Datavant Future of Healthcare Hackathon: Best Public Health App
Author
Publish Date
Read Time
Datavant
September 22, 2022
From September 8–11, Datavant hosted its first annual Future of Healthcare Hackathon. Over 200 attendees spent the weekend developing innovative solutions to improve the future of healthcare. This week, we are excited to announce the various winners of the Hackathon.
The Winner of the Best in Category — Public Health App is: Exquisicare. Read on to learn more about this fantastic project.
Development Team
Edward Gent — Technology Associate at Morgan Stanley / Founder at Health Haven Technologies
SubbaRao Bellamkonda
Project Summary: Exquisicare — Using chat to treat opioid addiction
Since moving to the U.S., Edward Gent has been struck by the severity of the American opioid crisis. Bringing his broad awareness of comorbidities between different types of addiction, he aimed to leverage current approaches to cell phone addiction as a means to treat more serious and sinister opioid addictions. To do this, Gent built an automated Instagram chatbot, Exquisicare, that responds to DMs and advises people concerned about their risk of addiction on their actual risk. His model is built on a CDC data-trained classification model, and after engaging with a user, the chatbot can then refer that person to medical professionals if they so wish.
Project Inspiration
Gent is a qualified nutritionist and via his startup, Health Haven, he assists people at developing nutritional optimization in partnership with the GBS/CIDP Foundation. He is deeply passionate about improving people’s overall health, and hopes to inspire others to develop a similar passion. While working on this project, Gent came to appreciate the magnitude of the opioid crisis in the U.S., which is currently growing 30% YoY, a growth rate he hasn’t observed in other medical afflictions or causes of death. This was personally relevant to him, having recently undergone surgery and been given an opioid prescription, which came with a letter of warning regarding post-recovery addiction risks.
Using Python, Gent trained the classifier to make predictions based on patient input and embedded the app with a Firebase backend to securely store conversation metadata and intents. In his choice of Python, Gent traded-off quality of model performance (little/no chatbot model confidence scores or classifier precision/r1/recall) in return for a pipeline that worked end to end. Because of the time constraints of the Hackathon, he was not able to set up a cloud deployment or incorporate a multiprocessing toolbox to allow multiple conversations to be had at once, both of which, he acknowledges, would be necessary for the project to scale. But because he used open source Instagram libraries, he was able to spend less time on UI/UX considerations and more on HIPAA compliance, data encryption, and implementation.
Implications
The goal of this app is to help reduce the >91,000 annual opioid related deaths in the US. Gent notes that in the face of such numbers, “Virtually any positive steps in this direction would be a huge win.”
Future Steps
Gent used CDC data provided by Datavant, which meant that, in his words, “the model code was a little brittle.” He also noted that the hyper parameters are probably overly biased and not suited to fitting predictions outside of the provided input feature space. The data largely considered addiction rate as a function of features that most people are unaware of and that are not “personal attributes,” which made it a challenge to develop useful questioning of the end user.
A big next step would be to expand the data sources used to train the app. In the longer term, the chatbot could also be used to gather patient data, including demographics and experience with addiction, which could be used to provide insights into the broader non-patient population.
Congratulations to Edward for developing this project!
Considering joining the Datavant team? Check out our careers page and see us listed on the 2022 Forbes top startup employers in America. We’re currently hiring remotely across teams and would love to speak with any new potential Datavanters who are nice, smart, and get things done and want to build the future tools for securely connecting health data and improving patient outcomes.
Spotlight on AnalyticsIQ: Privacy Leadership in State De-Identification
AnalyticsIQ, a marketing data and analytics company, recently adopted Datavant’s state de-identification process to enhance the privacy of its SDOH datasets. By undergoing this privacy analysis prior to linking its data with other datasets, AnalyticsIQ has taken an extra step that could contribute to a more efficient Expert Determination (which is required when its data is linked with others in Datavant’s ecosystem).
AnalyticsIQ’s decision to adopt state de-identification standards underscores the importance of privacy in the data ecosystem. By addressing privacy challenges head-on, AnalyticsIQ and similar partners are poised to lead clinical research forward, providing datasets that are not only compliant with privacy requirements, but also ready for seamless integration into larger datasets.
"Stakeholders across the industry are seeking swift, secure access to high-quality, privacy-compliant SDOH data to drive efficiencies and improve patient outcomes,” says Christine Lee, head of health strategy and partnerships at AnalyticsIQ.
“By collaborating with Datavant to proactively perform state de-identification and Expert Determination on our consumer dataset, we help minimize potentially time-consuming steps upfront and enable partners to leverage actionable insights when they need them most. This approach underscores our commitment to supporting healthcare innovation while upholding the highest standards of privacy and compliance."
Building Trust in Privacy-Preserving Data Ecosystems
As the regulatory landscape continues to evolve, Datavant’s state de-identification product offers an innovative tool for privacy officers and data custodians alike. By addressing both state-specific and HIPAA requirements, companies can stay ahead of regulatory demands and build trust across data partners and end-users. For life sciences organizations, this can lead to faster, more reliable access to the datasets they need to drive research and innovation while supporting high privacy standards.
As life sciences companies increasingly rely on SDOH data to drive insights, the need for privacy-preserving solutions grows. Data ecosystems like Datavant’s, which link real-world datasets while safeguarding privacy, are critical to driving innovation in healthcare. By integrating state de-identified SDOH data, life sciences can gain a more comprehensive view of patient populations, uncover social factors that impact health outcomes, and ultimately guide clinical research that improves health.
The Power of SDOH Data with Providers and Payers to Close Gaps in Care
Both payers and providers are increasingly utilizing SDOH data to enhance care delivery and improve health equity. By incorporating SDOH data into their strategies, both groups aim to deliver more personalized care, address disparities, and better understand the social factors affecting patient outcomes.
Tailored Member Programs: Payers develop specialized initiatives like nutrition delivery services and transportation to and from medical appointments.
Identifying Care Gaps: SDOH data helps payers identify gaps in care for underserved communities, enabling strategic in-home assessments and interventions.
Future Risk Adjustment Models: The Centers for Medicare & Medicaid Services (CMS) plans to incorporate SDOH-related Z codes into risk adjustment models, recognizing the significance of SDOH data in assessing healthcare needs.
Payers’ consideration of SDOH underscores their commitment to improving health equity, delivering targeted care, and addressing disparities for vulnerable populations.
Example: CDPHP supports physical and mental wellbeing with non-medical assistance
By integrating SDOH data, CDPHP enhanced their services to deliver comprehensive care for its Medicare Advantage members.
Providers Optimize Value-Based Care Using SDOH Data
Value-based care organizations face challenges in fully understanding their patient panels. SDOH data significantly assists providers to address these challenges and improve patient care. Here are some examples of how:
Onboard Patients Into Care Programs: Providers use SDOH data to identify patients who require additional support and connect them with appropriate resources.
Stratify Patients by Risk: SDOH data combined with clinical information identifies high-risk patients, enabling targeted interventions and resource allocation.
Manage Transition of Care: SDOH data informs post-discharge plans, considering social factors to support smoother transitions and reduce readmissions.
By leveraging SDOH data, providers gain a more comprehensive understanding of their patient population, leading to more targeted and personalized care interventions.
While accessing SDOH data offers significant advantages, challenges can arise from:
Lack of Interoperability and Uniformity: Data exists in fragmented sources like electronic health records (EHRs), public health databases, social service systems, and proprietary databases. Integrating and securing data while ensuring data integrity and confidentiality can be complex, resource-intensive and risky.
Lag in Payer Claims Data: Payers can take weeks or months to release claims data. This delays informed decision-making, care improvement, analysis, and performance evaluation.
Incomplete Data Sets in Health Information Exchanges (HIEs): Not all healthcare providers or organizations participate in HIEs. This reduces the available data pool. Moreover, varying data sharing policies result in data gaps or inconsistencies.
SDOH data holds immense potential in transforming healthcare and addressing health disparities.
With Datavant, healthcare organizations are securely accessing SDOH data, and further enhancing the efficiency of their datasets through state de-identification capabilities - empowering stakeholders across the industry to make data-driven decisions that drive care forward.
Careers
Join us on our quest to connect the world's health data
.svg)
