Machine learning, the process of training machines to automatically learn from data and make decisions, is being increasingly applied to the fields of healthcare and medical diagnostics. This paper is a state-of-the-art review of machine-learning-based prediction modelling in primary care with a focus on analyzing the current methods available and identifying the challenges and future development opportunities. Machine learning technologies are enabling advanced predictive predictions and data-based decisions to improve practice in primary care, but more development and optimization is needed to make these practices more broadly applicable to primary care settings.
MDPI is a global open access publisher that publishes peer-reviewed journals across all disciplines. On top of their research-oriented activities, they publish books and advocate interdisciplinary collaborations and approaches towards addressing the most pressing global issues. MDPI has a range of services to support authors, such as helpful copy-editing and formatting services, to ensure a high-quality and journal-compliance level of their published materials. They also have automated editorial and publication systems for efficient and precise management of the entire publication process, which greatly reduces paperwork and costs.
The person mentioned in this article is Jean-Baptiste Poullet-Audet, a postdoctoral student at the Luxembourg School of Business who is also affiliated with McGill University. His research focuses on using predictive modelling to improve diagnostics, health care management, and risk prediction. He is particularly interested in the development and application of artificial intelligence tools in the medical field, such as using machine learning models for multi-modal prediction tasks and for predicting outcomes from a variety of medical data modalities. Additionally, he is interested in understanding the ethical implications of the use and development of these artificial intelligence-based tools.
