Comment by niekmaas
1 month ago
As a pathologist and neuro-oncology researcher, to save myself time trying to keep up with scientific literature, I'm working on https://www.summarized.science/ . Based topics of interest (suggestions are more than welcome), the tool queries the scientific literature for each month. Then, by quering some LLMs, it extracts themes and summaries. The tool already saves me time in my day to day life, but still needs a lot of finishing touches to promote actively. Anyhow, it is a lot of time working on a web development "side project" after a hiatus of more than a decade due to residency/PhD-program/kids etc. Input/feedback is more than welcome.
Subscribed!
As a layperson, I find this an approachable way to get an overview of a topic. However, I am only interested in a few select topics, and I was not able to find a way to subscribe to specific ones, such as #insulin-resistance (topic request ;-)
Another thing I really value in science YouTubers (e.g., youtube.com/@Physionic) is the deep dives they offer into the research—highlighting conflicting results, paying special attention to meta-analyses, etc. That would be amazing, although I realize it may be too much to ask.
No problem, and thanks for the request! #insulin-resistance is now added: https://www.summarized.science/topics/insulin-resistance/ . I ran it for each month of 2025, if you want to go back further just let me know.
Adding personalised highlights of topics of interest into the monthly emails is my top priority for 2026. Won't be too complicated, just have to set up the right API back-and-forths etc.
Good point about deep dives. I could do that for the topics I'm an expert in, however, by definition, I think this requires domain expertise and is therefore not scalable nor to be automated easily. I'm not sure if this fits the scope of the current project as I want people to find the papers of interest, read a quick summarization and then encourage them to read a selection of papers themselves.
Can you say more about the approach you take for summarization? Are the papers short enough that you just put the whole thing in the context window of the model you’re using, or do you do anything fancy? I’ve tried out various summarization approaches (hierarchical, aspect-based, incremental refinement), and am curious what you found works best for your use case.
Nice! I'm a gastroenterologist and I've been thinking about doing something very similar for some time now.
Well, you're absolutely the target audience. As you can see my focus so far is mostly on (neuro) oncology as this is my domain of interest/work. Let me know if you have any topic requests or have any ideas for additional features to make our lives as medical specialists/researchers easier. Contact form is on the site or just email whatever to the domain (catch-all doing the work).