Larsen Kristoffer, Zhao Chen, Keyak Joyce, Sha Qiuying, Paez Diana, Zhang Xinwei, Hung Guang-Uei, Zou Jiangang, Peix Amalia, Zhou Weihua
Department of Mathematical Sciences, Michigan Technological University, Houghton, MI, USA.
Department of Computer Science, Kennesaw State University, Marietta, GA, USA.
ArXiv. 2024 Apr 28:arXiv:2309.08415v4.
Current machine learning-based (ML) models usually attempt to utilize all available patient data to predict patient outcomes while ignoring the associated cost and time for data acquisition. The purpose of this study is to create a multi-stage machine learning model to predict cardiac resynchronization therapy (CRT) response for heart failure (HF) patients. This model exploits uncertainty quantification to recommend additional collection of single-photon emission computed tomography myocardial perfusion imaging (SPECT MPI) variables if baseline clinical variables and features from electrocardiogram (ECG) are not sufficient.
218 patients who underwent rest-gated SPECT MPI were enrolled in this study. CRT response was defined as an increase in left ventricular ejection fraction (LVEF) > 5% at a 6±1 month follow-up. A multi-stage ML model was created by combining two ensemble models: Ensemble 1 was trained with clinical variables and ECG; Ensemble 2 included Ensemble 1 plus SPECT MPI features. Uncertainty quantification from Ensemble 1 allowed for multi-stage decision-making to determine if the acquisition of SPECT data for a patient is necessary. The performance of the multi-stage model was compared with that of Ensemble models 1 and 2.
The response rate for CRT was 55.5% (n = 121) with overall male gender 61.0% (n = 133), an average age of 62.0±11.8, and LVEF of 27.7±11.0. The multi-stage model performed similarly to Ensemble 2 (which utilized the additional SPECT data) with AUC of 0.75 vs. 0.77, accuracy of 0.71 vs. 0.69, sensitivity of 0.70 vs. 0.72, and specificity 0.72 vs. 0.65, respectively. However, the multi-stage model only required SPECT MPI data for 52.7% of the patients across all folds.
By using rule-based logic stemming from uncertainty quantification, the multi-stage model was able to reduce the need for additional SPECT MPI data acquisition without sacrificing performance.
当前基于机器学习（ML）的模型通常试图利用所有可用的患者数据来预测患者预后，却忽略了数据采集相关的成本和时间。本研究的目的是创建一个多阶段机器学习模型，以预测心力衰竭（HF）患者的心脏再同步治疗（CRT）反应。该模型利用不确定性量化来建议在基线临床变量和心电图（ECG）特征不足时额外收集单光子发射计算机断层扫描心肌灌注成像（SPECT MPI）变量。
本研究纳入了218例接受静息门控SPECT MPI检查的患者。CRT反应定义为在6±1个月随访时左心室射血分数（LVEF）增加>5%。通过组合两个集成模型创建了一个多阶段ML模型：集成模型1使用临床变量和ECG进行训练；集成模型2包括集成模型1加上SPECT MPI特征。集成模型1的不确定性量化允许进行多阶段决策，以确定是否有必要为患者采集SPECT数据。将多阶段模型的性能与集成模型1和2的性能进行比较。
CRT的反应率为55.5%（n = 121），总体男性占61.0%（n = 133），平均年龄为62.0±11.8，LVEF为27.7±11.0。多阶段模型的表现与集成模型2（使用了额外的SPECT数据）相似，AUC分别为0.75和0.77，准确率分别为0.71和0.69，敏感性分别为0.70和0.72，特异性分别为0.72和0.65。然而，多阶段模型在所有折叠中仅需要52.7%的患者的SPECT MPI数据。
通过使用源于不确定性量化的基于规则的逻辑，多阶段模型能够在不牺牲性能的情况下减少额外SPECT MPI数据采集的需求。
Zotero 插件
