COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching

  title={COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching},
  author={Junyi Gao and Cao Xiao and Lucas Glass and Jimeng Sun},
  journal={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
  • Junyi Gao, Cao Xiao, +1 author Jimeng Sun
  • Published 2020
  • Computer Science
  • Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Clinical trials play important roles in drug development but often suffer from expensive, inaccurate and insufficient patient recruitment. The availability of massive electronic health records (EHR) data and trial eligibility criteria (EC) bring a new opportunity to data driven patient recruitment. One key task named patient-trial matching is to find qualified patients for clinical trials given structured EHR and unstructured EC text (both inclusion and exclusion criteria). How to match complex… Expand
HINT: Hierarchical Interaction Network for Trial Outcome Prediction Leveraging Web Data
HINT learns a dynamic attentive graph neural network to predict trial outcome based on a comprehensive and diverse set of web data including molecule information of the drugs, target disease information, trial protocol and biomedical knowledge. Expand
Machine Learning Applications for Therapeutic Tasks with Genomics Data
In this review, twenty-two genomics applications of machine learning that can enable faster and more efficacious therapeutic development are studied, from discovering novel targets, personalized medicine, developing gene-editing tools all the way to clinical trials and post-market studies. Expand
Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification
A Deep High-Resolution PseudoSiamese Framework (PS-HRNet) is proposed to solve the problem of matching person images with the same identity from different cameras and a pseudo-siamese framework is constructed to reduce the difference of feature distributions between low- resolution images and high-resolution images. Expand
Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
  • F. Xie, Han Yuan, +5 authors Nan Liu
  • Computer Science
  • ArXiv
  • 2021
This paper presents a meta-modelling system that allows for the simulation of the dynamic response of the immune system to assess the severity of organ failure in a number of patients. Expand


DeepEnroll: Patient-Trial Matching with Deep Embedding and Entailment Prediction
A cross-modal inference learning model is proposed to jointly encode enrollment criteria and patients records into a shared latent space for matching inference to solve the core problem of patient-trial matching. Expand
CAMP: Co-Attention Memory Networks for Diagnosis Prediction in Healthcare
A model called Co-Attention Memory networks for diagnosis Prediction (CAMP) is proposed, which tightly integrates historical records, fine-grained patient conditions, and demographics with a three-way interaction architecture built on co-attention. Expand
GRAM: Graph-based Attention Model for Healthcare Representation Learning
Compared to the basic RNN, GRAM achieved 10% higher accuracy for predicting diseases rarely observed in the training data and 3% improved area under the ROC curve for predicting heart failure using an order of magnitude less training data. Expand
MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare
Multilevel Medical Embedding (MiME) is proposed which learns the multilevel embedding of EHR data while jointly performing auxiliary prediction tasks that rely on this inherent EHR structure without the need for external labels. Expand
Criteria2Query: a natural language interface to clinical databases for cohort definition
Criteria2Query is a natural language interface that facilitates human-computer collaboration for cohort definition and execution using clinical databases and supports fully automated and interactive modes for autonomous data-driven cohort definition by researchers with minimal human effort. Expand
Learning Eligibility in Cancer Clinical Trials using Deep Neural Networks
It is shown that representation learning using {deep} neural networks can be successfully leveraged to extract the medical knowledge from clinical trial protocols for potentially assisting practitioners when prescribing treatments. Expand
Publicly Available Clinical BERT Embeddings
This work explores and releases BERT models for clinical text: one for generic clinical text and another for discharge summaries specifically, and demonstrates that using a domain-specific model yields performance improvements on three common clinical NLP tasks as compared to nonspecific embeddings. Expand
StageNet: Stage-Aware Neural Networks for Health Risk Prediction
This work proposes a Stage-aware neural Network (StageNet) model to extract disease stage information from patient data and integrate it into risk prediction, which outperforms state-of-the-art models in risk prediction task and patient subtyping task. Expand
EliIE: An open-source information extraction system for clinical trial eligibility criteria
EliIE, an OMOP CDM-based information extraction system for automatic structuring and formalization of free-text EC outperforms existing systems and shows promise to improve. Expand
EliXR: an approach to eligibility criteria extraction and representation
This study presents a semi-automated data-driven approach to developing a semantic network that aligns well with the top-level information structure in clinical research eligibility criteria text and demonstrates the feasibility of using the resulting semantic role labels to generate semistructured eligibility criteria with nearly perfect interrater reliability. Expand