Jung In Park, a professor at the University of California Irvine’s School of Nursing, discusses the growing role of AI in nursing and the need for nurses to adapt to technology. She emphasizes the importance of understanding AI and machine learning, their applications in healthcare, and their potential to improve patient outcomes. The use of AI in diagnostics, personalized treatment planning, patient monitoring, and administrative tasks is highlighted, along with the benefits of AI in enhancing accuracy, efficiency, and healthcare quality. Park also shares her plans to utilize large language models for predicting patient outcomes.
Jung In Park, an esteemed professor at the University of California Irvine’s School of Nursing, is at the forefront of integrating artificial intelligence (AI) into nursing practices. In a recent interview, she sheds light on the positive impact AI has on nursing care and offers insights on how nurses can prepare for an increasingly AI-driven future.
The healthcare industry is witnessing a projected annual growth of 37% in the AI market until 2030. While only a fraction of healthcare organizations worldwide currently employ AI models, the mounting opportunities and pressures to leverage AI’s capabilities for advancing patient care and medicine are undeniable.
As the industry evolves, nurses are required to enhance their technological proficiency to adapt effectively.
The Sue & Bill Gross School of Nursing at the University of California Irvine leads the way in utilizing AI and machine learning to enhance care. Jung In Park, an associate professor at the university, holds a Ph.D. in nursing informatics from the University of Minnesota and a bachelor’s degree in nursing from Seoul National University. With expertise in healthcare technology, she focuses on leveraging machine learning to improve care and health outcomes. Furthermore, she aids current and future nurses in equipping themselves with the necessary skills to utilize new technologies.
Healthcare IT News recently interviewed Park to delve into how the School of Nursing at Irvine is utilizing AI and machine learning. The interview covers the applications of AI in healthcare delivery, the improvements it brings to patient outcomes, and Park’s plans to utilize large language models and generative AI.
Q: How does the University of California Irvine School of Nursing promote the adoption of AI and machine learning among nurses? What should nurses know about AI?
A: The Sue & Bill Gross School of Nursing at the University of California Irvine recognizes the immense potential of informatics and AI in nursing research and education. The emergence of informatics and data technology allows nurse researchers to focus on using AI and machine learning techniques with extensive datasets, providing new insights into quality nursing care.
AI, along with wearable technology, plays a crucial role in developing responsive and personalized treatments, enabling advanced and sustainable care. Collaborations with colleagues across various disciplines on campus and from the public and private sectors help explore the expanding potential of these advancements.
Moreover, we offer nursing informatics courses at various levels to students. Teaching nursing students about AI, machine learning, and informatics is vital as these technologies become increasingly integrated into healthcare. Nurses need to be prepared to navigate and utilize them effectively in their practice.
Understanding AI and machine learning empowers nurses to leverage data-driven insights, enhance patient care, and adapt to the evolving technological landscape in healthcare. AI applications in healthcare encompass diagnostics, personalized treatment planning, patient monitoring, and automating routine tasks for operational efficiency.
Nurses must effectively collaborate with AI systems while upholding their professional judgment and expertise. Continuous learning is essential to keep pace with AI advancements, ensuring their safe and effective utilization. Equipped with a solid understanding of AI, nurses can harness its potential benefits to deliver high-quality, patient-centered care.
Q: In which areas of healthcare delivery, particularly in nursing, is AI being applied? How are caregivers utilizing this technology?
A: AI is revolutionizing various aspects of healthcare delivery. I utilize large health datasets such as electronic health records, national cancer registries, and sensor data from wearables to develop machine-learning models that predict different patient outcomes, including hospital-acquired infections, 30-day readmissions, and survival rates.
In diagnostics and imaging, AI algorithms analyze medical images, detecting abnormalities and enhancing accuracy. Clinical decision support systems utilize AI to analyze patient data, assisting healthcare professionals in decision-making and reducing errors.
AI’s capacity to analyze large datasets, including genomic information, enables precision medicine by tailoring treatments to individual patients. Remote patient monitoring through AI-enabled devices and wearables enables proactive and personalized care. Additionally, AI streamlines administrative tasks optimizes resource allocation, and improves operational efficiency.
AI-powered chatbots and virtual assistants offer round-the-clock access to healthcare information and support patient engagement.
Healthcare providers, organizations, and researchers are among the users of AI technology in healthcare. Physicians, nurses, and radiologists leverage AI to improve diagnostics, personalize treatments, tailor nursing care plans, and optimize operations. Healthcare organizations benefit from AI’s efficiency-enhancing capabilities and resource utilization. Researchers employ AI to analyze extensive datasets, driving healthcare advancements. Overall, AI technology in healthcare delivery improves accuracy, efficiency, patient outcomes, healthcare quality, and patient satisfaction.
Q: How does the application of AI enhance patient outcomes? What other benefits does it offer?
A: The application of AI in healthcare significantly improves patient outcomes in various ways. AI algorithms analyze patient data, including medical images and electronic health records, to enhance diagnosis and early detection. This leads to more accurate and timely diagnoses, facilitating prompt intervention and treatment initiation.
AI enables personalized treatment plans by analyzing extensive patient data, incorporating factors like genomic information, to tailor treatments to individual patients. This enhances treatment effectiveness while reducing adverse effects. Furthermore, AI systems provide evidence-based recommendations and insights to healthcare professionals, supporting their clinical decision-making process.
By identifying suitable treatment options and predicting patient outcomes, AI reduces medical errors and enhances patient safety.
AI-enabled devices and wearables enable continuous remote monitoring of patient’s health indicators, facilitating early detection of changes or deterioration. This enables timely intervention, preventing adverse events and reducing hospital readmissions.
AI technology also streamlines workflow processes, automates administrative tasks, optimizes resource allocation, and improves operational efficiency. This reduces the burden on healthcare professionals, allowing them to focus more on direct patient care, thereby enhancing patient experiences and outcomes.
Q: Do you have plans to utilize large language models/generative AI? What are the reasons behind your decision?
A: Yes, I intend to utilize a large language model to predict patient outcomes, with a particular focus on factors such as the risk of mortality and hospital-acquired conditions. This powerful model comprehends and analyzes unaltered text extracted from clinical notes within electronic health records, providing relevant estimates for patient care.
The model can effectively process various types of clinical notes, ranging from radiology reports and nursing documentation to patient progress notes and discharge instructions, even when standardized language is absent. This capability allows the model to interpret unique abbreviations and terms used by individual writers.
Operating by predicting the most appropriate word to complete a sentence, drawing on real-world language patterns, the large language model’s predictive accuracy improves over time as more data are fed into it.
Leveraging this model can offer real-time support to healthcare providers in their clinical decision-making, alerting them to critical factors that may potentially lead to adverse events, and providing valuable insights.
