| Abstrakt: |
Purpose: Integrating data science techniques in healthcare has emerged as a transformative force and holds immense potential for improving patient outcomes, enhancing operational efficiency, and advancing medical research by utilizing medical information. This paper aims to explore various data science techniques employed in the field of healthcare, highlight corresponding challenges, and identify opportunities for innovation. Methods: A comprehensive literature review was conducted to gather insight into the current use to data science applications in healthcare domain. We explored various databases like Google Scholar, PubMed, IEEE Xplore using relevant keywords such as "data science", "data science in healthcare", "data science techniques", "data science applications in healthcare", "Machine Learning in healthcare", and "Predictive Analytics". We focused on papers published between 2015 and 2023. Results: Data Science techniques including Artificial Intelligence, Machine Learning, Deep Learning, Natural Language Processing, etc. are being used for tasks such as disease prediction, personalized treatment recommendation, medical imaging analysis, and healthcare resource optimization. Nonetheless, challenges such as data privacy, quality, data access and ethics in using healthcare data were identified as barriers in their extensive implementation. Conclusions: Important insights that could improve patient outcomes and lower healthcare expenditures can be obtained by employing data science techniques on data generated through wearable technology, medical imaging, Electronic Health Records (EHR), etc. To fully utilize data science in healthcare, however, data quality, privacy, and security issues must be resolved, and deliberative frameworks must be created to enable the use of data science in healthcare in an ethical and responsible manner. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink