Molecular detection of spotted fever group of Rickettsiae in acute encephalitis syndrome cases from eastern Uttar Pradesh region of India.

The Eastern Uttar Pradesh region of India is known for its endemicity of acute encephalitis syndrome (AES). Decades of research have established that Orientia tsutsugamushi, a causative of scrub typhus, is a substantial contributor (>60%) for the AES cases besides other aetiology, but additional factors in the remaining proportion are still unidentified. Rickettsial infections are challenging to diagnose in clinical settings due to overlapping clinical symptoms, the absence of definitive indicators, a low index of suspicion, and the lack of low-cost, rapid diagnostic tools. Hence, the present study was designed to determine the load of rickettsial infections among AES cases. Furthermore, we aim to find out the prevalent rickettsial species in AES cases as well as in the vector population at this location. The study included the whole blood/cerebrospinal fluid of AES patients and arthropod specimens from rodents. The molecular identification was performed using the 23S-5S intergenic spacer region and ompB gene with genomic DNA obtained from studied specimens. We detected 5.34% (62/1160) of rickettsial infection in AES cases. Among these, phylogenetic analysis confirmed the presence of 54.8% Rickettsia conorii (n = 34) and 16.1% of Rickettsia felis (n = 10), while the rest proportion of the isolates was unidentified at the species level. Furthermore, R. felis was identified in one CSF sample from AES patients and three flea samples from Xenopsylla cheopis. Rickettsia spp. was also confirmed in one Ornithonyssus bacoti mite sample. The results of this investigation concluded the presence of spotted fever group Rickettsia spp. among AES identified cases as well as in the mite and flea vectors that infest rodents.

Evolving Long Short-Term Memory Network-Based Text Classification.

Recently, long short-term memory (LSTM) networks are extensively utilized for text classification. Compared to feed-forward neural networks, it has feedback connections, and thus, it has the ability to learn long-term dependencies. However, the LSTM networks suffer from the parameter tuning problem. Generally, initial and control parameters of LSTM are selected on a trial and error basis. Therefore, in this paper, an evolving LSTM (ELSTM) network is proposed. A multiobjective genetic algorithm (MOGA) is used to optimize the architecture and weights of LSTM. The proposed model is tested on a well-known factory reports dataset. Extensive analyses are performed to evaluate the performance of the proposed ELSTM network. From the comparative analysis, it is found that the LSTM network outperforms the competitive models.