Thalassemia and iron deficiency are the most common etiologies for microcytic anemia and there are indices discriminating both from common laboratory simple automatic counters. In this study a new classifier for discriminating thalassemia and non-thalassemia microcytic anemia was generated via combination of exciting indices with machine-learning techniques. A total of 350 Taiwanese adult patients whose anemia diagnosis, complete blood cell counts, and hemoglobin gene profiles were retrospectively reviewed. Thirteen prior established indices were applied to current cohort and the sensitivity, specificity, positive and negative predictive values were calculated. A support vector machine (SVM) with Monte-Carlo cross-validation procedure was adopted to generate the classifier. The performance of our classifier was compared with original indices by calculating the average classification error rate and area under the curve (AUC) for the sampled datasets. The performance of this SVM model showed average AUC of 0.76 and average error rate of 0.26, which surpassed all other indices. In conclusion, we developed a convenient tool for primary-care physicians when deferential diagnosis contains thalassemia for the Taiwanese adult population. This approach needs to be validated in other studies or bigger database.

Currently, the contribution of kidney function decline in renal and patient outcomes is unclear. There are few data on the associations of different etiologies of estimated glomerular filtration rate (eGFR) decline with outcomes in multidisciplinary care. The purpose of this investigation was to establish whether eGFR decline in patients with disease is an important risk factor for developing end-stage renal disease (ESRD) and death. From December 1, 2001 to December 31, 2011, 5097 adults with chronic kidney disease (CKD) received biochemical tests, physical examinations, a pathological examination, and a comprehensive questionnaire. We used linear regression models and multivariate Cox proportional hazards model to examine the outcome of eGFR decline in renal diseases with different etiologies. Mean age was 68.1±16.1 (standard deviation, SD) years, and 63.3% patients were male. In the studied cohort, 58.2% of the patients had systemic disease-related nephropathy (SDRN), 29.4% had primary renal diseases (PRDs), and 12.4% had other etiologies. The eGFR decline in SDRN had a significant association with dialysis in the Cox proportional hazards model [crude hazard ratio (HR) = 1.07, 95% confidence interval (CI), 1.04 to 1.10; adjusted HR 1.05, 95% CI, 1.02 to 1.08]. Diabetic nephropathy (DN) had the most severe eGFR decline in CKD stages 3, 4, and 5, and all contributed to the initiation of dialysis and death regardless of whether DN with or without eGFR decline was considered to be the cause. Although hypertensive nephropathy (HN) was related to significant acceleration of eGFR decline, it did not lead to poor outcome. There were still discrepancies between eGFR decline and outcomes in PRDs, hypertensive nephropathy, and lupus nephritis. eGFR decline and CKD staging provide an informative guide for physicians to make proper clinical judgments in the treatment of CKD, especially SDRN. Poor control of the underlying systemic disease will thus lead to more rapid progression of SDRN.