Back

Retrospective Observational Study on an AI-Powered Symptom Checker for Pre-Diagnosis of Anxiety Disorders

Orelogio, A. A.; Garcia-Esquirol, O.; Rodriguez, M. E.; Malet, A.; Sarrias Ramis, E.

2023-05-28 psychiatry and clinical psychology
10.1101/2023.05.24.23290449 medRxiv
Show abstract

ObjectiveTo describe the data obtained about diagnoses of anxiety disorders from the Mediktor database to reveal the relationship with the current scientific evidence. MethodsThis retrospective observational study uses secondary data obtained from the Mediktor database and evaluated age, sex, and the most frequent reason for consultation. Descriptive statistics were used to analyze the variables of the sample and their association with pre-diagnosis anxiety disorders. A significance level of p < 0.05 was set for all statistical tests, and all analyses were conducted using Power BI and Google Sheets. ResultsYoung adults (18-35 years old) were more likely to be pre-diagnosed with anxiety disorders compared to individuals in other life stages and the proportion of anxiety disorders was found to be higher in females compared to males, both with a statistically significant p-value of less than 0.01. ConclusionsThe data observed in Mediktor relates to current scientific evidence and it has the potential as a technological tool for early detection of anxiety disorders.

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.