HINT: Hierarchical interaction network for clinical-trial-outcome predictions

Tianfan Fu, Kexin Huang, Cao Xiao, Lucas M. Glass, Jimeng Sun

Research output: Contribution to journalArticlepeer-review

Abstract

Clinical trials are crucial for drug development but often face uncertain outcomes due to safety, efficacy, or patient-recruitment problems. We propose the Hierarchical Interaction Network (HINT) to predict clinical trial outcomes. First, HINT encodes multi-modal data (drug molecule, target disease, trial eligibility criteria) into embeddings. Then, HINT trains knowledge-embedding modules using drug pharmacokinetic and historical trial data. Finally, a hierarchical interaction graph connects all of the embeddings to capture their interactions and predict trial outcomes. HINT was trained and validated on 1,160 phase I trials, 4,449 phase II trials, and 3,436 phase III trials. It obtained 0.665, 0.620, and 0.847 F1 scores on separate test sets of 627 phase I, 1,653 phase II, and 1,140 phase III trials, respectively. HINT significantly outperforms the best baseline method on most metrics. The benchmark dataset and codes are released at https://github.com/futianfan/clinical-trial-outcome-prediction.

Original languageEnglish (US)
Article number100445
JournalPatterns
Volume3
Issue number4
DOIs
StatePublished - Apr 8 2022
Externally publishedYes

Keywords

  • clinical-trial-outcome prediction
  • data mining
  • deep learning
  • graph neural network
  • neural network
  • trial outcome prediction benchmark

ASJC Scopus subject areas

  • Decision Sciences(all)

Fingerprint

Dive into the research topics of 'HINT: Hierarchical interaction network for clinical-trial-outcome predictions'. Together they form a unique fingerprint.

Cite this