Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Sep 29;23(10):1275.
doi: 10.3390/e23101275.

On Building and Evaluating a Medical Records Exploration Interface Using Text Mining Techniques

Úrsula Torres Parejo  1 , Jesús Roque Campaña  2 , María Amparo Vila  2 , Miguel Delgado  2
Affiliations

On Building and Evaluating a Medical Records Exploration Interface Using Text Mining Techniques

Úrsula Torres Parejo et al. Entropy (Basel). .

Abstract

Medical records contain many terms that are difficult to process. Our aim in this study is to allow visual exploration of the information in medical databases where texts present a large number of syntactic variations and abbreviations by using an interface that facilitates content identification, navigation, and information retrieval. We propose the use of multi-term tag clouds as content representation tools and as assistants for browsing and querying tasks. The tag cloud generation is achieved by using a novelty mathematical method that allows related terms to remain grouped together within the tags. To evaluate this proposal, we have carried out a survey over a spanish database with 24,481 records. For this purpose, 23 expert users in the medical field were tasked to test the interface and answer some questions in order to evaluate the generated tag clouds properties. In addition, we obtained a precision of 0.990, a recall of 0.870, and a F1-score of 0.904 in the evaluation of the tag cloud as an information retrieval tool. The main contribution of this approach is that we automatically generate a visual interface over the text capable of capturing the semantics of the information and facilitating access to medical records, obtaining a high degree of satisfaction in the evaluation survey.

Keywords: content identification; electronic health records; health information systems; knowledge representation; visual interface.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Stages of the experimentation process.
Figure 2
Figure 2
Phases of the methodological process.
Figure 3
Figure 3
AP-Sequence generated from the spanning sequence {left fourth toe amputation}.
Figure 4
Figure 4
Visualization of the AP-Sequence in Figure 3.
Figure 5
Figure 5
Tag cloud after postprocessing and colour with 0.3% of support.
Figure 6
Figure 6
Bar graphs and the pie charts for each of the variables.
Figure 7
Figure 7
Mean graph with confidence intervals at 95% for the degree of agreement (from one to five) with different assertions about the characteristics of the tag cloud.
See this image and copyright information in PMC

References

    1. Yan S., He L., Seo J., Lin M. Concurrent healthcare data processing and storage framework using deep-learning in distributed cloud computing environment. IEEE Trans. Ind. Inform. 2020;17:2794–2801. doi: 10.1109/TII.2020.3006616. - DOI
    1. Algarni A., Ahmad M., Attaallah A., Agrawal A., Kumar R., Khan R. A fuzzy multi-objective covering-based security quantification model for mitigating risk of web based medical image processing system. Int. J. Adv. Comput. Sci. Appl. 2020;11:481–489. doi: 10.14569/IJACSA.2020.0110159. - DOI
    1. Ketcheng Q., Wang L. Research on Visual Data Mining Technology. J. Phys. Conf. Ser. 2021;1748:1–7.
    1. Liu L., Liu L., Fu X., Huang Q., Zhang X., Zhang Y. A cloud-based framework for large-scale traditional Chinese medical record retrieval. J. Biomed. Inform. 2018;77:21–33. doi: 10.1016/j.jbi.2017.11.013. - DOI - PubMed
    1. Viégas F.B., Wattenberg M. TIMELINES Tag clouds and the case for vernacular visualization. Interactions. 2008;15:49–52. doi: 10.1145/1374489.1374501. - DOI

LinkOut - more resources