Search

Introduction- The health hazard of glass factories has been classified in the ILO encyclopedia. Injuries, heat exhaustion, respiratory morbidity, ophthalmic morbidity, and nephrolithiasis are conditions in Glass factories worldwide. Material and Methods: A descriptive study was conducted in the small-scale glass factory situated in the district Firozabad, Uttar Pradesh, India, to estimate the eye conditions among glass factory workers. Informed consent was obtained from 140 respondents. The visual acuity was measured using Snellen's chart placed at six meters with adequate illumination. Each eye was tested separately for refractive error with and without glasses (where applicable), the dry eye with Schirmer strip, cataract with torchlight and direct ophthalmoscope, Conjunctivitis, and later refracted using retinoscope Trial & error method. Data analysis was done using the Statistical Package for Social Sciences (SPSSv16). Descriptive and inferential statistics were used to present the results of the study. Results: This study screened 140 participants, 2 of whom were female and 138 of whom were male. In a survey of 140 factory employees (76.42%), respondents reported no ocular complaints while at work. In (23.57%) of the employees, Asthenopic symptoms continued. 15.71% were reported feeling dryness at work.

COVID-19 detection using Artificial Intelligence and Computer-Aided Diagnosis has been the subject of several studies. Deep Neural Networks with hundreds or even millions of parameters (weights) are referred to as "black boxes" because their behavior is difficult to comprehend, even when the model's structure and weights are visible. On the same dataset, different Deep Convolutional Neural Networks perform differently. So, we do not necessarily have to rely on just one model; instead, we can evaluate our final score by combining multiple models. While including multiple models in the voter pool, it is not always true that the accuracy will improve. So, In this regard, the authors proposed a novel approach to determine the voting ensemble score of individual classifiers based on Condorcet's Jury Theorem (CJT). The authors demonstrated that the theorem holds while ensembling the N number of classifiers in Neural Networks. With the help of CJT, the authors proved that a model's presence in the voter pool would improve the likelihood that the majority vote will be accurate if it is more accurate than the other models. Besides this, the authors also proposed a Domain Extended Transfer Learning (DETL) ensemble model as a soft voting ensemble method and compared it with CJT based ensemble method. Furthermore, as deep learning models typically fail in real-world testing, a novel dataset has been used with no duplicate images. Duplicates in the dataset are quite problematic since they might affect the training process. Therefore, having a dataset devoid of duplicate images is considered to prevent data leakage problems that might impede the thorough assessment of the trained models. The authors also employed an algorithm for faster training to save computational efforts. Our proposed method and experimental results outperformed the state-of-the-art with the DETL-based ensemble model showing an accuracy of 97.26%, COVID-19, sensitivity of 98.37%, and specificity of 100%. CJT-based ensemble model showed an accuracy of 98.22%, COVID-19, sensitivity of 98.37%, and specificity of 99.79%.

In the medical field, day by day a new technology is introduced to reduce the efforts of doctors as well as patients. Before the actual treatment, patients' needs satisfaction to diagnose a defect in the body part. The current techniques available to detect the correct fractured/damaged bone part of a human is either a Computerized Tomography scan or Magnetic Resonance Imaging scan. The mentioned techniques are either unavailable in rural areas or are costly compare to the X-ray technique. This issue attracts the attention to design a technique that converts a 2-Dimensional (2-D) images into its equivalent 3- Dimensional (3-D) images. For this purpose, the authors used the Generative Adversarial Network to implement a technique that takes an X-ray image as input and gives its equivalent 0° to 360° images.

Cancer is utmost dangerous disease that leads to death stage if not cured on time. Breast cancer is the second most common disease after lung cancer in women. Therefore, its early detection is of utmost importance. Machine learning plays an important role to predict breast cancer in the early stages. In this paper, the authors present a comparison study to predict breast cancer on the Breast Cancer Wisconsin Diagnostic dataset by applying six different machine learning algorithms such as CART, logistic regression, support vector classifier, hard voting classifier, Extreme Gradient Boosting, and artificial neural network. Authors have used various metrics for model evaluation keeping accuracy as one of the most important factors since higher accuracy models can help doctors to better detect the presence of breast cancer.

Amidst the global pandemic and catastrophe created by 'COVID-19', every research institution and scientist are doing their best efforts to invent or find the vaccine or medicine for the disease. The objective of this research is to design and develop a deep learning-based multi-modal for the screening of COVID-19 using chest radiographs and genomic sequences. The modal is also effective in finding the degree of genomic similarity among the Severe Acute Respiratory Syndrome-Coronavirus 2 and other prevalent viruses such as Severe Acute Respiratory Syndrome-Coronavirus, Middle East Respiratory Syndrome-Coronavirus, Human Immunodeficiency Virus, and Human T-cell Leukaemia Virus. The experimental results on the datasets available at National Centre for Biotechnology Information, GitHub, and Kaggle repositories show that it is successful in detecting the genome of 'SARS-CoV-2' in the host genome with an accuracy of 99.27% and screening of chest radiographs into COVID-19, non-COVID pneumonia and healthy with a sensitivity of 95.47%. Thus, it may prove a useful tool for doctors to quickly classify the infected and non-infected genomes. It can also be useful in finding the most effective drug from the available drugs for the treatment of 'COVID-19'.

Low vision devices are used to improve the visual performance of patient with low vision, hence allowing them to carry out their daily activities. The objective was to provide best low vision correct to a patient with heredomacular degeneration. A 10 year old girl came to our OPD in September 2015. The patient had history of reduced vision in both eyes since, 1 year. She was now unable to distinguish writing on the school blackboard. Her mother had observed over the last 6 months that she held reading matter very close to his face. Her mother also reported that she preferred to study in dim illumination. The patient had no known precipitating factor and no family history of similar symptoms. The patient had history of using glasses. The patient was diagnosed to have adult onset heredomacular degeneration and explained that the visual prognosis is guarded. In view of no definite treatment for this condition, the patient was prescribed spectacles. Heredomacular degenerations tend to be progressive and a long-term follow up is required.

Breast Cancer is the second most dangerous cancer in the world. Most of the women die due to breast cancer not only in India but everywhere in the world. In 2011, USA stated that one in eight women suffered from cancer. Breast cancer develops due to the abnormal cell division in the breast itself which results in the formation of either benign or malignant cancer. So, it is very important to predict breast cancer at an early stage and by providing proper treatment, many lives can be saved. This paper aims to give a comparative study by applying different machine learning algorithms such as Support Vector Machine, K-Nearest Neighbour, Naive Bayes, Decision Tree, K-means and Artificial Neural Networks on Wisconsin Diagnostic dataset to predict breast cancer at an early stage.

The advancement in technology is a root cause for the significant decrease in physical activities. Moreover, changes in food habits and increases in mental stress cause most common health disorders such as diabetes and high blood pressure. A statistical report on diabetes, available on the World Health Organization’s website, shows an exponential increase in the past few years. Across the world, there is a significant increase in the number of diabetic patients, from 108 million in 1980 to 422 million in 2014. The International Diabetes Federation claims that 425 million people currently suffer from diabetes. As diabetes adversely affects people from all age groups, it has become a cause of concern to predict this disorder well in advance. This motivated the authors to focus on diabetes prediction. In this chapter, the authors present the state of art in the arena of diabetes prediction. They identify challenges in existing techniques, namely Naive Bayes, decision tree, and support vector machine, and they propose effective solutions for these. The proposed model performs an analysis of publicly available data gathered from diabetic patients listing the causing factors of diabetes, most affected age groups, work style, and food habits. The model applies artificial neural networks for detecting diabetes and identifying its type. It is efficient in predicting the survival rate of diabetic patients. The prediction proves useful in preventing other health disorders such as retinopathy, nephropathy, and cardiovascular disorders that may arise due to diabetes. For evaluation of the proposed model, the authors use the “Pima Indian Diabetes” dataset. The dataset includes the medical history of 768 patients. It considers nine different symptoms as parameters for occurrence of diabetes. The highest accuracy of 85.09% proves the efficacy of the proposed work.

On the internet, a large number of information is available, which consolidates data and hyperlinks. With the large heterogeneous information resource, it is very difficult to locate the coveted data that matched with client needs and intrigue. To recover the relevant report from the user’s query, we use different types of algorithms. Page Ranking is additionally one of the groundbreaking algorithms to recover the best significant records that likewise lessen the client’s searching time. Web mining instruments are utilized by page ranking algorithm. Web mining device is utilized to arrange, group, and rank the report so the client can without much of a stretch finish the guide the query item and search the required data content. Mining can be done using two types, namely “Web Structure Mining” and “Web Content Mining”. In Web Structure Mining, rank the pages on the preface of their hyperlinks and in Web Content Mining, rank the pages on the premise of content of the pages. This paper portrays the examination and consolidates investigation of Web Structure Mining and Web Content Mining to enhance the positioning of pages.

With large number of documents on the web, there is a increasing need to be able to retrieve the best relevant document. There are different techniques through which we can retrieve most relevant document from the large corpus. Similarity between words, sentences, paragraphs and documents is an important component in various tasks such as information retrieval, document clustering, word-sense disambiguation, automatic essay scoring, short answer grading, machine translation and text summarization. Text similarity means user’s query text is matched with the document text and on the basis on this matching user retrieves the most relevant documents. Text similarity also plays an important role in the categorization of text as well as document. We can measure the similarity between sentences, words, paragraphs and documents to categorize them in an efficient way. On the basis of this categorization, we can retrieve the best relevant document corresponding to user’s query. This paper describes different types of similarity like lexical similarity, semantic similarity etc.

Background: Raised intaocular pressure is considered as a major risk factor for developing optic neuropathy. Intraocular pressure (IOP) depends on various systemic and local factors and it has been postulated that IOP increases proportionately with increase in systolic blood pressure and increase in degree of obesity. The aim of this study was to compare the Body Mass Index (BMI) and Intraocular Pressure (IOP) in adult population.Methods: Four hundred ninety nine participants (284 male, 215 female) aged between 20 to 70 years were included in the cross-sectional study. On the basis of BMI subjects were divided into four categories i.e. underweight, normal weight, overweight and obese as per revised body type classification for Indian population recommended by Ministry of Health and Diabetes foundation of India. The mean IOP difference was 14.6±1.8 as compared amongst the four categories.Results: The participants were divided into six categories according to age and the mean IOP of different age groups was calculated. The changes in the mean IOP of males was 15.8±2.5 mm of Hg and the mean IOP of females was 14.7±2.2 mm of Hg. The results of the current study were statistically significant p

Background: Patients admitted for cataract surgery have a fear of worst pain due to peribulbar injection for anaesthesia rather than surgery itself. The aim of this study is to find out the threshold of pain associated with the anaesthetic peribulbar injection for cataract surgery.Methods: This prospective randomised study was carried out at Ophthalmology department of Maharishi Markandeshwar University from 10 January 2017 to 22 March 2017. 100 patients undergoing elective cataract surgery were administered a peribulbar block. Before injection all patients were briefed about the procedure and counselled regarding the degree of pain that they may experience. Patients were asked to grade the pain of peribulbar anaesthetic injection, using a Visual Analogue Scale (VAS).Results: Focus of the study was on the degree of pain associated with anaesthetic peribulbar injection for cataract surgery. 100 patients (60 males and 40 females) were included in the study. 90 (90%) patients were having their first surgery, they were more apprehensive especially about the injection associated pain. 10 (10%) patients with history of previous cataract surgery were calm, confident and claimed that they felt no pain at all. 92 (92%) patients had just needle prick lead to heaviness or mild pain. Only small percentage of patients i.e. 8 (8%) had injection associated moderate to severe pain.Conclusions: The study revealed that the peribulbar anaesthesia for cataract surgery is safe and highly effective. The degree of pain associated with peribulbar injection is much less than what the patients actually have in their mind and fear of. The study also shows ‘pain threshold’ and anxiety level as major factors for pain perception.

Background: Diabetes mellitus (DM) is a major cause of avoidable blindness in developing and developed countries. The International Diabetes Federation (IDF)’s Diabetes Atlas reports that India has the highest number of people with diabetes (nearly 25%) in the world, and hence considered to be the “Diabetes Capital of the World”.Methods: This is a hospital record based study was planned to estimate the prevalence of Diabetes Mellitus in various age groups in rural population of Mullana, District Ambala(Haryana).Results: Out of 1050 patients screened 50 were found to be having Diabetes mellitus (DM) 1000 were non-diabetic i.e. prevalence of Diabetes mellitus (DM) was found to be 4.76%. Out of 362 males screened 22 were suffering from Diabetes mellitus (DM) i.e. prevalence of 6.07%. Whereas out of 688 females screened 28 were suffering from Diabetes mellitus (DM) i.e. prevalence of 4.06%. Prevalence of Diabetes mellitus (DM) in males was found to be maximum in age group of more than 70 years i.e. 6.97% as compare to female i.e.5.29%.Conclusions: Thus, the current study recorded high prevalence of Diabetes mellitus (DM) among rural population which should be a cause of concern for health care providers.

Background: As your eyes are one of the most important organ in the human body and vision is one of the most wonderful gift. But often many people neglect the importance of eye care and do not pay proper attention towards eye care. An estimated 180 million people world- wide are visibly disabled, of whom nearly 45 million are blind, four out of five of them live in developing countries. Blindness is one of the most significant social problems in India with uncorrected refractive errors as the second major cause accounting for 19.7% of blindness and low vision. Refractive error is an optical defect, intrinsic to the eye which prevents light from being brought to a single point focus on the retina, thus reducing normal vision. Diagnosis and treatment of refractive errors is relatively simple and is one of the easiest ways to reduce impaired vision. Three main types are considered as refractive errors: hypermetropia (farsightedness), myopia (nearsightedness) and astigmatism.Methods: This study was conducted in various schools of Haryana. It included 1000 school going children of age group of 6 to 12 years enrolled in 6 rural schools (619 students) and 4 urban schools (381 students). Cases were defined is visual acuity