RESUMO
Objectives: Diabetes and its complications are commonly associated with depressive symptoms, and few studies have investigated the diagnosis effect of depressive symptoms in patients with diabetes. The present study used a network-based approach to explore the association between depressive symptoms, which are annotated from electronic health record (EHR) notes by a deep learning model, and the diagnosis of type 2 diabetes mellitus (T2DM) and its complications. Methods: In this study, we used anonymous admission notes of 52,139 inpatients diagnosed with T2DM at the first affiliated hospital of Nanjing Medical University from 2008 to 2016 as input for a symptom annotation model named T5-depression based on transformer architecture which helps to annotate depressive symptoms from present illness. We measured the performance of the model by using the F1 score and the area under the receiver operating characteristic curve (AUROC). We constructed networks of depressive symptoms to examine the connectivity of these networks in patients diagnosed with T2DM, including those with certain complications. Results: The T5-depression model achieved the best performance with an F1-score of 91.71 and an AUROC of 96.25 compared with the benchmark models. The connectivity of depressive symptoms in patients diagnosed with T2DM (p = 0.025) and hypertension (p = 0.013) showed a statistically significant increase 2 years after the diagnosis, which is consistent with the number of patients diagnosed with depression. Conclusion: The T5-depression model proposed in this study can effectively annotate depressive symptoms in EHR notes. The connectivity of annotated depressive symptoms is associated with the diagnosis of T2DM and hypertension. The changes in the network of depressive symptoms generated by the T5-depression model could be used as an indicator for screening depression.
RESUMO
BACKGROUND: Thyroid cancer is a common endocrine tumor, the incidence of which is increasing each year. Early diagnosis and treatment can effectively prevent thyroid cancer. This article uses Chinese's ultrasound reports to determine the value of early diagnosis. METHODS: The clinical data center of the First Affiliated Hospital of Nanjing Medical University was screened for patients diagnosed with a thyroid nodule, who had undergone a thyroid function test, ultrasound records and pathological assessment. A total of 811 patients with a total of 1,290 pathologically confirmed nodules (506 benign and 784 malignant) were enrolled. Logistic regression was used to analyze the variables that significantly affected malignant nodules. The sensitivity and specificity of ultrasound thyroid imaging-reporting and data system (TI-RADS) classification results for benign and malignant tumors were calculated. RESULTS: The age of the patients had a very significant difference in the classification of benign and malignant nodules (P<0.001), and the marital status was significantly different (P<0.05). Gender and medical insurance had no significant effect (P>0.05). Thyroglobulin (TG), free thyroxine (FT4), and free triiodothyronine (FT3) had significant effects (P=0.003) on the incidence of malignant nodules in patients, while thyroid-stimulating hormone (TSH) had no significant effect (P>0.05). Ultrasound analysis showed a Youden's index of 78.97%, a positive predictive value of 93.20%, and a negative predicted value of 84.10% at the most excellent classification effect. The sensitivity was 89.0%, the specificity was 89.9%; much greater than the classification model based on the thyroid function test (sensitivity =80.6%, specificity =55.8%). CONCLUSIONS: The present study verifies the effectiveness of using TI-RADS classification for diagnosis of benign and malignant thyroid nodules, and explores the use of new analysis methods for clinical data. To reduce dependence on the doctors, ultrasound image data and clinical phenotypic data can be further used to assist clinical decision making.