ABSTRACT
Big data in healthcare is a fast advancing area. With new diseases being continuously discovered, for instance, the COVID19 pandemic, there is a tremendous surge in data generation and a huge burden falls on the medical personnel where automation and emerging technologies can contribute significantly. Combining big data with the emerging technologies in healthcare is the need of the hour. In this chapter, first, we focus on the collection of big data in healthcare using emerging technologies like Radio Frequency Identification (RFID), Wireless Sensor Networks (WSN), and Internet of Things (IoT) along with its applications in medical field. We then explore the issues and challenges faced during data collection. Next, we bring out the different data analysis approaches. Then, the challenges and issues during data analysis are explored. Finally, the current research trends going on in the field are summarized. © 2022 Scrivener Publishing LLC.
ABSTRACT
BACKGROUND: The corona virus disease which is declared by the WHO as a pandemic and India has emerged as fifth worst hit nation in terms of total number of cases. It has significant impact on hematopoietic system, haemostasis as well as immune system. It would be of utmost importance to explore if the most routinely used tests could serve as an aid in determining patients clinical status or predicting severity of the disease. METHODS A prospective cross-sectional study was conducted on 130 RT -PCR positive patients over a period of 4 months (march -July 2021). The cases were subclassified based on disease severity into mild, moderate, and severe cases. The haematological parameter and infectious biomarkers in these cases were studied. RESULTS The median age was 45 years. Haematological parameters like TLC, Neutrophil count, NLR ratio and Inflammatory markers like LDH,CRP,D-Dimer and Ferritin were significantly higher in severe disease (P<0.05) in comparison to moderate and mild cases, while lymphocyte count was lower in severe cases. It showed a strong positive correlation with disease severity. The diagnostic values were assessed by ROC and AUC. The best cut off value obtained for Total count was16,195, with sensitivity66% and specificity96% .CRP was39.65, with sensitivity94% and specificity87% .D-dimer was0.555, with sensitivity100%and specificity 100% .Ferritin was481.0, with sensitivity100% and 86% specificity . CONCLUSION Our study suggests simple haematological parameters along with infectious biomarkers can be used in the identification of severe cases and as a screening tool in assessing clinical severity and guiding appropriate management. Copyright © 2022 Ubiquity Press. All rights reserved.
ABSTRACT
The world is witnessing the COVID-19 pandemic, which originated in the city of Wuhan, China, and has quickly spread to the whole world, with many cases having been reported in India as well. The healthcare system is going through unprecedented load on its resources while the available infrastructure is inadequate.COVID-19 samples are being tested at a massive scale and even small optimizations at this scale can save time, huge amounts of money, and resources. Particularly, the manual approach or even baseline greedy approach being used to allocate COVID-19 samples to medical labs across a state can lead to underutilization of resources. Hence, this work proposes a system to optimize the problem of allocation of medical samples to medical testing laboratories with high efficiency and minimal economic penalty. We use the Mixed Integer Programming (MIP) Model using high-performance MIP based solvers for custom applications by providing a tight integration with the branch-and-cut algorithms of the supported solvers to improve the results compared to baseline greedy approach. The system provides a transportation schedule optimized with respect to capacity of different labs and COVID-19 cases across the state of Karnataka. We tested the model on various datasets and observed significant improvement over the baseline greedy model.