Interpretable Link Prediction in AI-Driven Cancer Research: Uncovering Co-Authorship Patterns

2025-12-19

AI Summary

This study investigates the evolution of scholarly collaboration in AI-driven cancer research to inform interdisciplinary team formation and resource allocation. We constructed 36 dynamic co-authorship networks from 7,738 AI–cancer interdisciplinary publications, modeling three relationship states: newly formed, sustained, and terminated collaborations. Methodologically, we innovatively integrate explainable AI (SHAP) into collaboration prediction—first such application in science-of-science research—by jointly encoding attribute features (e.g., disciplinary similarity, author seniority, productivity) and structural features (e.g., common neighbors), and benchmarking four classifiers; random forest achieves the highest recall. Key findings reveal a dual-role effect of disciplinary similarity: it promotes new collaborations but inhibits termination; conversely, high productivity and deep expertise significantly increase termination likelihood. These results provide interpretable, evidence-based insights for science policy design and collaborative team incubation.

Technology Category

• Humans and AI: Teamwork, Team formation
• Knowledge Representation and Reasoning: Action, Change, and Causality
• Reasoning under Uncertainty: Causality

Application Category

• Social Networks and Social Media: Computational social science
• Web Mining and Content Analysis: Interdisciplinary science discovery with web data mining
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Artificial intelligence (AI) is transforming cancer diagnosis and treatment. The intricate nature of this disease necessitates the collaboration of diverse stakeholders with varied expertise to ensure the effectiveness of cancer research. Despite its importance, forming effective interdisciplinary research teams remains challenging. Understanding and predicting collaboration patterns can help researchers, organizations, and policymakers optimize resources and foster impactful research. We examined co-authorship networks as a proxy for collaboration within AI-driven cancer research. Using 7,738 publications (2000-2017) from Scopus, we constructed 36 overlapping co-authorship networks representing new, persistent, and discontinued collaborations. We engineered both attribute-based and structure-based features and built four machine learning classifiers. Model interpretability was performed using Shapley Additive Explanations (SHAP). Random forest achieved the highest recall for all three types of examined collaborations. The discipline similarity score emerged as a crucial factor, positively affecting new and persistent patterns while negatively impacting discontinued collaborations. Additionally, high productivity and seniority were positively associated with discontinued links. Our findings can guide the formation of effective research teams, enhance interdisciplinary cooperation, and inform strategic policy decisions.

Problem

• Predicting collaboration patterns in AI-driven cancer research
• Identifying factors influencing new, persistent, and discontinued co-authorships
• Guiding effective team formation and policy decisions through interpretable models

Innovation

• Constructed overlapping co-authorship networks from publications
• Engineered attribute-based and structure-based features for classifiers
• Used SHAP for interpretability in link prediction models