Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy.
Sensors (Basel). 2024 Oct 15;24(20):6635. doi: 10.3390/s24206635.
Parenteral artificial nutrition (PAN) is a lifesaving medical treatment for many patients worldwide. Administration of the wrong PAN drug can lead to severe consequences on patients' health, including death in the worst cases. Thus, their correct identification, just before injection, is of crucial importance. Since most of these drugs appear as turbid liquids, they cannot be easily discriminated simply by means of basic optical analyses. To overcome this limitation, in this work, we demonstrate that the combination of speckle pattern (SP) imaging and artificial intelligence can provide precise classifications of commercial pharmaceutical suspensions for PAN. Towards this aim, we acquired SP images of each sample and extracted several statistical parameters from them. By training two machine learning algorithms (a Random Forest and a Multi-Layer Perceptron Network), we were able to identify the drugs with accurate performances. The novelty of this work lies in the smart combination of SP imaging and machine learning for realizing an optical sensing platform. For the first time, to our knowledge, this approach is exploited to identify PAN drugs.
肠外营养（PAN）是全球许多患者的救命治疗方法。如果给错了 PAN 药物，会对患者的健康造成严重后果，在最坏的情况下甚至可能导致死亡。因此，在注射前正确识别药物至关重要。由于这些药物大多呈混浊液体，仅凭基本的光学分析很难区分。为了克服这一限制，在本工作中，我们证明了散斑图案（SP）成像和人工智能的组合可以对用于 PAN 的商业药物混悬剂进行精确分类。为此，我们获取了每个样本的 SP 图像，并从中提取了几个统计参数。通过训练两种机器学习算法（随机森林和多层感知机网络），我们能够以准确的性能识别药物。这项工作的新颖之处在于巧妙地结合了 SP 成像和机器学习，实现了光学传感平台。据我们所知，这是首次将这种方法用于识别 PAN 药物。
