Department of Functional Imaging and Artificial Intelligence, Kanazawa University Graduate School of Medicine, 13-1 Takara-machi, Kanazawa, 920-8640, Japan.
Department of Cardiology, Hakodate-Goryoukaku Hospital, Hakodate, Japan.
J Nucl Cardiol. 2022 Feb;29(1):190-201. doi: 10.1007/s12350-020-02173-6. Epub 2020 May 14.
Cardiac sympathetic dysfunction is closely associated with cardiac mortality in patients with chronic heart failure (CHF). We analyzed the ability of machine learning incorporating I-metaiodobenzylguanidine (MIBG) to differentially predict risk of life-threatening arrhythmic events (ArE) and heart failure death (HFD).
A model was created based on patients with documented 2-year outcomes of CHF (n = 526; age, 66 ± 14 years). Classifiers were trained using 13 variables including age, gender, NYHA functional class, left ventricular ejection fraction and planar I-MIBG heart-to-mediastinum ratio (HMR). ArE comprised arrhythmic death and appropriate therapy with an implantable cardioverter defibrillator. The probability of ArE and HFD at 2 years was separately calculated based on appropriate classifiers. The probability of HFD significantly increased as HMR decreased when any variables were combined. However, the probability of arrhythmic events was maximal when HMR was intermediate (1.5-2.0 for patients with NYHA class III). Actual rates of ArE were 3% (10/379) and 18% (27/147) in patients at low- (≤ 11%) and high- (> 11%) risk of developing ArE (P < .0001), respectively, whereas those of HFD were 2% (6/328) and 49% (98/198) in patients at low-(≤ 15%) and high-(> 15%) risk of HFD (P < .0001).
A risk model based on machine learning using clinical variables and I-MIBG differentially predicted ArE and HFD as causes of cardiac death.
心脏交感神经功能障碍与慢性心力衰竭（CHF）患者的心脏死亡率密切相关。我们分析了结合 I-间碘苄胍（MIBG）的机器学习在预测危及生命的心律失常事件（ArE）和心力衰竭死亡（HFD）风险方面的能力。
基于有记录的 2 年 CHF 结局患者（n=526；年龄 66±14 岁）创建了一个模型。使用包括年龄、性别、纽约心脏协会（NYHA）功能分级、左心室射血分数和平面 I-MIBG 心脏与纵隔比（HMR）在内的 13 个变量对分类器进行了训练。ArE 包括心律失常死亡和植入式心脏复律除颤器的适当治疗。根据适当的分类器分别计算了 2 年内发生 ArE 和 HFD 的概率。当任何变量结合时，HMR 降低，HFD 的概率显著增加。然而，当 HMR 处于中间水平时（NYHA Ⅲ级患者为 1.5-2.0），心律失常事件的概率最大。ArE 实际发生率分别为低风险（≤11%）患者的 3%（10/379）和高风险（>11%）患者的 18%（27/147）（P<0.0001），而 HFD 的实际发生率分别为低风险（≤15%）患者的 2%（6/328）和高风险（>15%）患者的 49%（98/198）（P<0.0001）。
基于机器学习使用临床变量和 I-MIBG 的风险模型可预测 ArE 和 HFD 作为心脏死亡的原因。
