Application of Artificial Intelligence Techniques for the Estimation of Basal Insulin in Patients with Type I Diabetes.

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.

Castleman's disease presented as a retroperitoneal mass.

OBJECTIVE: We report one case of Castleman's disease and review published literature. METHODS: We report the case of a 58 year old man who was referred to our institution because of lumbar pain. A computed tomography scan revealed a retroperitoneal mass. Open surgical exploration and excision were carried out. Finally pathological examination addressed the diagnosis. RESULTS: Pathological examination demonstrated findings characteristic of unicentric hyaline vascular type of Castleman's disease. After surgical excision and 12 months follow-up there is no evidence of recurrence disease. CONCLUSIONS: Castleman's disease is a rare lymphoproliferative disorder of uncertain etiology. Retroperitoneal localization is exceptional.

Enfermedad de Castleman de localización retroperitoneal: A propósito de un caso / Castleman´s disease presented as a retroperitoneal mass

OBJETIVO: Presentamos el caso de una enfermedad de Castleman de localización retroperitoneal y revisamos la literatura. MÉTODO: Se presenta el caso de un paciente de 58 años de edad que fue remitido a nuestro centro por dolor lumbar. La tomografía axial computerizada demostró una masa retroperitoneal. Se decide entonces llevar a cabo una exploración quirúrgica y exéresis de la misma. Finalmente el estudio histológico determinó el diagnóstico. RESULTADOS: El estudio histológico fue congruente hiperplasia angiofolicular (enfermedad de Castleman) unicéntrica tipo hialino-vascular. Tras tratamiento quirúrgico radical el paciente evolucionó de forma satisfactoria encontrándose libre de recurrencia a los 12 meses. CONCLUSIONES: La enfermedad de Castleman es un proceso linfoproliferativo poco frecuente y de etiología desconocida. La localización retroperitoneal es excepcional (AU)

OBJECTIVE: We report one case of Castleman’s disease and review published literature. METHODS: We report the case of a 58 year old man who was referred to our institution because of lumbar pain. A computed tomography scan revealed a retroperitoneal mass. Open surgical exploration and excision were carried out. Finally pathological examination addressed the diagnosis. RESULTS: Pathological examination demonstrated findings characteristic of unicentric hyaline vascular type of Castleman’s disease. After surgical excision and 12 months follow-up there is no evidence of recurrence disease. CONCLUSIONS: Castleman’s disease is a rare lymphoproliferative disorder of uncertain etiology. Retroperitoneal localization is exceptional (AU)

Factors influencing the progression of renal damage in patients with unilateral renal agenesis and remnant kidney.

BACKGROUND: Although some studies have shown that the risk to develop proteinuria and renal insufficiency is increased in patients with a remnant kidney (RK) or unilateral renal agenesis (URA), other patients maintain normal renal function and negative proteinuria, and the reasons to explain these different outcomes are not known. METHODS: We performed a retrospective study of 54 patients with a severe reduction in renal mass (33 patients with URA and 21 with RK). Follow-up was 100 +/- 72 months. RESULTS: Twenty patients (group 1) showed normal renal function at presentation, whereas the 34 remaining (group 2) had proteinuria, and some of them renal insufficiency. Group 2 patients were older and had a higher blood pressure and BMI than group 1 patients. Eleven patients of group 1 remained normal throughout follow-up (group 1A), whereas the remaining 9 developed proteinuria/renal insufficiency (group 1B). BMI at presentation was significantly higher in group 1B: 27 +/- 3.6 kg/m(2) versus 21.6 +/- 2.6 kg/m(2), and BMI was the only factor statistically associated with the risk to develop proteinuria/renal insufficiency in group 1. Among group 2 patients, renal function remained stable in 20 (group 2A), and deteriorated (>50% increase of baseline serum creatinine) in the remaining 14 patients (group 2B). BMI at presentation and treatment with ACEI during follow-up were the only factors statistically associated with the risk for renal failure progression among group 2 patients. CONCLUSION: Overweight plays a fundamental role in the appearance of proteinuria and renal damage in patients with severe renal mass reduction.

Incidence of contralateral germ cell testicular tumors in South Europe: report of the experience at 2 Spanish university hospitals and review of the literature.

PURPOSE: The crude and cumulative incidence of contralateral germ cell testicular tumors (GCTTs) is between 1% to 5% and 3% to 6% at 10 to 15 years in previously reported studies. To evaluate the real incidence of a second GCTT in a southern European population the medical records of 623 patients with GCTT successfully treated between 1976 and 1993 at 2 university hospitals were reviewed. MATERIALS AND METHODS: All patients had been treated with standard treatment strategies according to disease stage and diagnosis year. Contralateral biopsy at GCTT diagnosis was not performed in any patient. Only those with a survival of 1 year or greater were included. In addition to the imaging and biochemical (tumor markers) procedures used to diagnose disease relapse, physical examination of the contralateral testis and/or testicular ultrasound was done yearly. RESULTS: At a median followup of 8.6 years (range 2 to 19.7) 6 patients (1%) had a contralateral GCTT, which was synchronous in 1 and metachronous in 5. The cumulative risk of a contralateral GCTT was 1.2% (95% CI 0.1% to 2.3%) at 15 years and it did not depend on the treatment for the first GCTT. CONCLUSIONS: The incidence of contralateral GCTT in our series was lower than expected compared with other published series. This finding mirrors the lower incidence of GCTT in the general population in our country than in other areas with a higher incidence of contralateral GCTT. Therefore, contralateral testicular biopsy at initial diagnosis is not mandatory in our experience.