Dealing with the doctor's fax machine: From API to AI
How AI can replace outdated data sharing in healthcare
The highlights:
Healthcare IT is siloed and slow. During the pandemic, it took years to automate sharing hospital occupancy data!
I tested how LLMs can share data without extensive API development.
This technology could reduce IT fragmentation, cut through bureaucracy, and make healthcare more enjoyable and patient-centered.
Read time: 6 minutes
In this edition of Transforming Med.Tech, I dive into how Large Language Models (LLMs) may become the unexpected heroes in healthcare's battle against fragmented IT systems. First, however, I owe you an apology for the delay in this newsletter. Having another child has certainly impacted my ability to keep up with side projects like this one. But the sleepless nights have not kept me from experimenting with Generative AI, so let's get started!
From intelligence to integration
Halfway into 2024, it's becoming clear that the AI landscape is evolving. The rapid leaps in LLM "intelligence" we saw last year have plateaued somewhat. Instead, there is a pivot towards smart applications of these powerful tools, integrating AI seamlessly into our everyday lives. For example, my bank does not allow me to export my credit card transactions (really, ING?), but Claude transformed a PDF output of transactions into a neat CSV file in only a few seconds. Simple AI solutions can save tons of time.
I believe healthcare, in particular, is ripe for this kind of innovation. Walk into a typical modern hospital, and you may encounter cutting-edge imaging technology next to fax machines that stopped being cutting-edge before you were born. The industry is understandably conservative – after all, lives are at stake. But this caution has led to a fragmented IT landscape where data sharing often feels stuck in the last century. Could smart integration of AI tools be of help to travel these silos? I explored this with a case study.
A case study: sharing pandemic data
In the early days of the COVID-19 pandemic, governments had to coordinate patient distribution to minimize the pressure on healthcare providers. Hospitals were scrambling to share occupancy data, often relying on manual processes that were time-consuming and error-prone. Whereas video conferencing tools suddenly advanced rapidly, healthcare IT took ages to develop data-sharing APIs (application programming interfaces), even in these unprecedented times. In the Netherlands, for example, IT workers manually uploaded data every day, and only two years into the pandemic, this process was fully automated.
I tested if the flexibility of LLMs would have been of help in the pandemic's need for data sharing. Using OpenAI's ChatGPT and Anthropic's Claude and simple prompts, I created "hospital bots" and a "data collector bot," each with dedicated tasks to share and collect data, respectively. Here's a taste of what they can do:
1. Negotiate data formats: "Hey, Hospital A bot, what format would you prefer for the occupancy data?". They can agree on JSON, free text, tables, whatever is preferred:
2. Share data on demand: "Hospital B bot, could you please provide today's ICU occupancy?" You can even let it check for consistency and automatically ask for error corrections:
3. Extract data from various sources: "Here's our dashboard. Can you pull out the relevant numbers?" These bots only need access to a screen and can figure out where the requested information is.
And of course, you can then format the output in any way, ready for sharing with other institutes.
Reimagining data sharing and referrals
But why stop at simple occupancy data? Let's think bigger. Imagine a GP considering referring a patient to a cardiologist. I created dedicated chatbots, where the knowledge of the specialist's chatbot was restricted to relevant medical guidelines. The conversation of the GP's chatbot with the specialist's bot looked something like this:
GP Bot: "I have a 55-year-old male patient with suspected atrial fibrillation. Here's a summary of his case."
Specialist Bot: "Thank you. Based on the current guidelines, we need the following additional information before a referral: 1. Recent ECG results; 2. Thyroid function tests; 3. Echocardiogram report, if available; Have these been performed?"
GP Bot: "The ECG and thyroid tests are complete, but the patient hasn't had an echocardiogram yet; I will order one before the referral."
This kind of interaction ensures that all relevant data are shared (and only relevant data), that referral guidelines are followed, and that necessary pre-referral steps are taken. This results in efficient use of everyone's time and improves the quality of care.
Beyond APIs and bureaucracy
Implementing comprehensive APIs across fragmented healthcare IT systems is a herculean task, requiring coordination between multiple vendors and navigating a bureaucratic maze. LLMs offer a shortcut. Of course, we must balance the incredible potential of LLMs with careful consideration of accuracy, privacy, and security. But language evolved to deal with the chaos and unpredictability of our world, and the inherent flexibility of language-based models is enormously valuable. They can quickly capture the essence of large amounts of data (such as clinical notes or my diary). They don't need carefully structured data or predefined interfaces, they can work with what's on the screen – be it a web page, a PDF, or the user interface of any existing application. Even if we could find the time, money, and commitments of multiple vendors, carefully constructed APIs are unlikely to ever reach this level of flexibility.
Conclusion
The potential of LLMs to revolutionize data sharing in healthcare is immense. Imagine a world where doctors spend less time fighting with referral and data sharing systems, and more time connecting with patients. Where crucial medical information doesn't sit in the fax machine's inbox, but flows seamlessly, with better outcomes and safer care.
So, what do you think? Did my experiments convince you that LLMs are going to replace APIs? And is healthcare IT ready to implement LLM-based solutions?
Thanks for sharing your thoughts! And with my sleepless nights slowly becoming more bearable, I am confident that the next newsletter will not keep you waiting so long. Until then, keep innovating and stay curious!
Great insights into a fascinating use of LLM's! I had no idea they worked in this capacity.