Evaluation the diagnostic accuracy of albuminuria detection in semi-quantitative urinalysis.

BACKGROUND: Taiwan has the highest end-stage renal disease prevalence in the world, and the costs on the maintenance of dialysis imposes a great financial burden on National Health Insurance. Routine urinalysis provides an opportunity for the early detection of microalbuminuria. We evaluated the accuracy of semi-quantitative chemical methods from Siemens Novus Pro12 dipstick for albumin-creatinine ratio (ACR). METHODS: We collected 1029 random urine samples and performed urinary analytic tests by Siemens Novus with Pro12 dipsticks and also calculated the urinary ACR. The reference method was performed by Hitachi LST008, a quantitative assay. The percentage of exact agreement in ACR was 81.9% between Siemens Novus and Hitachi LST008. The percentage of agreement within 1 level between the 2 methods was 98.5%. When ACR > 30 mg/g was defined as the threshold for positive results, the sensitivity, specificity, positive, and negative predictive values for microalbuminuria were 87.2%, 91.6%, 91.5%, and 87.3%, respectively. There were 778 cases with negative results of urinary protein, analyzed by conventional dipsticks. 149 of 778 (19.2%) cases were positive, measured by Pro12 dipsticks, and 111 of 149 (74.5%) cases were confirmed positive ACR by Hitachi LST008. CONCLUSIONS: Urinary ACR measured by Siemens Novus with Pro12 dipsticks was shown to be a reliable test for detection of microalbuminuria.

Increase Trichomonas vaginalis detection based on urine routine analysis through a machine learning approach.

Trichomonas vaginalis (T. vaginalis) detection remains an unsolved problem in using of automated instruments for urinalysis. The study proposes a machine learning (ML)-based strategy to increase the detection rate of T. vaginalis in urine. On the basis of urinalysis data from a teaching hospital during 2009-2013, individuals underwent at least one urinalysis test were included. Logistic regression, support vector machine, and random forest, were used to select specimens with a high risk of T. vaginalis infection for confirmation through microscopic examinations. A total of 410,952 and 428,203 specimens from men and women were tested, of which 91 (0.02%) and 517 (0.12%) T. vaginalis-positive specimens were reported, respectively. The prediction models of T. vaginalis infection attained an area under the receiver operating characteristic curve of more than 0.87 for women and 0.83 for men. The Lift values of the top 5% risky specimens were above eight. While the most risky vigintile was picked out by the models and confirmed by microscopic examination, the incremental cost-effectiveness ratios for T. vaginalis detection in men and women were USD$170.1 and USD$29.7, respectively. On the basis of urinalysis, the proposed strategy can significantly increase the detection rate of T. vaginalis in a cost-effective manner.