Search

Background: Artificial intelligence (AI) can play a significant role in the future of thyroidology. Thyroid nodules are common conditions that may benefit from AI through more accurate and efficient diagnosis, risk stratification, and medical or surgical management. Objective: This paper aims to review the latest developments in AI applications for diagnosing and managing thyroid nodules and cancers. Methods: English full-text articles published in the PubMed and Google Scholar databases from January 2014 to March 2024 were collected and reviewed to provide a comprehensive understanding of the topic. A total of 45 studies were selected based on relevance, robust methodology, statistical significance, and broader topic coverage. Results: Artificial intelligence has emerged as a powerful tool for managing thyroid nodules. First, several studies have demonstrated how AI-powered ultrasound interpretation enhances the diagnosis and classification of nodules while reducing the need for invasive fine-needle aspiration (FNA) biopsies. Second, AI significantly improves the cytopathological differentiation between benign and malignant thyroid nodules by minimizing reliance on pathologists' expertise and implementing standardized diagnostic criteria. When cytopathology is inconclusive, AI also aids in identifying molecular markers from omics data, distinguishing between normal and cancerous cells. Moreover, AI tools have been developed for prognosis assessment, predicting distant metastasis, recurrence, and surveillance by integrating medical imaging features with molecular and clinical factors. Additionally, some AI tools are designed for intraoperative evaluation, improving surgical techniques and reducing complications during thyroidectomy. In non-surgical treatments, several models have been developed to optimize therapeutic doses of radioactive iodine (RAI) and predict the outcomes of new drug formulations. Conclusions: Artificial intelligence has the potential to assist physicians in accurate thyroid nodule diagnosis, classification, decision-making, optimizing treatment strategies, and improving patient outcomes. However, there are still limitations to this technology. Artificial intelligence-driven tools require further advancements before they can be fully integrated into clinical practice and replace specialists. [ABSTRACT FROM AUTHOR]

Context: The diagnostic methods for diabetes mellitus (DM), a chronic metabolic disorder characterized by elevated blood sugar levels, are rapidly evolving thanks to artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL). This review explores the applications of AI in risk assessment and diagnosing different types of diabetes. Evidence Acquisition: The review highlights the effectiveness of various ML models, including support vector machines (SVMs), random forests (RFs), and DL techniques like convolutional neural networks (CNNs), in achieving high diagnostic accuracy. Challenges include limited data availability, interpretability of complex models, and the need for standardized performance metrics. Results: Machine learning methods like SVMs and RFs are highly effective at diagnosing different types of diabetes, and DL techniques like CNNs also show great promise. Conclusions: Overall, AI has immense potential to revolutionize diabetes diagnosis by facilitating risk assessment and early detection, improving treatment efficacy, and preventing severe complications. [ABSTRACT FROM AUTHOR]

Background & Objectives: Diabetes is a known chronic disease affecting more than 400 million people and causing millions of deaths worldwide annually. The World Health Organization predicts that by 2030, diabetes will become the seventh leading cause of death. In the last decades, numerous chemotherapy approaches have been used. However, herbal remedies have accounted for more than 70 percent of the total administered antidiabetic treatments during the last decade. In this study, we aimed to develop a novel natural antidiabetic therapy with Trigonella foenum-graecum (T. foenum-graecum) L. and Citrullus colocynthis (C. colocynthis) (L.). Based on past studies, using C. colocynthis singly can cause diarrhea, abdominal pain, and heartburn, hence in order to reduce these complications, we applied this plant in combination with T. foenum-graecum based on the recommendations of Persian medicine references. Materials & Methods: We admitted 34 diabetics aged 30 -65 years old to design a double-blind parallel randomized controlled clinical trial. We prepared therapeutic capsules containing a combination of 40 mg of C. colocynthis and 350 mg of T. foenum-graecum L. We divided participants into an interventional (n=17) and placebo (n=17) groups and measured fasting blood sugar (FBS) levels, lipid profile, and liver function tests initially. After two weeks, all participants returned for a visit, and FBS and blood sugar (BS) were measured. At the end (12th week), all outcomes were measured and analyzed using an independent t-test and Chi -squared (χ²). Results: The FBS levels decreased significantly in the intervention group compared to that of the control group (171.8±54.9 versus 149.6±46.4, p=0.024), but the improvement s in the lipid profile and liver function were not statistically significant. Conclusion: This study unveiled that combination of T. foenum-graecum L. and C. colocynthis L. at safe levels significantly decreased the FBS levels among T2DM patients. Further studies are needed to provide more efficient antidiabetic effects with the low side effects. [ABSTRACT FROM AUTHOR]

Developing self-care behaviors is a fundamental yet challenging strategy to prevent the complications of diabetes. This three-arm randomized controlled trial aimed to compare the effectiveness of combined mindfulness and self-regulation-based intervention with self-regulation-based intervention on self-care behaviors of Iranian older adults with diabetes in 2021–2022. Three public diabetic clinics were randomly assigned to three study groups and then 45 participants were randomly recruited from every clinic. 24-week educational interventions via WhatsApp included a self-regulation-based intervention (SRIP), a combined mindfulness and self-regulation intervention (CMSRIP), and routine care with training on COVID-19 prevention were performed in two intervention groups and a control group respectively. Data were collected at baseline and four and 16 weeks using a Mindfulness-based questionnaire (MSCS) and a summary of the diabetes self-care activities scale (SDSCA). The SPSS software (V. 22) was used to analyze data through ANOVA test, chi-square tests, one-way ANOVA, Levene's test, and Repeated measures MANCOVA at a significance level of less than 0.05. The total scores of MSCS and SDSCA in four and 16 weeks significantly increased compared to the baseline in both SRIP and CMSRIP groups (P <.001), but not in the control group. The mean scores of MSCS and SDSCA at week 4 in CMSRIP group improved significantly more than SRIP group (98.43 ± 5.83 vs. 90.31 ± 12.62 and 70.38 ± 4.18 vs. 62.35 ± 5.53). Combined mindfulness and self-regulation education are significantly effective in promoting self-care skills and improving cognitive processes and can used to improve older adults' self-care behaviors. This trial (ISRCTN77260130) was retrospectively registered on 28/09/2021. [ABSTRACT FROM AUTHOR]