Data Harmonization for Heterogeneous Datasets: A Systematic Literature Review

Abstract

As data size increases drastically, its variety also increases. Investigating such heterogeneous data is one of the most challenging tasks in information management and data analytics. The heterogeneity and decentralization of data sources affect data visualization and prediction, thereby influencing analytical results accordingly. Data harmonization (DH) corresponds to a field that unifies the representation of such a disparate nature of data. Over the years, multiple solutions have been developed to minimize the heterogeneity aspects and disparity in formats of big-data types. In this study, a systematic review of the literature was conducted to assess the state-of-the-art DH techniques. This study aimed to understand the issues faced due to heterogeneity, the need for DH and the techniques that deal with substantial heterogeneous textual datasets. The process produced 1355 articles, but among them, only 70 articles were found to be relevant through inclusion and exclusion criteria methods. The result shows that the heterogeneity of structured, semi-structured, and unstructured (SSU) data can be managed by using DH and its core techniques, such as text preprocessing, Natural Language Preprocessing (NLP), machine learning (ML), and deep learning (DL). These techniques are applied to many real-world applications centered on the information-retrieval domain. Several assessment criteria were implemented to measure the efficiency of these techniques, such as precision, recall, F-1, accuracy, and time. A detailed explanation of each research question, common techniques, and performance measures is also discussed. Lastly, we present readers with a detailed discussion of the existing work, contributions, and managerial and academic implications, along with the conclusion, limitations, and future research directions.

Recent Advances of Utilizing Artificial Intelligence in Lab on a Chip for Diagnosis and Treatment

“…In order to deal with heterogeneity in these forms of data, Data harmonization (DH) is based on its core techniques including Natural Language Preprocessing (NLP), text preprocessing, and some of the machine learning methods and deep learning can be helpful. [ 149 ] ML algorithms play a significant role in this regard. Each algorithm has its own set of benefits and drawbacks, as well as its own specific area of implementation.…”

Recent Advancements in Emerging Technologies for Healthcare Management Systems: A Survey

“…This pertains to electronic medical records (EMRs), which may include all forms of data [ 120 ]. For instance, structured data refers to data that are simple to categorize in a database; they might contain a set of features and records such as patient’s biodata and generic health complaints such as fever or nausea [ 121 ]. On the other hand, some health data are unstructured and are usually in the form of photographs, text files (medical reports and summaries), and audio/visual recordings.…”

“…Realizing and exploiting different forms of data on a large scale would be highly valuable in implementing ML techniques in HMS [ 121 ]. Furthermore, when ML is used successfully, it may assist doctors in making near-perfect diagnoses, determining and improving patients’ overall health, and lowering costs [ 122 ].…”

“…Also, most of the hospital visitations are evitable and ML may be utilized to aid in diagnosis and administer suitable therapy. As a result, expenditures are reduced by keeping patients out of expensive emergency rooms [ 121 ].…”

Analysis of Deep Learning Techniques for Dental Informatics: A Systematic Literature Review

“…Structuring electronic dental records through DL for a clinical decision support system. Medical informatics’ fundamental and difficult objective is to extract information from unstructured clinical text [ 172 ].…”