Healthcare Diagnostics Service Using Federated Learning

Healthcare systems around the world rely on powerful computational prediction tools in order to make accurate diagnostics with regard to the human body. In order to estimate the severity of lung damage post-COVID infection, healthcare providers rely on AI prediction tools to perform diagnosis. While such tools exist at a rudimentary level, there is a growing demand for more reliable and democratised systems that train models over a diverse data-set. To that end, the focus of this research paper turns to federated learning, a distributed machine learning paradigm. The system proposed consists of a central server that pools features and weights across various nodes, thereby cutting bias in the prediction models. This also achieves data decentralisation which ensures patient privacy. An end-to-end application is realised that facilitates distributed training of batch data that is visualised in real-time with the help of sockets. The application also features an inference service, classifying chest x-rays based on whether the image displays damage in case of Pneumonia. © 2023 IEEE.

Prediction of Noninvasive Ventilation Failure in COVID-19 Patients: When Shall We Stop?

INTRODUCTION: In coronavirus disease 2019 (COVID-19), there are no tools available for the difficult task of recognizing which patients do not benefit from maintaining respiratory support, such as noninvasive ventilation (NIV). Identifying treatment failure is crucial to provide the best possible care and optimizing resources. Therefore, this study aimed to build a model that predicts NIV failure in patients who did not progress to invasive mechanical ventilation (IMV). METHODS: This retrospective observational study included critical COVID-19 patients treated with NIV who did not progress to IMV. Patients were admitted to a Portuguese tertiary hospital between October 1, 2020, and March 31, 2021. The outcome of interest was NIV failure, defined as COVID-19-related in-hospital death. A binary logistic regression was performed, where the outcome (mortality) was the dependent variable. Using the independent variables of the logistic regression a decision-tree classification model was implemented. RESULTS: The study sample, composed of 103 patients, had a mean age of 66.3 years (SD=14.9), of which 38.8% (40 patients) were female. Most patients (82.5%) were autonomous for basic activities of daily living. The prediction model was statistically significant with an area under the curve of 0.994 and a precision of 0.950. Higher age, a higher number of days with increases in the fraction of inspired oxygen (FiO2), a higher number of days of maximum expiratory positive airway pressure, a lower number of days on NIV, and a lower number of days from disease onset to hospital admission were, with statistical significance, associated with increased odds of death. A decision-tree classification model was then obtained to achieve the best combination of variables to predict the outcome of interest. CONCLUSIONS: This study presents a model to predict death in COVID-19 patients treated with NIV in patients who did not progress to IMV, based on easily applicable variables that mainly reflect patients' evolution during hospitalization. Along with the decision-tree classification model, these original findings may help clinicians define the best therapeutical approach to each patient, prioritizing life-comforting measures when adequate, and optimizing resources, which is crucial within limited or overloaded healthcare systems. Further research is needed on this subject of treatment failure, not only to understand if these results are reproducible but also, in a broader sense, helping to fill this gap in modern medicine guidelines.

Artificial Neural Network based Automatic Prediction Unit for COVID 19 in Asymptomatic Patient

In this pandemic situation of COVID 19 virus attack in human race for the last few months the disease occurrence prediction and patient's condition monitoring is being a major thrust area in the global medical field by the researchers. The major problem of this disease is that the asymptomatic patient are acting as a carrier without knowledge. Which leads to a major threat in spreading the disease which even cause death in other people even after maintaining the social distancing. More over according to the research, rate of death is more in heart related disease affected patients. There is a vital need to detect cases at the early stages to minimize mortality especially in heart patients. In our work, we have designed and developed a trained Artificial Neural Network which can predict COVID 19 in asymptomatic patients and also can used for conditioning monitoring in COVID affected patients. Here we have used 2500 patients' details as training and testing data for the ANN network and 50 Symptoms as input variables. The Patients data are collected in Government Sivagangai Medical College and Hospital, Thirupathur village, Sivagangai district, Tamilnadu, India. © 2022 IEEE.

A Domain Model for SARS-Co V-2 Rational Vaccine Design to Engineer a Prediction Tool for Binding Affinity and Antigenicity

One of our greatest present challenges are designing vaccines against SARS COV2 and its variants. Rational vaccine design uses computational methods prior to development of a vaccine for testing in animals and humans the latest methods in rational vaccine design use machine learning techniques to predict binding affinity and antigenicity but offer the researchers only isolated stand-Alone tools. A difficulty that software engineers and data scientist face in development of tools for doctors and researchers is their lack of knowledge of the medical domain. This paper presents a set of domain model developed in collaboration between software engineers and a medical researcher in the process of building a tool scientists could use to predict binding affinity and antigenicity of potential designs of SARS COV2 vaccines. A domain model visualizes the real-world entities and their interrelationships, that together define the domain space. This domain model will be useful to other software engineers trying to predict other characteristics of vaccines, such as potential autoimmunity response. © 2021 IEEE.

Optimization and Adaptation of a Resource Planning Tool for Hospitals Under Special Consideration of the COVID-19 Pandemic

Hospitals and health-care institutions need to plan the resources required for handling the increased load, i.e., beds and ventilators during the COVID-19 pandemic. BaBSim.Hospital, an open-source tool for capacity planning based on discrete event simulation, was developed over the last year to support doctors, administrations, health authorities, and crisis teams in Germany. To obtain reliable results, 29 simulation parameters such as durations and probabilities must be specified. While reasonable default values were obtained in detailed discussions with medical professionals, the parameters have to be regularly and automatically optimized based on current data. We investigate how a set of parameters that is tailored to the German health system can be transferred to other regions. Therefore, we use data from the UK. Our study demonstrates the flexibility of the discrete event simulation approach. However, transferring the optimal German parameter settings to the UK situation does not work-parameter ranges must be modified. The adaptation has been shown to reduce simulation error by nearly 70%. The simulation-via-optimization approach is not restricted to health-care institutions, it is applicable to many other real-world problems, e.g., the development of new elevator systems to cover the last mile or simulation of student flow in academic study periods. © 2021 European Union

Detecting Anomalies in Daily COVID-19 Cases Data From Brazil Capitals Using GSP Theory

The COVID-19 pandemic has created an urgency for studies to understand the spread of the virus, in particular, to predict the number of daily cases. This type of investigation depends heavily on the data collected and made available manually. Therefore, data are susceptible to human errors which can cause anomalies in the dataset. Understanding and correcting anomalies in real-world application data is an important task to ensure the reliability of the data analysis and prediction tools. This paper presents a spectral anomaly detection and correction strategy that uses concepts from the graph signal processing (GSP) theory. The main advantage of the introduced strategy is to analyze the variation in the daily number of cases with the proximity relation between the investigated locations. Experiments were carried out with real meteorological and mobility data for predicting the number of COVID-19 cases by the classic prediction model known as autoregressive integrated moving average exogenous (ARIMAX). Then, the anomaly detection method was applied to determine the relationship between the prediction errors and the anomalous variations identified by the tool. The results show a strong relationship between the anomalous variations and the errors made by the model and attest to the increase in the accuracy of the prediction model after the normalization of the anomalies. © 2021 IEEE