Hinrichs Nils, Meyer Alexander, Koehler Kerstin, Kaas Thomas, Hiddemann Meike, Spethmann Sebastian, Balzer Felix, Eickhoff Carsten, Falk Volkmar, Hindricks Gerhard, Dagres Nikolaos, Koehler Friedrich
Department of Cardiothoracic and Vascular Surgery, Deutsches Herzzentrum der Charité, Berlin, Germany.
Institute of Medical Informatics, Charité - Universitätsmedizin Berlin, Berlin, Germany.
Front Cardiovasc Med. 2024 Sep 20;11:1457995. doi: 10.3389/fcvm.2024.1457995. eCollection 2024.
Remote patient management may improve prognosis in heart failure. Daily review of transmitted data for early recognition of patients at risk requires substantial resources that represent a major barrier to wide implementation. An automated analysis of incoming data for detection of risk for imminent events would allow focusing on patients requiring prompt medical intervention.
We analysed data of the Telemedical Interventional Management in Heart Failure II (TIM-HF2) randomized trial that were collected during quarterly in-patient visits and daily transmissions from non-invasive monitoring devices. By application of machine learning, we developed and internally validated a risk score for heart failure hospitalisation within seven days following data transmission as estimate of short-term patient risk for adverse heart failure events. Score performance was assessed by the area under the receiver-operating characteristic (ROCAUC) and compared with a conventional algorithm, a heuristic rule set originally applied in the randomized trial.
The machine learning model significantly outperformed the conventional algorithm (ROCAUC 0.855 vs. 0.727, < 0.001). On average, the machine learning risk score increased continuously in the three weeks preceding heart failure hospitalisations, indicating potential for early detection of risk. In a simulated one-year scenario, daily review of only the one third of patients with the highest machine learning risk score would have led to detection of 95% of HF hospitalisations occurring within the following seven days.
A machine learning model allowed automated analysis of incoming remote monitoring data and reliable identification of patients at risk of heart failure hospitalisation requiring immediate medical intervention. This approach may significantly reduce the need for manual data review.
远程患者管理可能改善心力衰竭的预后。每日审查传输数据以早期识别有风险的患者需要大量资源，这是广泛实施的主要障碍。对传入数据进行自动分析以检测即将发生事件的风险，将有助于专注于需要及时医疗干预的患者。
我们分析了心力衰竭远程医疗干预管理II（TIM-HF2）随机试验的数据，这些数据是在季度住院就诊期间以及从无创监测设备的每日传输中收集的。通过应用机器学习，我们开发并在内部验证了一个风险评分，用于估计数据传输后七天内心力衰竭住院的风险，以此作为短期患者发生不良心力衰竭事件风险的估计。通过受试者操作特征曲线下面积（ROCAUC）评估评分性能，并与传统算法（一种最初应用于随机试验的启发式规则集）进行比较。
机器学习模型显著优于传统算法（ROCAUC为0.855对0.727，<0.001）。平均而言，机器学习风险评分在心力衰竭住院前的三周内持续上升，表明有早期检测风险的潜力。在模拟的一年情景中，仅每日审查机器学习风险评分最高的三分之一患者，就可检测到接下来七天内发生的95%的心力衰竭住院病例。
机器学习模型允许对传入的远程监测数据进行自动分析，并可靠地识别有心力衰竭住院风险且需要立即医疗干预的患者。这种方法可能显著减少人工数据审查的需求。
