Shimoni Sara, Sergienko Ruslan, Martinez-Legazpi Pablo, Meledin Valery, Goland Sorel, Tshori Sagie, George Jacob, Bermejo Javier, Rokach Lior
The Heart Institute, Kaplan Medical Center, Rehovot, Israel and Hebrew University and Hadassah Medical School, Jerusalem, Israel.
Department of Health Policy and Management, Faculty of Health Sciences, Ben Gurion University of the Negev, Beer Sheva, Israel.
JACC Adv. 2024 Aug 14;3(9):101135. doi: 10.1016/j.jacadv.2024.101135. eCollection 2024 Sep.
Aortic valve stenosis of any degree is associated with poor outcomes.
The authors aimed to develop a risk prediction model for aortic stenosis (AS) prognosis using machine learning techniques.
A prognostic algorithm was developed using an AS registry of 10,407 patients undergoing echocardiography between 2008 and 2020. Clinical, echocardiographic, laboratory, and medication data were used to train and test a time-to-event model, the random survival forest (RSF), for AS patient's prognosis. The composite outcome included aortic valve replacement or mortality. The SHapley Additive exPlanations method attributed the importance of variables and provided personalized risk assessment. The algorithm was validated in 2 external cohorts of 11,738 and 954 patients with AS.
The median follow-up of the primary cohort was 48 (21-87) months. In this period, 1,116 patients underwent aortic valve replacement, and 5,069 patients died. RSF had an area under the curve (AUC) of 0.83 (95% CI: 0.80-0.86) and 0.83 (95% CI: 0.81-0.84) for outcomes prediction at 1 and 5 years, respectively. Using a cut-off of 50%, the RSF sensitivity and specificity for the composite outcome, were 0.80 and 0.73, respectively. Validation performance in the 2 external cohorts was similar, with AUCs of 0.73 (95% CI: 0.72-0.74) and 0.74 (95% CI: 0.72-0.76), respectively. AS severity, age, serum albumin, pulmonary artery pressure, and chronic kidney disease emerged as the top significant variables in the model.
In patients with AS, a machine learning algorithm predicts outcomes with good accuracy, and prognostic characteristics were identified. The model can potentially guide risk factor modification and clinical decisions to improve patient prognosis.
任何程度的主动脉瓣狭窄都与不良预后相关。
作者旨在使用机器学习技术开发一种用于预测主动脉瓣狭窄（AS）预后的风险预测模型。
利用一个包含2008年至2020年间接受超声心动图检查的10407例患者的AS登记系统开发了一种预后算法。临床、超声心动图、实验室和用药数据用于训练和测试一个用于AS患者预后的事件发生时间模型——随机生存森林（RSF）。复合结局包括主动脉瓣置换或死亡。SHapley值相加解释法确定了变量的重要性并提供了个性化风险评估。该算法在两个分别包含11738例和954例AS患者的外部队列中进行了验证。
主要队列的中位随访时间为48（21 - 87）个月。在此期间，1116例患者接受了主动脉瓣置换，5069例患者死亡。RSF在1年和5年结局预测时的曲线下面积（AUC）分别为0.83（95%CI：0.80 - 0.86）和0.83（95%CI：0.81 - 0.84）。以50%为临界值时，RSF对复合结局的敏感性和特异性分别为0.80和0.73。在两个外部队列中的验证表现相似，AUC分别为0.73（95%CI：0.72 - 0.74）和0.74（95%CI：0.72 - 0.76）。AS严重程度、年龄、血清白蛋白、肺动脉压和慢性肾脏病是模型中最重要的显著变量。
在AS患者中，一种机器学习算法能准确预测结局，并确定了预后特征。该模型可能有助于指导危险因素的调整和临床决策，以改善患者预后。
