The Use of Natural Language Processing for Market Orientation on Rare Diseases

Introduction

In this article, we describe different ways for a market player to get information about the rare disease healthcare market. As rare diseases are concerned, there is little information available, and it is challenging to integrate the topic into a comprehensive market strategy with information flows. Stakeholders are dependent on search engines and databases, and it is essential to know which is the most appropriate. A relatively small number of articles on rare diseases exists; however, the quantity is still a challenge, especially if several rare diseases are searched simultaneously. Natural Language Processing can provide support through finding relevant articles quickly, and by helping to find the “needle in the haystack” through mathematical operations and subsequent visualizations. These methods also represent an essential accomplishment for physicians, as they can usually only control a small part of known diseases. Furthermore, NLP is crucial for patients, relatives, and other stakeholders who are not familiar with the subject matter.

A low prevalence characterizes rare diseases, and the global number of incidences for each disease is low. The impression may arise that they do not impact the health care market. However, the situation is different: Collectively, about 10% of the US population is affected by a rare (also called orphan) disease as many countries are undertaking efforts to provide patients with orphan diseases with highly qualified medicines. In the USA, the Orphan Drug Act has been in place since 1983, and in China, efforts are being made to improve patient care (Kang et al., 2019). Rare diseases affect the medical market in at least two ways.

On the one hand, these drugs are commonly quite expensive because they become visible in the market. On the other hand, it generally takes several years until a rare disease is discovered at all so that unnecessary examinations and treatments cost enormous amounts of money (Svenstrup et al., 2015). Therefore, healthcare professionals need to quickly discover the right information on rare diseases, and Natural Language Processing (NLP) can provide useful help.

The problem with transparency in the rare diseases market is that there is little information about specific rare diseases, and it can be very laborious to find orientation in the market. Thus, how do we orientate ourselves in a market about which hardly any information is available? Moreover, how do we find our way through it?

The proclamation for a business that improves its market orientation also expands its market performance has been issued for more than 60 years. Narver and Slater (1990) introduce an efficient instrument the degree of market orientation in 1990 and show that customer and competitor orientation includes all activities to obtain information about buyers and competitors. It is essential to cover the target market and to disseminate the resulting reports internally. In 2005, Kirca et al. provide a quantitative summary of the bivariate findings regarding forerunners and the effects of performing market-orientation research and confirm that market intelligence is a compulsory prerequisite to participate in a market successfully. Intelligence seems feasible for a transparent and information-rich market, but information on rare diseases is scarce. For a large corporation or an organization in a transparent market, it is not challenging to establish a sophisticated marketing strategy. However, if management attention is scarce to investigate an opaque market such as the marketing of rare diseases, the trade-off for a strategy is the in-situ information search in the Web and literature databases (see also Christen et al., 2009). Thus, we need to look for ways to utilize search engines to get a quick overview of the market. Besides, it is crucial that we also evaluate the results. It is, therefore, advisable to compare the results with professional databases. FindZebra is a database that focuses on rare diseases, and MEDLINE or PubMed is a database of medical articles.