🚀 ATTD 2025 is almost here! 🚀
We’re excited to be heading to ATTD next week to connect with researchers, innovators, and industry leaders from around the world! 🌍💡
To help you make the most of the conference, we’ve put together an exclusive ATTD Cheat Sheet 📋—a comprehensive list of all speakers, affiliations, and over 500 presentation slots! 🎤🔬
👉 Want access?
Show Syntactiq some love by following us on LinkedIn and dropping "ATTD Cheat Sheet" in the comments—we’ll DM you the link! 💙
Let’s meet up and discuss how you would utilize 1,000,000+ contextual patient days to accelerate the development of better solutions for people living with diabetes!
📅 Book a slot with us here: https://lnkd.in/d_MicvSS#ATTD2025#DiabetesTech#Innovation#Syntactiq#Data#diabetes#technology
Happy to be attending this year and honored to get the opportunity to present my project Diabetes Cockpit App in person along with with SmartStart Health, BOYDSense, SNAQ, OneTwo Analytics & Beep Insights.
Ten years ago, individuals living with diabetes had limited data to manage. Today, with Continuous Glucose Monitors (CGMs), wearables, and closed-loop systems slowly entering the arena, the volume of available data has skyrocketed. This brings both potential new insights and added complexity. Diabetes Cockpit App is a modern, user-centric, and community-driven platform designed to help people with diabetes make sense of their growing data. It started with a focus on closed-loop users and is currently expanding into MDI.
My pitch is gonna be on Wednesday, happy to see you there and catch a coffee talking about synergies the next big things in digital diabetes!
Reach out to me if you wanna chat and see you there,
at European Association for the Study of Diabetes e.V. (EASD)#easd#diabetescockpit
LLMs are everywhere but particularly in healthcare we need to be mindful of their nature and strengths but also where they have weak spots. We always try to put safety and privacy first and believe we found a good way forward for this use case.
Great article/meditation by Lukas Schuster about the next release greatly enhancing Sams (LLM to talk about your diabetes data) capabilities while improving privacy.
It's hard to avoid the current hype around LLMs like Claude (Anthropic
) , GPT-4 (OpenAI), Llama (Meta), and others. It feels like we are throwing LLMs at new problems every day to see what sticks. I often see concepts and prototypes, but it’s rarer to see actual released products, even more so in healthcare.
I've spent the last few months building and improving a use case in diabetes that I will release in the next few days. Diabetes Cockpit App has been my main private project over the past few years, and its aim is to provide up-to-date analytics and support to lift some of the burden of making sense of data for people living with diabetes.
When implementing LLMs in a healthcare product, I had to experiment and find work-arounds for various issues and weaknesses. So here is my contribution to the current conversation around the LLM hype and my experience in releasing a LLM application in a Healthcare related mobile app.
Link -> https://lnkd.in/dZDq28iN
What are your experiences with shipping LLMs in Healthcare, did you face similar challenges? How did you solve them?
#llm#ai#openai#diabetes#healthcare#claude#product#digital#cockpit#diabetescockpit
TLDR
LLMs have limitations in healthcare but excel at summarizing information. We built a prototype using LLMs for diabetes care, enhancing data accessibility and accuracy with privacy-safe tools. This helps leverage their strengths and trust their outputs more.
-
There has been a lot of discussion lately about AI, particularly LLMs, in healthcare. We're often led to believe there's nothing they can't do. However, many of our friends remain skeptical, raising valid points such as "They're not always good with calculations" or "They're probability machines and can't make medical decisions!" We acknowledge these concerns and agree that we're still some way off from allowing AI to make medical decisions or provide medical advice autonomously, without human oversight. Nonetheless, this doesn't mean that they aren't already incredibly useful.
LLMs excel at summarizing and presenting information in a way that is easy for humans to digest, which is a significant need in healthcare. They also support the use of tools, allowing us to assist them with tasks they're less proficient at, like solving complex math problems or tailoring medical data to fit specific needs and requirements.
Over the past few days, we've experimented with our own diabetes dataset (its Lukas Schuster's data) and developed a prototype that we believe extends the capabilities of LLMs in diabetes care. By augmenting LLMs with tools for data access in a privacy-safe manner, and ensuring accurate calculations and precise metric definitions, we can achieve impressive results.
We are excited to extend their use to make data more accessible for us. We should leverage their strengths, augment context information, and incorporate useful tools so that we can have greater trust in their outputs.
