Treffer: Developing and Testing an Algorithm to Identify Future Innovative Research Areas in Digitalization Conditions (using a Medical-sector example).

Predicting more relevant areas of medical research, with a prediction period starting at five years, is currently done exclusively by experts, while the results of such forecasts are extremely ineffective and differ significantly, depending on their source. Modern development trends in world science require the creation of a universal forecasting tool that can be used as a basic resource— providing objective, system-independent information. This condition justifies the relevance of the present study. This study’s goal was to develop and test an algorithm to identify future innovative research areas in digitalization conditions (using the medical sector as an example). During this research, a prognostic model was developed based on the hype cycle, which makes determining a list of possible areas for hardware development in the medical sector possible, presenting this list as a set of tokens that are decoded using mental analysis and automated through the Python programming language. The process of identifying future innovative research areas comprises the following stages: identifying the aggregator (hub) research results, parsing primary information, translating the analyzed information, forming a set of lexemes, forming an analytical dataframe, constructing regression models for the highlighted lexemes, forming and storing the resulting dataframe, and metathinking the highlighted lexemes. In total, 4,000 study names were analyzed, based on the ResearchGate platform, which made obtaining 28 significant lexemes based on the results of metathinking possible. Next, an associative map was created using the most promising research areas in medicine, namely: diagnosing viral infections, the spread of viral infections, coronaviruses, cardiovascular diseases, and lung diseases. The obtained algorithm for the automatic determination of promising research areas can be modified by choosing different sources of information. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Technology is the property of Universitas Indonesia, International Journal of Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)