Application of Internet of Things on the Healthcare Field Using Convolutional Neural Network Processing.

Population at risk can benefit greatly from remote health monitoring because it allows for early detection and treatment. Because of recent advances in Internet-of-Things (IoT) paradigms, such monitoring systems are now available everywhere. Due to the essential nature of the patients being monitored, these systems demand a high level of quality in aspects such as availability and accuracy. In health applications, where a lot of data are accessible, deep learning algorithms have the potential to perform well. In this paper, we develop a deep learning architecture called the convolutional neural network (CNN), which we examine in this study to see if it can be implemented. The study uses the IoT system with a centralised cloud server, where it is considered as an ideal input data acquisition module. The study uses cloud computing resources by distributing CNN operations to the servers with outsourced fitness functions to be performed at the edge. The results of the simulation show that the proposed method achieves a higher rate of classifying the input instances from the data acquisition tools than other methods. From the results, it is seen that the proposed CNN achieves an average accurate rate of 99.6% on training datasets and 86.3% on testing datasets.

Antibiotic susceptibility pattern of Neisseria gonorrhoeae strains isolated from five cities in India during 2013-2016.

PURPOSE: Emergence of multidrug resistance in Neisseria gonorrhoeae, an STI of public health significance is the biggest challenge to gonorrhoea control. Monitoring for antimicrobial resistance is essential for the early detection of emergent drug resistance patterns. METHODOLOGY: One hundred and twenty four N. gonorrhoeae strains were isolated between September 2013-August 2016 [82-New Delhi, 3-Pune, 3-Mumbai, 20-Secunderabad and 16-Hyderabad] to determine antimicrobial susceptibility and to compare the CLSI disc diffusion method with Etest for these strains. The results of the two methods were compared by using kappa statistics. RESULTS: Ninety eight percent [CI: 96.2-100] of isolates were resistant to ciprofloxacin, 52 % [CI: 43.2-60.8] to penicillin, 56 % [CI: 47.2-64.7] to tetracycline and 5 % [CI: 1.2-8.8] to azithromycin. All the strains were susceptible to spectinomycin, ceftriaxone and cefixime except for two strains which showed decreased susceptibility to ceftriaxone and cefixime. Kappa scores for penicillin, azithromycin, ciprofloxacin, ceftriaxone and cefixime showed that the CLSI method had high agreement with Etest while tetracycline had substantial agreement. CONCLUSION: Our data suggest that the disc diffusion method which is both cost effective and more feasible, can effectively be used routinely for monitoring antibiotic susceptibility in N. gonorrhoeae, in limited resource countries like India. We demonstrate the emergence of decreased susceptibility to ceftriaxone and cefixime and threshold levels of resistance to azithromycin in India. This underscores the importance of maintaining continued surveillance for antibiotic resistance in N. gonorrhoeae and a potential requirement for strategic change in guidelines in the not so distant future.

Enteric Parasitic Infections in Relation to Diarrhoea in HIV Infected Individuals with CD4 T Cell Counts <1000 Cells/µl in Chennai, India.

AIM: This study was conducted to estimate the prevalence of enteric parasites in HIV patients in Chennai and to correlate with CD4 counts and diarrhoeal status. MATERIAL AND METHODS: Faecal specimens from 100 HIV infected individuals with CD4 < 1000/µl were screened for enteric parasites with wet mounts, modified acid-fast stain for coccidian parasites, modified trichrome stain for Microsporidia, before and after the stool concentration. Agar plate culture for Strongyloides was put up. Chi-square and ANOVA tests were used for statistical analysis. RESULTS: Study group comprised of 38 subjects with acute diarrhoea, 30 with chronic diarrhoea (> 2 weeks) and remaining 32 without diarrhoea. Enteric parasites were detected in 33% of subjects; Isoapora belli (21) being the commonest followed by E.histolyt/Entamoeba dispar (5), Entamoeba coli (2), Cryptosporidium spp (2), Hookworms (2), Strongyloides stercoralis (2), Giardia lamblia (1) and Microsporidium spp (1). There was a significant inverse relation between CD4 counts and duration of diarrhoea. Opportunistic parasites were isolated from the subjects with wide range of CD4 counts and different diarrhoeal status but most commonly from chronic diarrhoea patients. CONCLUSION: The prevalence of intestinal parasitic infections in HIV patients is high in Chennai, India, especially at CD4 <1000/µl, I.belli infection being the commonest. Routine screening of all HIV patients with low CD4 counts for coccidian parasitic infections by using simple stool microscopic techniques can help in early diagnosis and treatment.

Comparison of syndromic diagnosis of reproductive tract infections with laboratory diagnosis among rural married women in Medak district, Andhra Pradesh.

INTRODUCTION: In developing countries, reproductive tract infections (RTI) commonly affect the quality of life. Many reproductive tract infections including sexually transmitted infections (STI) and cervical cancers remain asymptomatic for long periods. Syndromic case management (SCM) is the mainstay in the control of RTI/STI, especially at primary level, where laboratory diagnosis is not possible. However, lab diagnosis should be used when it is available. OBJECTIVE: To assess the consistency of syndromic diagnosis with laboratory diagnosis. MATERIALS AND METHODS: A total of 407 women were screened. Women were categorized according to Syndromic Diagnosis of RTI/STI based on history and clinical examination. Microbiological tests and Pap smears were done to confirm the diagnosis and compared with Syndromic Diagnosis. RESULTS: Microbiologically, 33.14% were positive for at least one organism. Bacterial vaginosis was the most common finding (14%). Pap smear showed 32.9% inflammatory changes and 0.25% low-grade squamous intraepithelial lesion. Sensitivity and specificity of syndromic diagnosis with laboratory findings: Vaginal discharge syndrome with microbiological tests- (Se 58.9; Sp55.1%) Lower abdominal pain syndrome with microbiological tests-(Se 14.4%; Sp76.6%) CONCLUSION: The findings of this study highlight the wide variation of syndromic and laboratory diagnosis.