Search

Breast cancer is the most frequently occurring cancer disease in women. It is reported almost 14% of cancers in Indian women are breast cancer. It becomes very crucial to predict breast cancer earlier to minimize the deaths. This research article helps to predict breast cancer earlier and reduce the immature deaths of women in India. In this paper, the authors have used the Logistic Regression method to classify the disease. The authors simulate the results using logistic regression with 10-fold cross-validations and with a different train-test split of the dataset. The 10-fold cross validations display its potential with almost 94% performance in the research paper. With all features and 90-10 , 80-20,50-50, 66-34 splits, and 10-fold cross-validations the authors achieve 96% accuracy. we have used different accuracy measures like accuracy, sensitivity, specificity, and kappa statistics to get the novelty of the model. In this study, the authors use the Wisconsin (Diagnostic) Data Set for Breast Cancer, Created by Dr. William H. Wolberg, General Surgery Dept., University of Wisconsin, Clinical Science Centre, Madison, WI 53792 wolberg@eagle.surgery.wisc.edu available at the UCI ML Repository website.

Suicide is nowadays a crucial public health issue. In various communities, people are much more affected by this severe tendency. Nowadays, suicide connects to mental illness. Along with depression, drug misuse is an equally important risk factor. Although anxiety, personality, and trauma-related issues, as well as genetic and mental disorders, also equally contributed to this health issue. This research work conducts to find the relation among suicidal tendencies, depression, anxiety, daily stresses, and mental health among all people, including employees, non-employee, students, old age, and all others. Step-by-step multiple linear regression, logistic regression analyses, confusion matrix, and cross-validation use for the data analysis. Suicidal illusions have a significant and positive relation with depression, anxiety, mental stress, and drug use disorder. In this research work regression technique showed that depression is the most crucial feature in the prediction of suicidal behavior, where anxiety, mental health, and daily stresses are the next, followed by respectively. Psychological problems and mental health issues with other factors such as gender problems, marital problems, and hallucinations play a role in suicidal thoughts [1]. Through this research, approximately 84 percent (%) of the data predict correctly.

Communication and transportation are important aspects of human life, but in Nepal, the geographically challenging topography and disconnected communities by more than 6000 rivers and rivulets, present great challenges in their daily lives for accessing basic health services, education, and household chores. Bridges are one of the major means of connecting the rural population in Nepal, but the lack of appropriate and safe means of crossing torrential rivers has resulted in increased suffering for local communities and developmental challenges for the actors involved in this sub-sector. The focus of this research is to technically analyse the potential bridge sites based on the major prioritization indices and to determine risk factors related to particular locations leading to solutions for the permanent transportation problem. The government has been trying its’ best in collaboration with various development actors to address the problem and help to reduce the risks related to potential loss of lives while crossing the mountainous terrain to various destinations. Many practices proposed or implemented have been proven to be risky, especially for children, men, women, and the elderly population. This research aims to establish a proven module to construct a trail bridge as a safer means of transport across the hills that would accelerate access to basic services such as education, healthcare, and provide people with new development prospects. The innovative idea involves supporting the construction of a trail bridge to support services such as education, medical facilities, and household chores. The data has been analysed using Multiple Regression Analysis (MRA). In this research, the authors predicted the risk factor of the possibility of death due to the lack of a bridge, which depends on the total population, total households, river type, width of the bridge, etc. The model was evaluated using 50-50%, 66-34%, and 80-20% train-test splits and 10-fold cross-validation and an accuracy of approximately 70% was achieved. The authors collected data by mobilizing local NGOs and informing the public through local radio to conduct a comprehensive study of nationwide bridge demand. The secondary source of data for post-bridge building assessment is extracted through the project management information system.

The liver is the largest internal organ of the human body. It is responsible for conversion of food intake into useful nutrients and also helps to store them. It is responsible for conversion of toxic molecules into harmless particles. But recent studies report significant deaths due to liver diseases. It is mainly due to unhealthy diet habits and unhealthy routine of people. In the race of doing work people are ignoring their health resulting in abnormal health and affecting the liver significantly. Therefore prediction of liver disease with high accuracy and speed is an important concern. The liver tissues undergo deformation or abnormalities comparatively slower than other body tissues, so detection becomes more difficult. In recent decades, the use of automatic decision making systems and tools has found a significant role in the medical field. As the medical field deals with human life, by using the knowledge of machine learning, deep learning, artificial intelligence, and big data we can help in rapid and appropriate treatment and cure. This will help physicians in making the correct decision at the right moment and appropriate procedure. In this regard, this study provides an extensive review of the progress of applying Artificial Intelligence in forecasting and detection liver diseases and then summarizes related limitations of the studies followed by future research.

COVID-19, a contagious disease which resulted in a worldwide pandemic just like “The Great Plague of Marseille” in 1720, “The First Cholera Pandemic” in 1820, and “The Spanish Flu” in 1920, claimed many lives. In December 2019 this disease was identified in the Chinese city Wuhan. After that researchers have found many relations in the ethnicity, occurrence, symptoms, severity, age and death. The study of these factors and their co-relation has helped in identifying who are at a greater risk of the disease and its repercussions. In this paper, authors have predicted the death rate of COVID-19 patients (Sex, Current Status, ICU, Medical Condition, Hospitalization) in the age group 10-19 years. Data has been analysed through Logistic Regression Analysis (LR). The proposed model is tested on the “COVID-19_Case_Surveillance_Public_Use_Data” from the UCI Machine Learning Repository.

Blood pressure (BP) is the pressure of circulating blood against the walls of blood vessels. Cholesterol is any of a class of certain organic particles called lipids [1]. High blood pressure along with high cholesterol are two of the main causes of heart disease. Heart disease, stroke, and other cardiovascular (blood vessel) diseases are among the primary cause of death. Approximately 10 million people every year die having high blood pressure and it was found that 6 in 10 Indians have abnormal levels of blood cholesterol [2]. An increase in blood cholesterol signifies an increase in a man's blood pressure, which can easily lead to abnormal blood pressure,e.g. high blood pressure. Generally, Prediction refers to the output of an algorithm after it has been trained on a dataset. Here Authors tried to predict whether a sample can have blood pressure and cholesterol or both present or not by analyzing some datasets. Generally, for making these types of predictions, machine learning algorithms are a very appropriate and most-used technique. A Multiple Linear Regression was applied in this study. Data has been analyzed through Multiple Linear Regression Analysis (MRA). The proposed model is tested on a Primary Data Set, prepared by Techno Engineering College Banipur’s students, and the relevant data of this Dataset has been collected from some districts in West Bengal, India. Through this research, approximately 76 percent of the data was predicted correctly.

The correct prediction of heart disease can prevent life threats, and incorrect prediction can prove to be fatal at the same time. In this paper machine learning algorithm is applied to compare the results and analysis of primary dataset. The dataset consists of 46 attributes among these Information gain is used to select 24 features for performing the analysis. Various promising results are achieved and are validated using accuracy and confusion matrix. The dataset consists of some irrelevant features which are handled and data are also normalized for getting better results. Using machine learning approach, 77.78% accuracy was obtained. Multiple linear regressions are used to construct and validate the prediction system. Our experimental result shows that multiple linear regressions are suitable for modelling and predicting cholesterol.

A novel deadly virus named COVID-19 was born in China in 2019. In early 2020, the COVID-19 virus spread worldwide, causing severe infections and deaths due to its infectious characteristics and no medical treatment. It has been termed the most consequential global crisis since the World Wars. The defence involved against COVID-19 spread includes sores like social distancing, personal hygiene, wearing a mask, and using sanitizer. The disaster, affecting billions of lives economically and socially improved its infection impact and has motivated the scientific community to come up with solutions based on computerized digital technologies for diagnosis, prevention, rescue, and estimation of COVID-19. An Artificial Intelligence based analysis made an effort to focus on the available data concerning COVID-19. All of these scientific efforts demand that the data brought to service for analysis should be open source to assist the extension, validation, and collaboration of the work in the fight against the global disaster pandemic. We survey and compare research works in these directions that are accompanied by open-source data and code. We hope that the article will provide the scientific community with an initiative to start open-source-extensible and transparent research in the collective fight against the COVID-19 pandemic. The authors collected data on student spending time on online platforms and facing health issues during the lockdown period from DELHI NCR. The authors gather information primarily from the ‘UCI Repository’“ https://archive.ics.uci.edu/ml/datasets”. The dataset for this study is extracted to predict the number of students who faced health issues during the lockdown period for COVID-19. The authors used logistic regression, 50-50,66-34,80-20 train-test splits and 10-fold cross-validation to analyze the data set.

Machine Learning (ML) is a specific type of artificial intelligence that allows systems to learn from data and detect patterns without much human intervention. As technology expands, machine learning provides an exciting opportunity in the health sector to improve the accuracy of diagnoses, personalise health care. Cancer has been characterised as a heterogeneous disease consisting of many different subtypes. In cancer research, it has become a necessity to diagnose and prognosis the type of cancer as early as it can facilitate the subsequent clinical management of patients. To accomplish the detection of cancer properly there are certain techniques in Machine learning which have been widely applied in cancer research for the development of predictive models, resulting in effective and accurate decision making. SVM, KNN, DT, LR, CNN, ANN, RF, MLP etc are such types of techniques in ML to model the progression and treatment of cancerous conditions. Apart from ML techniques there are certain image processing tools that are being introduced to detect cancer. Getting a clear cut classification from a biopsy image is an inconvenient task as the pathologist must know the detailed features of a normal and the affected cells. In this paper we are going to review the effectiveness of these various kinds of ML approaches to detect different types of cancer in some previous research papers which have already been done. The analyses and assessment techniques of the selected papers are discussed and an appraisal of the findings presented to conclude the article.

Psychiatry begun to develop empirical approaches only in the past 30 years to conceptualizing, assessing and documenting positive mental health. In society we accept mental disorders as normal and try to hide it. The author has come across the fact that how severe Mental illness affect our life and the measures that can be taken to heal the same. Authors have designed means of prediction of depression of an individual. Real data has been collected from people ranging from 18 to 59 years of age. Neurotic sufferings cannot be fully understood without understanding real health and sound approach towards life so, the authors have taken approach of all the factors including depression, anxiety, stress, eating disorder, short temper, hallucination, loneliness, suicidal attempt, constant guilt feeling, fearful all these and more, realistic disturbing state and trait that result in various mental diseases has been considered and analysed. Authors have used logistic regression model on the study they have come across for predicting depression of an individual.

Viral hepatitis is the inflammation and damage of liver cells due to infection. There are different causes of hepatitis, but the symptoms can be similar. As of 30 June 2022, 473 cases of acute hepatitis of unknown aetiology among children aged 16 years and under have been reported from the World Health Organization European Region. Simply more than (56.7%) of these cases have been reported from the UK. The majority (76.1%) of reported cases are five years old or younger. In this review, some machine learning order procedures are applied to Hepatitis informational index procured from UCI AI Storehouse. Naïve Bayes Classifier, Logistic Regression, and J48 Decision Tree are utilized as grouping algorithms and they have been contrasted agreeing with the filter-based selection method. For channel-based feature determination, Cfs Subset Eval, Data Gain Attribute Eval, and Principal Components have been utilized and their presentation of them is assessed as far as accuracy, review, F-Measure, and ROC Region. Among the pre-owned classification algorithms, Naïve Bayes Classifier has higher classification accuracy on the data set than the others with applied and nonapplied filter-based feature choices. Additionally, we proclaim that the best filter-based feature choice is Principal Components because of the highest classification precision for hepatitis patients.

The study of Homeless people is challenging, and describing Black Homelessness is especially difficult because of spotty record keeping[1]. The story of homeless Afro-Americans is often absent from the usual textbook study of homeless people. Homelessness is incompatibly experienced among historically marginalized groups in the united states, but for Black Americans, the distinction is especially stark[1]. Homeless condition is often occurred to the condition of poverty, less number of house, and less number of beds in the room. In most homes, there are fewer than three bedrooms and the income of each family is less, most of the rooms are already occupied. Some people in the Afro-American community are living their lives as renters what are the rent cost including the utilities like electricity, gas, water, etc is also very high. The communication system of the caucasian population is bad also, there is no phone in the family. The main reason for homelessness is that a huge number of people are immigrating within the last 5 years. The economic condition of Afro-Americans is at the poverty level, with few services, and often very poor educational opportunities. Here the data was analyzed using Multiple Regression Analysis (MRA). The proposed model is tested on the “Communities and Crime Data Set” from the UCI Machine Learning Repository: which is available at https://archive.ics.uci.edu/ml/datasets/communities+and+crime. Through this research, approximately 99.49 percent of the data was predicted correctly.

A Brain tumor is a growth of cells in the brain or near it. Brain tumors can happen in the brain tissue close by locations include nerves, the pituitary gland, central nervous system , meninges and the membranes that cover the surface of the brain[1]. A glioma is a tumor that forms in the brain or spinal cord A glioma is a tumor of the central nervous system that makes an appearance from glial stem or progenitor cells. Glial cells are a type of cell generally present in the nervous system. Gliomas predominantly occur in the brain and, rarely, in the spinal cord. They grow in approximately 6.6 per 100,000 individuals each year. They transpire at various ages, controlled by the subtype. Growing gliomas can compact areas of the brain where they occur and cause various symptoms including headaches, nausea, vomiting, cognitive impairment, seizures, gait imbalance, language impairment [2] A meningioma is a tumor that makes an appearance from the meninges — the membranes that surround the brain and spinal cord. In spite of the fact that not technically a brain tumor, it is included in this category because it may compress or squeeze the adjacent brain, nerves and vessels Meningiomas are tumors of the meninges, mostly benign and often managed by surgical resection, with radiation therapy and chemotherapy reserved for high-risk or refractory disease.[3]. Tumors can start nearly anywhere in the body. Tumors that start in the pituitary gland are called pituitary tumors. The anterior pituitary tumors start in the larger, front part of the pituitary gland known as the anterior pituitary. The posterior pituitary: The smaller, back part of the pituitary gland is an extension of brain tissue from the hypothalamus. The posterior pituitary stores and releases hormones made by the hypothalamus (vasopressin and oxytocin) into the bloodstream [4]. Machine learning applications in healthcare are already having a positive impact, and its potential is still in the early stages of being realized to deliver care[2]. In the future, machine learning in healthcare will become increasingly important as we strive to make sense of the ever-growing clinical data sets in healthcare. Heart disease cancer, and brain tumors are diagnosed using medical imaging procedures such as MRI scans, CT scans, and ECG. As a result, deep learning assists doctors in better analyzing diseases and providing the best treatment to patients. In this paper specific brain tumor segmentation and classification have been done using a Deep Convolutional Neural Network that incorporates a multiscale approach. . The proposed neural model can look over MRI images containing three types of tumors: glioma, meningioma, and pituitary tumor. Data has been collected from https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset?select=Training This dataset ecompasses 7023 images of human brain MRI images which are classified into 4 classes: glioma - meningioma - no tumor and pituitary. no tumor class images were taken from the Br35H dataset. The goal of this work was to aid clinical researchers in gaining a clear and intuitive understanding of the application of data-mining technology on clinical data to promote the production of research results that are beneficial to doctors and patients.

The objective of this research work is to classify brain tumor images into 4 different classes by using Convolutional Neural Network (CNN) algorithm i.e. a deep learning method with VGG16 architecture. The four classes are pituitary, glioma, meningioma, and no tumor. The dataset used for this research is a publicly available MRI Image dataset of brain tumor with 7023 images. The methodology followed in this project includes data pre-processing, model building, and evaluation. The dataset is pre-processed by resizing the images to 64x64 and normalizing the pixel values. The VGG16 architecture is used to build the CNN model, and it is trained on the pre-processed data for 10 epochs with a batch size of 64. The model is evaluated using the area under the operating characteristic curve (AUC) metric of the receiver. The results of this project show that the CNN model with VGG16 architecture achieves an AUC of 0.92 for classifying brain tumor images into four different classes. The model performs best for classifying meningioma with AUC of 0.90, followed by pituitary with AUC of 0.91, glioma with AUC of 0.93, and no tumor with AUC of 0.89. In conclusion, the CNN model with VGG16 architecture is an effective approach for classifying brain tumor images into multiple classes. The model achieves high accuracy in identifying different types of brain tumors, which could potentially aid in early diagnosis and treatment of brain tumors.