[fao_]

> As i said, brain swelling from the surgery.

Which constitutes brain trauma!

> Which wasnt the case, it worked and he collected his dataset with his ancient hardware till it had to be removed again.

Unfortunately as others have pointed out, his dataset is pretty worthless and the claims around it have been largely unsubstantiated. From your earlier post,

> And the frame of the article is aimed at clicks and keeping the reader hooked by creating the impression he had made some monumental mistake.

IMHO he had, and if you ask literally any neurosurgeon or anyone working in neuroscience I'm willing to bet that they would say the same.

[fundamental]

> his dataset is pretty worthless and the claims around it have been largely unsubstantiated.

The really sad part of it is that with fairly minor changes it could have been a landmark dataset IMO. Having better recording equipment, a lower noise floor environment for data collection (e.g. don't run fluorescent lights while recording), having precise timestamps integrated into the recording, better temporal separation between recording of various phrases, adding simultaneous EMG/EEG, etc would have resolved quite a few data related issues. It's a unique situation (for good reason), but bad data...

From seeing the data, I suspect the electrode placement was in a good enough location that novel things could have been done with a cleaner data source. I guess the major limiting factor is that absolutely no one would want to be involved with the project at that stage. What sort of IRB would approve any of this? Better data would answer some key questions that could generalize to lock-in patients (theoretically) and worst case it would provide a strong indicator that no significant BCI can be made for the task given the electrode placement.

[cf141q5325]

>Which constitutes brain trauma!

Yes, i got that from your post the first time. Like i said, brainswelling from the surgery. It read to me as if the article wanted to create another picture. The author not mentioning up front that it was only the probes that got implanted left to me the impression that the speech problems were due to an error with the implant. Which it wasnt.

>Unfortunately as others have pointed out, his dataset is pretty worthless and the claims around it have been largely unsubstantiated.

One said the approach was worthless, because there exist better (less invasive and cheaper) approaches using eye movement tracking apps today. It was also as the reason given why nobody else researched into this. That wasnt however aimed at the dataset. The feedback to the dataset started at

>When Kennedy finally did present the data that he’d gathered from himself ...

Notably >By taking on the risk himself, by working alone and out-of-pocket, Kennedy managed to create a sui generis record of language in the brain, Chang says: “It’s a very precious set of data, whether or not it will ultimately hold the secret for a speech prosthetic. It’s truly an extraordinary event.”

>IMHO he had, and if you ask literally any neurosurgeon or anyone working in neuroscience I'm willing to bet that they would say the same.

He was 66 and was first left hanging waiting for a willing subject who could still talk to validate earlier results. He then couldnt afford recertification of his invention and was faced with nobody else working on this approach.

You are skipping over the fact that it worked. His lifes work and deep obsession turned out to work. He did it, what more is there to say other then good for him? Even if the dataset would turn out to be without practical implications, you can see at his pondering at the very end, whether to put an implant into the other site, that he would have regretted it deeply to have it sit there and stare at him for the rest of his life.