Background Fever of unknown origin (FUO) is a group of diseases with heterogeneous complex causes that are misdiagnosed or have delayed diagnoses. Previous studies have focused mainly on the statistical analysis and research of the cases. The treatments are very different for the different categories of FUO. Therefore, how to intelligently diagnose FUO into one category is worth studying. Objective We aimed to fuse all of the medical data together to automatically predict the categories of the causes of FUO among patients using a machine learning method, which could help doctors diagnose FUO more accurately. Methods In this paper, we innovatively and manually built the FUO intelligent diagnosis (FID) model to help clinicians predict the category of the cause and improve the manual diagnostic precision. First, we classified FUO cases into four categories (infections, immune diseases, tumors, and others) according to the large numbers of different causes and treatment methods. Then, we cleaned the basic information data and clinical laboratory results and structured the electronic medical record (EMR) data using the bidirectional encoder representations from transformers (BERT) model. Next, we extracted the features based on the structured sample data and trained the FID model using LightGBM. Results Experiments were based on data from 2299 desensitized cases from Peking Union Medical College Hospital. From the extensive experiments, the precision of the FID model was 81.68% for top 1 classification diagnosis and 96.17% for top 2 classification diagnosis, which were superior to the precision of the comparative method. Conclusions The FID model showed excellent performance in FUO diagnosis and thus would be a potentially useful tool for clinicians to enhance the precision of FUO diagnosis and reduce the rate of misdiagnosis.

BackgroundHealth question-answering (QA) systems have become a typical application scenario of Artificial Intelligent (AI). An annotated question corpus is prerequisite for training machines to understand health information needs of users. Thus, we aimed to develop an annotated classification corpus of Chinese health questions (Qcorp) and make it openly accessible.MethodsWe developed a two-layered classification schema and corresponding annotation rules on basis of our previous work. Using the schema, we annotated 5000 questions that were randomly selected from 5 Chinese health websites within 6 broad sections. 8 annotators participated in the annotation task, and the inter-annotator agreement was evaluated to ensure the corpus quality. Furthermore, the distribution and relationship of the annotated tags were measured by descriptive statistics and social network map.ResultsThe questions were annotated using 7101 tags that covers 29 topic categories in the two-layered schema. In our released corpus, the distribution of questions on the top-layered categories was treatment of 64.22%, diagnosis of 37.14%, epidemiology of 14.96%, healthy lifestyle of 10.38%, and health provider choice of 4.54% respectively. Both the annotated health questions and annotation schema were openly accessible on the Qcorp website. Users can download the annotated Chinese questions in CSV, XML, and HTML format.ConclusionsWe developed a Chinese health question corpus including 5000 manually annotated questions. It is openly accessible and would contribute to the intelligent health QA system development.Electronic supplementary materialThe online version of this article (10.1186/s12911-018-0593-y) contains supplementary material, which is available to authorized users.

No abstract

This study sought to investigate the prevalence and prognostic significance of malnutrition in patients with an abnormal glycemic status and coronary artery disease (CAD). This secondary analysis of a multicenter prospective cohort included 5710 CAD patients with prediabetes and 9328 with diabetes. Four objective tools were applied to assess the nutritional status of the study population. The primary endpoint was all-cause death. The association of malnutrition with clinical outcomes was examined using Cox proportional hazards regression. The proportion of malnutrition varied from 8% to 57% across the assessment tools. Diabetic patients were more likely to be malnourished than prediabetic patients. During a median follow-up of 2.1 years, 456 all-cause deaths occurred. The adjusted hazard ratios and 95% confidence interval for all-cause deaths of moderate–severe malnutrition defined by different tools ranged from 1.59 (1.03, 2.46) to 2.08 (0.92, 4.73) in prediabetic patients and 1.51 (1.00, 2.34) to 2.41 (1.78, 3.27) in diabetic patients. In conclusion, malnutrition is not rare in CAD patients with abnormal glycemic status. Moderate–severe malnutrition strongly predicted all-cause death regardless of the assessment tool. Assessing the nutritional status for all CAD patients with prediabetes and diabetes to identify individuals at high risk of all-cause death may help the risk assessment and prognosis improvement.