Predicting Big Data Adoption in Companies With an Explanatory and Predictive Model

Ramos, Ángel Francisco Villarejo; Cabrera-Sánchez, Juan-Pedro; Lara‐Rubio, Juan; Liébana‐Cabanillas, Francisco

doi:10.3389/fpsyg.2021.651398

Cited by 4 publications

(3 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EHR data are largely structured, e.g., comorbidities, laboratory tests, and vital signs, and numerical. In general, DL models such as MLP are known to achieve good results for Big Data [ 19 ]. In this study, we used 23,712 datasets and applied the MLP model.…”

Section: Discussionmentioning

confidence: 99%

Deep learning approach for early prediction of COVID-19 mortality using chest X-ray and electronic health records

2023

View full text Add to dashboard Cite

Background An artificial-intelligence (AI) model for predicting the prognosis or mortality of coronavirus disease 2019 (COVID-19) patients will allow efficient allocation of limited medical resources. We developed an early mortality prediction ensemble model for COVID-19 using AI models with initial chest X-ray and electronic health record (EHR) data. Results We used convolutional neural network (CNN) models (Inception-ResNet-V2 and EfficientNet) for chest X-ray analysis and multilayer perceptron (MLP), Extreme Gradient Boosting (XGBoost), and random forest (RF) models for EHR data analysis. The Gradient-weighted Class Activation Mapping and Shapley Additive Explanations (SHAP) methods were used to determine the effects of these features on COVID-19. We developed an ensemble model (Area under the receiver operating characteristic curve of 0.8698) using a soft voting method with weight differences for CNN, XGBoost, MLP, and RF models. To resolve the data imbalance, we conducted F1-score optimization by adjusting the cutoff values to optimize the model performance (F1 score of 0.77). Conclusions Our study is meaningful in that we developed an early mortality prediction model using only the initial chest X-ray and EHR data of COVID-19 patients. Early prediction of the clinical courses of patients is helpful for not only treatment but also bed management. Our results confirmed the performance improvement of the ensemble model achieved by combining AI models. Through the SHAP method, laboratory tests that indicate the factors affecting COVID-19 mortality were discovered, highlighting the importance of these tests in managing COVID-19 patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning approach for early prediction of COVID-19 mortality using chest X-ray and electronic health records

2023

View full text Add to dashboard Cite

show abstract

“…Performance expectancy consists of the hopes individuals have by applying technology (Villarejo-Ramos et al, 2021), and it is considered to predict intention best to use (Venkatesh et al, 2003). The literature shows both perspectives, namely, technology acceptance not being directly influenced by performance expectancy (Yang et al, 2019), while another research confirms this positive relationship (Cabrera-S anchez and Villarejo-Ramos, 2019), and the first hypothesis is formed based on this assumption: H1.…”

Section: Unified Theory Of Acceptance and Use Of Technologymentioning

confidence: 97%

“…Still considered to be new, the term “Big Data” refers to the massive amount of data created through the interaction between customers and companies; it is used for analyses that allow an accurate perception of the behavior and trajectories of individuals and, thus, make the consumer experience more assertive (Aloysius et al , 2018), contributing to improvements on processes (Villarejo-Ramos et al , 2021).…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Antecedents of big data analytics adoption: an analysis with future managers in a developing country

Moraes

Pelegrini

Marchi

et al. 2022

View full text Add to dashboard Cite

Purpose This paper aims to identify the antecedents’ factors that positively and negatively influence the intention to use big data analytics (BDA) by future managers of companies. Design/methodology/approach The sample comprised 364 business students from a public university in Brazil. The methodology had a quantitative approach, with the use of structural equation modeling. Findings This paper presented a robust model with a high explanatory factor for the intention to use BDA, in which the elements of positive influence on the intention to use are expected performance, social influence and cost–benefit, and the negative influence factor is resistance to use. Research limitations/implications Research on BDA has improved the understanding of the phenomenon, mostly emphasizing the technical dimensions of BDA and underestimating organizational and human dimensions. This research contributed to the literature by presenting new insights into these organizational and human aspects by presenting influencing factors for future managers. User resistance is a variable that can incorporate technology adoption theories in BDA. Practical implications The results present a positive perception of future managers in the decision on financial resources in the acquisition of new technologies and enable managers to improve planning, investment and choice of technologies while presenting insights from the next generation. Issues regarding privacy, security and ethical aspects are key to minimizing user resistance. Originality/value This paper fills a significant research gap on the adoption of BDA, presenting the perception of future managers on fundamental aspects of adoption in a developing country. In addition, the research offers a theoretical model with new latent variables for a current and relevant topic.

show abstract

Factor Influencing the Adoption of Big Data Analytics: A Systematic Literature and Experts Review

Aldossari,

Mokhtar,

Abdul Ghani

2023

SAGE Open

View full text Add to dashboard Cite

In the current market landscape, enterprises face tremendous pressure to remain competitive and innovative to extend their businesses globally. Thus, a need exists for a new data analysis technique and a tool known as Big Data Analytics (BDA), which refers to massive data sets in light of their volume, velocity, variety, and veracity. Small and Medium Enterprises (SMEs) face challenges in obtaining and utilizing the knowledge derived from big data to make informed decisions regarding market selection and adopting appropriate internationalization strategies. These enterprises encounter resource limitations that hinder their ability to effectively acquire and implement big data insights for strategic decision-making in these areas. This systematic literature review aims to investigate the state of research on adopting big data analytics in SMEs. The study focuses on identifying key factors that influence the adoption of BDA. The study extracted 13 significant factors that are the highest influencers for BDA in SMEs. Those factors are top management support, training, relative advantage, it infrastructure, security, compatibility, complexity, adaptability, government it policies, competency, collaboration, digital transformation tools, and decision quality. The findings of this review are useful for practitioners, researchers, and decision-makers in understanding the factors that influence the adoption of big data analytics and the potential benefits and challenges associated with its implementation. Findings will shed light on the interplay between data governance and other factors influencing adoption, providing valuable insights for organizations seeking to establish robust data governance frameworks that support successful BDA initiatives.

show abstract

Predicting Big Data Adoption in Companies With an Explanatory and Predictive Model

Cited by 4 publications

References 64 publications

Deep learning approach for early prediction of COVID-19 mortality using chest X-ray and electronic health records

Deep learning approach for early prediction of COVID-19 mortality using chest X-ray and electronic health records

Antecedents of big data analytics adoption: an analysis with future managers in a developing country

Factor Influencing the Adoption of Big Data Analytics: A Systematic Literature and Experts Review

Contact Info

Product

Resources

About