Back

Harnessing Internet Search Data as a Potential Tool for Medical Diagnosis

Downing, G. J.; Tramontozzi, L. M.; Garcia, J.; Villanueva, E.

2024-05-06 health informatics
10.1101/2024.05.03.24305695 medRxiv
Show abstract

ObjectivesTo explore the potential and challenges of utilizing internet search data in medical diagnosis, focusing on ethical, technical, and policy considerations by assessing the current state of research, identifying gaps and limitations, and proposing future research directions to advance this emerging field. MethodsA comprehensive analysis of peer-reviewed literature and informational interviews with subject matter experts was conducted to examine the landscape of internet search data utilization in medical research. Searchers were performed for published peer-reviewed literature in PubMed (October to December 2023). ResultsSystematic selection according to predefined criteria resulted in the inclusion of 43 articles of the 2,499 identified citations. The analysis revealed a nascent domain of internet search data research in medical diagnosis, characterized by advancements in analytics and data integration. Although significant challenges such as bias, data privacy, and infrastructure limitations hinder widespread adoption, emerging initiatives could reshape data collection methodologies and privacy safeguards. ConclusionsSignals correlating with diagnostic considerations have been identified in certain diseases and conditions, indicating the potential for such data to enhance clinical diagnostic capabilities. However, leveraging internet search data for improved early diagnosis and healthcare outcomes requires effectively addressing ethical, technical, and policy challenges. By fostering interdisciplinary collaboration, advancing infrastructure development, and prioritizing patient engagement and consent, researchers can unlock the transformative potential of internet search data in medical diagnosis to ultimately enhance patient care and advance healthcare practice and policy.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.