This paper proposes a disease detection system where it receives the query in form of symptoms of the disease in the Bengali language. This system is able to handle natural language queries in Bengali. The proposed system assists a layman to detect a probable disorder or disease in their body using disease symptoms. The proposed research work is challenging due to insufficient resources in vernacular languages like Bengali. This system receives a description of the patient's symptoms in the Bengali language and after processing the natural language text, it detects any potential disorders or diseases that may have occurred. This research work has been implemented separately by using the two most popular sequential prediction models. One is Bi-directional Long Short-Term Memory (Bi-LSTM) and the other is Bi-directional Gated Recurrent Unit (Bi-GRU). Both Bi-GRU and Bi-LSTM have provided significant results on a dataset of 3714 samples. The raw clinical text categorization data has been gathered from the Kaggle to build the detection model. The performances of disease detectability of both models have been measured using precision, recall and f1-score. The accuracy of the proposed system using the Bi-LSTM and the Bi-GRU models are 97.85% and 99.73%, respectively.
Background: This study was undertaken to introduce a non- invasive technique for clinical diagnosis of spinal cord deformities. The purpose of the present study is to evaluate the postural deformities and onset of thoracic Kyphosis and lumber Lordosis among agricultural workers and Information Technology workers. Methodology: This cross-sectional study was carried out on thirty Agricultural workers (41-45 years) and twenty-five Information Technology workers (21-25 years) and their age matched control groups. The subjects were taken from their respective population by simple random sampling method. Measurements were made by Flexicurve Ruler in special standing posture. Kyphosis and Lordosis angles and Indices were calculated. Results: It indicates that maximum percentage of subjects had kyphotic angle between 400 -600. Twenty-three out of 30 agricultural workers (76.66%) and 22 out of 25(88%) information technology workers had kyphosis angle between 400- 600 but the same in case of control groups were 60% and 64% respectively. Maximum subjects had lordotic angle between 300 - 500. Thirteen out of 30 agricultural workers (43.33%) and 17 out of 25 information technology workers (68%) had lordotic angle in between 300 -500.The same in case of control groups were 43.33% and 56% respectively. Kyphosis index, Kyphosis angle and lordosis index, lordosis angle are significantly lower (p<0.05) in agriculture workers in comparison to its control group but the differences are not significant in case of information technology workers as well as between agriculture group and information technology group. But information technology workers show higher values of Kyphosis and lordotic index than agriculture workers, probably due to prolong sitting posture at work. Again 47% agricultural workers and 11% IT workers reported lumbar pain when compared to control groups (10% and none respectively). Conclusion: Although no significant deviation of kyphotic and lordotic angle has been observed in agricultural and information technology workers but significantly higher percentage of these 2 groups reported shoulder and lumbar pain indicating risk of dysfunction in shoulder, pelvic girdle and spine. Thus measurement of thoracic kyphosis and lumbar lordosis may be useful in examining the degree of spinal cord deformities. By utilizing these information therapeutic and ergonomic intervention can be applied and application of modern sophisticated machine for improvement in postural condition can reduce their work stress and disabilities.
Purpose: To assess Visual Display Terminal(VDT) exposure as a risk factor for paediatric Dry Eye Disease(DED). Methodology: In this cross sectional study, children(5-15 years) from both urban and rural regions with VDT(computer,smartphone,television) exposure(1-2,3-4,>=5hours) were enrolled. Dry eye evaluation was done using Ocular Surface Disease Index (OSDI) Questionnaire, Schirmer's without anesthesia, Fluorescein-Tear lm Break-up Time(F-TBUT) and corneal , conjunctival uorescein staining as per Tear Film and Ocular Surface Society(TFOS) Dry Eye Workshop II Guidelines 2017(DEWS II). DED diagnosis was based on OSDI grading(>=13) and objective tests(>=1 positive test). Results: 315 children exposed to VDTwere selected for the study. Burning sensation and redness were the most common symptoms. Prevalence of DED was observed to be 6.03%(19 children-38 eyes). Mean age and hours of VDT exposure was signicantly higher and hours of outdoor activity and sleep signicantly lower in DED children compared to NON DED children(p<.05). Urban elder children had highest DED prevalence rate of 13.19% .Prevalence of DED in children using VDTfor 1-2 hours was .74%,3-4 hours was 28.57%, and >=5 hours was 47.83% (p=<.001). Children with short hours of outdoor activity(<3hours) had DED prevalence of 24.62 % whereas children with longer outdoor activity(>=3 hours) showed 1.20% prevalence(p<.001). Children with less hours of sleep(<8hours) showed DED prevalence of 22.58% and those with longer hours(>=8 hours) of sleep had only 1.98% DED prevalence (p<.001). Conclusion: DED was found to be associated with elder age, longer hours of VDT exposure , short hours of outdoor activity and sleep in VDTexposed children.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.