RESUMO

ABSTRACT Introduction: Metastatic disease of the thyroid corresponds to 2% of thyroid malignancies in autopsy series. Up to 50% of metastases are due to renal cell carcinoma (Ree). These can occur several years after diagnosis or nephrectomy. An isolated presence in the thyroid gland is rare. Clinical case presentation: We present the case of a 68-year-old woman with a history of Ree managed with nephrectomy and retroperitoneal lymphadenectomy. After 7 years free of symptoms, she noticed a mass over the thyroid region. Ultrasonography reported bilateral thyroid nodules. Due to the oncologic history and the affirmation of symptoms during swallowing, a full thyroidectomy was performed. The histopathological report was compatible with Ree metastasis. Discussion: The literature shows that the median time for thyroid metastasis in patients with Ree is 92 months. Most patients are asymptomatic, and a full thyroidectomy is recommended to prevent disease progression with a favorable impact on Survival. Conclusion: In patients with thyroid nodules and a history of Ree, metastasis should be suspected.

RESUMEN Introducción: La enfermedad metastásica a tiroides corresponde a 2% de las malignidades tiroideas en series de autopsias. Hasta el 50% de las metástasis se deben a carcinoma de células renales (Ree). Estas pueden ocurrir varios años después del diagnóstico o la nefrectomía. La presentación aislada en la glándula tiroides es rara. Presentación caso clínico: Presentamos el caso de una mujer de 68 años con historia de Ree manejada con nefrectomía y linfadenectomía retroperitoneal. Tras 7 años libre de síntomas notó la aparición de una masa sobre la región tiroidea. La ultrasonografía reportó nódulos tiroideos bilaterales. Por el antecedente oncológico y la afirmación de síntomas durante la deglución se le realizó tiroidectomía total. El reporte histopatológico fue compatible con metástasis de Ree. Discusión: La literatura muestra que el tiempo medio de metástasis a tiroides en pacientes con Ree es 92 meses. La mayoría de los pacientes son asintomáticos. Se recomienda la tiroidectomía total para prevenir progresión de la enfermedad con impacto favorable en la supervivencia. Conclusión: En los pacientes con nódulos tiroideos y antecedente de Ree se debe sospechar enfermedad metastásica.

RESUMO

Neuroblastoma is a solid tumor considered almost exclusively pediatric, with more than 95% of patients diagnosed before 10 years of age, with a mostly benign clinical course and with encouraging survival rates in these age ranges. It occurs rarely in adolescents, and the presentation in young adults or older people is even rarer; consequently, a more severe prognosis and higher mortality rates have been documented within this population. This is also due to a great limitation within the treatment since the chemotherapeutic regimens proposed so far are valid for pediatric patients, with low tolerance to it within the adult population. We present the case of a 24-year-old female patient with catecholamine-secreting neuroblastoma who obtained surgical management, with subsequent local tumor recurrence, with subsequent need for onco-specific and symptomatic management.

RESUMO

Artificial intelligence techniques have been positioned in the resolution of problems in various areas of healthcare. Clinical decision support systems developed from this technology have optimized the healthcare of patients with chronic diseases through mobile applications. In this study, several models based on this methodology have been developed to calculate the basal insulin dose in patients with type I diabetes using subcutaneous insulin infusion pumps. Methods. A pilot experimental study was performed with data from 56 patients with type 1 diabetes who used insulin infusion pumps and underwent continuous glucose monitoring. Several models based on artificial intelligence techniques were developed to analyze glycemic patterns based on continuous glucose monitoring and clinical variables in order to estimate the basal insulin dose. We used neural networks (NNs), Bayesian networks (BNs), support vector machines (SVMs), and random forests (RF). We then evaluated the agreement between predicted and actual values using several statistical error measurements: mean absolute error (MAE), mean square error (MSE), root-mean-square error (RMSE), Pearson's correlation coefficient (R), and determination coefficient (R 2). Results. Twenty-four different models were obtained, one for each hour of the day, with each chosen technique. Correlation coefficients obtained with RF, SVMs, NNs, and BNs were 0.9999, 0.9921, 0.0303, and 0.7754, respectively. The error increased between 06:00 and 07:00 and between 13:00 and 17:00. Conclusions. The performance of the RF technique was excellent and got very close to the actual values. Intelligence techniques could be used to predict basal insulin dose. However, it is necessary to explore the validity of the results and select the target population. Models that allow for more accurate levels of prediction should be further explored.