The increasing prevalence of autoimmune thyroid diseases and thyroid cancer highlights the urgent need for improved diagnostic support approaches. Traditional diagnostic methods often rely primarily on biochemical markers or qualitative imaging evaluations, which may delay accurate disease identification and hinder timely treatment. The present study demonstrates that machine learning models integrating biochemical, demographic, and ultrasound data achieve strong classification performance for thyroid disorder identification. Tree-based algorithms, such as XGBoost and Random Forest, demonstrated strong performance, while deep learning models achieved high accuracy in imaging-based classification tasks. Although the results highlight the potential of multi-source data-driven approaches to support clinical decision-making, performance variability indicates the need for validation on larger and more diverse datasets. Future work should focus on expanding data sources, incorporating additional biomarkers, and improving model interpretability to facilitate clinical translation.
Because one in three of all individuals die from atherosclerotic cardiovascular disease (ASCVD), prevention of ASCVD is key to public health worldwide. Lipid clinics provide specialized diagnostic assessment, lifestyle management, and evidence-based lipid-lowering treatment to prevent ASCVD and acute pancreatitis in high-risk individuals. This includes individuals with familial hypercholesterolemia and/or markedly increased lipoprotein(a), statin intolerance, refractory or difficult-to-control low-density lipoprotein (LDL) cholesterol, severe hypertriglyceridaemia, and other rare or complex lipid disorders. Such specialized care not only benefits the individual patients and their families but facilitates dissemination of best practices in lipid disorder management to healthcare professionals in individual nations. Despite this, there is a lack of guidance on standards and metrics needed to establish a well-harmonized national lipid clinic network in most countries capable of offering comprehensive care. This consensus paper from the European Atherosclerosis Society Lipid Clinic Network aims to meet this unmet clinical need. We provide recommendations to enhance education and training on lipid disorders and to harmonize lipid clinics at both national and international levels. Furthermore, we provide guidance on optimal staffing structures and development of registries to improve diagnosis and management of lipid disorders. Finally, we offer recommendations to national and regional policymakers on funding of lipid clinics, with the long-term goal of reducing the overall societal burden and costs of cardiovascular and other lipid-related diseases.
Mitochondrial membrane protein-associated neurodegeneration (MPAN) is a rare neurological disease with childhood or adult onset. It is a subtype of clinically and genetically heterogeneous group of disorders, collectively known as neurodegeneration with brain iron accumulation . MPAN is generally associated with biallelic pathogenic variants in C19orf12. Herein, we describe genetic and clinical findings of two MPAN cases from Turkey. In the first case, we have identified the relatively common pathogenic variant of C19orf12 in the homozygous state, which causes late-onset MPAN. The second case was homozygous for an essential splice-site variation.
Penile fracture is an uncommon condition in day-to-day urological practice. Though most cases of penile fracture are traumatic in nature, these are typically unilateral. Synchronous bilateral cases have been rarely reported. We present the third case recorded to date, to the best of our knowledge, of a metachronous penile fracture to the contralateral corpora due to trauma related to sexual intercourse. The first presentation demonstrated a significant tear to the left corporal body at surgical exploration that was repaired. There was no postoperative complications or erectile dysfunction on outpatient follow-up. Six months thereafter, the patient had another similar presentation and demonstrated a right corporal body fracture which was repaired surgically on an urgent basis. Prompt diagnosis and low threshold for surgical intervention are essential to reduce morbidity and prevent long-term complications.
Purpose This study aimed to investigate the effectiveness of abdominal subcutaneous fat thickness (ASFT) in predicting antenatal insulin therapy (AIT) in patients with gestational diabetes mellitus (GDM). Methods A prospective study was conducted on patients with regulated blood sugar levels (n = 50) and those with unregulated blood sugar (n = 50) although medical nutrition therapy (MNT) was initiated and then AIT was applied. Using receiver operator characteristic (ROC) curve analysis, appropriate ASFT cut-off point values were found for the prediction of cases that required AIT after MNT in GDM pregnancies. Results Patients with GDM who needed AIT had a significantly higher ASFT value compared to those with GDM who did not need AIT. The optimal ASFT cutoff was 21.7 mm in predicting cases that required AIT after MNT (sensitivity, specificity, negative, and positive predictive values were 68.0%, 64.0%, 65.8%, and 66.6%, respectively). The risk of AIT increased 3.77-fold in those with ASFT > 21.7 mm in GDM pregnancies (p = 0.001). Conclusion The ASFT value was significantly higher in cases with GDM, with blood glucose levels not regulated despite MNT and AIT being then needed, compared to patients with blood glucose levels regulated by MNT, and who did not need AIT. Also, patients requiring AIT can be determined with moderate to high sensitivity and specificity using a cut-off value of ASFT > 21.7 mm. The ASFT > 21.7 mm cut-off point was seen to be more effective than BMI >= 30 kg/m(2) in the determination of cases where AIT is required.
