Medical priority fusion: achieving dual optimization of sensitivity and interpretability in nipt anomaly detection

2025-09-22

AI Summary

In non-invasive prenatal testing (NIPT), high diagnostic sensitivity and model interpretability are mutually challenging yet both mandatory for clinical deployment. To address this, we propose a medicine-first fusion framework that introduces, for the first time, a mathematically constrained weighted fusion mechanism integrating naïve Bayes (ensuring probabilistic interpretability) and decision trees (providing explicit rule-based logic). This synergy is optimized via constrained multi-objective optimization to jointly enhance sensitivity and interpretability. Evaluated on 1,687 real-world clinical samples, the framework achieves 89.3% sensitivity and an 80% interpretability score—significantly outperforming individual models (McNemar test; effect size *d* = 1.24) and meeting Grade A clinical deployment criteria. The framework establishes a verifiable, traceable, and robust modeling paradigm for high-stakes medical AI systems.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Clinical machine learning faces a critical dilemma in high-stakes medical applications: algorithms achieving optimal diagnostic performance typically sacrifice the interpretability essential for physician decision-making, while interpretable methods compromise sensitivity in complex scenarios. This paradox becomes particularly acute in non-invasive prenatal testing (NIPT), where missed chromosomal abnormalities carry profound clinical consequences yet regulatory frameworks mandate explainable AI systems. We introduce Medical Priority Fusion (MPF), a constrained multi-objective optimization framework that resolves this fundamental trade-off by systematically integrating Naive Bayes probabilistic reasoning with Decision Tree rule-based logic through mathematically-principled weighted fusion under explicit medical constraints. Rigorous validation on 1,687 real-world NIPT samples characterized by extreme class imbalance (43.4:1 normal-to-abnormal ratio) employed stratified 5-fold cross-validation with comprehensive ablation studies and statistical hypothesis testing using McNemar's paired comparisons. MPF achieved simultaneous optimization of dual objectives: 89.3% sensitivity (95% CI: 83.9-94.7%) with 80% interpretability score, significantly outperforming individual algorithms (McNemar's test, p < 0.001). The optimal fusion configuration achieved Grade A clinical deployment criteria with large effect size (d = 1.24), establishing the first clinically-deployable solution that maintains both diagnostic accuracy and decision transparency essential for prenatal care. This work demonstrates that medical-constrained algorithm fusion can resolve the interpretability-performance trade-off, providing a mathematical framework for developing high-stakes medical decision support systems that meet both clinical efficacy and explainability requirements.

Problem

• Resolving the trade-off between diagnostic sensitivity and interpretability in clinical machine learning
• Developing explainable AI systems for non-invasive prenatal testing anomaly detection
• Creating medically-constrained optimization framework that maintains both accuracy and transparency

Innovation

• Constrained multi-objective optimization framework
• Fusion of Naive Bayes and Decision Tree
• Mathematically-principled weighted fusion under constraints