In the dynamic landscape of healthcare, the delicate balance of sharing health information has become increasingly critical, particularly concerning teenagers. Patient portals, designed to facilitate the efficient exchange of health information among patients, families, and healthcare providers, encounter a unique challenge when it comes to adolescents.
The Problem:
State laws may grant minors the right to consent to specific sensitive care, allowing them to keep this information confidential from their guardians. This is essential for building trust with vulnerable youth who might otherwise avoid seeking necessary care. However, configuring Electronic Health Records (EHRs) and patient portals to respect these privacy rights while facilitating essential information sharing poses a technical challenge.
“Some organizations respond to this challenge by withholding all health information from guardians,” noted Dr. Natalie Pageler, Chief Health Information Officer and Division Chief, Clinical Informatics, at Stanford Medicine Children’s Health. “However, this approach can inadvertently create barriers to optimal care.”
The Solution:
To address this challenge, Stanford Medicine Children’s Health, under the guidance of Dr. Pageler, leveraged AI technology to navigate the nuances of health information sharing with teens and their families. The use of natural language processing (NLP) played a pivotal role in setting up a dual monitoring system to ensure privacy and autonomy for teenage patients while maintaining necessary guardian involvement.
The AI Technology Implementation:
The first step involved using NLP to monitor provider notes for inappropriate sensitive content, flagging any notes that contained information about sensitive care that a teenager had consented to. This ensured the confidentiality of such information from guardians.
The second step utilized a natural language algorithm to monitor messages within teen patient portal accounts, detecting any inappropriate use by guardians attempting to access sensitive information. This struck a balance, involving guardians to an appropriate extent, as defined by the law and the teenager’s consent.
Results and Transformative Outcomes:
The implementation of these AI-driven monitoring systems produced transformative results. The patient message algorithm revealed that over 50% of teen portal accounts were being inappropriately accessed by guardians. This led to the development of a custom guardrail intervention, reducing inappropriate account activations and prompting the integration of a similar guardrail into Epic’s foundation system, impacting teens worldwide.
Additionally, the NLP algorithm for provider notes uncovered that more than 20% of notes contained inappropriate confidential content. The automated review process proved up to six times more efficient than manual review, contributing to increased productivity and identifying opportunities to enhance provider note templates.
Looking Ahead:
Stanford Medicine Children’s Health sees these successes as just the beginning of a transformative journey. They are exploring ways to integrate these AI algorithms into the note generation process, aiming to further decrease documentation burden and enhance the efficiency of provider communication.
Advice for Others:
Dr. Pageler emphasizes the importance of recognizing the unique needs of different patient populations, urging a nuanced approach to health information sharing. Implementing technology solutions like AI and NLP requires a deep understanding of both clinical and technical aspects of healthcare. Assembling a diverse team of clinical informaticists, data scientists, and legal experts is crucial to navigate the complex intersection of healthcare and technology successfully.
Stanford’s success in this endeavor is attributed to its commitment to interdisciplinary education, fostering a blend of clinical and technical expertise within its team. This approach enables the development and implementation of solutions tailored to the specific needs of patients, particularly children and their families.
