Prognosis Prediction
Prognosis prediction aims to forecast the likely course of a disease or condition, guiding treatment decisions and resource allocation. Current research heavily utilizes machine learning, employing diverse architectures like convolutional neural networks (CNNs), transformers, and Bayesian networks, often incorporating multimodal data (imaging, clinical records, genomics) to improve prediction accuracy. This field is crucial for personalized medicine, enabling more effective patient stratification and potentially reducing healthcare costs through optimized treatment strategies. Furthermore, research emphasizes improving model interpretability and robustness to variations in data distribution, enhancing clinical trust and facilitating wider adoption.
Papers
INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis
Shih-Cheng Huang, Zepeng Huo, Ethan Steinberg, Chia-Chun Chiang, Matthew P. Lungren, Curtis P. Langlotz, Serena Yeung, Nigam H. Shah, Jason A. Fries
Semi-supervised ViT knowledge distillation network with style transfer normalization for colorectal liver metastases survival prediction
Mohamed El Amine Elforaici, Emmanuel Montagnon, Francisco Perdigon Romero, William Trung Le, Feryel Azzi, Dominique Trudel, Bich Nguyen, Simon Turcotte, An Tang, Samuel Kadoury