ABSTRACT
Big data is a very large size of datasets which come from many different sources and are in a wide variety of forms. Due to its enormous potential, big data has gained popularity in recent years. Big data enables us to investigate and reinvent numerous fields, including the healthcare industry, education, and others. Big data specifically in the healthcare sector comes from a variety of sources, including patient medical information, hospital records, findings from physical exams, and the outcomes of medical devices. Covid19 recently, one of the most neglected areas to concentrate on has come under scrutiny due to the pandemic: healthcare management. Patient duration of stay in a hospital is one crucial statistic to monitor and forecast if one wishes to increase the effectiveness of healthcare management in a hospital, even if there are many use cases for data science in healthcare management. At the time of admission, this metric aids hospitals in identifying patients who are at high Length of Stay namely LS risk (patients who will stay longer). Once identified, patients at high risk for LS can have their treatment plans improved to reduce LS and reduce the risk of infection in staff or visitors. Additionally, prior awareness of LS might help with planning logistics like room and bed allotment. The aim of the suggested system is to precisely anticipate the length of stay for each patient on an individual basis so that hospitals can use this knowledge for better functioning and resource allocation using data analytics. This would contribute to improving treatments and services. © 2023 IEEE.
ABSTRACT
Sporadic occurrences of transmissible diseases have severe and long-lasting effects on humankind throughout history. These outbreaks have molded the political, economic, and social aspects of human life. Pandemics have redefined some of the basic beliefs of modern healthcare, pushing researchers and scientists to develop innovative solutions to be better equipped for future emergencies. Numerous attempts have been made to fight Covid-19-like pandemics using technologies such as the Internet of Things, wireless body area network, blockchain, and machine learning. Since the disease is highly contagious, novel research in patients' health monitoring system is essential for the constant monitoring of pandemic patients with minimal or no human intervention. With the ongoing pandemic of SARS-CoV-2, popularly known as Covid-19, innovations for monitoring of patients' vitals and storing them securely have risen more than ever. Analyzing the stored patients' data can further assist healthcare workers in their decision-making process. In this paper, we surveyed the research works on remote monitoring of pandemic patients admitted in hospitals or quarantined at home. First, an overview of pandemic patient monitoring is given followed by a brief introduction of enabling technologies i.e. Internet of Things, blockchain, and machine learning to implement the system. The reviewed works have been classified into three categories; remote monitoring of pandemic patients using IoT, blockchain-based storage or sharing platforms for patients' data, and processing/analyzing the stored patients' data using machine learning for prognosis and diagnosis. We also identified several open research issues to set directions for future research.
ABSTRACT
All the nations' administrative units are concerned about the COVID-19 outbreak in different regions of the world. India is also trying to control the spread of the virus with strict measures and has managed to slow down its growth rate. The administration of each country faces the challenge of maintaining records of corona patients. To address this challenge, this work builds a website from scratch using real-time APIs for data visualization. The website provides information on the number of active cases, death cases, recovery cases, and total cases of COVID-19 patients in each country. The data can be visualized using graphs, making it easier to compare the situation in different countries. The website allows for monitoring which country has a higher number of deaths, patients, favorable recovery rates, and a large number of active cases. The COVID-19 status regarding patients can be analyzed through graphical representation using real-time data. © 2023 IEEE.
ABSTRACT
This work focuses on the development of a portable physiological monitoring framework that can continuously monitor the patient's heartbeat, oxygen levels, temperature, ECG measurement, blood pressure, and other fundamental patient's data. As a result of this, the workload and the chances of being infected by COVID-19 of the health workers will be reduced and an efficient patient monitoring system can be maintained. In this paper, an IoT based continuous monitoring system has been developed to monitor all COVID-19 patient conditions and store patient data in the cloud server using Wi-Fi Module-based remote communication. In this monitoring system, data stored on IoT platform can be accessed by an authorized individual and ailments can be examined by the doctors from a distance based on the values obtained. If a patient's physical condition deteriorates, the doctor will immediately receive the emergency alert notification. This model proposed in this research work would be extremely important in dealing with the Corona epidemic around the world. © 2022 IEEE.
ABSTRACT
India as a country of contrast and diversity has witnessed digital evolution in different waves and stages. The technology is already an integral part of lives of millions in India;however, its application in the health management remains limited unlike developed economies. COVID-19 pandemic has plunged the country into universal, regional, or local lockdowns repeatedly since the last year. An unexpected and unforeseen impact of this has been the usage of technology for doctor-patient interactions through telemedicine. Hitherto limited to certain pockets, virtual interactions with doctors, ordering laboratory investigations through an application or procuring medicines through internet, are now part of mainstream patient behavior. This is a crucial change in the mindset but requires a lot more to be done at various levels to tap its full potential with rheumatologists being at the forefront and leading the change in their specialty. The pool of rheumatologists is very small and mostly concentrated in few urban areas, leading to diagnostic delay, suboptimal treatment, and poor outcomes. Technology could, therefore, become a catalyst for change and harbinger for greater clinician access. There are plenty of discussions about the impact and potential of deep learning, artificial intelligence, remote monitoring with wearables, etc., but plenty of them may not be relevant to Indian patients in the current scenario. Hence, the context, relevance, and applicability are the key for rheumatologists when making a judgment.
ABSTRACT
Artificial intelligence leverages sophisticated computation and inference to generate insights, enables the system to reason and learn, and empowers decision making of clinicians. Starting from data (medical images, biomarkers, patients' data) and using powerful tools such as convolutional neural networks, classification, and regression models etc., it aims at creating personalized models, adapted to each patient, which can be applied in real clinical practice as a decision support system to doctors. This chapter discusses the use of AI in medicine, with an emphasis on the classification of patients with carotid artery disease, evaluation of patient conditions with familiar cardiomyopathy, and COVID-19 models (personalized and epidemiological). The chapter also discusses model integration into a cloud-based platform to deal with model testing without any special software needs. Although AI has great potential in the medical field, the sociological and ethical complexity of these applications necessitates additional analysis, evidence of their medical efficacy, economic worth, and the creation of multidisciplinary methods for their wider deployment in clinical practice. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
This study aims to compare the performance of data classifying for COVID-19 patients. In this study, the patients' data acquired from the department of disease control (1,608,923 patients) are collected. They are patients records from January 2020 to October 2021. The study focus on three main data classification techniques: Random forest;Neural Network;and Naïve Bayes. The authors study the comparative performance of the techniques. We apply the split test method to evaluate the performance of data prediction. The data are divided into two parts: training data. The results show that Random Forest has an accuracy of 93.51%. Neural network has an accuracy of 93.02%. Naive Bayes has an accuracy of 27.54%. This presents the Random Forest with the highest accuracy Figure for screening of COVID-19 patients © 2022 IEEE.
ABSTRACT
Patients with COVID-19 generally recover within a fortnight or a month. However, some patients, even those with milder types of the disease, experience symptoms after they have recovered. Symptoms of COVID-19 might continue for months at a time. The virus affects the heart, brain, and lungs, perhaps leading to long-term health-related problems. Thus, it is critical to keep track of any post-COVID symptoms to prevent further complications. Keeping that in focus, two apps are created to monitor these symptoms in people who have recovered from COVID 19 with comorbidities includes Diabetes, coronary artery diseases and hypertension. In this project, the patient's data was obtained from selected hospitals in Pune, and stored in Google Firebase. This data was used while making the backend algorithms for the apps. Android Studio and Figma were used to design and develop these apps. One app will be used by the patients, which allows them to post their health conditions if they are suffering with symptoms of post COVID complications and another App will be used by the investigators to monitor these symptoms and provides an access to post the advises pertaining to the patient's health condition. The biggest challenge is with patients suffering from conditions like hypertension, diabetes and other chronic illness which can be fatal if not monitored and addressed, specially for the elderly to frequently visit the hospital just for monitoring. The prime objective of the app developed in this work is to provide monitoring and to prevent post COVID complications and save the life of patients who have recovered from COVID and already have underlying issues. These apps allow researchers/Doctors to contact the patients personally to counsel them against the symptoms they are experiencing. Both these apps were tested in Android 8 Oreo and are functional in Android 8 Oreo, Android 9 Pie, Android 10, and Android 11 supported devices. These applications will soon be deployed in the Play Store. © 2023 IEEE.
ABSTRACT
Covid-19 spread is worldwide;India is now at the second place where this epidemic is spreading with high rate. The state of Uttarakhand, a hilly state of India also has a significant impact of Covid-19. This paper suggests that machine learning techniques with IOT can equipped the doctors, and lab technicians to deal with this pandemic. Here, we also design a prediction system to help the doctors so that they can keep the records of infected patients. We used IoT, machine learning and ensemble methods for healthcare to store infected patient's data in the cloud database, and enable doctors/others to screen patient's data about their disease. We developed a decision support system to detect the diseases quickly and the treatment can be initiated immediately. © 2022 IEEE.
ABSTRACT
Early in 2020, the coronavirus Covid-19, which is produced by the SARS-CoV -2 strain, first gained international attention as a severe health threat. Covid-19 spread quickly around the world, forcing everyone to fight with preventative measures like masks, hand washing, and preserving social distance. But to prevent the virus, vaccination has been playing a key role. Vaccination records that contain patient data make this system very complicated because there is a risk of a privacy breach. Hackers may steal the personal health information of individuals or may carry out cyberattacks against any national health data server. Additionally, there is a chance that dishonest people can purchase and sell fake vaccine certificates on the black market. Blockchain can provide a solution to this regard by its features like data immutability, privacy, transparency and decentralization. For people, governments, and organizations interested in blockchain-based systems, we analyze the blockchain based vaccination management system in this study and provide a current summary. We envision our study to motivate more blockchain based systems. © 2022 IEEE.
ABSTRACT
The history of the medical robot is not very far from the first experiment in the 1980s. Nowadays robot in the medical sector plays a vital role in monitoring patient's health condition from distance. This paper aimed at developing an auxiliary medical solution that could provide a wide range of non-invasive diagnoses carried out by an automated robot whose motion can also be controlled manually using either a mobile application or voice command. The authors also incorporate modern features of video conferences and automated patient data management systems using the Internet of Things (IoT) which eventually facilitate medical practitioners in proper investigation from distance. The results of the clinical trial among 6 persons indicated that the robot could measure different health parameters properly using the proposed non-invasive method. The non-invasive results are verified by standard testing equipment and conventional clinical investigation and are also presented in this paper. The developed medical robot having a wide range of functionality could play a significant role in reducing human workload and ensuring timely medical assistance during a challenging crisis pandemic period like COVID-19. © 2023 IEEE.
ABSTRACT
Patient sensing and data analytics provide information that plays an important role in the patient care process. Patterns identified from data and Machine Learning (ML) algorithms can identify risk/abnormal patients' data. Due to automatization this process can reduce workload of medical staff, as the algorithms alert for possible problems. We developed an integrated approach to monitor patients' temperature applied to COVID-19 elderly patients and an ML process to identify abnormal behavior with alerts to physicians. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Chest X-ray images provide critical information for the diagnosis of COVID-19. Machine learning techniques for COVID-19 detection require substantial amounts of chest images to discover correct patterns. However, concerns over confidentiality and privacy have limited access to patients' data. The distribution of samples across normal/abnormal classes is typically biased or skewed due to unavailability of sufficient data because of COVID-19 recency. Existing synthetic COVID-19 data generation approaches fail to generate high-resolution and diverse images. Moreover, there is a lack of research identifying whether synthetic images represent patients at high risk of severe disease, which is critical for making treatment decisions. We propose a High-Resolution COVID-19 X-Ray Generator (HRCX) framework based on a combination of a generative adversarial network and a predictive learning model that uses limited available chest images to generate balanced diverse high-resolution COVID-19 images with their severity scores. We use StyleGAN2 with adaptive discriminator augmentation, which controls generated images' style and generates diverse patterns. In addition, we provide a COVID-19 severity index to aid in predicting illness severity. We generated 3300 high-quality and diverse COVID-19 X-Ray images with a resolution of 512x512, which we further increased to 1024x1024 with the help of Super-Resolution. Additionally, severity scores of 300 images are calculated and demonstrated to be effective in both normal and infected cases. © 2023 ACM.
ABSTRACT
Background Prolonged periods of ventilation can be associated with significant physical and psychological short- and longterm effects, research supports early rehabilitation in adult icu, however little evidence is available in PICU and potential benefits. Method An early mobility guideline was implemented into PICU in November 2020, focusing on early rehabilitation, mobilizing patients more frequently, and reducing levels of sedation through regular assessment of COMFORT and Delirium scoring. Baseline data from November 2019- February 2020- was obtained to compare ventilation hours of patients with respiratory aetiology to patients post early mobility implementation from November 2020- February 2021. Patients from birth to 18 years with respiratory aetiology, requiring invasive ventilation were screened, and retrospective data was obtained from electronic notes, anonymised and entered into SPSS. Results Findings identified Before Early mobility group to have a mean ventilation time of 68.90 hours and After early mobility group 69.25 hours. No significant differences were identified between the two groups. Patients had a diagnosis of respiratory aetiology, however the COVID 19 pandemic altered respiratory pathogens seen within PICU, changing the cohort of patients seen in both groups. However, further analysis highlighted reductions in patients requiring NIV after extubation, 46.5% Before and 23.7% After Early Mobility cohort, and risks of accidental extubation Before Early mobility group 1% accidental extubation and After group 2 5.3%, identifying no significant risk. Conclusion PICU early mobility studies are limited (Johnston et al 2019) and behind the wealth of studies available within AICU (Cameron et al 2015). However critically ill children are at risk of co-morbidities and early mobility within PICU is vital. The service evaluation identified no significant change in ventilation hours After Early mobility guideline implementation, or risks of accidental intubation. However, highlighted a reduction of the use of NIV, highlighting the need for further research within PICU.
ABSTRACT
This research develops a COVID-19 patient recovery prediction model using machine learning. A publicly available data of infected patients is taken and pre-processed to prepare 450 patients' data for building a prediction model with 20.27% recovered cases and 79.73% not recovered/dead cases. An efficient logistic regression (ELR) model is built using the stacking of random forest (RF) and logistic regression (LR) classifiers. Further, the proposed model is compared with state-of-art models such as logistic regression (LR), support vector machine (SVM), decision tree (C5.0), and random forest (RF). All the models are evaluated with different metrics and statistical tests. The results show that the proposed ELR model is good in predicting not recovered/dead cases and handling imbalanced data. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
The future of the healthcare sector and its systems are beginning to take shape by combining technological innovations with traditional techniques to generate new and efficient solutions for patient care and data storage. Most conventional medical information management and storage systems are centralized, which means there is a risk of data loss in the event of malicious attacks or even natural disasters because of the single point of failure that centralized systems have. Blockchain technology is decentralized and emerging, offering the potential to significantly revolutionize how data is stored and managed in the healthcare industry. This paper presents the advantages of using blockchain in the healthcare sector, as this technology has a strategic role in both the management of stored data and the creation of predictive systems that could prevent a pandemic like the one generated by the SARS-Cov-2 virus. We present different existing studies and the method addressed in the ongoing STAMINA project. © 2022 IEEE.
ABSTRACT
BACKGROUND: Supplemental oxygen therapy is central to the treatment of acute hypoxaemic respiratory failure, a condition which remains a major driver for morbidity and mortality in intensive care. Despite several large randomised clinical trials comparing a higher versus a lower oxygenation target for these patients, significant differences in study design impede analysis of aggregate data and final clinical recommendations. METHODS: This paper presents the protocol for conducting an individual patient data meta-analysis where full individual patient data according to the intention-to-treat principle will be pooled from the HOT-ICU and HOT-COVID trials in a one-step procedure. The two trials are near-identical in design. We plan to use a hierarchical general linear mixed model that accounts for data clustering at a trial and site level. The primary outcome will be 90-day all-cause mortality while the secondary outcome will be days alive without life-support at 90 days. Further, we outline 14 clinically relevant predefined subgroups which we will analyse for heterogeneity in the intervention effects and interactions, and we present a plan for assessing the credibility of the subgroup analyses. CONCLUSION: The presented individual patient data meta-analysis will synthesise individual level patient data from two of the largest randomised clinical trials on targeted oxygen therapy in intensive care. The results will provide a re-analysis of the intervention effects on the pooled intention-to-treat populations and facilitate subgroup analyses with an increased power to detect clinically important effect modifications.
Subject(s)
COVID-19 , Respiratory Insufficiency , Humans , Lung , Respiratory Insufficiency/therapy , Oxygen , Critical Care/methods , Randomized Controlled Trials as Topic , Meta-Analysis as TopicABSTRACT
Motivated by the quest for decreased healthcare costs and further fueled by the COVID pandemic, wearable devices have gained major attention in recent years. Yet, their secure usage and patients' privacy continue to be concerning. To address these issues, the paper presents SWeeT, a novel lightweight protocol for allowing flexible and secure access to the collected data by multiple caregivers while sustaining the patient's privacy. Particularly, SWeeT deploys Physically Unclonabale Functions (PUFs) to generate encryption keys to safeguard the patients' data during transmission. The computation overhead is significantly reduced by applying very simple encryption operations while enabling frequent change of the keys to sustain robustness. SWeeT is shown to counter impersonation, Sybil, man-in-the-middle, and forgery attacks. SweeT is validated through experiments using implementation on an Artix7 FPGA and through formal security analysis. © 2022 IEEE.
ABSTRACT
BACKGROUND: Numerous clinical trials have been initiated to find effective treatments for COVID-19. These trials have often been initiated in regions where the pandemic has already peaked. Consequently, achieving full enrollment in a single trial might require additional COVID-19 surges in the same location over several years. This has inspired us to pool individual patient data (IPD) from ongoing, paused, prematurely-terminated, or completed randomized controlled trials (RCTs) in real-time, to find an effective treatment as quickly as possible in light of the pandemic crisis. However, pooling across trials introduces enormous uncertainties in study design (e.g., the number of RCTs and sample sizes might be unknown in advance). We sought to develop a versatile treatment efficacy assessment model that accounts for these uncertainties while allowing for continuous monitoring throughout the study using Bayesian monitoring techniques. METHODS: We provide a detailed look at the challenges and solutions for model development, describing the process that used extensive simulations to enable us to finalize the analysis plan. This includes establishing prior distribution assumptions, assessing and improving model convergence under different study composition scenarios, and assessing whether we can extend the model to accommodate multi-site RCTs and evaluate heterogeneous treatment effects. In addition, we recognized that we would need to assess our model for goodness-of-fit, so we explored an approach that used posterior predictive checking. Lastly, given the urgency of the research in the context of evolving pandemic, we were committed to frequent monitoring of the data to assess efficacy, and we set Bayesian monitoring rules calibrated for type 1 error rate and power. RESULTS: The primary outcome is an 11-point ordinal scale. We present the operating characteristics of the proposed cumulative proportional odds model for estimating treatment effectiveness. The model can estimate the treatment's effect under enormous uncertainties in study design. We investigate to what degree the proportional odds assumption has to be violated to render the model inaccurate. We demonstrate the flexibility of a Bayesian monitoring approach by performing frequent interim analyses without increasing the probability of erroneous conclusions. CONCLUSION: This paper describes a translatable framework using simulation to support the design of prospective IPD meta-analyses.
Subject(s)
COVID-19 , Humans , COVID-19/epidemiology , Computer Simulation , Research Design , Sample Size , Bayes TheoremABSTRACT
India as a country of contrast and diversity has witnessed digital evolution in different waves and stages. The technology is already an integral part of lives of millions in India;however, its application in the health management remains limited unlike developed economies. COVID-19 pandemic has plunged the country into universal, regional, or local lockdowns repeatedly since the last year. An unexpected and unforeseen impact of this has been the usage of technology for doctor-patient interactions through telemedicine. Hitherto limited to certain pockets, virtual interactions with doctors, ordering laboratory investigations through an application or procuring medicines through internet, are now part of mainstream patient behavior. This is a crucial change in the mindset but requires a lot more to be done at various levels to tap its full potential with rheumatologists being at the forefront and leading the change in their specialty. The pool of rheumatologists is very small and mostly concentrated in few urban areas, leading to diagnostic delay, suboptimal treatment, and poor outcomes. Technology could, therefore, become a catalyst for change and harbinger for greater clinician access. There are plenty of discussions about the impact and potential of deep learning, artificial intelligence, remote monitoring with wearables, etc., but plenty of them may not be relevant to Indian patients in the current scenario. Hence, the context, relevance, and applicability are the key for rheumatologists when making a judgment. © 2022 Wolters Kluwer Medknow Publications. All rights reserved.