iiinova — where your digital self keeps evolving

Reposted by Shishir Rao

Aashika Sekar @aashikasekar.bsky.social · 10/07/2026

1/8 🎉 Super excited to share my work with Paulo Ribeiro at @qmbci.bsky.social- now published @embojournal.org ! We show PP2A can activate the Hippo pathway in Drosophila, in addition to its role as a Hippo negative regulator as part of the STRIPAK complex. 🧵A short thread on what we found below!

163

Shishir Rao @rnshishir.bsky.social · 12/06/2025

🌍 Why it matters: TRisk offers a scalable, equitable approach to prevention. More than just achieving strong predictive performance, TRisk can reduce over-treatment - crucial for efficient allocation of therapies - while identifying those most likely to benefit⚕️🫀🤖

100

Shishir Rao @rnshishir.bsky.social · 12/06/2025

📉 What this means for CVD prevention: In the general population: 🩺 TRisk reduced treatment recommendations by 34% vs QRISK3, without increasing false negatives. In diabetes: 🩺 24% fewer treatment recommendations w respect to "treat all" strategy, with minimal missed cases (0.2%).

In primary prevention cohort, TRisk at 15% threshold reduced patients selected for preventive therapy by 34% without gain in false negatives with respect to status-quo approach. In diabetes cohort, similarly TRisk at 10% reduced patients selected by 25% and 15% with minimal false negatives with respect to status-quo "treat all" and QRISK3 approaches respectively.

100

Shishir Rao @rnshishir.bsky.social · 12/06/2025

⚙️ What we found: For incident CVD prediction, TRisk showed: ✅ Higher discrimination (C-index 0.91) and net benefit than benchmark models ✅ Better performance across age, sex & socio-economic deprivation groups ✅ Less sensitivity to age ranges ✅ Excellent calibration

100

Shishir Rao @rnshishir.bsky.social · 12/06/2025

🧠 How we built it: TRisk is a Transformer-based survival model trained on: 🔹 2.2M patient records for training 🔹 750K for validation 🔹 3.8k diagnoses, 390 meds, 1.4k tests for model input Importantly, it uses raw, longitudinal EHR sequences (figure) - no manual variable selection and no imputation.

TRisk architecture uses Transformer embeddings and attention built on the BEHRT model. Ordinary differential equations based neural network modelling framework is used for survival modelling.

100

Shishir Rao @rnshishir.bsky.social · 12/06/2025

📚 Why now? Current tools for CVD prediction like QRISK3 often over-recommend treatment—especially in diabetes, where everyone is treated regardless of risk. TRisk changes that. It analyses full EHR histories to predict CVD risk more precisely, not just based on age or a fixed checklist.

100

Shishir Rao @rnshishir.bsky.social · 12/06/2025

Thanks @erictopol.bsky.social🙌 Kazem and I are excited to share our paper, now in press at The Lancet Digital Health! We introduce TRisk, a Transformer-based survival model for 10-year CVD risk prediction and more refined preventive therapy recommendations 🫀📊 A short 🧵...

130