• 1 Post
  • 7 Comments
Joined 3 years ago
cake
Cake day: June 13th, 2023

help-circle
  • What do you suggest? I take pretty extreme “voting with your dollars” positions that have excluded me from a ton of social and family things. I have protested, taken days off work, marched, signed petitions. I’ve donated to progressive politicians, I’ve talked about what’s going on to apathetic people to the point where they don’t talk to me much anymore or ask to stop talking politics. Everything I’ve voted for has pretty much passed, and my representatives do the right things for the most part. I actively participate in a local network of people connecting resources to protect immigrants by hosting some services on my self-hosted network for people to organize on (I have personally sponsored meshtastic communicators and provided access to an anti-ice private channel).

    I’m pretty tired of doing what feels like a huge amount of effort, only to be told I should be doing something different or more. I fought so hard against the right, that the flanking snark attacks from the left and the implication that I’m somehow complicit by not doing enough or the right thing are driving me towards apathy. I’m fucking exhausted.




  • Devil’s advocate…this is one of the few good opportunities for ML. If you train a model on a specific dataset with expert validation, this has the opportunity to save lives.

    First, radiology isn’t one thing; different radiologists with different expertise looking at the same imaging can see different things. Second, there are not enough radiologists; my wife is an ER doctor who only does overnights and her hospital network has a central radiology center that reviews all films from all the hospitals, and it’s always backlogged and waiting on results impacts outcomes in a real way. Third, there are simply human limits to what we can visually perceive, take a look at this study: https://pmc.ncbi.nlm.nih.gov/articles/PMC3964612/

    Radiological ML models could change healthcare. Imagine a world where part of your annual preventative care you go and get a full body CT. The ML model can compare your CT with references in your demographics AND your prior years, and find changes/issues before they’re crises. That’s simply not an amount of data analysis that could be done by an army of radiologists, and has the opportunity to spot things like tumors or organ swelling way earlier. I get that the late stage capitalism reality is “they’ll use the data to farm money out of you” but from an actual technological standpoint, this could have real life-saving and improving implications for a lot of people and removes a huge bottleneck in healthcare.