Search

Objective: To develop a machine learning tool to integrate clinical data for the prediction of non-benign thyroid cytology and histology., Context: Papillary thyroid carcinoma is the most common endocrine malignancy. Since most nodules are benign, the challenge for the clinician is to identify those most likely to harbor malignancy while limiting exposure to surgical risks among those with benign nodules., Methods: Random forests (augmented to select features based on our clinical measure of interest), in conjunction with interpretable rule sets, were used on demographic, ultrasound, and biopsy data of thyroid nodules from children younger than 18 years at a tertiary pediatric hospital. Accuracy, false-positive rate (FPR), false-negative rate (FNR), and area under the receiver operator curve (AUROC) are reported., Results: Our models predict nonbenign cytology and malignant histology better than historical outcomes. Specifically, we expect a 68.04% improvement in the FPR, 11.90% increase in accuracy, and 24.85% increase in AUROC for biopsy predictions in 67 patients (28 with benign and 39 with nonbenign histology). We expect a 23.22% decrease in FPR, 32.19% increase in accuracy, and 3.84% decrease in AUROC for surgery prediction in 53 patients (42 with benign and 11 with nonbenign histology). This improvement comes at the expense of the FNR, for which we expect 10.27% with malignancy would be discouraged from performing biopsy, and 11.67% from surgery. Given the small number of patients, these improvements are estimates and are not tested on an independent test set., Conclusion: This work presents a first attempt at developing an interpretable machine learning based clinical tool to aid clinicians. Future work will involve sourcing more data and developing probabilistic estimates for predictions., (© The Author(s) 2021. Published by Oxford University Press on behalf of the Endocrine Society.)

Diabetes mellitus (DM) in children is most often caused by impaired insulin secretion (type 1 DM). In some children, the underlying mechanism for DM is increased insulin resistance, which can have different underlying causes. While the majority of these children require insulin dosages less than 2.0 U/kg/day to achieve normoglycemia, higher insulin requirements indicate severe insulin resistance. Considering the therapeutic challenges in patients with severe insulin resistance, early diagnosis of the underlying cause is essential in order to consider targeted therapies and to prevent diabetic complications. Although rare, several disorders can attribute to severe insulin resistance in pediatric patients. Most of these disorders are diagnosed through advanced diagnostic tests, which are not commonly available in low- or middle-income countries. Based on a case of DM with severe insulin resistance in a Surinamese adolescent who was later confirmed to have autosomal recessive congenital generalized lipodystrophy, type 1 (Berardinelli-Seip syndrome), we provide a systematic approach to the differential diagnosis and work-up. We show that a thorough review of medical history and physical examination generally provide sufficient information to diagnose a child with insulin-resistant DM correctly, and, therefore, our approach is especially applicable to low- or middle-income countries., (© The Author(s) 2021. Published by Oxford University Press on behalf of the Endocrine Society.)

Context: C-type natriuretic peptide (CNP) is critically involved in endochondral bone growth. Variants in the genes encoding CNP or its cyclic guanosine monophosphate (cGMP)-forming receptor (natriuretic peptide receptor-B [NPR-B], gene NPR2) cause monogenic growth disorders. Here we describe a novel gain-of-function variant of NPR-B associated with tall stature and macrodactyly of the great toes (epiphyseal chondrodysplasia, Miura type)., Design: History and clinical characteristics of 3 family members were collected. NPR2 was selected for sequencing. Skin fibroblasts and transfected HEK-293 cells were used to compare mutant versus wild-type NPR-B activities. Homology modeling was applied to understand the molecular consequences of the variant., Results: Mother's height was +2.77 standard deviation scores (SDS). The heights of her 2 daughters were +1.96 SDS at 7 years and +1.30 SDS at 4 years of age. Skeletal surveys showed macrodactyly of the great toes and pseudo-epiphyses of the mid- and proximal phalanges. Sequencing identified a novel heterozygous variant c.1444_1449delATGCTG in exon 8 of NPR2, predicted to result in deletion of 2 amino acids Met482-Leu483 within the submembrane region of NPR-B. In proband's skin fibroblasts, basal cGMP levels and CNP-stimulated cGMP production were markedly increased compared with controls. Consistently, assays with transfected HEK-293 cells showed markedly augmented baseline and ligand-dependent activity of mutant NPR-B., Conclusions: We report the second activating variant within the intracellular submembrane region of NPR-B resulting in tall stature and macrodactyly. Our functional and modeling studies suggest that this domain plays a critical role in the baseline conformation and ligand-dependent structural rearrangement of NPR-B required for cGMP production., (© Endocrine Society 2020. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)