|Irina Rudskaya||Peter the Great St. Petersburg Polytechnic University, St. Petersburg, Polytechnicheskaya, 29, 194064, Russia|
|Ivan Ozhgikhin||Peter the Great St. Petersburg Polytechnic University, St. Petersburg, Polytechnicheskaya, 29, 194064, Russia|
|Darya Kryzhko||Peter the Great St. Petersburg Polytechnic University, St. Petersburg, Polytechnicheskaya, 29, 194064, Russia|
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.
Development of medicine; Digitalization; Hardware; Hype cycle; Identification algorithm; Innovative research areas
The research process in the field of medicine is one of the most complex research processes—both structurally and substantially—since it is characterized by the main participants’ desire for system cooperation. However, the process of cooperation does not allow for a management of the forecast horizon, which involves identifying the most appropriate period of time for the implementation of the project. Accordingly, most specific research aims to solve current, not future, problems in medicine. At the same time, proposing innovative solutions for tasks that are not yet identified makes creating unique competitive advantages possible—the core of future markets.
One of the most common models describing the process of technological development is the Gartner hype cycle. In 1995, analysts from the Gartner company established that the development of a company that creates and introduces innovative technology to the market is characterized by the specific function of developing an information space—a fifth-degree polynomial that determines the five stages of developing the information background surrounding innovative solutions. In the information space of any stable trend described by the Gartner model, a field of research characterized by high commercial potential can be identified (O’Leary, 2008). This high commercial potential is defined by the prospect of a synergetic effect from the appearance not only of an innovative solution but also of its accompanying market and consumer infrastructure, which supplements and develops an opportunity to use this innovative solution (Kudryavtseva et al., 2017). Therefore, after identifying this research area during the hype cycle’s earlier stages, a developer can create a potentially promising vector to develop their own research (Lyu et al., 2015). These specifics are most relevant to the development of medical equipment.
The model presented in this study clearly expresses functional specifics since each of its stages can be described by the certain function of a second- or third-degree polynomial (Dedehayir and Steinert, 2016). Consequently, if an information space is described by a system of polynomial functions and this system is itemized into its elementary components, determining the lexical categories characterized by one of the Gartner model’s stages is possible.
In conclusion, we can add that today, the trend of developing personalized medicine has made producers’ ability to design and launch (often in small batches) medical technology that can complete clearly defined tasks, when applied to a specific medical method, more and more important. Meanwhile, the process of determining the most promising research areas in developing medicine can be algorithmized and automated. This study proposed a forecasting model to form a set of the most promising research areas in medical hardware development. This model was based on fractionation of the current research context according to the hype cycle, which differs from alternative models by minimizing expert evaluation components and forming a vector of current studies, based on objective information. Based on this model, an algorithm was developed for identifying the most promising research areas in medical hardware development, presented as a set of tokens that were decoded using mental analysis and automated using the Python programming language. This forecasting model’s results established that the most promising research lies in the following areas: diagnosing viral infections, the spread of viral infections, coronaviruses, cardiovascular diseases, and lung diseases.
reported study was funded by the Russian Foundation for Basic Research (RFBR),
according to research project ? 18-310-20012.
Dedehayir, O., Steinert, M., 2016. The Hype Cycle Model: A Review and Future Directions. Technological Forecasting and Social Change, Volume 108, pp. 28–41
Hannebauer, C., Hesenius, M., Gruhn, V., 2018. Does Syntax Highlighting Help Programming Novices? Empirical Software Engineering, Volume 23(5), pp. 2795–2828
Hardeniya, N., Perkins, J., Chopra D., Joshi, N., Mathur I., 2016. Natural Language Processing: Python and NLTK. Packt Publishing Ltd.
Huang, M.-H., Chang, C.-P., 2016. A Comparative Study on Three Citation Windows for Detecting Research Fronts. Scientometrics, Volume 109(3), pp. 1835–1853
Kudryavtseva, T.J., Ivanova, E.A., Kozlova, E.A., Skhvediani, A.E., 2017. Pricing and Assessment of Competitiveness of Innovative Medical Devices in the Context of Commercialization Strategy. Academy of Strategic Management Journal, Volume 16(Special Issue 1), pp. 110–122
Lyu, P.-H., Yao, Q., Mao, J., Zhang, S. J., 2015. Emerging Medical Informatics Research Trends Detection Based on MeSH Terms. Informatics for Health and Social Care, Volume 40(3), pp. 210–228
Martin, W.A., Church, K.W., Patil, R.S., 1987. Preliminary Analysis of a Breadth-First Parsing Algorithm: Theoretical and Experimental Results. Natural Language Parsing Systems. Springer, pp. 267–328
Muscanell, N., Utz, S., 2017. Social Networking for Scientists: An Analysis on How and Why Academics Use ResearchGate. Online Information Review. Emerald Publishing Limited
Muslim, E., Riansa, I., 2017. Analytic Hierarchy Process (AHP) Pairwise Matrix with One Missing Value. International Journal of Technology, Volume 8(7), pp. 1356–1360
Nakayama, T., 1996. Method and Apparatus for Highlighting and Categorizing Documents Using Coded Word Tokens. Google Patents
O’Brien, K., 2019. ResearchGate. Journal of the Medical Library Association: JMLA, Volume 107(2), p. 284
O’Leary, D.E., 2008. Gartner’s Hype Cycle and Information System Research Issues. International Journal of Accounting Information Systems, Volume 9(4), pp. 240–252
Rahmatin, N., Santoso, I., Indriani, C., Rahayu, S., Widyaningtyas, S., 2018. Integration of the Fuzzy Failure Mode and Effect Analysis (Fuzzy FMEA) and the Analytical Network Process (ANP) in Marketing Risk Analysis and Mitigation. International Journal of Technology, Volume 9(4), pp. 809–818
Rudskaya, I., Rodionov, D., 2017. Econometric Modeling as a Tool for Evaluating the Performance of Regional Innovation Systems (with Regions of the Russian Federation as The Example). Academy of Strategic Management Journal, Volume 16(2)