JMIR Publications

ABSTRACT

Background:

Fever of Unknown Origin (FUO) is a group of diseases with heterogeneous complex causes, which is used to be misdiagnosed or delayed diagnosed. Previous studies mainly focus on the cases statistical analysis and research. The treatment direction is far different for different categories of FUO. So how to diagnose FUO to one category intelligently is worth studying.

Objective:

We would like to fuse all the medical data together to predict the cause category of FUO patients by machine learning method automatically, which could help doctors to diagnose FUO more accurately.

Methods:

In this paper, we innovatively built the FUO Intelligent Diagnosis (FID) model to help clinicians predict the cause category firstly and improve the precision of diagnosis manually. First, we classified FUO cases into four categories (infections, immune diseases, tumors and others) according to the huge different causes and treatment methods. Then, we cleaned the basic information data, clinical examination results and structured the electronic health records (EHRs) data by BERT model. Next, we extracted features based on the structured sample data and trained the FID by LightGBM.

Results:

Experiments were based on 2299 desensitized cases data from Peking Union Medical College Hospital. By extensive experiments, the precision of FID was 81.7% for the top 1 classification diagnosis, and 96.2% for the top 2 classification diagnosis, which was superior to the comparative methods. Besides, we found for the tumors FUO patients, the average age was higher than that of others and there were more female patients in immune diseases FUO.

Conclusions:

In conclusion, FID showed excellent performance in FUO diagnosis and it would be meaningful for the clinicians to enhance the precision of FUO diagnosis and reduce the misdiagnosis rate.