Low responsiveness of ML models to critical or deteriorating health conditions
1–10 of 57 posts
Re: Low responsiveness of ML models to critical or deteriorating health conditions
#2[flagged]
Re: Low responsiveness of ML models to critical or deteriorating health conditions
#3I work in the ICU monitoring field, on the R&D team of a company with live systems at dozens of hospitals and multiple FDA approvals. We use extended Kalman filters (i.e. non-blackbox "ML") to estimate certain lab values of patients that are highly indicative of them crashing, based on live data from whatever set of monitors they're hooked up to - and it's highly robust.
What the authors of this paper are doing is throwing stuff at the wall to see if it works, and publishing results. That's not necessarily a bad thing at all, but I say this to underline that their results are not at all reflective of SOTA capabilities, and they're not doing much exploration of prior art.
Re: Low responsiveness of ML models to critical or deteriorating health conditions
#4LLM models are organic? They somehow obbey the laws of Thermodinamycs by some parallel on algorythms and underlying Math? It would be amazing if it were some parallel between Biologhycs (specially Funghi with emergent properties) and neural networks...
Re: Low responsiveness of ML models to critical or deteriorating health conditions
#5For IHM prediction, LSTM models and transformer models were trained for 100 epochs using the MIMIC-III and eICU datasets separately.
I might be blind, but I don't see any mention of loss. Did they stop at 100 because it was a nice round number or because it was a good place to stop?
The LSTM model they used had 7k trainable parameters, the CW-LSTM model 153k while the transformer model had 800k parameters (300k trainable parameters and 600k optimizer parameters as they say).
I don't follow the field close enough, but is it reasonable these models all converged at the same time, given the large difference in size?
They mention the transformer model outperforming the LSTMs, but I wonder if it could have done a lot better.
Re: Low responsiveness of ML models to critical or deteriorating health conditions
#6[flagged]
Is this an ad?
Re: Low responsiveness of ML models to critical or deteriorating health conditions
#7I work in the ICU monitoring field, on the R&D team of a company with live systems at dozens of hospitals and multiple FDA approvals. We use extended Kalman filters (i.e. non-blackbox "ML") to estimate certain lab values of patients that are highly indicative of them crashing, based on live data from whatever set of monitors they're hooked up to - and it's highly robust. What the authors of this paper are doing is th…
Parameter estimation is ML now?
Re: Low responsiveness of ML models to critical or deteriorating health conditions
#8I work in the ICU monitoring field, on the R&D team of a company with live systems at dozens of hospitals and multiple FDA approvals. We use extended Kalman filters (i.e. non-blackbox "ML") to estimate certain lab values of patients that are highly indicative of them crashing, based on live data from whatever set of monitors they're hooked up to - and it's highly robust. What the authors of this paper are doing is th…
Calling EKFs "ML" is certainly a choice.
Re: Low responsiveness of ML models to critical or deteriorating health conditions
#9For IHM prediction, LSTM models and transformer models were trained for 100 epochs using the MIMIC-III and eICU datasets separately. I might be blind, but I don't see any mention of loss. Did they stop at 100 because it was a nice round number or because it was a good place to stop? The LSTM model they used had 7k trainable parameters, the CW-LSTM model 153k while the transformer model had 800k parameters (300k train…
What ever happened to early stopping?
I see so many papers where people train neural networks with half-baked recipes. I think I saw early stopping first around 1990 but it is so often for people to pick some arbitrary number of epochs to run. I have to admit I never liked the term "early stopping", I think people should have called it just "stopping", because it makes it seem optional.
Back when I was training LSTM networks it was straightforward to train nets reliably with early stopping...