Lower intrafamilial transmission rate of hepatitis B in patients with hepatitis d coinfection: a data-mining approach.

BACKGROUND: The presence of an infected family member significantly increases the risk of HBV transmission, but many socio-demographic and viral characteristics of family members affect the transmission rate. OBJECTIVES: In this study, we have used data mining techniques to investigate the impact of different variables in intrafamilial transmission of HBV infection. PATIENTS AND METHODS: demographic information, viral markers, and medical history of 330 patients with chronic hepatitis B and their offspring attending a referral center in Tehran were collected. Data-mining techniques were administered to detect patterns. RESULTS: The overall transmission rate was 15.7% (5.4% and 27.3% for male and female index cases respectively). In female patients, HBe Ag positively affected the transmission rate (49% vs. 23.4%). There was a dominant change in transmission rate of female patients with negative results for Hbe Ag with HDV coinfection, where the transmission rate changed from 25% in patients with negative results for HDV Ab to 5% in those with positive results. In Hbe Ag negative male index cases, the transmission rate was 1.3% in cases with positive results for HDV Ab compared to 7% in those with negative findings. The overall transmission rate was statistically different between patients with positive and negative results for HDV Ab (P = 0.016). CONCLUSIONS: There is a minor but consistent pattern change in the presence of HDV infection which reduces familial transmission of HBV, especially in female patients with negative results for HBe Ag.

Designing a Human T-Lymphotropic Virus Type 1 (HTLV-I) Diagnostic Model using the Complete Blood Count.

OBJECTIVE(S): Infection caused by Human T-Lymphotropic Virus Type 1 (HTLV-I) can be observed in some areas of Iran in form of endemic. Most of the cases are asymptomatic, and few cases progress to malignancies and neural diseases. Designing and implementing a model to screen people especially in endemic regions can help timely detection of infected people and improve the prognosis of the disease. MATERIALS AND METHODS: In this study, results of the complete blood count (CBC-diff) for 599 healthy people and the patients with different types of Leukemia and HTLV-I have been examined. Modeling was made using CHAID method. The final model was carried out based on the number of white blood cells (WBC), platelets, and percentages of eosinophils. RESULTS: The accuracy of the final model was 91%. By applying this model to the CBC-diff results of people without symptoms or miscellaneous patients in endemic regions of our country, disease carriers can be identified and referred for supplementary tests. CONCLUSION: With regard to the prevalence of different complications in infected people, these individuals can be identified earlier, leading to the improvement of the prognosis of this disease and the increase of the health status especially in endemic regions.

Risk factors associated with life-threatening infections in children with febrile neutropenia: a data mining approach.

PURPOSE: To determine risk factors (RFs) and their relationship with life-threatening infection (LTI) in children with febrile neutropenia (FN). METHOD: In this cross-sectional study, from December 2008 to November 2009, all children with FN admitted to Dr Sheikh Pediatric Hospital were enrolled. For each patient, demographic, clinical, and laboratory data were recorded and they were followed up for occurrence of LTI. RESULTS: One hundred and twenty episodes of FN in 68 patients were analyzed. The most common underlying disease was acute lymphoblastic leukemia (53.3%), 9 (7.5%) died from an infection and 35 patients (29.1%) had a LTI. Five variables were identified as RFs for LTI, that is, body temperature ≥39°C (P=0.000), presence of mucositis (P=0.000), abnormal chest x-ray (P=0.001), platelet count <20,000/mm (P=0.000), and absolute neutrophil count <100/mm (P=0.001). Risk of LTI was increasing according to number of RFs presented at the beginning of admission (from 2.8% in patients without RF to 100% in patients with 5 RF). Data mining analysis showed relationship between RFs with platelet count as the most important variable in the high-risk group for LTI. CONCLUSIONS: Evaluation of important RFs and judging the severity of patients' condition by studying the importance and relationship between RF at the time of admission can be a useful method for screening LTI in children with FN.

Canonical correlation analysis for data reduction in data mining applied to predictive models for breast cancer recurrence.

Data mining methods can be used for extracting specific medical knowledge such as important predictors for recurrence of breast cancer in pertinent data material. However, when there is a huge quantity of variables in the data material it is first necessary to identify and select important variables. In this study we present a preprocessing method for selecting important variables in a dataset prior to building a predictive model.In the dataset, data from 5787 female patients were analysed. To cover more predictors and obtain a better assessment of the outcomes, data were retrieved from three different registers: the regional breast cancer, tumour markers, and cause of death registers. After retrieving information about selected predictors and outcomes from the different registers, the raw data were cleaned by running different logical rules. Thereafter, domain experts selected predictors assumed to be important regarding recurrence of breast cancer. After that, Canonical Correlation Analysis (CCA) was applied as a dimension reduction technique to preserve the character of the original data.Artificial Neural Network (ANN) was applied to the resulting dataset for two different analyses with the same settings. Performance of the predictive models was confirmed by ten-fold cross validation. The results showed an increase in the accuracy of the prediction and reduction of the mean absolute error.