A systematic literature review of data science, data analytics and machine learning applied to healthcare engineering systems

Salazar-Reyna, Roberto; Aleu, Fernando González; Granda-Gutierrez, Edgar M.A.; Díaz-Ramírez, Jenny; Garza‐Reyes, Jose Arturo; Kumar, Anil

doi:10.1108/md-01-2020-0035

Cited by 24 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As deep learning algorithms have evolved, convolutional neural networks (CNNs) have been shown to automatically learn features from text and reduce manual input of feature information, resulting in better text classification capabilities than traditional machine learning algorithms. In their study, Salazar-Reyna et al [30] applied different machine learning algorithms to classify documents and found that deep learning algorithms are superior to traditional machine learning algorithms. Sood et al [4] performed a multi-level classification of 1.7 million documents information in an international scientific journal index based on CNN models and obtained satisfactory scientometric classification results.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Finally, typical terms describing the literature topics were included in the feature term lexicon in coordination with the knowledge of subject matter experts. Validation of terms for inclusion in the final lexicon was performed using two methods: validation by three subject matter experts and comparison with existing terms from the data science and analytics literature [4,30,41,42]. The final validated lexicon of feature terms will be used in downstream literature classification tasks by helping to select appropriate data science terms from publication platforms/databases (e.g., ProQuest, EBSCOhost, and Scopus) and pre-annotating these terms to support the development of a deep-learning application for classifying mentions of data science and analytics in the literature.…”

Section: Building Stop and Feature Terms Lexiconsmentioning

confidence: 99%

“…A typical convolutional layer usually uses a pooling function in its last phase to change the output of the layer. In this study, we used max-pooling [30], one of the widely used pooling functions that returns the maximum output within a rectangular neighborhood. Max-pooling is a pooling operation that computes the maximum value for patches of a feature map and uses it to create a down-sampled (pooled) feature map.…”

Section: Deep Learning For Literature Classificationmentioning

confidence: 99%

“…As shown in Figure 5, the CNN model consists of an input layer, a convolution layer, a pooling layer, and a SoftMax layer, and uses a gradient descent method to inversely adjust the weighting parameters [30]. The input layer of the CNN is the term vector matrix D * , and the convolution layer performs the convolution operation on the original feature matrix with multiple convolution kernels to form the feature map.…”

Section: Deep Learning For Literature Classificationmentioning

confidence: 99%

See 3 more Smart Citations

Scientometric Analysis and Classification of Research Using Convolutional Neural Networks: A Case Study in Data Science and Analytics

et al. 2022

View full text Add to dashboard Cite

With the increasing development of published literature, classification methods based on bibliometric information and traditional machine learning approaches encounter performance challenges related to overly coarse classifications and low accuracy. This study presents a deep learning approach for scientometric analysis and classification of scientific literature based on convolutional neural networks (CNN). Three dimensions, namely publication features, author features, and content features, were divided into explicit and implicit features to form a set of scientometric terms through explicit feature extraction and implicit feature mapping. The weighted scientometric term vectors are fitted into a CNN model to achieve dual-label classification of literature based on research content and methods. The effectiveness of the proposed model is demonstrated using an application example from the data science and analytics literature. The empirical results show that the scientometric classification model proposed in this study performs better than comparable machine learning classification methods in terms of precision, recognition, and F1-score. It also exhibits higher accuracy than deep learning classification based solely on explicit and dominant features. This study provides a methodological guide for fine-grained classification of scientific literature and a thorough investigation of its practice.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Building Stop and Feature Terms Lexiconsmentioning

confidence: 99%

Section: Deep Learning For Literature Classificationmentioning

confidence: 99%

Section: Deep Learning For Literature Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Scientometric Analysis and Classification of Research Using Convolutional Neural Networks: A Case Study in Data Science and Analytics

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Highlighted the gaps and challenges, and proposed a detailed methodology for the benchmarking and evaluation of AI techniques used in all COVID-19 medical images classification tasks [21] COVID-19 pandemic Explained the role of AI in fighting pandemics [34] Data harmonization (DH) and health management decision-making Collected definitions and concepts of DH and addressed the causal relation between DH and decision-making in health management [35] Healthcare aspects Provided an overview of the big data analytics publication dynamics in healthcare and discussed several examples to this field [36] Healthcare engineering systems Synthesized and analyzed publications covering data analytics, big data, data mining, and machine learning in the field of Healthcare Engineering Systems [37] Mobile health (m-health)…”

Section: Sourcementioning

confidence: 99%

Applications of Big Data Analytics to Control COVID-19 Pandemic

Alsunaidi

Almuhaideb

Ibrahim

et al. 2021

Sensors

100

View full text Add to dashboard Cite

The COVID-19 epidemic has caused a large number of human losses and havoc in the economic, social, societal, and health systems around the world. Controlling such epidemic requires understanding its characteristics and behavior, which can be identified by collecting and analyzing the related big data. Big data analytics tools play a vital role in building knowledge required in making decisions and precautionary measures. However, due to the vast amount of data available on COVID-19 from various sources, there is a need to review the roles of big data analysis in controlling the spread of COVID-19, presenting the main challenges and directions of COVID-19 data analysis, as well as providing a framework on the related existing applications and studies to facilitate future research on COVID-19 analysis. Therefore, in this paper, we conduct a literature review to highlight the contributions of several studies in the domain of COVID-19-based big data analysis. The study presents as a taxonomy several applications used to manage and control the pandemic. Moreover, this study discusses several challenges encountered when analyzing COVID-19 data. The findings of this paper suggest valuable future directions to be considered for further research and applications.

show abstract