Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis.

As more diagnostic testing options become available to physicians, it becomes more difficult to combine various types of medical information together in order to optimize the overall diagnosis. To improve diagnostic performance, here we introduce an approach to optimize a decision-fusion technique to combine heterogeneous information, such as from different modalities, feature categories, or institutions. For classifier comparison we used two performance metrics: The receiving operator characteristic (ROC) area under the curve [area under the ROC curve (AUC)] and the normalized partial area under the curve (pAUC). This study used four classifiers: Linear discriminant analysis (LDA), artificial neural network (ANN), and two variants of our decision-fusion technique, AUC-optimized (DF-A) and pAUC-optimized (DF-P) decision fusion. We applied each of these classifiers with 100-fold cross-validation to two heterogeneous breast cancer data sets: One of mass lesion features and a much more challenging one of microcalcification lesion features. For the calcification data set, DF-A outperformed the other classifiers in terms of AUC (p < 0.02) and achieved AUC=0.85 +/- 0.01. The DF-P surpassed the other classifiers in terms of pAUC (p < 0.01) and reached pAUC=0.38 +/- 0.02. For the mass data set, DF-A outperformed both the ANN and the LDA (p < 0.04) and achieved AUC=0.94 +/- 0.01. Although for this data set there were no statistically significant differences among the classifiers' pAUC values (pAUC=0.57 +/- 0.07 to 0.67 +/- 0.05, p > 0.10), the DF-P did significantly improve specificity versus the LDA at both 98% and 100% sensitivity (p < 0.04). In conclusion, decision fusion directly optimized clinically significant performance measures, such as AUC and pAUC, and sometimes outperformed two well-known machine-learning techniques when applied to two different breast cancer data sets.

Multivalent benzoboroxole functionalized polymers as gp120 glycan targeted microbicide entry inhibitors.

Microbicides are women-controlled prophylactics for sexually transmitted infections. The most important class of microbicides target HIV-1 and contain antiviral agents formulated for topical vaginal delivery. Identification of new viral entry inhibitors that target the HIV-1 envelope is important because they can inactivate HIV-1 in the vaginal lumen before virions can come in contact with CD4+ cells in the vaginal mucosa. Carbohydrate binding agents (CBAs) demonstrate the ability to act as entry inhibitors due to their ability to bind to glycans and prevent gp120 binding to CD4+ cells. However, as proteins they present significant challenges in regard to economical production and formulation for resource-poor environments. We have synthesized water-soluble polymer CBAs that contain multiple benzoboroxole moieties. A benzoboroxole-functionalized monomer was synthesized and incorporated into linear oligomers with 2-hydroxypropylmethacrylamide (HPMAm) at different feed ratios using free radical polymerization. The benzoboroxole small molecule analogue demonstrated weak affinity for HIV-1BaL gp120 by SPR; however, the 25 mol % functionalized benzoboroxole oligomer demonstrated a 10-fold decrease in the K(D) for gp120, suggesting an increased avidity for the multivalent polymer construct. High molecular weight polymers functionalized with 25, 50, and 75 mol % benzoboroxole were synthesized and tested for their ability to neutralize HIV-1 entry for two HIV-1 clades and both R5 and X4 coreceptor tropism. All three polymers demonstrated activity against all viral strains tested with EC(50)s that decrease from 15000 nM (1500 microg mL(-1)) for the 25 mol % functionalized polymers to 11 nM (1 microg mL(-1)) for the 75 mol % benzoboroxole-functionalized polymers. These polymers exhibited minimal cytotoxicity after 24 h exposure to a human vaginal cell line.