Hacker News new | past | comments | ask | show | jobs | submit login
ARPA-H announces awards to develop novel technologies for precise tumor removal (arpa-h.gov)
133 points by melling 29 days ago | hide | past | favorite | 26 comments



This is the sort of thing I'd love to see NIH have many parallel research tracks on this stuff, given backing & support to make the research happen & to release the work.

Precision medicine has so much potential, feels so in line for some really wild breakthroughs, with its ability to make so many exact & small operations.

I wonder where the Obama Precision Medicine (2015) work has gotten to so far. https://obamawhitehouse.archives.gov/the-press-office/2015/0...


The biggest Obama spend was to create a research cohort (https://allofus.nih.gov/). So far, it hasn't paid dividends in an appreciable way, but the UK Biobank (on which the US program is partially modeled) started in 2006 and is now contributing immensely to the development of medicine.

The US program has the potential to be even more valuable if managed well, but I haven't seen overwhelming indications of reaching that potential yet; however, I think a few more years are needed for a clear evaluation.


Sadly the All of Us program (of which I am a research subject [and researcher]) hasn't done any sort of imaging or ECG. They did draw blood, so that allowed for genome sequencing. That may also, in principle, allow for assaying new biomarkers (I don't believe anything like that has been funded though).


Thanks for the insight! I have used UKB data extensively, but haven't seen much from All of US, so I was wondering if I had missed something. . .


All of Us is great for disease labels and for genetic validation (and discovery). I like it a lot. I just have... ideas for how they could make it more valuable. Ideas that I stole from Rory Collins. https://www.ukbiobank.ac.uk/media/gnkeyh2q/study-rationale.p...


2009-2010 Meaningful Use criteria required physicians to implement electronic care records.

There's now FHIR for sharing records between different vendors' EHR systems. There's a JSONLD representation of FHIR.

Which health and exercise apps can generate FHIR for self-reporting?

Can participants forward their other EHR/EMR records to the All of Us program?

Can participants or Red Cross or other blood donation services forward collected vitals and sample screening data to the All of Us program?


The imaging reports are being imported, but not the images.

The bigger issue is that clinical imaging is done due to medical indications. Medical indications dramatically confound the results. A key element of the UK Biobank's value is that imaging and ECG are being done without any clinical indication.


So they need more data from healthy patients when they're healthy in order to determine what's anomalous?

SIEM tools do anomaly detection with lots of textual log data and sensor data.

What would a Cost-effectiveness analysis say about collecting data from healthy patients: https://en.wikipedia.org/wiki/Cost-effectiveness_analysis

TIL the ROC curve applies to medical tests.


This program is incredibly difficult to get access to and has been monopolized by a few elite institutions whose name recognition potential seems to have blinded funders. These institutions basically control everything about the cohort, but they're not innovating well with the data that's available and I haven't seen much of anything interesting coming out of the investment. This is in stark contrast to the UK Biobank which has access control but is relatively egalitarian in access. It's been producing major results since just a few years after it's inception, and continues to.


Are you thinking of the Million Veteran Program? All of Us is readily accessible to most US institutions and is rolling out a plan to expand access.


Ostensibly this is part of the ‘cancer moonshot’ started during the Obama White House following the death of Beau Biden, as mentioned by another reply, and continued today by the Biden administration.


Biden's son died of cancer so this is basically his pet project.


He died from a glioblastoma. Car-t therapy is promising for that.

https://www.massgeneral.org/news/press-release/clinical-tria...



> The agency’s commitment is not expected to exceed $150 million to develop novel technologies that will allow surgeons to remove cancerous tumors with higher accuracy. If successful, these technologies will revolutionize surgeries, dramatically reducing rates of repeat procedures.

How does an incremental improvement in surgery (or chemo, or radiotherapy) constitute a cancer "moonshot" in 2024?


I didn’t see the word moonshot used anywhere.

However, I think the “moonshot” concept is improving, and attempting, many different ideas and techniques over the next 25 years.

I looked up the original moonshot announcement:

https://www.whitehouse.gov/briefing-room/statements-releases...


While it’s not in the ARPA-H announcement, the broader press coverage is using the moonshot frame. https://www.nytimes.com/2024/08/13/us/politics/biden-researc...


It's part of the cancer moonshot announced near the end of the Obama administration and headed by then-VP Biden after his son died of cancer. This is just one small funding part of that broader effort.


Moonshot or no, these incremental improvements in surgery do translate into cured patients and saved lives. Surgery is the initial intervention in many cancers and the course of disease is highly sensitive to it.


What is the mandate of ARPA-H as compared to NIH? NIH already hands out $30 billion a year for research. Is the structure of the ARPA-H research different in an appreciable way?


ARPA-H, FWIW, is setup within the NIH. But it is structured to focus on more of "breakthrough" type processes, procedures, devices etc. Also the ARPA-H proposals are not driven solely by peer-review scoring unlike most NIH funding mechanisms. Typically ARPA-H tends to me across specific disease areas and more general in nature


>> What is the mandate of ARPA-H as compared to NIH?

ARPA-H has a much more commercial/translational focus, much like DARPA



Isn’t this just applying the new SAM2 to the tumor bots?


There is no mention of “tumor bots” or any solution that seems primarily powered by an out-of-the-box 2D segmentation capability.


You know an ounce of prevention is worth a ton of cure... maybe upsetting the petrochemical pharmaceutical agribusiness industry about exposing so many people to high levels of mutagenic carcinogens should be higher on the priority list - but then a certain proportion of brainwashed zombies would have mental health crises over the fact they'd been lied to all their lives, oh dear. Gotta protect the mental health of the herd, before they're trotted off to the slaughter.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: