PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 29, 20260 citationsOpen Access

A System and Method for Concurrent Multi-Disease Prediction via Knowledge-Guided Graph Neural Networks and Ensemble Learning

View Full Paper
HSHarsh SawantBVBhavana VaddadiJSJessica Suthar

Key Points

  • To develop a framework for predicting multiple diseases concurrently using advanced modeling techniques.
  • Utilized an LSTM-based encoder to model patient health states as temporal sequences.
  • Constructed a hybrid knowledge graph integrating SNOMED-CT and DisGeNET ontologies with co-occurrence weights.
  • Employed a joint co-training loss to fuse tabular ensemble and Graph Neural Networks.
  • Achieved strong performance in predicting heart disease with F1=0.8923 and ROC-AUC=0.9310.
  • Parkinson's prediction attained an accuracy of 0.9231 with perfect recall (1.000).
  • Diabetes model demonstrated ROC-AUC=0.8388, with comorbidity analysis indicating a +5.17% elevation in heart disease risk in diabetic patients.

Abstract

Chronic disease management reveals a fundamental gap in clinical AI: most deployed prediction systems evaluate a single disease in isolation, despite overwhelming clinical evidence that patients develop and manage multiple interrelated conditions simultaneously. This paper presents an architecture for concurrent multi-disease prediction that addresses three core limitations of prior work. First, the patient health state is modeled as a temporal sequence using an LSTM-based encoder that captures disease trajectory alongside current biomarker values. Second, a hybrid knowledge graph is constructed from SNOMED-CT and DisGeNET ontology priors overlaid with data-driven co-occurrence weights. Third, the tabular ensemble and Graph Neural Network are fused through a joint co-training loss enabling shared gradient flow. Experimental results on three benchmark datasets demonstrate strong performance: the Heart Disease model achieves F1=0.8923 and ROC-AUC=0.9310; Parkinson's attains accuracy=0.9231 with perfect recall (1.000); and the Diabetes model achieves ROC-AUC=0.8388. Comorbidity analysis further confirms a +5.17% average heart disease risk elevation in the diabetic cohort, validating inter-disease interaction modeling.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Sawant et al. (2026) studied this question.

synapsesocial.com/papers/69f154a4879cb923c4944e00https://doi.org/10.5281/zenodo.19809190
Ask AI
Helpful
Bookmark
Share
View Full Paper