Machine learning approaches for discerning intercorrelation of hematological parameters and glucose level for identification of diabetes mellitus.

BACKGROUND: The aim of this study is to explore the relationship between hematological parameters and glycemic status in the establishment of quantitative population-health relationship (QPHR) model for identifying individuals with or without diabetes mellitus (DM). METHODS: A cross-sectional investigation of 190 participants residing in Nakhon Pathom, Thailand in January-March, 2013 was used in this study. Individuals were classified into 3 groups based on their blood glucose levels (normal, Pre-DM and DM). Hematological (white blood cell (WBC), red blood cell (RBC), hemoglobin (Hb) and hematocrite (Hct)) and glucose parameters were used as input variables while the glycemic status was used as output variable. Support vector machine (SVM) and artificial neural network (ANN) are machine learning approaches that were employed for identifying the glycemic status while association analysis (AA) was utilized in discovery of health parameters that frequently occur together. RESULTS: Relationship amongst hematological parameters and glucose level indicated that the glycemic status (normal, Pre-DM and DM) was well correlated with WBC, RBC, Hb and Hct. SVM and ANN achieved accuracy of more than 98 % in classifying the glycemic status. Furthermore, AA analysis provided association rules for defining individuals with or without DM. Interestingly, rules for the Pre-DM group are associated with high levels of WBC, RBC, Hb and Hct. Conclusion This study presents the utilization of machine learning approaches for identification of DM status as well as in the discovery of frequently occurring parameters. Such predictive models provided high classification accuracy as well as pertinent rules in defining DM.

Implementation of External Quality Assessment Scheme in Clinical Chemistry for District Laboratories in Bhutan.

External Quality Assessment Scheme (EQAS) involves evaluation of a number of laboratories by an outside agency on the performance of a number of laboratories based on their analytical performance of tests on samples supplied by the external agency. In developing countries, establishment of national EQAS by preparing homemade quality control material is a useful scheme in terms of resources and time to monitor the laboratory performance. The objective of this study is to implement an EQAS to monitor the analytical performance of the district laboratories in Bhutan. Baseline information was collected through questionnaires. Lyophilized human serum including normal and abnormal levels were prepared and distributed to 19 participating laboratories. Nine routine analytes were included for the study. Their results were evaluated using Variance index scores (VIS) and Coefficient of variations (CV) was compared with Clinical Laboratory Improvement Act (CLIA) Proficiency Testing Criteria (PT) for each analyte. There was significant decrease in CV at the end of the study. The percentages of results in acceptable VIS as 'A' were 63, 60, 66, 69, 73 and 74, 75, 76 and 79 % in November 2009-July 2010 respectively. From our results, we concluded that, establishment of EQAS through distribution of home-made quality control material could be the useful scheme to monitor the laboratory performance in clinical chemistry in Bhutan.

Detection of a known mutation M412T in the LDL receptor in a Chinese Thai FH family.

BACKGROUND: Familial hypercholesterolemia (FH) is an autosomal dominant hypercholesterolemia caused by mutation in the LDL receptor gene. M412T mutation of the LDL receptor gene was previously observed in a single female patient diagnosed as having primary hypercholesterolemia. However, the analysis was incomplete and there was no confirmation of the M412T as the FH-causing mutation. We identified a mutation in the LDL receptor gene that underlines the severe FH phenotype in a new case, a female Chinese Thai patient. METHODS: Identification was made by PCR-SSCP, direct DNA sequencing and confirmed by allele specific amplification (ASA) originally designed for this current study. RESULTS: The entire LDL receptor gene screening revealed the genetic alteration that also caused M412T mutation in this new index patient. ASA analysis confirmed the DNA sequence in this patient and further identified three family members as M412T carriers. CONCLUSIONS: The finding of this mutation in 2 apparently unrelated index patients and the co-segregation of M412T and FH phenotype in the family of the present index case should provide evidence and confirm that the M412T was likely to be a disease-causing mutation. Whether M412T is common either as a founder or recurrent mutation among FH Chinese Thai population is unknown at present and remains to be clarified.