{
  "id": 15797467,
  "title": "Q&A: AI tool automates echocardiogram assessment of the heart's right ventricle",
  "url": "https://urgent.news/2026/10/20/q-a-ai-tool-automates-echocardiogram-assessment-of-the-hearts-right",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-20T20:00:10.000Z",
  "source": {
    "name": "Medical Xpress",
    "slug": "medical-xpress",
    "url": "https://medicalxpress.com/news/2026-10-qa-ai-tool-automates-echocardiogram.html"
  },
  "original_language": "en",
  "account": "A new study has created DROID-RV, a deep learning model capable of estimating right ventricular size and function from echocardiograms. Lead authors Mostafa Al-Alusi and Patrick Ellinor from the Mass General Brigham Heart and Vascular Institute describe how this tool could revolutionize the assessment of the right ventricle (RV) in routine clinical settings. The RV, which pumps blood to the lungs, is difficult to evaluate using standard echocardiograms due to its unique shape and location behind the breastbone. Current methods like cardiac MRI are more accurate but expensive and not as widely available. Using a deep learning model trained on over 380,000 echocardiogram clips, DROID-RV demonstrated impressive accuracy in estimating RV diameter within 3 millimeters on average and identifying reduced RV function. Crucially, the model's predictions of enlarged RV size or impaired function were linked to higher risks of heart failure, atrial fibrillation, and mortality in patients. Even after accounting for factors like age, sex, and left ventricular function, the model's assessments remained significant predictors of adverse cardiovascular outcomes. This suggests the model captures nuanced information from echocardiogram videos that traditional measurements might miss. The authors hope DROID-RV will enable faster, more consistent RV assessments in primary care, flagging abnormal exams for further evaluation. In cases where MRI or expert review is unavailable, DROID-RV could inform decisions about additional testing. The study also hints at the potential for these models to predict future cardiovascular disease independently of the echocardiographer's assessment, opening avenues for direct outcome prediction in the future.",
  "summary": "A new study develops and tests DROID-RV, a deep learning model that estimates right ventricular size and function from echocardiograms, and assesses how those estimates relate to later health outcomes. Mostafa Al-Alusi, M.D., M.S., and Patrick T. Ellinor, M.D., Ph.D., of the Mass General Brigham Heart and Vascular Institute, are the lead and senior authors of a paper published in Nature…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}