Jacob Rosenthal
@jacobrosenth.al
AI + medicine. MD-PhD student at Weill Cornell / Cornell Tech.
Interests: computer vision, LLMs, clinical trials, medical AI governance, radiology, python, chess, running, birds, cortados
Interests: computer vision, LLMs, clinical trials, medical AI governance, radiology, python, chess, running, birds, cortados
This piece from more than 30 years ago is incredible - replace "computers" with "AI" and it could have been written yesterday. I predict that it will still be relevant 30 years in the future for whatever the next big technology leap will be
academic.oup.com/jamia/articl...
academic.oup.com/jamia/articl...
Dehumanization of Patient Care—Are Computers the Problem or the Solution?
Edward H. Shortliffe, MD, PhD; Dehumanization of Patient Care—Are Computers the Problem or the Solution?, Journal of the American Medical Informatics Assoc
academic.oup.com
February 14, 2025 at 3:32 AM
This piece from more than 30 years ago is incredible - replace "computers" with "AI" and it could have been written yesterday. I predict that it will still be relevant 30 years in the future for whatever the next big technology leap will be
academic.oup.com/jamia/articl...
academic.oup.com/jamia/articl...
Regulation can boost innovation by building trust! In absence of regulations, more likely to have bad events that end up delaying whole fields of research. Eg after Jesse Gelsinger’s death, all gene therapy trials were paused in the US. Tragic for his family and net negative for scientific progress!
December 13, 2024 at 3:10 PM
Regulation can boost innovation by building trust! In absence of regulations, more likely to have bad events that end up delaying whole fields of research. Eg after Jesse Gelsinger’s death, all gene therapy trials were paused in the US. Tragic for his family and net negative for scientific progress!
What benchmarks should we be using to evaluate medical AI models? Answer: all benchmarks have limitations. Need to instead use real-world metrics that reflect what actually matters to patients. Huge opportunity for AI models fully integrated into EHR.
Ayers et al, JAMA 2024
Ayers et al, JAMA 2024
December 8, 2024 at 1:16 AM
What benchmarks should we be using to evaluate medical AI models? Answer: all benchmarks have limitations. Need to instead use real-world metrics that reflect what actually matters to patients. Huge opportunity for AI models fully integrated into EHR.
Ayers et al, JAMA 2024
Ayers et al, JAMA 2024
Tech Debt in ML Systems (Sculley et al, NeurIPS 2015)
Takeaways:
1. SYSTEMS are what matter most, not individual models
2. Training new models is not the only way to conduct research and/or have impact
3. Models are useless w/o infrastructure for data ingestion, serving predictions, and monitoring
Takeaways:
1. SYSTEMS are what matter most, not individual models
2. Training new models is not the only way to conduct research and/or have impact
3. Models are useless w/o infrastructure for data ingestion, serving predictions, and monitoring
December 7, 2024 at 4:48 PM
Tech Debt in ML Systems (Sculley et al, NeurIPS 2015)
Takeaways:
1. SYSTEMS are what matter most, not individual models
2. Training new models is not the only way to conduct research and/or have impact
3. Models are useless w/o infrastructure for data ingestion, serving predictions, and monitoring
Takeaways:
1. SYSTEMS are what matter most, not individual models
2. Training new models is not the only way to conduct research and/or have impact
3. Models are useless w/o infrastructure for data ingestion, serving predictions, and monitoring
Great list. That’s the first AI paper that I have seen quote the Talmud!
December 6, 2024 at 3:59 PM
Great list. That’s the first AI paper that I have seen quote the Talmud!
There aren’t many everyday scenarios where we have access to such precise probabilities to base decisions on. Usually it is more coarse: my mental model is closer to a categorical (eg certain, likely, unlikely, etc.) than a continuous probability. In which case 70% and 80% both fall under “likely”
December 3, 2024 at 7:14 PM
There aren’t many everyday scenarios where we have access to such precise probabilities to base decisions on. Usually it is more coarse: my mental model is closer to a categorical (eg certain, likely, unlikely, etc.) than a continuous probability. In which case 70% and 80% both fall under “likely”
*whoosh* The sound of your pun going over my head
Although to be fair, I don’t think TI-basic even has classes!
Although to be fair, I don’t think TI-basic even has classes!
November 17, 2024 at 11:42 PM
*whoosh* The sound of your pun going over my head
Although to be fair, I don’t think TI-basic even has classes!
Although to be fair, I don’t think TI-basic even has classes!
Why not both? I first learned how to code on my graphing calculator while bored in class in 8th grade
November 17, 2024 at 11:20 PM
Why not both? I first learned how to code on my graphing calculator while bored in class in 8th grade
Are there any datasets that are truly unbiased?
A more pragmatic challenge is how we can best assess and mitigate biases in data/models, knowing that there will always be *some* biases (in the statistical sense)
A more pragmatic challenge is how we can best assess and mitigate biases in data/models, knowing that there will always be *some* biases (in the statistical sense)
November 17, 2024 at 2:39 PM
Are there any datasets that are truly unbiased?
A more pragmatic challenge is how we can best assess and mitigate biases in data/models, knowing that there will always be *some* biases (in the statistical sense)
A more pragmatic challenge is how we can best assess and mitigate biases in data/models, knowing that there will always be *some* biases (in the statistical sense)
He applied to medical school twice but didn’t get in. I wonder what he would think about the arc of technology in medicine
November 17, 2024 at 2:22 PM
He applied to medical school twice but didn’t get in. I wonder what he would think about the arc of technology in medicine