Medical informatics labor market analysis using web crawling, web scraping, and text mining

Objectives: The European University Association (EUA) defines employability as a major goal of higher education. Therefore, competence-based orientation is an important aspect of education. The representation of a standardized job profile in the field of medical informatics, which is based on the most common labor market requirements, is fundamental for identifying and conveying the learning goals corresponding to these competences. Methods: To identify the most common requirements, we extracted 544 job advertisements from the German job portal, STEPSTONE. This process was conducted via a program we developed in R with the rvest library, utilizing web crawling, web extraction, and text mining. After removing duplicates and filtering for jobs that required a bachelor's degree, 147 job advertisements remained, from which we extracted qualification terms. We categorized the terms into six groups: professional expertise, soft skills, teamwork, processes, learning, and problem-solving abilities. Results: The results showed that only 45% of the terms are related to professional expertise, while 55% are related to soft skills. Studies of employee soft skills have shown similar results. The most prevalent terms were programming, experience, project, and server. Our second major finding is the importance of experience, further underlining how essential practical skills are. Conclusions: Previous studies used surveys and narrative descriptions. This is the first study to use web crawling, web extraction, and text mining. Our research shows that soft skills and specialist knowledge carry equal weight. The insights gained from this study may be of assistance in developing curricula for medical informatics.

Automated summary

This study used web crawling and text mining techniques to analyze German job advertisements, finding that soft skills and professional expertise are equally important. The results highlight the importance of practical experience and can guide the development of medical informatics curricula.