Stanford uses AI to navigate sharing health information with teens and their families
In the rapidly evolving healthcare landscape, sharing health information is a delicate balance, especially when it comes to teens.
THE PROBLEM
Patient portals facilitate the efficient sharing of health information between patients, their families and healthcare providers. However, a unique challenge arises when it comes to teenagers.
Certain state laws may allow minors to consent to specific types of sensitive care and give them the right to keep this information confidential from their guardians. This is crucial for building trust with vulnerable young people, who might otherwise avoid seeking the care they need.
Yet it is technically challenging to configure EHRs and patient portals in a way that respects these privacy rights while facilitating the necessary exchange of information.
“Some organizations are responding to this challenge by withholding all health information from guardians,” said Dr. Natalie Pageler, chief health information officer and division chief of clinical informatics at Stanford Medicine Children’s Health. “However, this approach can unintentionally create barriers to optimal care. The reality is that most health information is not sensitive and can be critical in engaging families in teen health care, especially for those with chronic medical conditions.
“Investing in the technical work to create a nuanced approach to health information sharing is not just a necessity, it’s an opportunity,” she continued. “It’s an opportunity to revolutionize the way we handle teen health data, so that both teens and their guardians have appropriate access to the information they need.”
This goes beyond just adhering to laws or future-proofing systems: it’s about creating a care environment where teenagers, regardless of their background, feel safe, supported and empowered, she added.
“Additionally, this nuanced approach supports the concept of progressive responsibility in teen health care,” Pageler said. “As they get older, they gradually take more responsibility for their health decisions. By giving them control over their sensitive health information, we facilitate this transition to adulthood and promote a sense of responsibility and autonomy.
“This work is about recognizing the critical role families can play in supporting teens’ health, while respecting teens’ rights to privacy in certain areas,” she continued. “By finding this balance, we can improve patient outcomes, build trust and set a new standard in patient-centered care.”
This is where AI and language models come in.
PROPOSAL
Pageler and staff saw a significant opportunity to leverage AI technology to help navigate the nuances of sharing health information with teens and their families and to increase the efficiency of caregiver note-writing, messaging and manual monitoring programs.
“The first step in achieving these goals was to use natural language processing to establish a dual monitoring system,” she explained. “This system aimed to ensure the privacy and autonomy of teenage patients while maintaining the necessary level of involvement of guardians in their healthcare.
“Our goal is to further reduce the documentation burden and improve the efficiency and effectiveness of supplier communications.”
Dr. Natalie Pageler, Stanford Medicine Children’s Health
“First, the AI technology was used to check vendor notes for inappropriate sensitive content,” she continued. “This means the AI system is trained to identify and flag any notes that contain information about sensitive care that a teen had consented to, such as contraception or STD treatment. This system is designed to ensure that this information is kept confidential from guardians, while respecting the teen’s privacy and autonomy.”
Second, a natural language algorithm was developed to monitor messages within teen patient portal accounts. The system is designed to detect any inappropriate use of the account by the guardian, such as attempts to access sensitive information.
This ensured that the guardian was appropriately involved in the teen’s health care, but not beyond the limits set by law and the teen’s consent.
“The combination of these two AI monitoring systems is designed to provide a comprehensive solution to optimally support teens and families’ engagement in their healthcare,” Pageler explains. “These systems are designed to ensure that both provider notes and patient portal accounts are used appropriately, while respecting the rights of the teen and guardian.
“This has not only helped build trust among the teens, but also ensures that guardians can effectively support their child’s healthcare,” she added.
MEETING THE CHALLENGE
Stanford Medicine Children’s Health embarked on an innovative journey, leveraging the expertise of its clinical informatics specialists who specialize in pediatrics and adolescent medicine. These experts, well versed in the nuances of California’s adolescent confidentiality laws, painstakingly labeled large data sets of teens’ progress notes and patient portal messages. This formed the basis of the project.
“Our computer scientists then joined forces with our data scientists to develop two groundbreaking natural language processing algorithms,” Pageler explains. “The first algorithm is designed to automate audits and feedback for our healthcare providers, improve the integrity of their notes, and enable optimal health information sharing with teens and guardians.
“The second algorithm is designed to provide alerts to our patient portal team, allowing them to quickly address potentially compromised patient portal accounts for teens and guardians,” she continued.
The advent of large language models has opened up a world of possibilities.
“We are now exploring how we can leverage these advances to further expand our work and better support teens and their families,” Pageler said. “We are currently evaluating the performance of GPT 4.0 compared to our homegrown NLP algorithms. We are also exploring how integrating this tool with the Epic EHR system can proactively guide providers in appropriate communications with teens and guardians, helping them documentation becomes better, efficient.
“This project is not just about using technology to solve a problem,” she continued. “It’s about revolutionizing the way we support and empower teens and their families. This is the future of pediatric healthcare and we’re excited to be at the forefront of this change.”
RESULTS
The journey with this technology has produced some truly transformative results, Pageler reported.
“First, our patient messaging algorithm has uncovered a surprising reality: more than 50% of our teen portal accounts guardians were approached unlawfully‘, she said. “This was a wake-up call, highlighting a significant invasion of adolescent privacy.
“But it also presented an opportunity for change,” she added. “We took immediate action and conducted further research to understand and address the problem. Our efforts culminated in the development of a adapted guardrail intervention significantly reducing inappropriate account activation errors. This solution was so effective that our vendor partner, Epic, incorporated a similar guardrail into its foundation system, extending the impact of our work to teens around the world.”
Second, the NLP algorithm for vendor annotations revealed that more than 20% of annotations contained inappropriate confidential content. The automated review process, powered by the algorithm was up to six times more efficient than manual review, a significant productivity gain. Most importantly, it helped staff identify opportunities to improve caregiver note templates, making it easier for caregivers to properly document and respect adolescent confidentiality.
“These successes are just the beginning,” Pageler said. “We are now exploring ways to integrate these algorithms into the note generation process. Our goal is to further reduce the documentation burden and improve the efficiency and effectiveness of supplier communications. This isn’t just about improving our systems; it’s about revolutionizing the way we engage teens and their families to help them live healthier, happier lives.”
ADVICE FOR OTHERS
As Stanford Medicine Children’s Health navigates the rapidly evolving healthcare technology landscape, it is critical to recognize the unique needs of different patient populations, Pageler advised.
“For example, children and their families need a nuanced approach to sharing health information that respects both the rights of the child and the role of the family in their care,” she said. “Implementing technology solutions such as AI and natural language processing can greatly enhance our ability to meet these needs, but it requires a deep understanding of both the clinical and technical aspects of healthcare.
“Building on this, building the right team is imperative to successfully navigate this complex intersection of healthcare and technology,” she continued. “This team should ideally consist of individuals with diverse but complementary skill sets: clinical informaticians who understand the unique needs of patients and the nuances of healthcare workflows, data scientists who can leverage the power of AI and natural language processing, and legal and privacy experts are well informed about healthcare legislation and regulations.”
Stanford has been successful in this regard because of its longstanding commitment to interdisciplinary education, she added.
“Our Biomedical Data Science Graduate Program, Clinical Informatics Fellowship and Masters in Clinical Informatics Management have played an important role in training a new generation of professionals adept at bridging the gap between clinical practice and technological innovation,” she concluded . “This mix of clinical and technical expertise within our team has enabled us to develop and implement solutions tailored to the specific needs of our patients, especially children and their families.”
Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email him: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.