Scholarlink

<p>Heart failure (HF) is a progressive and fatal disease that affects nearly 7 million individuals in the United States, with prevalence expected to surpass 10 million by 2040. Cardiopulmonary exercise testing (CPET) represents the gold standard for assessing functional capacity and predicting survival outcomes among HF patients but its widespread use is limited by <b>practical constraints</b>. Here we introduce a <b>multimodal multi-instance learning framework</b> that predicts peak oxygen consumption (peak VO₂), a critical indicator from CPET, using the <b>more accessible</b> transthoracic echocardiography (TTE) studies and electronic health records (EHR). By modeling the cross-modal interactions and the multi-instance structure of TTE studies, our approach significantly improves predictive accuracy and generalization. The model achieves an R² of 0.603 in peak VO₂ prediction and AUROC of 0.849 in high-risk patient identification, surpassing prior work (R² = 0.529, AUROC = 0.836). On the external validation cohort, the model achieves an R² of 0.541 compared to 0.395 and an AUROC of 0.870 compared to 0.797 from previous work. The improved performance more accurately allows for identification of patients who may benefit from advanced heart failure therapies that otherwise may have been missed.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multimodal multi-instance learning for cardiopulmonary exercise testing performance prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月3日

查看全文
  • Zhe Huang,
  • Weishen Pan,
  • Shudhanshu Alishetti,
  • Ashley N. Beecy,
  • Zhenzhen Liu,
  • Albert Gong,
  • Saebyeol Shin,
  • Kevin J. Clerkin,
  • Rochelle L. Goldsmith,
  • David T. Majure,
  • Chris Kelsey,
  • David vanMaanan,
  • Jeffrey Ruhl,
  • Naomi Tesfuzigta,
  • Erica Lancet,
  • Deepa Kumaraiah,
  • Gabriel Sayer,
  • Deborah Estrin,
  • Kilian Weinberger,
  • Nir Uriel,
  • Fei Wang

摘要

Heart failure (HF) is a progressive and fatal disease that affects nearly 7 million individuals in the United States, with prevalence expected to surpass 10 million by 2040. Cardiopulmonary exercise testing (CPET) represents the gold standard for assessing functional capacity and predicting survival outcomes among HF patients but its widespread use is limited by practical constraints. Here we introduce a multimodal multi-instance learning framework that predicts peak oxygen consumption (peak VO₂), a critical indicator from CPET, using the more accessible transthoracic echocardiography (TTE) studies and electronic health records (EHR). By modeling the cross-modal interactions and the multi-instance structure of TTE studies, our approach significantly improves predictive accuracy and generalization. The model achieves an R² of 0.603 in peak VO₂ prediction and AUROC of 0.849 in high-risk patient identification, surpassing prior work (R² = 0.529, AUROC = 0.836). On the external validation cohort, the model achieves an R² of 0.541 compared to 0.395 and an AUROC of 0.870 compared to 0.797 from previous work. The improved performance more accurately allows for identification of patients who may benefit from advanced heart failure therapies that otherwise may have been missed.