Dabakoğlu Elif, Yiğit Öyküm Esra, Topal Yaşar
Research Support and Funding Office, Mugla Sıtkı Koçman University, Mugla 48000, Türkiye.
Graduate School of Science and Engineering, Yıldız Technical University, Istanbul 34220, Türkiye.
Diagnostics (Basel). 2025 Sep 6;15(17):2258. doi: 10.3390/diagnostics15172258.
Differentiating pediatric pneumonia from acute bronchitis remains a persistent clinical challenge due to overlapping symptoms, often leading to diagnostic uncertainty and inappropriate antibiotic use. This study introduces DAPLEX, a structured ensemble learning framework designed to enhance diagnostic accuracy and reliability. A retrospective cohort of 868 pediatric patients was analyzed. DAPLEX was developed in three phases: (i) deployment of diverse base learners from multiple learning paradigms; (ii) multi-criteria evaluation and pruning based on generalization stability to retain a subset of well-generalized and stable learners; and (iii) complementarity-driven knowledge fusion. In the final phase, out-of-fold predicted probabilities from the retained base learners were combined with a consensus-based feature importance profile to construct a hybrid meta-input for a Multilayer Perceptron (MLP) meta-learner. DAPLEX achieved a balanced accuracy of 95.3%, an F1-score of ~0.96, and a ROC-AUC of ~0.99 on an independent holdout test. Compared to the range of performance from the weakest to the strongest base learner, DAPLEX improved balanced accuracy by 3.5-5.2%, enhanced the F1-score by 4.4-5.6%, and increased sensitivity by a substantial 8.2-13.6%. Crucially, DAPLEX's performance remained robust and consistent across all evaluated demographic subgroups, confirming its fairness and potential for broad clinical. The DAPLEX framework offers a robust and transparent pipeline for diagnostic decision support. By systematically integrating diverse predictive models and synthesizing both outcome predictions and key feature insights, DAPLEX substantially reduces diagnostic uncertainty in differentiating pediatric pneumonia and acute bronchitis and demonstrates strong potential for clinical application.
由于症状重叠，区分小儿肺炎和急性支气管炎仍然是一个长期存在的临床挑战，这常常导致诊断不确定性和不恰当的抗生素使用。本研究引入了DAPLEX，这是一个结构化的集成学习框架，旨在提高诊断的准确性和可靠性。对868名儿科患者的回顾性队列进行了分析。DAPLEX分三个阶段开发：(i) 部署来自多种学习范式的不同基础学习器；(ii) 基于泛化稳定性进行多标准评估和剪枝，以保留一组泛化良好且稳定的学习器；(iii) 互补驱动的知识融合。在最后阶段，将保留的基础学习器的折外预测概率与基于共识的特征重要性概况相结合，为多层感知器 (MLP) 元学习器构建混合元输入。在独立的验证测试中，DAPLEX的平衡准确率达到95.3%，F1分数约为0.96，ROC-AUC约为0.99。与最弱到最强的基础学习器的性能范围相比，DAPLEX将平衡准确率提高了3.5-5.2%，将F1分数提高了4.4-5.6%，并将灵敏度大幅提高了8.2-13.6%。至关重要的是，DAPLEX在所有评估的人口亚组中的性能保持稳健且一致，证实了其公平性和广泛临床应用的潜力。DAPLEX框架为诊断决策支持提供了一个强大且透明的流程。通过系统地整合不同的预测模型并综合结果预测和关键特征见解，DAPLEX大大降低了区分小儿肺炎和急性支气管炎的诊断不确定性，并显示出强大的临床应用潜力。
