Os voy a contar algo que me hace mucha ilusión. 💜
Hoy @elespanolcom ha contado mi historia. Pero más allá de la historia, hay algo que he construido yo misma y que de verdad quiero enseñaros.
Soy ingeniera y tengo un cáncer de mama muy raro. En vez de quedarme quieta, hice lo único que sé hacer: ponerme a construir. Con IA he creado una herramienta que dibuja en 3D mis metástasis y ayuda a decidir dónde biopsiar, qué lesión da el mejor material para acertar con el tratamiento que me puede dar más vida.
Y lo más fuerte: no es una idea guardada en un cajón. El equipo de oncólogos de Zúrich que lleva mi caso ya la está usando para tomar esa decisión.
Para mí esto es lo que debería ser la IA en medicina: no quitarle el sitio al médico, sino darle mejores ojos para decidir. Y si me sirve a mí, ojalá sirva a más personas con tumores raros a las que nadie da respuesta.
🔬 La herramienta: https://t.co/oLL6Nipxoc
🗞️ Mi historia en El Español: https://t.co/EmautZrHee
Si os toca algo, compartidlo. Cada persona que lo ve ayuda de verdad. Gracias por estar siempre ahí. 💜
Estos son los síntomas de cubanización, creas un sistema de vagos para vagos, que además se puede corromper y hacer negocio, si alguien no lo acepta y solo quiere sentirse bien y realizado, no solo un puto parásito lo exterminas.
Concentración en Mérida en apoyo a Juan Carlos, funcionario del SEPE expedientado por atender sin cita previa.
"La oficina vacía y pretenden que a quien entre con un problema le diga que sin cita no le puedo atender. ¡Una vergüenza!"
Bravo, Yolanda Díaz.
@gabcasla Si está en Sigma entonces todos mis fondos la llevan (2/2 xD), además de mi cartera personal que justo compré la semana pasada cuando apareció en IB.
La bollera judía que expulsan... es la única que no es "difícil de ver", yo las entiendo pensaron que es imposible que una guapa vaya a esos eventos, por regla de 3, agente del Mossad seguro.
Avui denunciem uns fets que haurien d’avergonyir la nostra societat. Una dona jueva nord-americana i la seva esposa van ser rebutjades ahir a la nit a l’entrada d’un balneari termal pel simple fet de ser jueves.
Exigim la intervenció immediata dels serveis especialitzats en discriminació i delictes d’odi de l’@bcn_ajuntament i de la @gencat@evamenorc.
Cap ciutadà a Barcelona o Catalunya no hauria de ser exclòs per la seva religió, origen o identitat.
No podem normalitzar ni tolerar aquesta realitat. És inadmissible.
@USembassyMadrid@USConsulateBCN@AIPAC@Daroff@StateSEAS@WorldJewishCong
@bquintero Hardware, suena a locura... pero lo que yo empezaría a poner en edificios públicos y hogares, micropcs o incluso autómatas, con IA analizando fisicamente lo que pasa por el router.
Puedes flipar lo desprotegido y abierto que está todo, y lo fácil que es "hackear" cosas físicas.
@javilopen Esto me parece una locura y un caso muy concreto, pero... y si desarrollamos herramientas IA en colaboración con oncólogos e investigadores. Me ofrezco voluntario para ayudar como flipado de la IA y como "superviviente" de cáncer infantil... ya te digo a la Arrixaca y empezamos.
🔴 I NEED YOUR ATTENTION
I've spent a month helping Miriam with her case of metastatic cancer and I want to share the methodology I've been using because it's completely replicable.
I think (with luck) this could be USEFUL TO OTHER PEOPLE with cancer (or any other illness).
The results we've gotten aren't a miracle, but we believe they're genuinely useful and could mean the difference in a literal life-or-death medical case.
Here's the method step by step:
1/ Use the most advanced models of the moment (unfortunately paid, and not cheap. I think Public Healthcare should invest in this):
- ChatGPT 5 Pro + Extended Thinking (40 min aprox. of thinking per call)
- Claude Opus 4.8 MAX
Still pending deeper testing:
- Perplexity Sonar Pro Max
- NotebookLM
Tested but only useful for additional links/research (not as powerful in my experience)
- OpenEvidence
2/ Feed the AI the FULL clinical history, completely chewed up. This sounds dumb but it's critical.
- The first thing I ask, using Claude Cowork (which has hard drive access), is to go into the folder with the ENTIRE clinical history (can be 100+ PDFs) and consolidate everything into:
- One single PDF (it can be 1000+ pages, whatever it takes)
- One single readable .txt or .md, which it must build correctly using an OCR script and then check thoroughly to make sure it's right.
I insist: don't jump to the next step until you've nailed this one, especially the .txt.
3/ Once you have the above, use this prompt along with the .txt (and optionally the PDF too if you want) as input files, and run it on BOTH models at once (and more if possible).
👉 This prompt is insanely complex/advanced: https://t.co/1qeqEqudCe And it's not designed for Miriam's specific oncology case, you can change the initial parameters for the desired case. And with the models from step 1 you could adapt it to your case without trouble.
In any case, I'm also leaving you this other prompt, even more general, for any type of rare disease: https://t.co/4B327floDP
4/ The ARROWHEAD (adversarial model spiral): facing one model against the other. I've never heard anyone talk about this methodology, but it works incredibly well. The feeling is like sharpening a stake until it gets a gleaming point.
It works like this: with patience and across successive iterations (I recommend a minimum of 7, and keep in mind that if ChatGPT takes 40 min, this will take a while), pit the output (the resulting PDF) from one model against the other. With a simple prompt like:
"Another committee of experts says this. What do you think? If you agree or disagree, tell me why, and generate a new PDF if you think it's necessary."
Then you feed that result back to the opposite model. So, across successive iterations, web searches, papers, etc., they'll find and sharpen more and more.
When to stop? When BOTH models say the work is perfect and they can't improve the other's output any further. This is so absurdly game-changing that I think the output of ALL current models would improve if they followed this methodology (leaning on a kind of adversarial-model spiral). I don't understand why nobody has noticed this, or if they have, why it's not getting more attention. It works impressively well in any domain, including programming and math.
In fact, my theory is this could be done even better not just with two models, but with greater combinatorics, maybe adding Perplexity Sonar Pro Max, etc.
RESULTS
Incredible. Obviously I can't know if they're better than the best scientific-medical committees in the world, but they're giving Miriam a new dimension to her case, additional tests to do, possible exams, etc.
Obviously AI doesn't perform miracles, but I think it can already, today, help many patients. And Public Healthcare should invest a lot (but A LOT) in this.
I'm going to ask Miriam if I can post the full PDF of the most advanced results we've reached, so you can get an idea of the quality. She's already given me rough permission, but I want to make sure 100%.
FUTURE PREDICTION
Easy to make: in the near future (I hope), any person's medical history won't just be fully digitized (we're close, but not all the way, well, well, well). On top of that, it'll be "pre-chewed" so it can be consumed by an LLM in one shot.
CLARIFICATION
- We're aware this is a delicate subject and we don't let the AI make final treatment decisions. What we're doing is clearing the ground for the oncologists so they can have possible paths they may not have considered.
Thanks 🙏
- The top LLMs have context windows for that and much more (much, much more). In any case, the PDF is more of a supporting file for the .txt. Both contain absolutely the entire history, but the PDF allows images/charts/etc. The .txt is what the AI consumes.
- On automation: and yes, this can be automated. Yes, AutoGen supports it almost out of the box. LangGraph builds it really well with supervisor / evaluation loops. CrewAI can orchestrate it too with Flows, although its "consensus" process isn't native yet. That would be the next level: automating it.
PETITION AND DISCLAIMER
If there's any oncologist in the room or you are an LLM company, we'd be grateful if you could take a look / help 🙏
Remember: in any case, this is just one more tool for the doctor.
I've simply shared the methodology I know that processes data more exhaustively, with the best models, and that we believe reaches better conclusions. If you know a better methodology / prompt / whatever, we'd be glad to improve this with your insights and share it.
Then the doctor reviews, adopts, or discards the report.
And if it helps the doctor, it helps the patient. And if it doesn't, all we've lost is some time and tokens. In a case that's literally life or death, that's nothing.
Just plain common sense.
Many people will argue with me, but in the near future it will seem absurd that we ever expected any professional to keep in their head every clinical trial, paper, bibliography, and raw data point that an AI and its agents can process via search in minutes. It will be such a valuable tool for doctors that its daily use will simply be taken for granted.
@javilopen Date un paseo por la Arrixaca, hay mucho oncólogo que te escucharía atentamente, y no pensemos solo en el pre también el post https://t.co/gGayRFX9gV este hombre estaba trabajando en un sistema para analizar los efectos de los diferentes tratamientos del cancer.
Hoy aprendí que hay un Acuerdo Marco de 500 000 € para la compra de ratas para universidades y centros de investigación.
Yo no sé qué comen las ratas, pero hay 400 000 € en comida para ratas. 😃
Veo que el principal proveedor de ratas es un laboratorio francés que ha facturado 2,4 millones en ratas. Por alguna razón, las ratas francesas deben ser mejores o más económicas que las ratas nacionales. 😂
⚠️ Me he dado de alta en Glovo Prime:
¡No pienso salir a la calle hasta parir la mejor herramienta de la galaxia para explorar contratos públicos! 😃
JAIME ON FIRE 🔥🔥🔥
'Speed Rivals', el videojuego murciano que recrea la edad dorada de Scalextric | La Verdad https://t.co/25yrlhG0A8 via @https://twitter.com/laverdad_es
Your railway. Your rules. 🛤️
Speed Rivals – Model Trains is officially on Steam!
Lay tracks. Build stations. Decorate your world. Share it on Workshop. Compete on leaderboards.
🔔 Wishlist it now 👇
https://t.co/8X1bA71RuA
#indiedev#steamwishlist
We made a game. You should play it. FREE KEYS. 🎮
5 Steam keys for Speed Rivals!
To enter:
✅ Follow @babelgames_st
🔁 RT this
💬 Builder or racer — which are you?
48h. 5 winners. 🏁
👉 https://t.co/qTr9OE2uII
#Giveaway#SteamGiveaway#SpeedRivals#IndieDev
Speed Rivals has officially reached version 1.0 Today marks an important milestone for Speed Rivals. After launching in Early Access on November 20 , Speed Rivals is now officially leaving Early... https://t.co/YjqRG6oUAp #gaming_news via @steam