Healthcare NLP Summit write-up 10/2023

The past year has been eventful in the fields of Machine Learning (ML) and Artificial Intelligence (AI). From October 3rd to 5th, 2023, John Snow Labs organized their second Natural Language Processing (NLP) Summit of the year. This event included a variety of informative presentations from both emerging start-ups and established players in the Language Model sector. This is the first part of a two-part conference write-up; it discusses trends and technologies, while the subsequent part will focus on applications in healthcare....

October 14, 2023 · 8 min · 1563 words · Markus Bockhacker

Healthcare NLP Summit write-up

I spent the last two evenings attending John Snow Labs’ virtual “Healthcare NLP Summit,” and I found it to be a stimulating event. If you couldn’t attend, here are my notes: LLMs are all the hype Large-language-models (LLMs) were the overarching topic of the conference, and some speakers (particularly from marketing and sales) were excited about the possibilities. However, there wasn’t a clear vision of what these possibilities entailed. Senior researchers and executives had a different sentiment....

April 6, 2023 · 3 min · 527 words · Markus Bockhacker

Death by EHR

This article describes how the poorly designed EHR user interfaces from the early 2000s have lead to physician fatigue and put patients at risk. Fast forward to 2022, where we see issues with data quality when trying to use EHR data to generate Real-World-Evidence. Turns out, these 40-Item-Dropdown-Fields have lead users to rather „misuse“ freetext fields for orders and documentation - thereby causing sparse datasets and challenges for pseudonymization. This is just another reason to strongly focus on UX of EHR systems and other medical devices....

December 30, 2021 · 1 min · 104 words · Markus Bockhacker

Idea vs. Reality: the Importance of Interdisciplinary Teams in AI and Medical Research

In 2021, one of the most thought-provoking articles highlighted the gap between the excitement surrounding AI in healthcare and the actual products that emerged. This divergence underscores a crucial lesson: the necessity of interdisciplinary development teams. Silos in Expertise During the COVID-19 pandemic, numerous AI tools were rapidly developed to assist with hospital diagnoses and patient care. However, many of these tools failed to deliver on their promises. The root of this issue lies in the isolated development processes....

August 4, 2021 · 2 min · 277 words · Markus Bockhacker