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.

Qualitative analysis of the interdisciplinary interaction between data analysis specialists and novice clinical researchers.

BACKGROUND: The inherent complexity of statistical methods and clinical phenomena compel researchers with diverse domains of expertise to work in interdisciplinary teams, where none of them have a complete knowledge in their counterpart's field. As a result, knowledge exchange may often be characterized by miscommunication leading to misinterpretation, ultimately resulting in errors in research and even clinical practice. Though communication has a central role in interdisciplinary collaboration and since miscommunication can have a negative impact on research processes, to the best of our knowledge, no study has yet explored how data analysis specialists and clinical researchers communicate over time. METHODS/PRINCIPAL FINDINGS: We conducted qualitative analysis of encounters between clinical researchers and data analysis specialists (epidemiologist, clinical epidemiologist, and data mining specialist). These encounters were recorded and systematically analyzed using a grounded theory methodology for extraction of emerging themes, followed by data triangulation and analysis of negative cases for validation. A policy analysis was then performed using a system dynamics methodology looking for potential interventions to improve this process. Four major emerging themes were found. Definitions using lay language were frequently employed as a way to bridge the language gap between the specialties. Thought experiments presented a series of "what if" situations that helped clarify how the method or information from the other field would behave, if exposed to alternative situations, ultimately aiding in explaining their main objective. Metaphors and analogies were used to translate concepts across fields, from the unfamiliar to the familiar. Prolepsis was used to anticipate study outcomes, thus helping specialists understand the current context based on an understanding of their final goal. CONCLUSION/SIGNIFICANCE: The communication between clinical researchers and data analysis specialists presents multiple challenges that can lead to errors.

Validation of ICDPIC software injury severity scores using a large regional trauma registry.

BACKGROUND: Administrative or quality improvement registries may or may not contain the elements needed for investigations by trauma researchers. International Classification of Diseases Program for Injury Categorisation (ICDPIC), a statistical program available through Stata, is a powerful tool that can extract injury severity scores from ICD-9-CM codes. We conducted a validation study for use of the ICDPIC in trauma research. METHODS: We conducted a retrospective cohort validation study of 40,418 patients with injury using a large regional trauma registry. ICDPIC-generated AIS scores for each body region were compared with trauma registry AIS scores (gold standard) in adult and paediatric populations. A separate analysis was conducted among patients with traumatic brain injury (TBI) comparing the ICDPIC tool with ICD-9-CM embedded severity codes. Performance in characterising overall injury severity, by the ISS, was also assessed. RESULTS: The ICDPIC tool generated substantial correlations in thoracic and abdominal trauma (weighted κ 0.87-0.92), and in head and neck trauma (weighted κ 0.76-0.83). The ICDPIC tool captured TBI severity better than ICD-9-CM code embedded severity and offered the advantage of generating a severity value for every patient (rather than having missing data). Its ability to produce an accurate severity score was consistent within each body region as well as overall. CONCLUSIONS: The ICDPIC tool performs well in classifying injury severity and is superior to ICD-9-CM embedded severity for TBI. Use of ICDPIC demonstrates substantial efficiency and may be a preferred tool in determining injury severity for large trauma datasets, provided researchers understand its limitations and take caution when examining smaller trauma datasets.

Computational Methods for RNA Structure Validation and Improvement.

With increasing recognition of the roles RNA molecules and RNA/protein complexes play in an unexpected variety of biological processes, understanding of RNA structure-function relationships is of high current importance. To make clean biological interpretations from three-dimensional structures, it is imperative to have high-quality, accurate RNA crystal structures available, and the community has thoroughly embraced that goal. However, due to the many degrees of freedom inherent in RNA structure (especially for the backbone), it is a significant challenge to succeed in building accurate experimental models for RNA structures. This chapter describes the tools and techniques our research group and our collaborators have developed over the years to help RNA structural biologists both evaluate and achieve better accuracy. Expert analysis of large, high-resolution, quality-conscious RNA datasets provides the fundamental information that enables automated methods for robust and efficient error diagnosis in validating RNA structures at all resolutions. The even more crucial goal of correcting the diagnosed outliers has steadily developed toward highly effective, computationally based techniques. Automation enables solving complex issues in large RNA structures, but cannot circumvent the need for thoughtful examination of local details, and so we also provide some guidance for interpreting and acting on the results of current structure validation for RNA.

Inter-site and inter-scanner diffusion MRI data harmonization.

We propose a novel method to harmonize diffusion MRI data acquired from multiple sites and scanners, which is imperative for joint analysis of the data to significantly increase sample size and statistical power of neuroimaging studies. Our method incorporates the following main novelties: i) we take into account the scanner-dependent spatial variability of the diffusion signal in different parts of the brain; ii) our method is independent of compartmental modeling of diffusion (e.g., tensor, and intra/extra cellular compartments) and the acquired signal itself is corrected for scanner related differences; and iii) inter-subject variability as measured by the coefficient of variation is maintained at each site. We represent the signal in a basis of spherical harmonics and compute several rotation invariant spherical harmonic features to estimate a region and tissue specific linear mapping between the signal from different sites (and scanners). We validate our method on diffusion data acquired from seven different sites (including two GE, three Philips, and two Siemens scanners) on a group of age-matched healthy subjects. Since the extracted rotation invariant spherical harmonic features depend on the accuracy of the brain parcellation provided by Freesurfer, we propose a feature based refinement of the original parcellation such that it better characterizes the anatomy and provides robust linear mappings to harmonize the dMRI data. We demonstrate the efficacy of our method by statistically comparing diffusion measures such as fractional anisotropy, mean diffusivity and generalized fractional anisotropy across multiple sites before and after data harmonization. We also show results using tract-based spatial statistics before and after harmonization for independent validation of the proposed methodology. Our experimental results demonstrate that, for nearly identical acquisition protocol across sites, scanner-specific differences can be accurately removed using the proposed method.