Anubhav Jain

© 2015 Baum et al.; licensee BioMed Central. Background: Malaria is a public health problem in parts of Thailand, where Plasmodium falciparum and Plasmodium vivax are the main causes of infection. In the northwestern border province of Tak parasite prevalence is now estimated to be less than 1% by microscopy. Nonetheless, microscopy is insensitive at low-level parasitaemia. The objective of this study was to assess the current epidemiology of falciparum and vivax malaria in Tak using molecular methods to detect exposure to and infection with parasites; in particular, the prevalence of asymptomatic infections and infections with submicroscopic parasite levels. Methods: Three-hundred microlitres of whole blood from finger-prick were collected into capillary tubes from residents of a sentinel village and from patients at a malaria clinic. Pelleted cellular fractions were screened by quantitative PCR to determine parasite prevalence, while plasma was probed on a protein microarray displaying hundreds of P. falciparum and P. vivax proteins to obtain antibody response profiles in those individuals. Results: Of 219 samples from the village, qPCR detected 25 Plasmodium sp. infections, of which 92% were asymptomatic and 100% were submicroscopic. Of 61 samples from the clinic patients, 27 were positive by qPCR, of which 25.9% had submicroscopic parasite levels. Cryptic mixed infections, misdiagnosed as single-species infections by microscopy, were found in 7 malaria patients. All sample donors, parasitaemic and non-parasitaemic alike, had serological evidence of parasite exposure, with 100% seropositivity to at least 54 antigens. Antigens significantly associated with asymptomatic infections were P. falciparum MSP2, DnaJ protein, putative E1E2 ATPase, and three others. Conclusion: These findings suggest that parasite prevalence is higher than currently estimated by local authorities based on the standard light microscopy. As transmission levels drop in Thailand, it may be necessary to employ higher throughput and sensitivity methods for parasite detection in the phase of malaria elimination.

Humans' voice offers the widest variety of motor phenomena of any human activity. However, its clinical evaluation in people with movement disorders such as Parkinson's disease lags behind current knowledge on advanced analytical automatic speech processing methodology. Here, we use deep learning-based speech processing to differentially analyze voice recordings in 14 people with PD before and after dopaminergic medication using personalized Convolutional Recurrent Neural Networks and Phone Attribute Codebooks. p-CRNN yields an accuracy of 82.35% in the binary classification of ON and OFF motor states at a sensitivity/specificity of 0.86/0.78. The PAC-based approach's accuracy was slightly lower with 73.08% at a sensitivity/specificity of 0.69/0.77, but this method offers easier interpretation and understanding of the computational biomarkers. Both p-CRNN and PAC provide a differentiated view and novel insights into the distinctive components of the speech of persons with PD. Both methods detect voice qualities that are amenable to dopaminergic treatment, including active phonetic and prosodic features. Our findings may pave the way for quantitative measurements of speech in persons with PD.