Index IntroductionBackgroundImportance of the ProjectStakeholder and Customer PerspectiveProject Objectives and ScopeSummaryWhile machine learning is not a new technology, there are new developments coming faster than most some people can learn them. It's cutting edge technology in every sense of the word. If so, it should be handled with care. It could very well provide results with an accuracy rate impossible for medical applications. The capabilities required for the project are well within the feasible range. Most of the planned features revolve around dataset processing. Due to the above, a visible challenge here too is the problem of managing huge amounts of data and processing it accurately to obtain adequate results. The central metric of success is how accurately the machine learning algorithm predicts the diseases for which it is trained. It is expected to be above 96% - 98% to really make a difference, as medical diagnosis has very rigorous standards. The secondary parameters are the response and loading time of each module. A high value of module latency can make any user impatient. Apart from these 2, the other parameter is the number of features that work without bugs. This parameter should also ideally be above 90%, otherwise it can frustrate users. Say no to plagiarism. Get a tailor-made essay on "Why Violent Video Games Shouldn't Be Banned"? Get an Original Essay Although machine learning is a nascent specialization, we found an abundance of algorithms, not only in proposed state, but rigorously examined in research papers. Convolutional neural networks have been suggested for their high accuracy. Chinese researchers used convolutional neural networks in a large-scale analysis of hospital medical records in China and reported high accuracy in prediction across symptoms. Apart from this, many researchers have tested SVM and ANN, which conventionally were image classification algorithms. They also reported high accuracy. So far, our work has focused on training our algorithm, using openly available medical data. The algorithm did not show the required accuracy and will need to be trained further. The other module we created is the GUI. We built a web-based GUI in Flask, an open source Python framework. These two modules are the final points of the project and building them first allows you to conveniently build the ones in the middle. Comparing existing and actual results shows an accuracy gap that needs to be filled. However, we managed to achieve more versatility, which was probably the reason why the algorithm was less accurate. IntroductionHealthcare, although a new venture for the AI ​​machine learning industry, remains one of the most crucial sectors of public service. , one to which much funding and research has been devoted. With healthcare, we are arguably looking at the most cardinal and relevant applications of the advanced capabilities of artificial intelligence and machine learning. With the growth of big data in the biomedical and healthcare communities, accurate analysis of medical data benefits early disease detection, patient care, and community services. However, the accuracy of the analysis decreases when the quality of medical data is incomplete. In addition, different regions have unique characteristics of some regional diseases, which can weaken theprediction of epidemics. In this case, it is advisable to use mathematical models to eliminate any imperfections and aberrations, in order to have the rigorous standards of accuracy required by the field of medical diagnosis. AI presents challenges because of the complexity involved in finding the balance between too much and not enough. We can design systems that can process an extremely wide variety of inputs, but we can't actively ensure that the AI ​​responds the way we want. It may present us with output intended for another input, or it may not be able to process it due to the load caused by heavy processing on the interpreter. Therefore, the challenge is not just about managing inputs or creating features, but also about efficiency. Background There are many virtual assistants available on the market that offer high precision in handling inputs, especially Siri and Google Assistant. Siri is a virtual assistant that is part of Apple Inc.'s iOS, watchOS, macOS, HomePod, and tvOS operating systems. The assistant uses voice queries and a natural language user interface to answer questions, provide recommendations, and perform actions by delegating requests to a variety of Internet services. The software adapts to users' linguistic uses, searches and individual preferences, with continuous use. Google Assistant is an artificial intelligence-based virtual assistant developed by Google, mainly available on mobile and smart home devices. Unlike Google Now, Google Assistant can engage in two-way conversations. Amazon Alexa is a virtual assistant developed by Amazon, first used in the Amazon Echo and Amazon Echo Dot smart speakers developed by Amazon Lab126. It can interact with voice, play music, create to-do lists, set alarms, stream podcasts, play audiobooks, and provide real-time weather, traffic, sports, and other information, such as news. Alexa can also control various smart devices using itself as a home automation system. While nowhere near accurate, the application understands most commands with enough precision to extract results across them. There are many assistants in the healthcare sector as well. However, not many of them offer a service catalog along with machine learning applications. In addition to these assistants, there are also systems without AI features, such as WebMD, that provide symptom matching without the use of AI features. While you come across many AI-rich healthcare software, what you don't often see is these services consolidated into one package. For users, especially patients on drug therapy or bedridden, it is essential to receive assistance without the hassle of having to juggle multiple software platforms, annoyed as they already are by having to juggle drugs and healthcare routines.Importance of the projectThe purpose of the project in creating a smart yet lightweight healthcare assistant. This application will be able to help healthcare workers and other hospital staff work efficiently. This also aims to have a basic machine learning capability for disease prediction. In an age where medical diagnosis and treatment have made great strides, it is unfair to deny someone adequate healthcare due to lack of means. This project aims to make healthcare less exclusive than it currently is and to facilitate research and use of services. We often see the lack of adequate software to help with thesecases. The software can avoid the need to revisit doctors or spend hours independently researching complex medical terms and appendices, as many diagnosed patients tend to do. The use of a Bot here can automate such mundane tasks and still leave the patient satisfied and confident. Stakeholder and Customer Perspective The stakeholder perspective is crucial to the success of this project. This is partly due to the fact that medical diagnosis is an extremely delicate field and even the smallest error, evidently inevitable even in the most sophisticated software, can lead to a worsening of the patient's condition. It is also crucial to involve patients, as their familiarity with the equipment, both hardware and software, is necessary for the technology to function well. Stakeholders here include doctors and nurses Health insurance companies Hospitals Health departments (state and national/federal) Biotechnology manufacturers. Doctors and nurses are very conservative when it comes to the adoption of technology, especially software. Due to the sensitivity of the data and the need for accuracy, most doctors do not adopt or recommend any software, or indeed any new technology, until it has been rigorously tested and reviewed by various independent evaluators. In this respect health insurance companies are very similar to doctors and nurses, as the amount of money involved is extremely large. However, customers looking for health insurance plans were eager for this type of technology, evident from the high amount of Google searches for those choosing health insurance plans. Hospitals were also more available, provided they were supported by doctors. The use of cutting-edge technology in medical diagnosis is something that many hospitals in California, Massachusetts and New York were willing to try. Many, in fact, had already carried out large-scale tests on patients. Health departments place many restrictions on such technology unless it is used noninvasively or is complementary to orthodox methods. There are numerous regulations relating to the use of cutting-edge technologies in the medicinal field. Biotechnology manufacturing involves the production of diagnostic equipment, measurement equipment, support equipment, surgical instruments, etc. Manufacturers are generally enthusiastic about such technologies. It is also crucial to get their support as it facilitates synchronization between devices. Potential users, such as those who frequent forums related to healthcare, wearable technology, etc., seemed open to the idea, as anticipated. They seemed to like the idea of ​​machine learning being used to predict diseases, as well as other smaller features. Project Objectives and Scope The project aims to create an intelligent yet lightweight healthcare assistant. This application will be able to help healthcare workers and other hospital staff work efficiently. This also aims to have a basic machine learning capability for disease prediction. The main goal is to offer doctors and patients a way to easily perform mundane healthcare tasks, as well as advanced prediction services. We plan to offer several services in parallel. These services include, but are not limited to, Hospital Search Data Keeper Symptom Matching through Machine Learning Insurance Selector Wearable Technology Manager Information Catalog Doctor Search. In addition to the above features, we also aim to make the software robust, accurate and fast. Summary Health care, through a.