Dallas County Launches New Diabetes and Hypertension Surveillance Systems
DALLAS – On September 10, 2025, Dallas County Health and Human Services (DCHHS), in collaboration with Parkland Health and the Parkland Center for Clinical Innovation (PCCI), launched the Diabetes and Hypertension Surveillance Systems, which are powerful new tools designed to track and better understand diabetes and hypertension across Dallas County.
The systems will feature publicly accessible dashboards, available on the DCHHS Chronic Disease Prevention webpage, offering timely, reliable data to inform community health strategies, research, and public policy. The surveillance systems integrate multiple data sources to provide insight into key indicators and their impact by zip code or census tract:
-Clinical indicators such as ED visit, obesity, A1c measure, missed BP measure, etc.
-Social determinants of health indicators including education and literacy, household income, disease burden, food insecurity, etc.
-Other indicators such as “number of diabetes prescription fills in the past 3 months, etc.
The dashboards will allow users to explore population data by age, sex, race/ethnicity, and education, giving residents, providers, and policymakers a clearer picture of diabetes and hypertension vulnerabilities and patterns in Dallas County.
“The launch of our new diabetes and hypertension surveillance systems represents a major milestone in strengthening our public health response,” said Dr. Philip Huang, MD, MPH, DCHHS Director/Health Authority. “By combining clinical data with social and demographic information, we can better identify at-risk populations, guide policy, and ensure that prevention and treatment efforts reach those who need them most.”
“It takes a connected community to support the health and wellness of our region, and these AI-driven dashboards provide comprehensive, hyper-localized insights into the risks and underlying factors of some of the most prevalent and harmful chronic conditions. These insights and data are critical to coordinate support and align interventions for maximum impact and we’re excited to make these available to the whole community.”
Steve Miff, PhD, CEO at PCCI
“The creation of this dashboard has brought together the non-medical drivers of health and clinical diabetes data to allow us to both understand what is going on in our communities and how to create a multi-pronged approach to address it,” said Uma Gunasekaran, MD, Endocrinologist and Executive Medical Director of Parkland’s Global Diabetes Center. “This is great information for our health systems but also for the public to see as well.”
Join PCCI’s Mission to Support the Most Vulnerable in Our Community through the North Texas Giving Day
On Thursday, September 18, 2025, PCCI is participating in Communities Foundation of Texas’ North Texas Giving Day, an online giving extravaganza for non-profit organizations from the whole region. We’re raising funds to further our mission to support the health of vulnerable communities in North Texas through the responsible applications of AI and non-medical drivers of health (NMDoH) analytics, and your gift helps make this possible!
Additionally, your support will benefit PCCI’s women in data science intern program, the Sachs Summer Scholars. PCCI developed this STEM-focused program to help open doors to women seeking careers in data science. This is an industry challenge as, according to Girls Who Code, from 1984 to today, the number of female computer science graduates dropped from 37% to 18%. At PCCI we are committed to reversing this trend in the data science and technology industry all while focusing the intern’s contributions, efforts and learnings towards innovative, practical solutions supporting our local community.
Through early giving, you can make your North Texas Giving Day contribution now! The platform makes it simple and easy to give. Between now and September 18, you can make your gift online at NTGD-PCCI.
Save the Date for September 18, when you can follow along by checking the North Texas Giving Day leaderboards, prizes page, and social media channels for exciting updates and announcements.
Thanks for your support of PCCI and for being a part of the North Texas Giving Day movement!
If you are leading efforts to improve and understand public health in your community, we’ve researched and validated that PCCI’s Community Vulnerability Compass (CVC) offers an improvement in advanced insights and performance compared to existing tools that measure community socioeconomic conditions in our neighborhoods. Although getting here took a lot of innovation and perseverance, through a recent publication, we are now able to share what factors differentiate the CVC and why it offers the gold-standard of social determinants of health (SDOH) measurement.
In research published in JAMIA Open, through Oxford University Press’ platform, we detailed how the CVC can help lead the way in measuring community SDOH, while also offering deeper, hyper-localized insights unavailable anywhere else.
CVC provides a unique methodology embedded into an interactive dashboard that helps stakeholders—including community-based organizations (CBOs), safety-net hospitals, health systems, philanthropic organizations, governmental agencies, universities, and Managed Care Organizations (MCOs)—to make data-driven decisions that enhance health outcomes and drive equity in service delivery.
The CVC’s unique value proposition offers one-of-a-kind insights where it analyzes, at the ZIP Code, census tract, and block-group level, where a community’s most vulnerable residents live and the root cause factors limiting these residents’ ability to thrive. The CVC analyzes 26 clinical and socio-economic indicators that reveal the health, resiliency, and economic vibrancy of neighborhoods. CVC’s analyses provide true, holistic pictures of who needs the most assistance and where to find them, enabling proactive support of those in need.
Though the CVC offers an impressive set of features, as public health leaders, we have choices. There are many available tools we can use to better understand our communities and their social conditions. That is where CVC sets itself apart. It offers localized data to our partners or customers catchment area, not just generalized, large geographical regions. It shows— to the block group — what the social conditions are and the root causes of those conditions.
For example, our research reflected the differences between CVC and the Area Deprivation Index [ADI], Social Vulnerability Index [SVI], and Environmental Justice Index [EJI]). As presented in the article, the CVC’s Community Vulnerability Index (CVI), and 4 sub indexes, were used to classify all 18,638 Texas census-block groups as Very-High, High, Moderate, Low, and Very-Low social vulnerability. Individual patients were then assigned the vulnerability classification of their home address census-block group, creating a bridge between neighborhood-level data and individual-level health insights. CVC’s classifications were compared against three existing community vulnerability tools and validated against individual-level SDOH screening tools or Z-code documentation, but where we clearly separate ourselves from the others is we localize data to our partners or customers catchment area. Spearman rank correlation was used for neighborhood-level comparisons and precision/recall, for individual-level comparisons.
Let’s look at what each of these different systems offer and how we differ in features and performance.
Area Deprivation Index (ADI)
What the ADI Provides: The ADI is a composite measure that uses U.S. Census data to assess socioeconomic disadvantage at a neighborhood level. It provides valuable insights for healthcare providers and policymakers to understand and address health disparities.
CVC Difference: While ADI focuses on socioeconomic disadvantage, CVC goes beyond this by integrating various medical and non-medical determinants of health (NMDoH) indicators to provide actionable insights at the block-group level. CVC provides key insights to strengthen local interventions, empowering both health systems and CBOs to implement strategies directly targeting specific vulnerabilities in their communities.
The Social Vulnerability Index (SVI)
What The SVI Provides: Developed by the CDC, the SVI measures community resilience to external stresses using various social factors. It is commonly used for disaster preparedness and resource allocation.
CVC Difference: While SVI provides valuable data at a census tract level, CVC offers block-group-level insights, allowing for more precise targeting of interventions. CVC focuses on actionable data for public health departments, health systems, and CBOs, empowering them to engage effectively with vulnerable populations.
Environmental Justice Index (EJI)
What The EJI Provides: The EJI assesses the environmental and health burdens faced by disadvantaged communities. It focuses on exposure to environmental hazards, considering factors like pollution and access to green spaces, to identify areas at risk.
CVC Difference: CVC complements the EJI by not only focusing on environmental factors but also incorporating social vulnerabilities that contribute to overall health disparities. This broader perspective allows CVC to provide a more comprehensive understanding of community needs, facilitating targeted interventions that address factors: health, environment, and NMDoH.
In the research presented in the JAMIA paper, we see that overall, the CVC was comparable to, or outperformed, existing neighborhood indexes in measuring key SDOH at both the neighborhood and individual level. CVC showed a strong correlation with existing SDOH indexes from the ADI, SVI, and EJI across multiple social risk domains, demonstrating its ability to identify a cross-cutting range of social vulnerabilities and community equity markers. Additionally, CVC had very good recall rates for individual-level SDOH, both when validated against Z-code documentation and against self-reported survey tools (>75%).
This table, developed for the JAMIA paper, tells the full comparison article1:
Community Vulnerability Index (CVI) and CVC Subindexes Recall and Precision Rates for Self-Reported Social Determinants of Health (SDOH) Using Surveys.
SDOH
Community Vulnerability Index
Empowered People Subindex
Equitable Communities Subindex
Good Health Subindex
Household Essentials Subindex
Precision (%)
Recall (%)
Precision (%)
Recall (%)
Precision (%)
Recall (%)
Precision (%)
Recall (%)
Precision (%)
Recall (%)
Food Need
75.1
77.5
75.1
73.4
74.6
55.3
75.1
72.9
75.4
74.4
Housing Need
36.9
78.6
36.4
73.4
39.1
59.8
37.3
74.7
36.3
73.9
Safety Need
1.2
79.6
1.0
66.0
1.2
56.3
1.3
81.6
1.1
70.9
Transportation Need
31.9
79.3
31.9
75.2
33.5
59.9
32.5
76.0
31.8
75.7
Utility Need
42.6
77.0
42.7
73.2
41.4
53.7
42.3
71.8
42.8
74.0
For each CVC Index/Sub-index, the highest values of precision/recall are highlighted in green and the lowest in blue; CVC: Community Vulnerability Compass.
PCCI’s CVC has been incorporated into a variety of use cases and settings throughout Texas, including adoption by the Dallas County Department of Health & Human Services, the University Heath (San Antonio) Transplant Center and serves as the backbone for the United Way of Metropolitan Dallas’ Data Capacity Building Initiative, which is helping hundreds of organizations in North Texas turn insights into impact.
As a member of the public health community, I am excited to see how we can use the CVC to better understand the true health of our communities and the contributing root causes. The research we presented in the JAMIA paper is so important to me as it shows clearly how the CVC can give me insights unavailable through any other means.
The thought-provoking results we are seeing gives our public health leaders a trusted new technology that will enable the delivery of more precise approaches to address the needs of those most at-risk in our communities.
About Yolande Pengetnze
Yolande Pengetnze, MD, MS, FAAP, is PCCI’s Senior Vice President of Clinical Leadership where she leads multiple projects including population health quality improvement projects focusing on preterm birth prevention and pediatric asthma at the individual and the population level. Dr. Pengetnze received her MD from the University of Yaounde in Cameroon and completed a Pediatric Residency at Maimonides Medical Center in New York. She was a faculty member at UTSW’s General Pediatric Hospitalist Division where she completed a General Pediatric/Health Services Research Fellowship training and earned a Master of Sciences in Clinical Sciences.
###
1 Oxford Academic – JAMIA Open Journal, Published July 2025, The Community Vulnerability Compass: a novel, scalable approach for measuring and visualizing social determinants of health insights, https://doi.org/10.1093/jamiaopen/ooaf059
VIDEO: PCCI‘s Sachs Summer Scholars Innovation Showcase for 2025
This year’s class of PCCI’s Sachs Summer Scholars have spent this term working closely with PCCI’s data scientists and clinical leaders on programs that have real impact. They have also had a chance to witness Parkland Health and Parkland Community Health Plan programs to help them understand their contributions serving vulnerable communities. They’ve also had a lot of fun along their journey.
The Innovation Showcase video shows how the interns took on the opportunity to explore some of PCCI’s most forward-thinking initiatives. These talented interns presented their work on high impact PCCI projects focused on innovative healthcare, groundbreaking artificial intelligence programs, and non-medical drivers of health projects.
PCCI’s Sachs Summer Scholars is an internship program that demonstrates PCCI’s ongoing commitment to provide women opportunities to experience new, transformational concepts in the data science and health technology industry.
The Innovation Showcase spotlights the work of PCCI’s elite group of intern’s experiences working on innovative healthcare, groundbreaking artificial intelligence programs, and non-medical drivers of health projects such as preterm birth prevention, large language models, digital engagement scoring, and suicide risk modeling, to name a few.
As one of the top data science and technology-focused internships in North Texas, PCCI’s program immerses students in meaningful, real-world projects with actual impact through practical applications of analytics, computing, and data science, all while advancing the spirit of mentorship and advancement of female students.
For a full overview of this year’s class, go to: https://pccinnovation.org/pcciscd1-sachs-summer-scholars-interns-set-to-advance-ai-innovations-for-vulnerable-populations/
Please mark your calendar for this event and I look forward to seeing you there!
JAMIA Open Journal Examines PCCI’s Community Vulnerability Compass That Sets New Standard for Measuring Social Determinants of Health
JAMIA, through Oxford University Press’ platform, recently published and distributed an in-depth paper authored by Parkland Center for Clinical Innovation (PCCI), detailing how PCCI’s innovative Community Vulnerability Compass (CVC) elevates insights and performance of existing tools that measure community socioeconomic variation.
PCCI has achieved a significant breakthrough in addressing one of healthcare’s most pressing challenges: accurately identifying and measuring social determinants of health (SDOH) at scale. A cross-sectional study to build the CVC (2018-2023) and validate it (September 2023 to June 2024) was revealed in groundbreaking research published in JAMIA Open, a prestigious single-blind peer-reviewed, Gold Open Access journal that serves as a global forum for cutting-edge research in biomedical and health informatics. This publication demonstrates that PCCI’s CVC outperforms existing tools in measuring both neighborhood and individual-level social vulnerabilities.
Written by PCCI’s clinical and data science experts, the JAMIA article offers a comprehensive look at what tools are available to evaluate community SDOH elements, how the CVC tool works as well as the process and methods PCCI used to make head-to-head comparisons with other currently available tools.
As presented in the article, the CVC’s Community Vulnerability Index (CVI), and 4 subindexes were used to classify all 18,638 Texas census-block groups as Very-High, High, Moderate, Low, and Very-Low social vulnerability. Individual patients are then assigned the vulnerability classification of their home address census-block group, creating a bridge between neighborhood-level data and individual-level health insights. CVC’s classifications were compared against three existing community vulnerability tools, including Area Deprivation Index [ADI], Social Vulnerability Index [SVI], and Environmental Justice Index [EJI]) and validated against individual-level SDOH screening tools or Z-code documentation. Spearman rank correlation was used for neighborhood-level comparisons and precision/recall, for individual-level comparisons.
The paper shows that overall, the CVC was comparable to or outperformed existing neighborhood indexes in measuring key SDOH at both the neighborhood and individual level. CVC showed a strong correlation with existing SDOH indexes (ADI, SVI, and EJI) across multiple social risk domains, demonstrating its ability to identify a cross-cutting range of social vulnerabilities and community equity markers. Additionally, CVC had very good recall rates for individual-level SDOH both when validated against Z-code documentation and against self-reported survey tools (>75%).
“This paper summarizes countless hours of research and development that culminated in creating an industry leading SDOH measurement tool that has the potential and momentum to become the gold standard,” said Steve Miff, PhD, President and CEO of PCCI. “The data and information presented in the paper offers a fully transparent look into how the CVC works and its ability to surface hyper-localized insights that is novel and unique. We are very proud of achieving this key milestone and expanding of how the CVC can support communities and population health in ways that have previously been out of reach.”
The JAMIA article, co-authored by PCCI’s Yolande Pengetnze, MD, MS, Yusuf Tamer, PhD, Lance Rather, BS, and others, provided strong evidence of the benefit of gaining contextual understanding of social barriers to health in the individual’s micro-ecosystem.
“The JAMIA article digs deep into our approach and the steps we took to test how addressing social determinants at the block group level helps address specific needs and health of vulnerable populations,” said Yolande Pengetnze, MD, MS, PCCI’s Senior Vice President of Clinical Leadership. “This article shows clear, thought-provoking results that can equip public health leaders with a trusted tool enabling new methods of addressing the needs of those most at-risk in our communities.”
PCCI’s CVC analyzes, at the ZIP Code, census tract, and block-group level, where a community’s most vulnerable residents live and the root cause factors limiting these residents’ ability to thrive. The CVC analyzes 26 clinical and socio-economic indicators that reveal the health, resiliency, and economic vibrancy of neighborhoods. CVC’s analyses provide true, holistic pictures of who needs the most assistance and where to find them, enabling proactive support of those in need.
“This paper offers proof of the viability and potency of the CVC,” said Lance Rather, PCCI’s Senior Director, Product & Strategic Partnerships. “The paper offers clear evidence of how the CVC can provide data previously unavailable at the neighborhood level. Organizations that have implemented the CVC have discovered how rapidly and intuitively it transforms complex social vulnerability data into actionable insights that substantially advance their core missions. The use of the CVC can be applied in so many ways by different organizations, and we are excited at the possibilities that lay ahead.”
About PCCI
The Parkland Center for Clinical Innovation (PCCI) is a not-for-profit, mission-driven organization with industry-leading expertise in the responsible application of artificial intelligence, machine learning and non-medical drivers of health data modeling to address the needs of vulnerable populations. PCCI started as a department within Parkland Health and was spun out as an independent organization in 2012. PCCI strives to leapfrog the status quo by harnessing the transformative potential of data. Our unique capabilities allow us to provide innovative, actionable solutions that more effectively identify needs, prioritize services, empower providers, and engage patients.
JAMIA Open, a peer-reviewed journal from Oxford Academic Press, publishes a paper on PCCI’s Community Vulnerability Compass (CVC)
In a paper titled “The Community Vulnerability Compass: a novel, scalable approach for measuring and visualizing social determinants of health insights,” PCCI authors give a deep look at how the CVC is developed and deployed to create an accurate and scalable social determinants digital measurement tool that shows the true vulnerabilities residents face across our communities.
“This paper highlights the power of the CVC that gives us the ability to surface block-level insights allowing us to understand at scale the true nature and shared characteristics of critical non-medical vulnerabilities. This gives community and health leaders heightened, hyper-localized understanding of their neighborhoods they serve to create sustainable, customized solutions to support their health and wellness journey.”
PCCI COO, Aida Somun, MBA, has been invited to join the 2025 Board of Examiners for the Malcolm Baldrige National Quality Award
For the third time since 2019, the U.S. Department of Commerce’s National Institute of Standards and Technology (NIST), has invited Aida Somun, MBA, PMP, Chief Operating Officer at Parkland Center for Clinical Innovation (PCCI), to the 2025 Board of Examiners for the Malcolm Baldrige National Quality Award. The Baldrige Award is the nation’s highest honor for organizational innovation and performance excellence.
Appointed by the NIST Director, examiners are responsible for reviewing and evaluating applications submitted for the Baldrige Award, as well as other assessment-related tasks. The examiner board is composed of leading experts competitively selected from industry, professional, trade, education, health care, and nonprofit (including government) organizations from across the United States.
Those selected meet the highest standards of qualification and peer recognition, demonstrating competencies related to customer focus, communication, ethics, action orientation, team building, and analytical skills. All members of the board must take part in a nationally ranked leadership development course based on the Baldrige Excellence Framework and the scoring/evaluation processes for the Baldrige Award. They must also complete an independent review of a Baldrige Award application or other comparable examiner task.
Somun has 20 years of experience as a business leader known for driving profitable growth, cost savings and delivery. She ensures operational excellence through consistent contributions to bottom line efficiency, performance and process improvements. She is most passionate about leading and influencing strategic decision making for operationalizing the right innovative programs focused on improving individual’s health, both physical as well as socio-economic.
Somun recently was included in the Dallas Business Journal’s first-ever C-Suite Leaders Awards was also a recipient of the Dallas Business Journal’s 13th annual Women in Business Awards.
Named after Malcolm Baldrige, the 26th Secretary of Commerce, the Baldrige Award was established by Congress in 1987. Awards may be given annually to organizations in each of six categories: manufacturing, service, small business, education, health care, and nonprofit. The Award promotes innovation and excellence in organizational performance, recognizes the achievements and results of U.S. organizations, and publicizes successful performance strategies.
Five years after the chaos of COVID-19 comes a new era of AI innovation
By Steve Miff, PhD, President & CEO of PCCI
Five years ago this week, the COVID-19 pandemic threw our world into chaos. But that chaos also sparked an opportunity and a drive to accelerate innovation, through leveraging artificial intelligence with clinical knowledge in unprecedented ways. The results of these Covid-driven efforts have led to a fuller understanding of our community’s health, enabling the initiation of care further upstream and enhancing management of resources and costs in ways benefiting both patients and providers.
I can still remember that week five years ago. I had my bags packed and flight booked to travel to one of the biggest healthcare technology conferences, HIMSS, in Orlando, Fla., when the word came down. The government declared a full lockdown of the country thanks to the pernicious COVID-19 outbreak that the World Health Organization had declared a full-blown pandemic.
Sadly, the cost of COVID-19 in lives— 1.2 million deaths in the U.S. alone— was devastating and the reverberations of the pandemic still affect our daily lives.
However, the chaos and heartache also stimulated a new mindset for collaboration. While the lockdown closed our office doors, it opened new windows to collaborate with other stakeholders across our community. Our teams immediately partnered with Dallas County Health and Human Services (DCHHS), Parkland Health (Parkland) , and other local providers and governmental agencies to help support our North Texas public health leaders and families manage through the ever-changing nature of the COVID-19 pandemic. We deployed a transparent, data-driven set of analytics to inform the dynamic allocation of resources, guide triage protocols in emergency rooms, identify COVID-19 community hotspots, and predict rising waves of hospitalizations and capacity challenges. These collaborations would evolve into support for testing, vaccination distribution, and measuring of community-wide immunity to the infection.
While many of the solutions developed during COVID-19 were industry firsts, we continue today to leverage and expand on many of these same novel applications in AI and non-medical drivers of health (NMDoH) analytics.
Vulnerability Index
The development of the Covid Vulnerability Index and geo-mapped hotspotting created the dynamic dashboards that guided the local pandemic response, including the placement of the testing, and later vaccination sites. This novel approach later expanded into what’s now the Community Vulnerability Index, an industry leading NMDoH analytics method modeling community and neighborhood barriers to health and wellness.
Proximity Index
The Covid Proximity Index was used to predict the risk of infection daily at the individual level using advanced geomapping and data science techniques to guide personal awareness and behaviors, county-wide contact tracing, healthcare provider virtual care scheduling, and ED triage. We are so proud of the United States Patent for AI driven proximity index system and methods (US 12,087,449 B2) that was awarded to PCCI late last year. We’re now leveraging these methods alongside mobility data to understand access to vital services and placement of new access points in the community. The Proximity Index was also featured in the highly respected peer-reviewed New England Journal of Medicine Catalyst in a paper authored by Parkland’s CEO Frederick Cerise, MD and others.
Community Protection Modeling
The national Covid Community Protection Dashboard was launched in collaboration with the Institute for Healthcare Improvement (IHI), Civitas Networks for Health, and Cincinnati Children’s Hospital to model local behaviors and immunity patterns and help communities manage through new Covid variants and waves. We learned that the dynamic nature of modeling factors and a community’s protection depends on the characteristics of the most prevalent current variant and the immunity from prior vaccination and infections, adjusting for the time elapsed from the most recent immunizing event. These innovations translated into the development and deployment of the Pediatric Asthma Surveillance System (PASS), the soon to be released Diabetes/Hypertension Surveillance System, and the development of a novel Maternal Health Surveillance System. Each of the programs are (or will be) in use in Dallas County and provide life-saving support to its residents.
Better Preparedness for Future Crises
The pandemic brought Parkland, our main public health system, closer to DCHHS and many other public health leaders, working together with PCCI to build new policies and procedures to manage the COVID-19 emergency and future public health crises. And have no doubt about it, it is only a matter of when, not if, we will have more COVID-19-like outbreaks.
In the big picture for public health innovation, COVID-19 created a necessity for us to be innovative and try new ways to solve extremely difficult problems. This same way of thinking is helping us today as we tackle ongoing health challenges through improved collaborations and tools. For example, our Community Vulnerability Compass (CVC) is a tool that can provide deeps insights into the complexities of societal challenges to health, access, and community well-being affecting our neighborhoods throughout Texas. It can tell you, for example, what local daily challenges our residents face down to the block level. The CVC has been adopted by a variety of organizations around the state, led by the United Way of Metropolitan Dallas through its Data Capacity Building Initiative that, within five years, aims to equip over 200 community-based partners with robust data insights from the CVC.
And as previously mentioned, the PASS system is celebrating its two-year anniversary of providing residents of Dallas County unprecedented understanding of their vulnerability to asthma-related risks. PASS is a community-wide effort between the county, PCCI, and Parkland and is publicly available at the DCHHS website. It has been visited by thousands of Dallas County residents and was honored by the Dallas County Commissioners for its service to asthma sufferers and was described by the Dallas Morning News as “a win for Dallas County.” PASS has also been featured in the New England Journal of Medicine Catalyst.
The pandemic did put a damper on at least one of our innovations. The book, “Building Connected Communities of Care,” was due to drop via a major release at the Orlando HIMSS convention in March, 2020. The celebration and release was changed and conducted virtually and digitally. This guidebook helps communities and public health leaders create holistic community networks that support any number of health management issues. Thanks to its insights and easy-to-follow steps, “Building Connected Communities of Care” has become an invaluable resource for many public health leaders across the country. It was also featured in the New England Journal of Medicine Catalyst for its insights it offers in handling community healthcare crises.
The COVID-19 pandemic was not easy on anyone, but we are wise to remember what happened during those tough times and leverage the innovations and progress towards bigger and broader ongoing impact. We will continue to leverage the critical clinical and community health lessons COVID-19 taught us in innovative programs incorporating the newest AI technology. As a community, while we remember the terrible price COVID-19 cost our friends and families, we should feel some level of optimism that the next time we will be better prepared and stronger together.
Pre-pandemicPost pandemic
About Steve Miff
Dr. Steve Miff is the President and CEO of Parkland Center for Clinical Innovation (PCCI), a leading, research non-profit, artificial intelligence and cognitive computing organization affiliated with Parkland Health, one of the country’s largest and most progressive safety-net hospitals. Spurred by his passion to use next-generation analytics and technology to help serve the most vulnerable and underserved residents, Steve and his team focus on leveraging technology, data science, and clinical expertise to obtain unique non-medical-determinants-of-health data and incorporate those holistic, personal insights into point-of-care interventions.
PCCI Experts Set to Deliver Major Presentations to the nation’s healthcare leaders at HIMSS25
Starting March 5, PCCI experts are joining leaders from Parkland Health to present cutting-edge AI healthcare programs in prime spots at 2025 HIMSS Global Health Conference and Exhibition in Las Vegas, the epicenter of healthcare innovation.
The presentations are:
Creating a Large Language Model to Catalog Important Radiologist Recommendations
Wednesday, March 5, 3:15 PM to 4:15 PM PACIFIC
Speakers
Alex Treacher, PhD, Senior Data and Applied Scientist – PCCI
Albert Karam, Vice President, Data Strategy and Analytics – PCCI
Brett Moran, Chief Health Officer – Parkland Health
Abstract
Medical errors, the third leading cause of death in the U.S., include wrong or delayed diagnoses, causing more serious harm than any other type of medical error. Delayed or missed opportunities for diagnoses (MOD) are particularly common in diagnostic imaging, where incidental findings often require further evaluation. At Parkland Health, a major safety-net public health system, 1.7 percent of all CT and MRI studies involve such findings. To address this, a large language model (LLM) is developed that identifies and flags delayed surveillance recommendations from radiologists’ interpretations. These delayed recommendations result in MODs 17 percent of the time. This LLM has been integrated into the electronic health record (EHR) of Parkland Health, enabling centralized management and navigation of these cases. Our results demonstrate 95 percent accuracy in identifying imaging that requires follow-up based on physician notes and 85 percent accuracy in determining the appropriate timing for follow-up. This work outlines the process, development, tools, current performance, and future plans for building an automated system to enhance image surveillance and mitigate MODs in diagnostic imaging.
Yusuf Tamer, PhD, Principal Data and Applied Scientist- PCCI
Michael Lane, Senior Vice President, Chief Quality and Safety Officer – Parkland Health
Teresita Oaks, Director, Community Health Programs – Parkland Health
Abstract
In Dallas County’s safety-net population, an AI/machine learning-driven unsupervised clustering algorithm identifies clusters of diabetic and hypertensive patients with a combination of social and clinical risk factors associated with suboptimal quality of care (e.g., inadequate of Hemoglobin A1C monitoring) and poor disease control. Clusters analyses uncover underlying, actionable risk drivers such as criminal justice involvement and immigration concerns that require innovative, culturally-responsive approaches for a sustainable engagement of these vulnerable populations into effective preventive care. Additional in-depth analyses identify missed and potential opportunities for care engagement that inform innovative workflow modifications leveraging traditional (e.g., EHR-based standing orders) and nontraditional (e.g., telehealth modalities and mobile units) approaches to effectively engage and support these vulnerable populations and improve health quality, outcomes and equity countywide. The data sets and analytical approaches are scalable and replicable to other vulnerable populations nationwide.
