Sample-to-answer palm-sized nucleic acid testing device towards low-cost malaria mass screening.

The effectiveness of malaria screening and treatment highly depends on the low-cost access to the highly sensitive and specific malaria test. We report a real-time fluorescence nucleic acid testing device for malaria field detection with automated and scalable sample preparation capability. The device consists a compact analyzer and a disposable microfluidic reagent compact disc. The parasite DNA sample preparation and subsequent real-time LAMP detection were seamlessly integrated on a single microfluidic compact disc, driven by energy efficient non-centrifuge based magnetic field interactions. Each disc contains four parallel testing units which could be configured either as four identical tests or as four species-specific tests. When configured as species-specific tests, it could identify two of the most life-threatening malaria species (P. falciparum and P. vivax). The NAT device is capable of processing four samples simultaneously within 50 min turnaround time. It achieves a detection limit of ~0.5 parasites/µl for whole blood, sufficient for detecting asymptomatic parasite carriers. The combination of the sensitivity, specificity, cost, and scalable sample preparation suggests the real-time fluorescence LAMP device could be particularly useful for malaria screening in the field settings.

EEG feature selection method based on decision tree.

This paper aims to solve automated feature selection problem in brain computer interface (BCI). In order to automate feature selection process, we proposed a novel EEG feature selection method based on decision tree (DT). During the electroencephalogram (EEG) signal processing, a feature extraction method based on principle component analysis (PCA) was used, and the selection process based on decision tree was performed by searching the feature space and automatically selecting optimal features. Considering that EEG signals are a series of non-linear signals, a generalized linear classifier named support vector machine (SVM) was chosen. In order to test the validity of the proposed method, we applied the EEG feature selection method based on decision tree to BCI Competition II datasets Ia, and the experiment showed encouraging results.