I have been away for a while. I apologize for the delay in writing.
M
I have been watching with some interest all the activity that surrounds Generative AI through using ChatGPT4. The idea that you can ask a computer a question and it scans the electronic datasphere and gathers a whole bunch of “information” and then compresses it into a number of sentences which can be read in a form of basic interpretable English intrigues me. It took little time for me to understand why there is so much interest (and fear) about this new tool.
Since it is readily available at a kind-of-affordable cost, I figured I should learn a little more about what it can and cannot do.
Being of a certain age, the first thing I did was buy the book “AI For Dummies”. For my generation there is a “Dummies” book for almost every topic you can possibly want. It was not perfect, but then again what could I expect?
The next thing was to jump in with a question: "What is the future of laboratory external quality assessment?"
Almost as soon as I got my fingers of the keyboard, ChatGPT4 started to respond. It took all of maybe 5 seconds.
What I got back impressed me to the extend that the response was on-topic which means that it was framed around what I understand as laboratory external quality assessment.
The response was broken down into sections which included:
1. Integration of artificial intelligence (AI) to revolutionize the medical laboratories by improving accuracy, speed, and efficiency. It would do this through analyzing data, and assist through interpreting test results, and help identify potential errors or inconsistencies.
2. Digitalization and remote testing: The increasing digitalization of healthcare could lead to a shift from traditional paper-based proficiency testing to online platforms.
3. Remote proficiency testing could allow laboratories to participate in testing programs from anywhere, reducing the need for physical samples and paperwork. This would streamline the testing process, increase accessibility, and facilitate real-time performance monitoring.
4. Personalized proficiency testing: As healthcare moves towards personalized medicine, proficiency testing may also become more tailored to individual laboratory needs. Laboratories may receive customized samples or challenges that align with their specific testing capabilities or areas of expertise. This approach could help laboratories identify and address any weaknesses or gaps in their performance more effectively.
5. Continuous quality improvement: Proficiency testing programs are likely to focus more on continuous quality improvement rather than simply measuring a lab's performance. This could involve providing laboratories with detailed feedback and recommendations for improvement based on their performance in proficiency testing. Collaborative learning networks and knowledge sharing platforms may play a role in facilitating continuous quality improvement among laboratories.
6. Regulatory changes and standardization: Changes in regulatory requirements, such as the implementation of new quality management systems or accreditation standards, may affect the future of proficiency testing. Standardization of proficiency testing methods and metrics across different regions and countries could improve comparability and harmonization of laboratory performance assessment.
Some of this I found interesting, but with apologies to the gurus of artificial intelligence, while the subject was correct, for a lot of the response the tense was wrong. Most of it dealt with what is the near or distant past, or was just wrong.
For example while there is interest in virtual microscopy that can be on-line, for the microbiology and chemistry and blood banking, it is difficult to imagine that test competency can be monitored without physical samples.
Also the notion of personalized proficiency testing has been a fact for many years. Laboratories already select the companies, and the sample products they want to receive. While there may be some refinements, they will likely be minor.
What does sound interesting and maybe even futuristic, the use of EQA to monitor knowledge and performance on continuous improvement and knowledge of regulation changes, is already in place in some EQA programs already. In our program we call that para-examination EQA.
So here is
what I have learned… computers have
reached a new point where they are able to access the whole datasphere and
process large amount of data on a wide range of specific topics here and
now. Their memory systems can be trained
to look for specific words and patterns, frame them in a new way and restructure
it into something different. And present that is maybe new
and novel, but not ready to take over the world.
Interesting? … Yes. Helpful?... In some ways. Definitive? …. Not Yet.
It reminds me of another new thought (????) roaming across the drivelsphere. "… have a vision of what can be, unburdened by what has been. "
