Mohammed Akram, Podila Pradeep S B, Davis Robert L, Ataga Kenneth I, Hankins Jane S, Kamaleswaran Rishikesan
Center for Biomedical Informatics, University of Tennessee Health Science Center, Memphis, TN, United States.
Faith and Health Division, Methodist Le Bonheur Healthcare, Memphis, TN, United States.
J Med Internet Res. 2020 May 13;22(5):e14693. doi: 10.2196/14693.
Sickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications, including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable early identification and treatment and potentially reduce mortality.
The aim of this study was to test the hypothesis that machine learning physiomarkers can predict the development of organ dysfunction in a sample of adult patients with SCD admitted to intensive care units (ICUs).
We applied diverse machine learning methods, statistical methods, and data visualization techniques to develop classification models to distinguish SCD from controls.
We studied 63 sequential SCD patients admitted to ICUs with 163 patient encounters (mean age 30.7 years, SD 9.8 years). A subset of these patient encounters, 22.7% (37/163), met the sequential organ failure assessment criteria. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast Fourier transform, energy, and continuous wavelet transform) derived from heart rate, blood pressure, and respiratory rate was identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure from patients with SCD who did not meet the criteria. A multilayer perceptron model accurately predicted organ failure up to 6 hours before onset, with an average sensitivity and specificity of 96% and 98%, respectively.
This retrospective study demonstrated the viability of using machine learning to predict acute organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.
镰状细胞病（SCD）是一种红细胞的遗传性疾病，会导致多种急性和慢性并发症，包括疼痛发作、中风和肾脏疾病。SCD患者会出现慢性器官功能障碍，在疾病加重期间可能会进展为器官衰竭。导致器官衰竭的急性生理恶化的早期检测并非总能实现。能够预测器官衰竭的机器学习技术可能有助于早期识别和治疗，并有可能降低死亡率。
本研究的目的是检验以下假设：机器学习生理标志物可以预测入住重症监护病房（ICU）的成年SCD患者样本中器官功能障碍的发生。
我们应用了多种机器学习方法、统计方法和数据可视化技术来开发分类模型，以区分SCD患者与对照组。
我们研究了63例连续入住ICU的SCD患者，共163次患者就诊（平均年龄30.7岁，标准差9.8岁）。这些患者就诊中有22.7%（37/163）符合序贯器官衰竭评估标准。其他126次SCD患者就诊作为对照。从心率、血压和呼吸频率中提取了一组信号处理特征（如快速傅里叶变换、能量和连续小波变换），以区分发生急性生理恶化导致器官衰竭的SCD患者与未符合标准的SCD患者。多层感知器模型在器官衰竭发作前6小时就能准确预测，平均灵敏度和特异性分别为96%和98%。
这项回顾性研究证明了使用机器学习预测住院成年SCD患者急性器官衰竭的可行性。通过机器学习技术发现显著的生理标志物有可能进一步加速为医疗脆弱患者开发和实施创新的护理方案和策略。
