage of PCCI joining the HHS kidney initiative. Read below:
DALLAS – Parkland Center for Clinical Innovation (PCCI), which improves healthcare for vulnerable populations using advanced data science and clinical experts, is contributing its capabilities to support elements of the “Advancing American Kidney Health Initiative” announced by the U.S. Department of Health and Human Services (HHS) earlier this month.
The HHS initiative’s aim is to improve the lives of the 37 million patients who suffer from chronic kidney disease and more than 726,000 who have end-stage renal disease. There are nearly 100,000 Americans waiting on the list to receive a kidney transplant. Kidney disease ranks as the ninth leading cause of death in America, costs Medicare $114 billion a year and represents one of the most significant expenses for the VA’s health programs.
PCCI is contributing to the initiative through two grants to the University of Texas Southwestern Medical Center’s Miquel Vazquez, MD. Specifically, PCCI will be applying its proficiency with advanced data science applied to electronic health records to aid at-risk patient identification and develop predictive modeling. This effort is in support of preventing and mitigating kidney disease, keeping patients out of hospitals, and helping find different ways to define and manage kidney disease.
“We are very proud to contribute PCCI’s unique combination of advanced data science and clinical expertise to this important initiative,” said PCCI’s President and CEO, Steve Miff, PhD. “This program, under Dr. Vazquez, the grant principle, is critical to millions of Americans who are suffering from kidney disease. We are excited that PCCI’s experience applying healthcare data in clinical settings with veterans and other groups prone to kidney disease is aiding the kidney health initiative.”
Members of PCCI’s advanced analytics and clinical teams are participating in the initiative’s research studies and work groups, helping advance the program’s goal of transforming the way kidney disease is prevented and treated.
About Parkland Center for Clinical Innovation
Parkland Center for Clinical Innovation (PCCI) is an independent, not-for-profit, healthcare intelligence organization affiliated with Parkland Health & Hospital System. PCCI focuses on creating connected communities through data science and cutting-edge technologies like machine learning. PCCI combines extensive clinical expertise with advanced analytics and artificial intelligence to enable the delivery of patient-centric precision medicine at the point of care.
Pediatric asthma is the most prevalent chronic childhood illness, afflicting about 6.2 million children in the United States. However, asthma could be better managed by identifying and avoiding triggers, educating about medications and proper disease management strategies.
Parkland Center for Clinical Innovation (PCCI) has been working with the Parkland Community Health Plan (PCHP) for the past four years to help them with timely identification of high risk asthma members in the pediatric population. We have deployed a logistic regression model on claims data that is the foundation for an innovative care redesign and text based patient engagement program that has show consistent cost savings and clinical outcomes improvement for PCHP members. You can learn more about this program here.
Thus, this issue for us is not merely an academic exercise. We realize that a predictive model with improved statistical performance can yield even better health outcomes for these families and improved cost savings for PCHP. Keeping that in mind, we have regularly looked for ways to continue to improve our model that is not just limited to retraining the model but also finding ways to improve data quality and bringing in additional data sets for workflow improvement. More recently, we decided to retrain the model using deep learning techniques — more specifically using an ANN.
Our deep learning model produced an AUC of 0.845 which was only slightly better than the AUC of the current logistic regression model at 0.842.
You can read about details of our work at arXiv here.
Healthcare has high expectations for the level of transparency from machine learning algorithms deployed in a clinical setting. Deep learning models with their relative lack of transparency are not always the best contender for those situations. However, if the improvement in performance of the model for relevant statistical measures is significant enough, then there can be a strong case for deployment of a deep learning model over say, a logistic regression model.
However, in this case, with the exact same data set and initial feature list, ANN model only produced slightly higher statistical classification power than the Lasso logistic regression. This is consistent with the results from some other published research that has compared logistic regression and ANN models in multiple medical data classification tasks. This study further confirmed that the Lasso logistic regression model developed by PCCI in 2015 could produce desirable statistical performance that is non-inferior to deep learning models which are more difficult to interpret. And in order for our predictive models to be deployed and effectively improve patient care, we need to work closely with clinicians to explain predictions in comprehensive and interpretable formats to build trust and transparency with stakeholders.
For future studies, blender algorithms would be tested against other singular models to achieve better statistical performances. We would explore the temporal relationships in claims data using other deep learning models, like Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM).
The Dallas Business Journal has announced that PCCI’s CEO, Steve Miff, PhD., has been nominated for its “2019 Most Admired CEO Award” in the healthcare category.
Dr. Miff joined PCCI as president and CEO in January 2017 and leads a pioneering organization that brings together top data scientists and healthcare experts to create programs supporting the health of vulnerable populations.
The Dallas Business Journal’s Most Admired CEO Awards honors the executives who inspire those around them, hold their employees, products and services in the highest regard, run their companies with integrity and are shining examples of how all companies should be run and managed.
Dr. Miff is a recognized national thought leader with more than 20 years of experience in healthcare analytics and consulting. He is a first generation American and has experienced first-hand many of the same challenges as the people PCCI supports in its community.
The Dallas Business Journal will honor its winners at a dinner on September 25, 2019. Rick Allen, CEO of Paragon Healthcare Inc., was the previous winner of the award in the healthcare category.
About Parkland Center for Clinical Innovation
Parkland Center for Clinical Innovation (PCCI) is an independent, not-for-profit, healthcare intelligence organization affiliated with Parkland Health & Hospital System. PCCI focuses on creating connected communities through data science and cutting-edge technologies like machine learning. PCCI combines extensive clinical expertise with advanced analytics and artificial intelligence to enable the delivery of patient-centric precision medicine at the point of care.