RESUMEN
A disease is an abnormal condition that negatively impacts the functioning of the human body. Pathology determines the causes behind the disease and identifies its development mechanism and functional consequences. Each disease has different identification methods, including X-ray scans for pneumonia, covid-19, and lung cancer, whereas biopsy and CT-scan can identify the presence of skin cancer and Alzheimer's disease, respectively. Early disease detection leads to effective treatment and avoids abiding complications. Deep learning has provided a vast number of applications in medical sectors resulting in accurate and reliable early disease predictions. These models are utilized in the healthcare industry to provide supplementary assistance to doctors in identifying the presence of diseases. Majorly, these models are trained through secondary data sources since healthcare institutions refrain from sharing patients' private data to ensure confidentiality, which limits the effectiveness of deep learning models due to the requirement of extensive datasets for training to achieve optimal results. Federated learning deals with the data in such a way that it doesn't exploit the privacy of a patient's data. In this work, a wide variety of disease detection models trained through federated learning have been rigorously reviewed. This meta-analysis provides an in-depth review of the federated learning architectures, federated learning types, hyperparameters, dataset utilization details, aggregation techniques, performance measures, and augmentation methods applied in the existing models during the development phase. The review also highlights various open challenges associated with the disease detection models trained through federated learning for future research.
Asunto(s)
Enfermedad de Alzheimer , COVID-19 , Neoplasias Pulmonares , Médicos , Humanos , Biopsia , COVID-19/epidemiologíaRESUMEN
OBJECTIVE: The objective of this paper is to prepare the government and citizens of India to take or implement the control measures proactively to reduce the impact of coronavirus disease 2019 (COVID-19). METHOD: In this work, the COVID-19 outbreak in India has been predicted based on the pattern of China using a machine learning approach. The model is built to predict the number of confirmed cases, recovered cases, and death cases based on the data available between January 22, 2020, and April 3, 2020. The time series forecasting method is used for prediction models. RESULTS: The COVID-19 effects are predicted to be at peak between the third and fourth weeks of April 2020 in India. This outbreak is predicted to be controlled around the end of May 2020. The total number of predicted confirmed cases of COVID-19 might reach around 68 978, and the number of deaths due to COVID-19 are predicted to be 1557 around April 25, 2020, in India. If this outbreak is not controlled by the end of May 2020, then India will face a severe shortage of hospitals, and it will make this outbreak even worse. CONCLUSION: The COVID-19 pandemic may be controlled if the Government of India takes proactive steps to aggressively implement a lockdown in the country and extend it further. This presented epidemiological model is an effort to predict the future forecast of COVID-19 spread, based on the present scenario, so that the government can frame policy decisions, and necessary actions can be initiated.