The identification of a novel mutation (p.I223fs) in WRN associated with Werner syndrome.

PURPOSE: Werner syndrome (WS) is a rare autosomal recessive genetic disease caused by mutations in the WRN gene, and it is characterized by multiple manifestations corresponding to early-onset aging. This study reports the case of a WS patient with a novel WRN mutation. PATIENT AND METHODS: A 36-year-old male patient with WS was evaluated after approval from the local ethics committee. The clinical and biochemical findings of the patient were described. Peripheral blood sample was collected to extract genomic DNA for WRN gene exome sequencing. The three-dimensional (3D) protein structural prediction analysis was performed via the AlphaFold 2.2 program and PyMol software. RESULTS: We report the case of a clinically diagnosed WS patient with consanguineous parents who presented with complex manifestations including early-onset diabetes mellitus, binocular cataracts, cerebral infarction, cerebral atherosclerosis, hypertension, dyslipidemia, hypothyroidism, and suspected meningioma, accompanied by short stature, gray hair, rough skin with subcutaneous fat atrophy, a high-pitched voice, palmoplantar keratoderma, bilateral flat feet, and an indolent deep ulceration on the foot. Exome sequencing identified a novel homozygous frameshift mutation in the WRN gene, c.666-669 del TATT, p.I223fs. The 3D structure prediction showed that premature termination and significant structural changes could occur in the mutant WRN protein. CONCLUSION: We identified a novel homozygous frameshift mutation, p.I223fs, in WRN in a Chinese patient with WS, expanding the spectrum of mutations in WS.

Value of machine learning algorithms for predicting diabetes risk: A subset analysis from a real-world retrospective cohort study.

AIMS/INTRODUCTION: To compare the application value of different machine learning (ML) algorithms for diabetes risk prediction. MATERIALS AND METHODS: This is a 3-year retrospective cohort study with a total of 3,687 participants being included in the data analysis. Modeling variable screening and predictive model building were carried out using logistic regression (LR) analysis and 10-fold cross-validation, respectively. In total, six different ML algorithms, including random forests, light gradient boosting machine, extreme gradient boosting, adaptive boosting (AdaBoost), multi-layer perceptrons and gaussian naive bayes were used for model construction. Model performance was mainly evaluated by the area under the receiver operating characteristic curve. The best performing ML model was selected for comparison with the traditional LR model and visualized using Shapley additive explanations. RESULTS: A total of eight risk factors most associated with the development of diabetes were identified by univariate and multivariate LR analysis, and they were visualized in the form of a nomogram. Among the six different ML models, the random forests model had the best predictive performance. After 10-fold cross-validation, its optimal model has an area under the receiver operating characteristic value of 0.855 (95% confidence interval [CI] 0.823-0.886) in the training set and 0.835 (95% CI 0.779-0.892) in the test set. In the traditional LR model, its area under the receiver operating characteristic value is 0.840 (95% CI 0.814-0.866) in the training set and 0.834 (95% CI 0.785-0.884) in the test set. CONCLUSIONS: In the real-world epidemiological research, the combination of traditional variable screening and ML algorithm to construct a diabetes risk prediction model has satisfactory clinical application value.