Health misinformation refers to incorrect health and medical-related information originating from diverse sources and disseminated through multiple channels, including individuals, organizations, social media, websites, and even health professionals. Do Nascimento et al. (2022) emphasize the rapid spread of health misinformation through media posts and videos, particularly within closed online groups, significantly impacting individuals with low health literacy and elderly patients. According to the World Health Organization (2022), a substantial portion of health-related posts on social media contains misinformation, with up to 28.8% of health-related posts and nearly 60% of pandemic-related posts being identified as such. In the health misinformation problem area, previous studies have focused on detection methods, albeit with limitations. For example, studies by Liu et al. (2022) and Barve and Saini (2023) utilized traditional machine learning techniques, which may struggle with contextual meanings. In contrast, our research leverages bidirectional encoder representations from transformers (BERT) embeddings, enabling a more nuanced understanding of contextual meaning in text data, thereby addressing these limitations. Our research aims to automate the classification of fake healthcare news using the BERT technique. By leveraging advanced techniques like BERT to analyze and classify text data based on learned patterns and contextual understanding, our approach contributes to more accurately detecting healthcare misinformation. This approach helps determine whether a specific healthcare-related news article is real or fake. We’re utilizing the Design Science (Hevner and Chatterjee 2010) methodology to develop our approach as an artifact to classify healthcare misinformation automatically. Design Science’s structured way of conducting information systems research will ensure the effectiveness and reliability of our approach. The preliminary results of our proposed approach will be showcased during this TREO talk, inviting dialogue on topics for exploring Design Science as a viable approach for combating healthcare misinformation.