The Frailty Index and colon cancer: a 2-sample Mendelian-randomization study.

Background: Frailty is closely related to cancer. Previous research has shown that cancer patients are prone to frailty, and frailty increases the risk of adverse outcomes in cancer patients. However, it is unclear whether frailty increases the risk of cancer. This 2-sample Mendelian-randomization (MR) study sought to analyze the relationship between frailty and the risk of colon cancer. Methods: The database was extracted from the Medical Research Council Integrative Epidemiology Unit (MRC-IEU) in 2021. The genome-wide association study (GWAS) data related to colon cancer was obtained from the GWAS website (http://gwas.mrcieu.ac.uk/datasets), involving 462,933 individuals' gene information. Single-nucleotide polymorphisms (SNPs) were defined as the instrumental variables (IVs). The SNPs closely associated with the Frailty Index at a genome-wide significance level were selected. To further screen the IVs, we selected the confounding factors using the PhenoScanner (http://www.phenoscanner.medschl.cam.ac.uk/phenoscanner). To estimate the causal effect of the Frailty Index on colon cancer, the MR-Egger regression, weighted median (WM1), inverse-variance weighted (IVW), and weight mode (WM2) methods were applied to calculate the SNP-frailty index and the SNP-cancer estimates. Cochran's Q statistic was used to estimate heterogeneity. The two-sample Mendelian randomization (TSMR) analysis was performed using the "TwoSampleMR" and "plyr" packages. All the statistical tests were 2-tailed, and a P value <0.05 was considered statistically significant. Results: We selected 8 SNPs as the IVs. The results of the IVW analysis [odds ratio (OR) =0.995, 95% confidence interval (CI): 0.990-1.001, P=0.052] showed that the genetic changes in the Frailty Index were not statistically associated with the risk of colon cancer, and no significant heterogeneity between these 8 genes was observed (Q =7.382, P=0.184). The MR-Egger (OR =0.987, 95% CI: 0.945-1.031, P=0.581), WM1 (OR =0.995, 95% CI: 0.990-1.001, P=0.118), WM2 (OR =0.996, 95% CI: 0.988-1.004, P=0.356), and SM (OR =0.996, 95% CI: 0.987-1.005, P=0.449) results were also consistent with each other. The sensitivity analysis based on the leave-one-out method showed that the individual SNPs did not affect the robustness of the results. Conclusions: Frailty might have no effect on the risk of colon cancer.

Deep learning to diagnose Hashimoto's thyroiditis from sonographic images.

Hashimoto's thyroiditis (HT) is the main cause of hypothyroidism. We develop a deep learning model called HTNet for diagnosis of HT by training on 106,513 thyroid ultrasound images from 17,934 patients and test its performance on 5051 patients from 2 datasets of static images and 1 dataset of video data. HTNet achieves an area under the receiver operating curve (AUC) of 0.905 (95% CI: 0.894 to 0.915), 0.888 (0.836-0.939) and 0.895 (0.862-0.927). HTNet exceeds radiologists' performance on accuracy (83.2% versus 79.8%; binomial test, p < 0.001) and sensitivity (82.6% versus 68.1%; p < 0.001). By integrating serologic markers with imaging data, the performance of HTNet was significantly and marginally improved on the video (AUC, 0.949 versus 0.888; DeLong's test, p = 0.004) and static-image (AUC, 0.914 versus 0.901; p = 0.08) testing sets, respectively. HTNet may be helpful as a tool for the management of HT.

Improved diagnosis of thyroid cancer aided with deep learning applied to sonographic text reports: a retrospective, multi-cohort, diagnostic study.

OBJECTIVE: Large volume radiological text data have been accumulated since the incorporation of electronic health record (EHR) systems in clinical practice. We aimed to determine whether deep natural language processing algorithms could aid radiologists in improving thyroid cancer diagnosis. METHODS: Sonographic EHR data were obtained from the EHR database. Pathological reports were used as the gold standard for diagnosing thyroid cancer. We developed thyroid cancer diagnosis based on natural language processing (THCaDxNLP) to interpret unstructured sonographic text reports for thyroid cancer diagnosis. We used the area under the receiver operating characteristic curve (AUROC) as the primary metric to measure the performance of the THCaDxNLP. We compared the performance of thyroid ultrasound radiologists aided with THCaDxNLP vs. those without THCaDxNLP using 5 independent test sets. RESULTS: We obtained a total number of 788,129 sonographic radiological reports. The number of thyroid sonographic data points was 132,277, 18,400 of which were thyroid cancer patients. Among the 5 test sets, the numbers of patients per set were 439, 186, 82, 343, and 171. THCaDxNLP achieved high performance in identifying thyroid cancer patients (the AUROC ranged from 0.857-0.932). Thyroid ultrasound radiologists aided with THCaDxNLP achieved significantly higher performances than those without THCaDxNLP in terms of accuracy (93.8% vs. 87.2%; one-sided t-test, adjusted P = 0.003), precision (92.5% vs. 86.0%; P = 0.018), and F1 metric (94.2% vs. 86.4%; P = 0.007). CONCLUSIONS: THCaDxNLP achieved a high AUROC for the identification of thyroid cancer, and improved the accuracy, sensitivity, and precision of thyroid ultrasound radiologists. This warrants further investigation of THCaDxNLP in prospective clinical trials.