The increasing use of artificial intelligence and the explosive presence of generative AI (such as ChatGPT) are illuminating the field of medical information technology. The point is where to use AI and how to use it safely.
Dr. Nirav S. Shah is the Medical Director of Quality Innovation and Clinical Practice Analytics at NorthShore – Edward-Elmhurst Health. He is participating in HIMSS23 this week. His organization uses his AI and does it very well.
We interviewed Shah to hear his expert views and predictions on artificial intelligence and his expectations for HIMSS23.
Q. With executives from medical institutions like you gathering at HIMSS23, what do you think is the most important issue in medical information technology?
A. There are many macro trends occurring in healthcare today that are converging to bring specific IT issues to the fore.
Recently, the President authorized an end to the COVID-19 public health emergency. The aftermath of the pandemic has had far-reaching effects that ripple through the healthcare system.
Trends that existed before the pandemic are accelerating. Clinicians still struggle with burnout, and many continue to leave the field. This decline is exacerbating strain and strain on health care providers and health systems, impacting their ability to deliver care.
On the one hand, the population is aging, getting sicker and having more mental health problems.
As such, the lack of care over the past few years during the COVID emergency has created a void that is difficult to fill in an environment facing labor shortages and widespread burnout. Ultimately, it’s about enabling care, or working at the top of the license, empowering and optimizing care providers to deliver safe, seamless personal care.
Health information technology plays a key role in enabling healthcare providers. Recent advances in AI, especially large language models and generative AI, have seen the automation and augmentation of not only low-value tasks, but increasingly high-value tasks as well. worthwhile work.
Q. What are the challenges faced by organizations seeking help from HIMSS23 educational sessions and exhibition halls?
A. Coming back to these macro issues, we are looking for AI-powered tools that will enable our workforce to be more efficient and effective, and restore the joy of clinical care. A key element is how these tools integrate into your workflow to solve last-mile challenges.
A highly accurate tool is just as good as its ability to integrate into a provider’s workflow and enhance the care process.
We recently partnered with IQVIA on our natural language processing platform, and NorthShore’s analytics and informatics team, Edward-Elmhurst Health, gave a presentation at HIMSS23 titled “Implementing AI NLP Tool to Address SDOH Needs.” .
This talk highlights our efforts to solve last-mile challenges and enable frontline clinicians to treat patients more effectively with the help of AI.
The first use case with this platform is social determinants of health, extracting gaps in SDOH care from clinical notes and bringing that insight back into electronic health records, bringing it to clinicians, especially on the ED front. I was. Social Workers – Enable care to be delivered more efficiently and effectively.
Our ED social workers have traditionally utilized surrogate measures of the SDOH gap, such as predictive analyzes on readmission and mortality. They don’t always have clear and manageable SDOH needs.
With an NLP platform and implementation that our ED social workers dubbed a game changer, they found they could better target patients who had SDOH gaps and spent a lot of time trying to make a difference. I’m here.
Q. What do you see as the top healthcare IT challenges for CIOs, CMIOs, CISOs, and other healthcare IT leaders in provider organizations in the next year?
A. Nationwide, the capacity of the workforce to care for patients is being strained. These burdens are manifested in the access and capacity of overburdened care teams to address additional needs and challenges that may arise.
Careful consideration must be given to ways to reduce clinical burden, such as automating and augmenting with AI, outsourcing healthcare teams through expanded digital tools, and eliminating low-value interventions.
Interest and attention to the application of generative AI will continue this year. These tools include features for documenting clinical notes and patient instructions, assisting with medical coding and patient scheduling, and saving time in summarizing large amounts of data.
The capabilities of these models are astounding and the potential is immense, but they pose challenges for healthcare IT leaders. How do you manage the lifecycle of these models becoming exponentially powerful in months, what are the security implications of using these tools, how best to integrate these into your workflows How do I do that, and how do I deal with the black box nature of these models? How can these tools be safely deployed in patient-facing applications?
It’s an exciting area and it’s just getting started, but it’s only going to get more important in the year ahead.
Follow Bill’s HIT articles on LinkedIn. Bill Siwicki
Email the writer: [email protected]
Healthcare IT News is a publication of HIMSS Media.
