The use of artificial intelligence in assessing fever in the returning traveller: A scoping review
Author summary We wanted to understand how artificial intelligence has been used to help clinicians assess fever in people who become ill after international travel. This clinical problem is difficult because the list of possible infections is broad and depends on travel destination, exposure history, symptoms, and test results. We reviewed the published literature and found three eligible studies. These studies described different approaches: a rule-based expert system to generate a ranked list of possible diagnoses, a machine-learning model to predict malaria risk, and a model using immune markers to help distinguish between infections. All three studies suggested that artificial intelligence could support clinical assessment in controlled settings. We also found that all studies were conducted in hospital-based populations. None of the included studies reported real-world clinical implementation or user acceptability testing, and external validation was limited. We believe this review shows that artificial intelligence is a promising but early area in travel-related fever assessment. More research, including external validation and real-world implementation studies, is needed before these tools can be confidently adopted in routine clinical care.
