Mesalazine-induced renal calculi.

PATIENT: Female, 32 FINAL DIAGNOSIS: Renal colic Symptoms: Acute colic pain • macrohematuria MEDICATION: Mesalazine Clinical Procedure: CT scan of urinary tract • cystoscopy • gynecological consultation • stone analysis Specialty: Gastroenterology and Hepatology • Clinical Pharmacology. OBJECTIVE: Unexpected drug reaction. BACKGROUND: Mesalazine, a 5-aminosalicylic acid compound, is one of the cornerstones in modern treatment regimens of ulcerative colitis. It is generally well tolerated, although adverse reactions such as nephrotoxicity, perimyocarditis, and pancreatitis have been reported. CASE REPORT: We report the case of a 32-year-old woman with colitis who developed recurrent episodes of renal colic after introduction of mesalazine to her treatment. Biochemical analysis of the stones showed that they were composed of crystalized drug material. CONCLUSIONS: To our knowledge this is the first report of mesalazine precipitation in the urinary tract. We believe that it is vital for physicians to recognize this potentially severe adverse effect in the use of this treatment.

The crystallizing substochastic sequential machine extractor: CrySSMEx.

This letter presents an algorithm, CrySSMEx, for extracting minimal finite state machine descriptions of dynamic systems such as recurrent neural networks. Unlike previous algorithms, CrySSMEx is parameter free and deterministic, and it efficiently generates a series of increasingly refined models. A novel finite stochastic model of dynamic systems and a novel vector quantization function have been developed to take into account the state-space dynamics of the system. The experiments show that (1) extraction from systems that can be described as regular grammars is trivial, (2) extraction from high-dimensional systems is feasible, and (3) extraction of approximative models from chaotic systems is possible. The results are promising, and an analysis of shortcomings suggests some possible further improvements. Some largely overlooked connections, of the field of rule extraction from recurrent neural networks, to other fields are also identified.