Prediction of Anemia and Estimation of Hemoglobin Concentration Using a Smartphone Camera

This is a prospective convenience sample study conducted in Emergency Department (ED) patients of an academic teaching hospital. In an algorithm derivation phase, images of both conjunctiva were obtained from 142 patients in Phase 1 using a smartphone in addition to their measured hemoglobin via venipuncture. A region of interest targeting the palpebral conjunctiva was selected from each image. Image-based parameters were extracted and used in stepwise regression analyses to develop a prediction model of estimated hemoglobin from conjunctiva imaging (HBc). These data are in "eye_long_modeling 08JUN2021". In Phase 2, a validation model was constructed using data from 202 new ED patients, and their true hemoglobin values, found in file "clinical_set_lo_validation 08JUN2021". The final model based on all 344 patients was tested for accuracy in anemia and transfusion thresholds. Hemoglobin concentration ranged from 4.7 to 19.6 g/dL (mean 12.5).本研究为一项前瞻性便利抽样研究，研究对象为某教学医院急诊科（Emergency Department, ED）患者。在算法推导阶段，即第1阶段，研究人员使用智能手机采集了142名患者的双眼结膜图像，并通过静脉穿刺法检测其血红蛋白水平。从每张图像中选取针对睑结膜（palpebral conjunctiva）的感兴趣区域，提取基于图像的特征参数，并通过逐步回归分析构建基于结膜成像的血红蛋白预估模型（HBc）。相关数据存储于文件"eye_long_modeling 08JUN2021"中。在第2阶段，研究人员利用202名新增急诊科患者的数据构建了验证模型，其真实血红蛋白值存储于文件"clinical_set_lo_validation 08JUN2021"中。基于全部344名患者数据构建的最终模型，针对贫血及输血阈值场景进行了准确性测试。本次研究的血红蛋白浓度范围为4.7至19.6 g/dL，均值为12.5 g/dL。