🔍Excited to share our team's publication in @BMJ_EBM: "Integrating Large Language Models in Systematic Reviews: A Framework and Case Study using ROBINS-I for Risk of Bias Assessment." Dive into our article here📄: https://t.co/DFfdDPaiuq #SystematicReview #EvidenceBasedMedicine

The only port planner you’ll ever need. Check it out and let us know what you think: https://t.co/HahjEz1Hhh

You can change labels, adjust colors, and position ports exactly where you need them. No design skills. No complicated software. Just a simple tool that works.

Whether you’re preparing for a case presentation or an educational video, it gives you clean, customizable diagrams with anterior, lateral, and thorax views.

With @aabutaka, we’ve built a simple app that allows surgeons create professional port placement diagrams in seconds. https://t.co/HahjEz1Hhh

🚀 Just launched a new statistical tool! 📊 🔗 https://t.co/eBGb83wX8l ✅ Convert dispersion metrics (SE, CI, Range, IQR) into SD ✅ Combine multiple groups into one ✅ Auto-calculates combined n, mean, & SD ✅ Visualizes original & combined distributions

📢 New publication out! Our systematic review included 50 studies (45M+ patients) to quantify how hospital-acquired conditions affect length of stay. 🏥 Falls ➕5.2 days 🛏️ Pressure ulcers ➕12.9 days 🩸 CLABSIs ➕22.1 days 🩹 SSIs ➕7.9 days Read here:

A huge thank you to our incredible team of collaborators for their hard work and dedication to this project! 🙌 Your diverse expertise made this research possible. Looking forward to more exciting advancements together! 🚀🔬

(5/5) Excited for what’s next in AI-driven pathology & oncology! 💡🤖 #AIinPathology #HCC #LiverCancer #DigitalPathology #MachineLearning #CancerResearch

(4/5) This is a proof-of-concept that AI can objectively quantify histologic tumor differentiation, providing a new layer of prognostic insight in HCC. 🚀🔍

(3/5) To make these findings actionable, we built interactive web tools to predict outcomes for HCC patients! Try them out: 🖥️ Overall survival: https://t.co/V41O7wgNU4 🖥️ DFS: https://t.co/LDtKLl6bai 🖥️ Recurrence/metastasis:

(2/5) These AI-derived features outperformed standard clinical-pathologic variables in predicting: ✅ Overall survival (C-index: 0.81 vs 0.68) ✅ Disease-free survival (0.73 vs 0.68) ✅ Metastasis (0.78 vs 0.65)

(1/5) We trained a deep learning model to quantify histologic tumor differentiation in HCC, analyzing nuclear area, reticulin expression, and Hepar-1/Glypican-3 staining. 🧑‍⚕️💡

Our latest paper in Modern Pathology demonstrates how AI-powered histologic features improve risk stratification in hepatocellular carcinoma (HCC). 🔬🧠 📄 Paper:

Just launched my Text Memorization App! 🚀 🎙️ Speak → Reveal Words → Memorize Faster! 🔥 ✔️ Paste text & hide it ✔️ Recite aloud, app reveals correct words ✔️ Sequential & non-sequential modes Try it here: https://t.co/wvyOUZ5rYs Let me know what you think! 💡

1/4: Excited to share that our work on "Collaborative large language models for automated data extraction in living systematic reviews" has been published in the @JAMIA_Journal. Grateful to @IrbazRiaz @cbaral @M_Hassan_Murad @JeannePalmerMD for their support and guidance.

Perfect for researchers, students, and health professionals looking to better understand diagnostic test performance and visualize these concepts intuitively.

It also includes decision aids to interpret positive and negative test results. 🔗 Try it here:

2️⃣ Diagnostic Test Performance Calculator: Input total number of patients, disease prevalence, sensitivity, and specificity to generate a complete contingency table (TP, TN, FP, FN) along with all diagnostic metrics.

1️⃣ Diagnostic Test Performance Analyzer: Input TP, FP, FN, and TN to instantly calculate diagnostic measures (sensitivity, specificity, PPV, NPV, likelihood ratios, etc.) with interactive visualizations to make data interpretation easier. 🔗 Link:

🚀 Excited to introduce two tools I developed to enhance understanding and visualization of diagnostic test performance!