Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis
Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis
复制标题
使用中红外光谱和逻辑回归分析检测干人体血斑中的疟疾寄生虫
DOI：
10.1101/19001206
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Mwanga E
中科院分区：
文献类型：
--
作者：
Mwanga E
疟疾流行病学调查目前依赖于显微镜、聚合酶链反应测定（PCR）或疟原虫感染快速诊断检测试剂盒。这项研究调查了中红外（MIR）光谱与监督机器学习相结合是否可以构成一种直接从干燥的人类血斑快速筛查疟疾的替代方法。方法2018/19年度在坦桑尼亚东南部12个病区进行疟疾横断面调查，获取含有干血斑（DBS）的滤纸。采用衰减全反射-傅里叶变换红外（ATR-FTIR）光谱仪对DBS进行扫描，获得4000 cm−1 ~ 500 cm−1范围内的高分辨率MIR光谱。对光谱进行清洗以补偿大气水汽和二氧化碳的干扰波段，并根据PCR检测结果作为参考，用于训练不同的分类算法，以区分疟疾阳性和疟疾阴性的DBS论文。该分析考虑了296个人，包括123例聚合酶链反应证实的疟疾阳性和173例阴性。使用80%的数据集进行模型训练，之后通过80/20训练/测试分层分割的bootstrapping来优化最佳拟合模型。通过预测20% DBS验证集的恶性疟原虫阳性来评估训练的模型。结果logistic回归是最佳模型。以PCR为参照，模型预测p的总体准确率为92%。恶性疟原虫感染（特异性= 91.7%，敏感性= 92.8%）和预测混合感染的85%。恶性疟原虫卵形疟原虫（特异性85%，敏感性85%）。结论中红外光谱结合监督机器学习（MIR-ML）技术可用于人DBS中疟原虫的筛选。该方法有可能在非临床环境（例如，实地调查）和临床环境（诊断以帮助病例管理）中快速和高通量筛选疟原虫。然而，在使用该方法之前，我们需要在其他具有不同寄生虫种群的研究地点进行额外的现场验证，并深入评估MIR信号的生物学基础。改进分类算法，在更大的数据集上进行模型训练也可以提高特异性和敏感性。MIR-ML光谱系统在物理上坚固耐用，成本低，并且需要最少的维护。
BackgroundEpidemiological surveys of malaria currently rely on microscopy, polymerase chain reaction assays (PCR) or rapid diagnostic test kits forPlasmodiuminfections (RDTs). This study investigated whether mid-infrared (MIR) spectroscopy coupled with supervised machine learning could constitute an alternative method for rapid malaria screening, directly from dried human blood spots.MethodsFilter papers containing dried blood spots (DBS) were obtained from a cross-sectional malaria survey in 12 wards in southeastern Tanzania in 2018/19. The DBS were scanned using attenuated total reflection-Fourier Transform Infrared (ATR-FTIR) spectrometer to obtain high-resolution MIR spectra in the range 4000 cm−1to 500 cm−1. The spectra were cleaned to compensate for atmospheric water vapour and CO2interference bands and used to train different classification algorithms to distinguish between malaria-positive and malaria-negative DBS papers based on PCR test results as reference. The analysis considered 296 individuals, including 123 PCR-confirmed malaria positives and 173 negatives. Model training was done using 80% of the dataset, after which the best-fitting model was optimized by bootstrapping of 80/20 train/test-stratified splits. The trained models were evaluated by predictingPlasmodium falciparumpositivity in the 20% validation set of DBS.ResultsLogistic regression was the best-performing model. Considering PCR as reference, the models attained overall accuracies of 92% for predictingP. falciparuminfections (specificity = 91.7%; sensitivity = 92.8%) and 85% for predicting mixed infections ofP. falciparumandPlasmodium ovale(specificity = 85%, sensitivity = 85%) in the field-collected specimen.ConclusionThese results demonstrate that mid-infrared spectroscopy coupled with supervised machine learning (MIR-ML) could be used to screen for malaria parasites in human DBS. The approach could have potential for rapid and high-throughput screening ofPlasmodiumin both non-clinical settings (e.g., field surveys) and clinical settings (diagnosis to aid case management). However, before the approach can be used, we need additional field validation in other study sites with different parasite populations, and in-depth evaluation of the biological basis of the MIR signals. Improving the classification algorithms, and model training on larger datasets could also improve specificity and sensitivity. The MIR-ML spectroscopy system is physically robust, low-cost, and requires minimum maintenance.
登录
查看更多内容
影响因子：
3.4
作者：
Newman, Dave M.;Heptinstall, John;Mensz, Petra F.
通讯作者：
Mensz, Petra F.
影响因子：
3.2
作者：
Ntamatungiro AJ;Mayagaya VS;Rieben S;Moore SJ;Dowell FE;Maia MF
通讯作者：
Maia MF
使用近红外光谱检测伯氏疟原虫感染的史氏按蚊
DOI：
10.1101/195925
发表时间：
2018
期刊：
--
影响因子：
--
作者：
Esperança P
通讯作者：
Esperança P
使用中红外光谱和监督机器学习预测疟疾蚊子种类和种群年龄结构
DOI：
10.1101/414342
发表时间：
2018
期刊：
--
影响因子：
--
作者：
González-Jiménez M
通讯作者：
González-Jiménez M
影响因子：
11.8
作者：
Wilson, Michael L.
通讯作者：
Wilson, Michael L.