婴幼儿单纯室间隔缺损术前心力衰竭及术后不良事件发生预测因素的研究进展
Research Progress on Predictive Factors for Preoperative Heart Failure and Postoperative Adverse Events in Infants with Isolated Ventricular Septal Defect
摘要: 室间隔缺损(Ventricular Septal Defect, VSD)是临床上最常见的先天性心脏疾病(Congenital heart disease, CHD),不仅可单独发生,也可与其他复杂心脏畸形共存。VSD手术治疗在降低患儿的病死率和提高其生活质量方面具有不可忽视的作用。手术前心力衰竭(Heart Failure, HF)的准确诊断及干预是提高手术成功率、降低术后不良事件发生的关键。在成人心力衰竭诊断中常将脑钠肽(Brain Natriuretic Peptide, BNP)等生物标志物作为诊断和治疗的依据,然而小儿心力衰竭及先天性心脏病,没有任何临床生物标志物作为诊断或治疗的标准指南。在信息时代,基于机器学习(Machine Learning, ML)算法建立的模型可提高对相关危险因素预测的准确性。本文结合相关文献对室间隔缺损术前心力衰竭及术后不良事件发生的预测因素进行总结。
Abstract: Ventricular Septal Defect (VSD) is the most common congenital heart disease (CHD) clinically, which can occur either alone or in combination with other complex heart malformations. Surgical treatment of VSD plays a significant role in reducing mortality and improving the quality of life of affected children. Accurate diagnosis and intervention for heart failure (HF) before surgery are crucial for enhancing surgical success rates and minimizing postoperative adverse events. In adult heart failure diagnosis, biomarkers such as brain natriuretic peptide (BNP) are often used as a basis for diagnosis and treatment. Nevertheless, for pediatric heart failure and congenital heart disease, there are no clinical biomarkers serving as standard guidelines for diagnosis or treatment. In the information era, models based on machine learning (ML) algorithms can improve the accuracy of predicting relevant risk factors. This article summarizes the predictive factors for preoperative heart failure and postoperative adverse events in patients with ventricular septal defects, drawing on relevant literature.
文章引用:刘锦秀, 潘征夏. 婴幼儿单纯室间隔缺损术前心力衰竭及术后不良事件发生预测因素的研究进展[J]. 临床医学进展, 2025, 15(1): 211-217. https://doi.org/10.12677/acm.2025.151032

1. 引言

先天性心脏病是指胚胎发育时期,在遗传与环境等各种因素影响下,心脏和血管在形态和功能上发育异常,是我国最常见的出生缺陷[1]。室间隔缺损是室间隔在心室水平异常的血液分流通道,是婴幼儿最常见的先天性心脏病,占所有心脏畸形的40% [2]。随着治疗方式的进步,开胸直视下室间隔缺损修补术成功率高,术后不良事件发生率较低,但术前心力衰竭会影响术后患儿恢复,术前心力衰竭及术后可能发生的不良事件的准确预测及干预有利于患儿术后恢复。因此本文对婴幼儿室间隔缺损手术前心力衰竭及术后不良事件发生的预测因素进行综述。

2. 小儿心力衰竭

2.1. 小儿心衰的定义及分类

国际心肺移植学会将小儿心力衰竭定义为:由心室功能障碍、容量或压力超负荷单独或联合引起的一种临床和病理生理综合征。在儿童中,它导致特征性体征和症状,例如生长发育受限、喂养困难、呼吸窘迫、运动耐受性差和易疲劳,并且与循环、神经激素和分子异常相关[3]。由于HF的类型和病因众多且没有公认的通用分类,因此小儿HF的发病率和患病率尚不清楚[4] [5]

2.2. 先天性心脏病与小儿心力衰竭

HF是先天性或获得性心脏和非心脏疾病的结果,其有很多病因[3]。CHD患者中HF的比例低于其在心律失常或心肌病的比例,但CHD较心律失常或心肌病更为常见,因此CHD患儿在总体小儿HF计数中占比更大[6]。Sommers等人[7]发现,HF在CHD患者中发生率为39.1%,排除术后HF后发生率为23.7%,CHD患者总死亡率为6.3%,而14%的HF患者死亡。在欧洲的两项单中心研究表明,超过一半的儿科HF病例发生在CHD儿童中[7] [8]。在这些研究中,由于研究设计或HF定义存在差异,CHD人群的HF发生率不同,其中一项研究确定了所有先天性和获得性心脏病患者中10.4%的患者患有HF,另一项研究表明34%的CHD患者存在HF [7] [8]。Kambiz等人[9]发现大约25%的青少年和成人先天性心脏病(Adolescents and Adults With Congenital Heart Disease, ACHD)患者在30岁时发生HF,并且发病率随年龄增加而增加。已有研究表明HF是儿科和ACHD发病率和死亡率的重要原因[10]-[12]

2.3. 小儿心力衰竭临床表现

由于小儿HF诱因不同,因此其临床表现和症状也存在差异,研究表明其临床表现与患儿年龄也存在相关性[6] [13]。婴儿HF患儿早期临床表现通常是轻微的,最常见的表现是由于呼吸困难而出现的喂养困难[14]。随着病情进展,受HF影响的婴儿将表现为生长发育受限,其主要为生长曲线观察到的体重增加不理想。HF婴儿体格检查可表现为:呼吸急促或呼吸困难、心动过速、奔马律(S3, S4)、心脏增大和肝肿大等。幼儿和老年人可能会出现运动耐受性差,嗜睡,厌食,呼吸困难,咳嗽等。在婴儿和幼儿期以后,体格检查均可闻及奔马律,触及肝肿大以及外周水肿和颈静脉扩张。

3. 单纯室间隔缺损修补术后不良事件的危险因素

VSD可以是复杂心血管畸形组成的一部分,也可单独出现,即单纯性室间隔缺损(Isolated Ventricular Septal Defect, I-VSD)约占儿童CHD的37% [2]。VSD的发生率随首次检查时的年龄变化而变化,由于许多出生时存在的小缺损在不久后自然闭合,VSD发病率也取决于检查技术的灵敏度,据报道,高灵敏度彩色多普勒超声心动图筛查的新生儿患病率高达5%,其中大多数是微小的肌肉缺陷,在一岁以内可自然闭合[15]

VSD的主要治疗方式包括开胸直视修补术、经胸VSD封堵术、经皮介入VSD封堵术,目前常规几种治疗方式的手术效果都让人十分满意。开胸直视下VSD修补术是最常进行的儿科心脏手术。近年来,随着体外循环技术、心肌保护、麻醉和术后护理等的进步,手术进行VSD修补安全性得以提高,大大降低了术后死亡率。I-VSD手术修补术后不良事件发生率较低,其可能包括残余分流的再次手术、住院时间延长、心律失常、瓣膜损伤、心室功能抑制等[16]。尽管术后不良事件发生率较低,但仍有发生,最重要的是早期识别并尽早干预相关不良危险因素以改善预后。

Brett等人[17]回顾性分析了369例I-VSD修补术后的患儿发现对于年龄小于6个月接受VSD修补术的婴幼儿,术前体重每增加1公斤,住院时间缩短2.3天。在多因素风险分析中,年龄小于6个月的患者接受VSD修补术时,体重每减少1公斤,术后不良事件发生的风险增加1.8倍,而年龄大于6个月的患者没有显著差异,并得出结论小年龄(<6月龄)及术前低体重是接受VSD修补术的婴幼儿术后不良事件发生的重要预测因素。Servet等人[18]的研究支持这一结论。然而,Kogon等人[19]回顾性分析了255例I-VSD患儿发现对于有症状的低体重的婴幼儿早期手术干预不会提高术后不良事件发生的风险,这与Maartje等人[20]的研究结果一致。由此可见,VSD修补术后不良事件发生的风险因素在不同中心之间存在差异。

4. 小儿心力衰竭与室间隔缺损的临床生物标志物

4.1. 脑钠肽及氨基末端脑钠肽前体(N-Terminal Pro-Brain Natriuretic Peptide, NT-Pro BNP)

BNP是利钠肽激素家族的成员,主要由心室的心肌细胞在压力超负荷、容积扩张和心室壁应力增加作用下而分泌。在释放时,BNP主要作用为排水排钠、舒张血管。NT-pro BNP与BNP一起储存在心房颗粒中,并同时释放[21]。在成人HF中,BNP和NT-pro BNP是用于诊断和监测的生物标志物[22] [23],在儿童人群中,CHD患儿血浆BNP浓度升高,大多数研究表明血浆BNP水平与右心室扩张和肺动脉返流严重程度之间存在相关性[24]。潜伏青紫型先天性心脏病(potential cyanotic congenital heart disease, PCCHD)患儿血清BNP水平随着心脏缺损的增加以及HF和肺动脉高压(Pulmonary hypertension, PAH)的出现而逐渐升高[25]。这表明BNP及NT-pro BNP可作为小儿HF及CHD患儿诊断、治疗及预后的依据。

4.2. 其他生物标志物

肌酸激酶MB (Creatine Kinase MB, CK-MB)是心肌细胞结构蛋白,参与心肌细胞能量运转与收缩。CK-MB是目前应用最广泛的心肌损伤标志物。Robert等人[26]前瞻性研究282例疑似先天性心脏畸形而住院的儿童的总肌酸激酶(Total Creatine Kinase, CK)和心肌同工酶CK-MB活性,并与无此类异常的住院儿童进行比较发现,血清CK-MB活性和CK-MB百分比与CHD患儿缺损大小和出现充血性心力衰竭临床症状的年龄显著相关,血清CK-MB水平在患有大型左向右分流的CHD患儿中异常升高,其CHD主要为VSD。Neves AL等人[27]回顾性分析34例产前诊断为CHD的新生儿发现接受心脏修复手术患儿的血清CK-MB中位数(P25~P75)为[7.35 (4.90~13.40) ng/mL],显著高于无心脏修复手术患儿的血清CK-MB中位数(P25~P75)水平[4.2 (2.60~5.90) ng/mL; P = 0.032],血清CK-MB以4.6 ng/ml为截断值作为预测新生儿早期先天性心脏手术(Congenital Heart Surgery, CHS)的危险因素(敏感度87.5%、特异度63.6%);此外,他们在新生儿出生第一天完善超声心动图评估心脏功能,发现血清CK-MB水平与超声心动图检测的二尖瓣舒张早期、晚期峰值速度相关(P < 0.05),这表明了需要心脏修复手术的CHD新生儿出生后的血清CK-MB水平较高,可作为是评估心脏功能的指标。

生长分化因子-15 (growth differentiation factor-15, GDF-15)系转化生长因子β家族成员,它作为一种炎症标记物,在心血管疾病、代谢紊乱和神经退行性过程的发病机制中发挥作用。GDF-15是一种调节机体生长的心脏源性内分泌激素,可能由于其自分泌/旁分泌特性(抗氧化、抗炎、抗凋亡)而具有局部心脏保护作用。GDF-15表达在缺血/再灌注后的心肌细胞和心肌梗死(MI)后数小时内的心脏中被高度诱导[28]β2-微球蛋白(Beta-2microglobulin, β2-MG)是一种内源性低分子量血清球蛋白,由淋巴细胞、血小板和白细胞产生。它在人体内分布广泛,在血清中以游离形式存在,在健康个体的血清中浓度保持相对稳定。血清β2-MG水平与CHD、HF等心血管疾病的发病率和死亡率呈正相关[29]。Zhou XJ等人[30]研究表明在12~18个月大的CHD和HF患儿中GDF-15和β2-MG的血浆水平与心脏功能的严重程度呈正相关。GDF-15和β2-MG水平与心功能严重程度呈正相关,可作为CHD合并慢性心力衰竭(Chronic Heart Failure, CHF)早期诊断的理想指标,也可作为判断病情的临床指标。

半乳糖凝集素-3 (Galectin-3)是一种碳水化合物结合凝集素,由包括巨噬细胞在内的多种类型细胞释放以调节免疫和癌症中的炎症功能。Zhendong Cheng等人[31]对来自12项单独研究的6,440例CHF患者的结局进行荟萃分析发现血清半乳糖凝集素-3对CHF患者全因死亡和心血管死亡均有预测价值,血清半乳糖凝集素-3可用于CHF患者的风险分类。

心肌肌球蛋白结合蛋白C (Cardiac-Myosin-Binding-Protein-C, cMyBP-C)是一种粗丝相关蛋白,是决定肌节结构完整性以及收缩功能的特异性心肌细胞因子。El Amrousy等人[32]研究表明血浆cMyBP-C浓度可能是诊断儿童(平均年龄16个月) HF的良好临床生物标志物,以45 ng/mL为临界值,其敏感性为100%,特异性为96%。

5. 机器学习算法在婴幼儿室间隔缺损手术前心功能不全及术后不良事件发生中的预测 作用

CHD发病机制复杂,发病率高。我们在对CHD的理解中存在一些知识空白,传统的统计分析方法往往不足以帮助我们分析导致CHD的广泛的遗传和环境等因素。在信息技术时代,ML是提高我们对CHD的理解和治疗的有效途径[33] [34]。与传统模型相比,ML算法建立模型通常具有更好的预测性能,且在处理共线性问题和离群值方面具有更好的稳定性[35] [36]。Xinwei Du等人[37]对24,685名患者的单中心研究表明,结合手术风险范围内和术前相关因素,极限梯度提升(eXtreme Gradient Boosting, XGBoost)模型在院内死亡率预测方面的准确性高于先天性心脏手术风险调整-1 (Risk Adjustment in Congenital Heart Surgery-1, RACHS-1)和胸外科学会–欧洲心胸外科协会(Society of Thoracic Surgery-European Association for Cardiothoracic Surgery, STS-Ehrman)类别。Cida Luo等人[38]对来自重症监护III数据库的医疗信息市场的5676名患者的衍生数据集使用一种新的机器学习算法,构建了一个风险分层工具与使用逻辑回归模型和死亡率的常见风险评分进行比较表明,通过ML算法建立模型可以为ICU中的HF患者生成高性能的风险预测工具。当集成到电子健康记录系统时,机器学习算法可监测患者的临床数据,而不需要特定的心血管生物标志物和不同阶段的生存率。机器学习风险预测模型可以支持临床医生评估ICU中的HF患者并制定个性化治疗计划。

由此可见,在临床实践中,可以基于患儿电子病历数据库运用机器学习算法建立模型,用于术前HF及术后不良事件的风险预测,以改善CHD患儿的预后。

NOTES

*通讯作者。

参考文献

[1] 李烁琳, 顾若漪, 黄国英. 儿童先天性心脏病流行病学特征[J]. 中国实用儿科杂志, 2017, 32(11): 871-875.
[2] Penny, D.J. and Vick, G.W. (2011) Ventricular Septal Defect. The Lancet, 377, 1103-1112.
https://doi.org/10.1016/s0140-6736(10)61339-6
[3] Kirk, R., Dipchand, A.I., Rosenthal, D.N., Addonizio, L., Burch, M., Chrisant, M., et al. (2014) The International Society for Heart and Lung Transplantation Guidelines for the Management of Pediatric Heart Failure: Executive Summary. The Journal of Heart and Lung Transplantation, 33, 888-909.
https://doi.org/10.1016/j.healun.2014.06.002
[4] Hsu, D.T. and Pearson, G.D. (2009) Heart Failure in Children: Part I: History, Etiology, and Pathophysiology. Circulation: Heart Failure, 2, 63-70.
https://doi.org/10.1161/circheartfailure.108.820217
[5] Hsu, D.T. and Pearson, G.D. (2009) Heart Failure in Children: Part II: Diagnosis, Treatment, and Future Directions. Circulation: Heart Failure, 2, 490-498.
[6] Hinton, R.B. and Ware, S.M. (2017) Heart Failure in Pediatric Patients with Congenital Heart Disease. Circulation Research, 120, 978-994.
https://doi.org/10.1161/circresaha.116.308996
[7] Sommers, C., Nagel, B.H.P., Neudorf, U., et al. (2005) Congestive Heart Failure in Childhood: An Epidemiologic Study. Herz, 30, 652-662.
[8] Massin, M.M., Astadicko, I. and Dessy, H. (2008) Epidemiology of Heart Failure in a Tertiary Pediatric Center. Clinical Cardiology, 31, 388-391.
https://doi.org/10.1002/clc.20262
[9] Norozi, K., Wessel, A., Alpers, V., Arnhold, J.O., Geyer, S., Zoege, M., et al. (2006) Incidence and Risk Distribution of Heart Failure in Adolescents and Adults with Congenital Heart Disease after Cardiac Surgery. The American Journal of Cardiology, 97, 1238-1243.
https://doi.org/10.1016/j.amjcard.2005.10.065
[10] Harris, K.C., Voss, C., Rankin, K., Aminzadah, B., Gardner, R. and Mackie, A.S. (2018) Modifiable Cardiovascular Risk Factors in Adolescents and Adults with Congenital Heart Disease. Congenital Heart Disease, 13, 563-570.
https://doi.org/10.1111/chd.12612
[11] Parrott, A. and Ware, S.M. (2012) The Role of the Geneticist and Genetic Counselor in an ACHD Clinic. Progress in Pediatric Cardiology, 34, 15-20.
https://doi.org/10.1016/j.ppedcard.2012.05.004
[12] Webb, G., Mulder, B.J., Aboulhosn, J., Daniels, C.J., Elizari, M.A., Hong, G., et al. (2015) The Care of Adults with Congenital Heart Disease across the Globe: Current Assessment and Future Perspective. International Journal of Cardiology, 195, 326-333.
https://doi.org/10.1016/j.ijcard.2015.04.230
[13] Spaziani, G., Bennati, E., Marrone, C., Lucà, F., Iorio, A., Rao, C.M., et al. (2021) Pathophysiology and Clinical Presentation of Paediatric Heart Failure Related to Congenital Heart Disease. Acta Paediatrica, 110, 2336-2343.
https://doi.org/10.1111/apa.15904
[14] Mangili, G., Garzoli, E. and Sadou, Y. (2018) Feeding Dysfunctions and Failure to Thrive in Neonates with Congenital Heart Diseases. La Pediatria Medica e Chirurgica, 40.
https://doi.org/10.4081/pmc.2018.196
[15] Roguin, N., Du, Z., Barak, M., Nasser, N., Hershkowitz, S. and Milgram, E. (1995) High Prevalence of Muscular Ventricular Septal Defect in Neonates. Journal of the American College of Cardiology, 26, 1545-1548.
https://doi.org/10.1016/0735-1097(95)00358-4
[16] Scully, B.B., Morales, D.L.S., Zafar, F., McKenzie, E.D., Fraser, C.D. and Heinle, J.S. (2010) Current Expectations for Surgical Repair of Isolated Ventricular Septal Defects. The Annals of Thoracic Surgery, 89, 544-551.
https://doi.org/10.1016/j.athoracsur.2009.10.057
[17] Anderson, B.R., Stevens, K.N., Nicolson, S.C., Gruber, S.B., Spray, T.L., Wernovsky, G., et al. (2013) Contemporary Outcomes of Surgical Ventricular Septal Defect Closure. The Journal of Thoracic and Cardiovascular Surgery, 145, 641-647.
https://doi.org/10.1016/j.jtcvs.2012.11.032
[18] Ergün, S., Genç, S.B., Yildiz, O., Öztürk, E., Kafalı, H.C., Ayyıldız, P., et al. (2019) Risk Factors for Major Adverse Events after Surgical Closure of Ventricular Septal Defect in Patients Less than 1 Year of Age: A Single-Center Retrospective. Brazilian Journal of Cardiovascular Surgery, 34, 335-343.
https://doi.org/10.21470/1678-9741-2018-0299
[19] Kogon, B., Butler, H., Kirshbom, P., Kanter, K. and McConnell, M. (2007) Closure of Symptomatic Ventricular Septal Defects: How Early Is Too Early? Pediatric Cardiology, 29, 36-39.
https://doi.org/10.1007/s00246-007-9016-z
[20] Schipper, M., Slieker, M.G., Schoof, P.H. and Breur, J.M.P.J. (2016) Surgical Repair of Ventricular Septal Defect; Contemporary Results and Risk Factors for a Complicated Course. Pediatric Cardiology, 38, 264-270.
https://doi.org/10.1007/s00246-016-1508-2
[21] Shalmi, T.W., Jensen, A.S.B. and Goetze, J.P. (2024) Cardiac Natriuretic Peptides. Advances in Clinical Chemistry, 122, 115-139.
https://doi.org/10.1016/bs.acc.2024.06.009
[22] Don-Wauchope, A.C. and McKelvie, R.S. (2015) Evidence Based Application of BNP/NT-proBNP Testing in Heart Failure. Clinical Biochemistry, 48, 236-246.
https://doi.org/10.1016/j.clinbiochem.2014.11.002
[23] Castiglione, V., Aimo, A., Vergaro, G., Saccaro, L., Passino, C. and Emdin, M. (2021) Biomarkers for the Diagnosis and Management of Heart Failure. Heart Failure Reviews, 27, 625-643.
https://doi.org/10.1007/s10741-021-10105-w
[24] Cantinotti, M., Walters, H.L., Crocetti, M., Marotta, M., Murzi, B. and Clerico, A. (2015) BNP in Children with Congenital Cardiac Disease: Is There Now Sufficient Evidence for Its Routine Use? Cardiology in the Young, 25, 424-437.
https://doi.org/10.1017/s1047951114002133
[25] Yancy, C.W., Jessup, M., Bozkurt, B., Butler, J., Casey, D.E., Colvin, M.M., et al. (2017) 2017 ACC/AHA/HFSA Focused Update of the 2013 ACCF/AHA Guideline for the Management of Heart Failure. Journal of Cardiac Failure, 23, 628-651.
https://doi.org/10.1016/j.cardfail.2017.04.014
[26] Boucek, R.J., Kasselberg, A.G., Boerth, R.C., Parrish, M.D. and Graham, T.P. (1982) Myocardial Injury in Infants with Congenital Heart Disease: Evaluation by Creatine Kinase MB Isoenzyme Analysis. The American Journal of Cardiology, 50, 129-135.
https://doi.org/10.1016/0002-9149(82)90018-2
[27] Neves, A.L., Cabral, M., Leite-Moreira, A., Monterroso, J., Ramalho, C., Guimarães, H., et al. (2016) Myocardial Injury Biomarkers in Newborns with Congenital Heart Disease. Pediatrics & Neonatology, 57, 488-495.
https://doi.org/10.1016/j.pedneo.2015.11.004
[28] Rochette, L., Dogon, G., Zeller, M., Cottin, Y. and Vergely, C. (2021) GDF15 and Cardiac Cells: Current Concepts and New Insights. International Journal of Molecular Sciences, 22, Article 8889.
https://doi.org/10.3390/ijms22168889
[29] Drüeke, T.B. and Massy, Z.A. (2009) Progress in Uremic Toxin Research: β2‐Microglobulin. Seminars in Dialysis, 22, 378-380.
https://doi.org/10.1111/j.1525-139x.2009.00584.x
[30] Zhou, Z.X., Zhang, J., et al. (2020) Diagnostic Value of Growth Differentiation Factor-15 and β2-Microglobulin in Children with Congenital Heart Disease Combined with Chronic Heart Failure and Its Relationship with Cardiac Function. European Review for Medical and Pharmacological Sciences, 24, 8096-8103.
[31] Cheng, Z., Cai, K., Xu, C., Zhan, Q., Xu, X., Xu, D., et al. (2022) Prognostic Value of Serum Galectin-3 in Chronic Heart Failure: A Meta-Analysis. Frontiers in Cardiovascular Medicine, 9, Article 783707.
https://doi.org/10.3389/fcvm.2022.783707
[32] El Amrousy, D., Hodeib, H., Suliman, G., Hablas, N., Salama, E.R. and Esam, A. (2016) Diagnostic and Prognostic Value of Plasma Levels of Cardiac Myosin Binding Protein-C as a Novel Biomarker in Heart Failure. Pediatric Cardiology, 38, 418-424.
https://doi.org/10.1007/s00246-016-1532-2
[33] Morris, S.A. and Lopez, K.N. (2021) Deep Learning for Detecting Congenital Heart Disease in the Fetus. Nature Medicine, 27, 764-765.
https://doi.org/10.1038/s41591-021-01354-1
[34] Krittanawong, C., Rogers, A.J., Johnson, K.W., Wang, Z., Turakhia, M.P., Halperin, J.L., et al. (2020) Integration of Novel Monitoring Devices with Machine Learning Technology for Scalable Cardiovascular Management. Nature Reviews Cardiology, 18, 75-91.
https://doi.org/10.1038/s41569-020-00445-9
[35] Krittanawong, C., Johnson, K.W., Rosenson, R.S., Wang, Z., Aydar, M., Baber, U., et al. (2019) Deep Learning for Cardiovascular Medicine: A Practical Primer. European Heart Journal, 40, 2058-2073.
https://doi.org/10.1093/eurheartj/ehz056
[36] Krittanawong, C., Virk, H.U.H., Kumar, A., Aydar, M., Wang, Z., Stewart, M.P., et al. (2021) Machine Learning and Deep Learning to Predict Mortality in Patients with Spontaneous Coronary Artery Dissection. Scientific Reports, 11, Article No. 8992.
https://doi.org/10.1038/s41598-021-88172-0
[37] Du, X., Wang, H., Wang, S., He, Y., Zheng, J., Zhang, H., et al. (2022) Machine Learning Model for Predicting Risk of In-Hospital Mortality after Surgery in Congenital Heart Disease Patients. Reviews in Cardiovascular Medicine, 23, Article No. 376.
https://doi.org/10.31083/j.rcm2311376
[38] Luo, C., Zhu, Y., Zhu, Z., Li, R., Chen, G. and Wang, Z. (2022) A Machine Learning-Based Risk Stratification Tool for In-Hospital Mortality of Intensive Care Unit Patients with Heart Failure. Journal of Translational Medicine, 20, Article No. 136.
https://doi.org/10.1186/s12967-022-03340-8