Manish Sharma

100 Best Healthcare Technology Blogs and Websites in 2025 FeedSpot brings you the best list of Healthcare Technology blogs, ranked by relevance, online following, and freshness to keep you connected with the latest voices

Read bloggers.feedspot.com/healthcare_t...

Smarter AI Demands Smarter Context: How Yajur Healthcare is Re-Architecting Clinical Reasoning Pipelines - HCITExperts Blog by Yajur Healthcare Not just models. Context. Structure. Trust. By Manish Sharma | Founder & Director, Yajur Healthcare 1. The Bottleneck Isn’t Intelligence—It’s […]

hcitexpert.com/2025/07/smar...

@lifesciencenet.bsky.social

Reversible reduction in brain myelin content upon marathon running - Nature Metabolism Using magnetic resonance imaging on marathon runners, Ramos-Cabrer, Cabrera-Zubizarreta et al. report that the signal detected as a surrogate of myelin content is significantly reduced after exercise,...

The brain myelin content in marathon runners
“This study offers the striking observation that extreme exercise has a profound effect in the brain that is reflected in reversible structural alterations" @naturemetabolism.bsky.social
www.nature.com/articles/s42...
www.nature.com/articles/s42...

A Task Framework for Healthcare, for Enabling AI Agentic Workflows in EHR Systems by Manish Sharma, Yajur Healthcare - HCITExperts Blog by Yajur Healthcare As healthcare systems continue to evolve towards more integrated and data-driven models, the need for structured task execution mechanisms has […]

hcitexpert.com/2025/03/a-ta...

This is absolutely spot on! 😂

A clinical certification pathway for generalist medical AI systems There have been extensive evaluations of artificial intelligence (AI) systems for narrow medical tasks, but more work is needed to systematically evaluate and deploy AI systems that can perform a broad range of medical tasks. The medical training process itself might offer a template for addressing this challenge. Clinicians undergo rigorous education and training, progressing through stages of increasing responsibility and autonomy. Similarly, generalist medical AI systems could be subjected to a phased certification model before they are granted greater autonomy in patient care.

www.thelancet.com/journals/lan...

An evaluation framework for clinical use of large language models in patient interaction tasks https://www.nature.com/articles/s41591-024-03328-5 (read free: https://rdcu.be/d5oJ1) 🧬🖥️🧪 https://github.com/rajpurkarlab/craft-md

Clinical Data streams using federated data, clinical data summaries are not just discrete data points, they are an amalgamation of various contexts
Intelligent Care Systems
Pathways to move from care documentation systems to Intelligent Care Systems
Bio markers
Bridge RWD & RWE

www.nature.com/articles/s41...

Data Consent framework allows for FAIR data use and opt-ins or opt-outs. More about the Medical Data Infrastructure soon.

Ethical data acquisition for LLMs and AI algorithms in healthcare, Marta Williams et al

Data is what makes LLMs smart, probably it's time to give incentives to the citizens for adding their Anonymized data to their Health ID. Royalty can be paid (to the citizen) for each data use for LLM fine tuning. More incentives for recency, reduced incentives for older records.

Fine-Tuning Large Language Models For Oncology: Key Challenges & Recommendations

Yajur MDI

hcitexpert.com/2024/12/fine...

I'll get straight to the point.

We trained 2 new models. Like BERT, but modern. ModernBERT.

Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.

It's much faster, more accurate, longer context, and more useful. 🧵

YouTube video by Zero To Mastery PyTorch 101 Crash Course For Beginners in 2025 (+ Special Giveaway!)

PyTorch 101 🚀

A full PyTorch course (25 hours) for beginners covers the foundation of PyTorch, from processing tensor data to neural network applications such as classification, computer vision, and more.

📽️ www.youtube.com/watch?v=LyJt...

#python #datascience #MachineLearning #DeepLearning

You are right! I stand corrected. But will suggest the simplicity until a good critical mass of data achieved on notion

The AI revolution is running out of data. What can researchers do? AI developers are rapidly picking the Internet clean to train large language models such as those behind ChatGPT. Here’s how they are trying to get around the problem.

🧪 AI faces a significant data bottleneck: by 2028, training data may equal the total stock of public online text.

Solutions like synthetic data, smaller models, and specialized datasets are key to future advances.🩺💻 #MLSky

When starting out, suggest keeping it simple with Markdowns and using tags for concept links across the pages. The mindmap,visual graph is a great help in ensuring the connectedness of topics. I found the base Dataset you create allows you to progressively add to your usecases for work, research,etc

Inspired by @wimlds.bsky.social , I looked for a "Women in Machine Learning" starter pack and couldn't find one.
So I created one! May have some mistakes. I'll try to do an AI ethics one next. 🤗
go.bsky.app/LT6CwNN

x.com/sierracatali...

Genomics of Gene Expression Join Our Lab The Genomics of Gene Expression is led by Dr. Ana Conesa from the Institute for Integrative Systems Biology (I2SysBio), Spanish National Research Council (CSIC). We are interested in…

The @conesalab.bsky.social conesalab.org
is seeking to join motivated Postdocs through the #JuanDeLaCierva from @ageinves.bsky.social
tinyurl.com/32acz58 and #CIAPOS tinyurl.com/bmrex8cc
Contact us ASPA if interested in long-read, single-cell or spatial transcriptomics and multi-omics.

8 Google Employees Invented Modern AI. Here’s the Inside Story They met by chance, got hooked on an idea, and wrote the “Transformers” paper—the most consequential tech breakthrough in recent history.

Listen to article of about 8 Google authors who wrote the seminal 2017 transformers paper that started the current AI LLM revolution
www.wired.com/story/eight-...

Great look at 42 CFR Part 2 Final Rule from Melissa A Soliz, Outside Counsel for Velatura at the eHealth Exchange meeting.

Biggest takeaway for me is the need to know which data falls under Part 2 so you can share or not share that data based on various consents and legal requirements.

#eHx24

youtu.be/n1BVlDPercI?...