Big Data Decision Institute, Jinan University, Guangzhou 510632, PR China; School of Management, Jinan University, Guangzhou 510632, PR China.
Big Data Decision Institute, Jinan University, Guangzhou 510632, PR China; School of Medicine, Jinan University, Guangzhou 510632, PR China.
Int J Med Inform. 2024 Nov;191:105588. doi: 10.1016/j.ijmedinf.2024.105588. Epub 2024 Aug 5.
Accurate diagnoses and personalized treatments in medicine rely on identifying causality. However, existing causal discovery algorithms often yield inconsistent results due to distinct learning mechanisms. To address this challenge, we introduce MINDMerge, a multi-causal investigation and discovery framework designed to synthesize causal graphs from various algorithms.
MINDMerge integrates five causal models to reconcile inconsistencies arising from different algorithms. Employing credibility weighting and a novel cycle-breaking mechanism in causal networks, we initially developed and tested MINDMerge using three synthetic networks. Subsequently, we validated its effectiveness in discovering risk factors and predicting acute kidney injury (AKI) using two electronic medical records (EMR) datasets, eICU Collaborative Research Database and MIMIC-III Database. Causal reasoning was employed to analyze the relationships between risk factors and AKI. The identified causal risk factors of AKI were used in building a prediction model, and the prediction model was evaluated using the area under the receiver operating characteristics curve (AUC) and recall.
Synthetic data experiments demonstrated that our model outperformed significantly in capturing ground-truth network structure compared to other causal models. Application of MINDMerge on real-world data revealed direct connections of pulmonary disease, hypertension, diabetes, x-ray assessment, and BUN with AKI. With the identified variables, AKI risk can be inferred at the individual level based on established BNs and prior information. Compared against existing benchmark models, MINDMerge maintained a higher AUC for AKI prediction in both internal (AUC: 0.832) and external network validations (AUC: 0.861).
MINDMerge can identify causal risk factors of AKI, serving as a valuable diagnostic tool for clinical decision-making and facilitating effective intervention.
医学中的准确诊断和个性化治疗依赖于因果关系的识别。然而，现有的因果发现算法由于不同的学习机制往往会产生不一致的结果。为了解决这一挑战，我们引入了 MINDMerge，这是一个多因果调查和发现框架，旨在从各种算法中综合因果图。
MINDMerge 集成了五个因果模型，以协调不同算法产生的不一致。通过在因果网络中使用可信度加权和新的循环打破机制，我们最初使用三个合成网络开发和测试了 MINDMerge。然后，我们使用两个电子病历（EMR）数据集 eICU 协作研究数据库和 MIMIC-III 数据库验证了其在发现风险因素和预测急性肾损伤（AKI）方面的有效性。使用因果推理分析风险因素与 AKI 之间的关系。确定的 AKI 因果风险因素用于构建预测模型，并使用接收者操作特征曲线（AUC）和召回率评估预测模型。
合成数据实验表明，与其他因果模型相比，我们的模型在捕捉真实网络结构方面表现出色。MINDMerge 在真实数据上的应用揭示了肺部疾病、高血压、糖尿病、X 射线评估和 BUN 与 AKI 之间的直接联系。基于已识别的变量，可以根据已建立的 BNs 和先验信息在个体水平上推断 AKI 风险。与现有的基准模型相比，MINDMerge 在内部（AUC：0.832）和外部网络验证（AUC：0.861）中都保持了更高的 AKI 预测 AUC。
MINDMerge 可以识别 AKI 的因果风险因素，是临床决策的有价值的诊断工具，并有助于有效的干预。
