Validation of the myocardial-ischaemic-injury-index machine learning algorithm to guide the diagnosis of myocardial infarction in a heterogenous population: a prespecified exploratory analysis.
Validation of the myocardial-ischaemic-injury-index machine learning algorithm to guide the diagnosis of myocardial infarction in a heterogenous population: a prespecified exploratory analysis.
复制标题
DOI：
10.1016/s2589-7500(22)00025-5
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
High-STEACS Investigators
中科院分区：
文献类型：
--
作者：
Doudesis D;Lee KK;Yang J;Wereski R;Shah ASV;Tsanas A;Anand A;Pickering JW;Than MP;Mills NL;High-STEACS Investigators
心肌梗死的诊断途径依赖于固定的肌钙蛋白阈值，该阈值不能识别肌钙蛋白在个体内随年龄、性别和时间而变化。为了克服这一局限性，我们最近引入了一种机器学习算法来预测心肌梗死的可能性。我们的目的是评估该算法是否在常规临床实践中表现良好，并预测后续事件。使用在英国苏格兰进行的多中心随机试验的数据，在预先规定的探索性分析中验证了心肌缺血损伤指数（MI 3）算法，该试验包括接受系列高灵敏度心肌肌钙蛋白I测量的疑似急性冠状动脉综合征连续患者。排除ST段抬高型心肌梗死患者。MI 3结合了年龄、性别和两个肌钙蛋白测量值，以计算反映个体在索引访视期间发生心肌梗死的可能性的值（0-100），并在计算的评分下估计诊断性能指标（包括受试者工作特征曲线下面积，以及灵敏度、特异性、阴性预测值和阳性预测值）。使用先前定义的低概率阈值（1.6）和高概率MI 3阈值（49.7）确定了心肌梗死（1型或4 b型）索引诊断以及1年时后续心肌梗死或心血管死亡的模型性能。该试验在ClinicalTrials.gov注册，NCT 01852123。在2013年6月10日至2016年3月3日期间入组的20761例患者（64岁[SD 16]，9597例[46%]女性）被纳入High-STEACS试验队列，其中3272例（15.8%）患有心肌梗死。MI 3的受试者工作特征曲线下面积为0.949（95% CI 0.946 - 0.952）在预先规定的阈值下，将12983例（62.5%）患者确定为心肌梗死的低概率（MI 3评分<1.6;灵敏度99.3%[95%CI 99.0 - 99.6]，阴性预测值99.8%[99.8 - 99.9]），2961（14.3%）例在预先规定的阈值处为高概率（MI 3评分≥49·7;特异性95·0% [94·6-95·3]，阳性预测值70·4% [68·7-72·0]）。在1年时，高概率患者比低概率患者更常发生随后的心肌梗死或心血管死亡（2961例中520例[17.6%] vs 12983例中197例[1.5%]，p<0.0001）。在因疑似急性冠脉综合征而接受连续心肌肌钙蛋白测量的连续患者中，MI 3算法准确估计了心肌梗死的可能性，并预测了随后的不良心血管事件。通过提供个体概率，MI 3算法可以改善疑似急性冠状动脉综合征患者的诊断和风险评估。医学研究理事会、英国心脏基金会、国家健康研究所和NHSX。
Diagnostic pathways for myocardial infarction rely on fixed troponin thresholds, which do not recognise that troponin varies by age, sex, and time within individuals. To overcome this limitation, we recently introduced a machine learning algorithm that predicts the likelihood of myocardial infarction. Our aim was to evaluate whether this algorithm performs well in routine clinical practice and predicts subsequent events. The myocardial-ischaemic-injury-index (MI3) algorithm was validated in a prespecified exploratory analysis using data from a multi-centre randomised trial done in Scotland, UK that included consecutive patients with suspected acute coronary syndrome undergoing serial high-sensitivity cardiac troponin I measurement. Patients with ST-segment elevation myocardial infarction were excluded. MI3 incorporates age, sex, and two troponin measurements to compute a value (0–100) reflecting an individual's likelihood of myocardial infarction during the index visit and estimates diagnostic performance metrics (including area under the receiver-operating-characteristic curve, and the sensitivity, specificity, negative predictive value, and positive predictive value) at the computed score. Model performance for an index diagnosis of myocardial infarction (type 1 or type 4b), and for subsequent myocardial infarction or cardiovascular death at 1 year was determined using the previously defined low-probability threshold (1·6) and high-probability MI3 threshold (49·7). The trial is registered with ClinicalTrials.gov, NCT01852123. In total, 20 761 patients (64 years [SD 16], 9597 [46%] women) enrolled between June 10, 2013, and March 3, 2016, were included from the High-STEACS trial cohort, of whom 3272 (15·8%) had myocardial infarction. MI3 had an area under the receiver-operating-characteristic curve of 0·949 (95% CI 0·946–0·952) identifying 12 983 (62·5%) patients as low-probability for myocardial infarction at the pre-specified threshold (MI3 score <1·6; sensitivity 99·3% [95% CI 99·0–99·6], negative predictive value 99·8% [99·8–99·9]), and 2961 (14·3%) as high-probability at the pre-specified threshold (MI3 score ≥49·7; specificity 95·0% [94·6–95·3], positive predictive value 70·4% [68·7–72·0]). At 1 year, subsequent myocardial infarction or cardiovascular death occurred more often in high-probability patients than low-probability patients (520 [17·6%] of 2961 vs 197 [1·5%] of 12 983], p<0·0001). In consecutive patients undergoing serial cardiac troponin measurement for suspected acute coronary syndrome, the MI3 algorithm accurately estimated the likelihood of myocardial infarction and predicted subsequent adverse cardiovascular events. By providing individual probabilities the MI3 algorithm could improve the diagnosis and assessment of risk in patients with suspected acute coronary syndrome. Medical Research Council, British Heart Foundation, National Institute for Health Research, and NHSX.