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.

Does improved access to diagnostic imaging results reduce hospital length of stay? A retrospective study.

BACKGROUND: One year after the introduction of Information and Communication Technology (ICT) to support diagnostic imaging at our hospital, clinicians had faster and better access to radiology reports and images; direct access to Computed Tomography (CT) reports in the Electronic Medical Record (EMR) was particularly popular. The objective of this study was to determine whether improvements in radiology reporting and clinical access to diagnostic imaging information one year after the ICT introduction were associated with a reduction in the length of patients' hospital stays (LOS). METHODS: Data describing hospital stays and diagnostic imaging were collected retrospectively from the EMR during periods of equal duration before and one year after the introduction of ICT. The post-ICT period was chosen because of the documented improvement in clinical access to radiology results during that period. The data set was randomly split into an exploratory part used to establish the hypotheses, and a confirmatory part. The data was used to compare the pre-ICT and post-ICT status, but also to compare differences between groups. RESULTS: There was no general reduction in LOS one year after ICT introduction. However, there was a 25% reduction for one group - patients with CT scans. This group was heterogeneous, covering 445 different primary discharge diagnoses. Analyses of subgroups were performed to reduce the impact of this divergence. CONCLUSION: Our results did not indicate that improved access to radiology results reduced the patients' LOS. There was, however, a significant reduction in LOS for patients undergoing CT scans. Given the clinicians' interest in CT reports and the results of the subgroup analyses, it is likely that improved access to CT reports contributed to this reduction.

Boron and strontium isotopic characterization of coal combustion residuals: validation of new environmental tracers.

In the U.S., coal fired power plants produce over 136 million tons of coal combustion residuals (CCRs) annually. CCRs are enriched in toxic elements, and their leachates can have significant impacts on water quality. Here we report the boron and strontium isotopic ratios of leaching experiments on CCRs from a variety of coal sources (Appalachian, Illinois, and Powder River Basins). CCR leachates had a mostly negative δ(11)B, ranging from -17.6 to +6.3‰, and (87)Sr/(86)Sr ranging from 0.70975 to 0.71251. Additionally, we utilized these isotopic ratios for tracing CCR contaminants in different environments: (1) the 2008 Tennessee Valley Authority (TVA) coal ash spill affected waters; (2) CCR effluents from power plants in Tennessee and North Carolina; (3) lakes and rivers affected by CCR effluents in North Carolina; and (4) porewater extracted from sediments in lakes affected by CCRs. The boron isotopes measured in these environments had a distinctive negative δ(11)B signature relative to background waters. In contrast (87)Sr/(86)Sr ratios in CCRs were not always exclusively different from background, limiting their use as a CCR tracer. This investigation demonstrates the validity of the combined geochemical and isotopic approach as a unique and practical identification method for delineating and evaluating the environmental impact of CCRs.

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.

Plasma miRNAs as early biomarkers for detecting hepatocellular carcinoma.

The early detection of hepatocellular carcinoma (HCC) presents a challenge because of the lack of specific biomarkers. Serum/plasma microRNAs (miRNAs) can discriminate HCC patients from controls. We aimed to identify and evaluate HCC-associated plasma miRNAs originating from the liver as early biomarkers for detecting HCC. In this multicenter three-phase study, we first performed screening using both plasma (HCC before and after liver transplantation or liver hepatectomy) and tissue samples (HCC, para-carcinoma and cirrhotic tissues). Then, we evaluated the diagnostic potential of the miRNAs in two case-control studies (training and validation sets). Finally, we used two prospective cohorts to test the potential of the identified miRNAs for the early detection of HCC. During the screening phase, we identified ten miRNAs, eight of which (miR-20a-5p, miR-25-3p, miR-30a-5p, miR-92a-3p, miR-132-3p, miR-185-5p, miR-320a and miR-324-3p) were significantly overexpressed in the HBV-positive HCC patients compared with the HBV-positive cancer-free controls in both the training and validation sets, with a sensitivity of 0.866 and specificity of 0.646. Furthermore, we assessed the potential for early HCC detection of these eight newly identified miRNAs and three previously reported miRNAs (miR-192-5p, miR-21-5p and miR-375) in two prospective cohorts. Our meta-analysis revealed that four miRNAs (miR-20a-5p, miR-320a, miR-324-3p and miR-375) could be used as preclinical biomarkers (pmeta  < 0.05) for HCC. The expression profile of the eight-miRNA panel can be used to discriminate HCC patients from cancer-free controls, and the four-miRNA panel (alone or combined with AFP) could be a blood-based early detection biomarker for HCC screening.

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.

A new instrument for measuring anticoagulation-related quality of life: development and preliminary validation.

BACKGROUND: Anticoagulation can reduce quality of life, and different models of anticoagulation management might have different impacts on satisfaction with this component of medical care. Yet, to our knowledge, there are no scales measuring quality of life and satisfaction with anticoagulation that can be generalized across different models of anticoagulation management. We describe the development and preliminary validation of such an instrument - the Duke Anticoagulation Satisfaction Scale (DASS). METHODS: The DASS is a 25-item scale addressing the (a) negative impacts of anticoagulation (limitations, hassles and burdens); and (b) positive impacts of anticoagulation (confidence, reassurance, satisfaction). Each item has 7 possible responses. The DASS was administered to 262 patients currently receiving oral anticoagulation. Scales measuring generic quality of life, satisfaction with medical care, and tendency to provide socially desirable responses were also administered. Statistical analysis included assessment of item variability, internal consistency (Cronbach's alpha), scale structure (factor analysis), and correlations between the DASS and demographic variables, clinical characteristics, and scores on the above scales. A follow-up study of 105 additional patients assessed test-retest reliability. RESULTS: 220 subjects answered all items. Ceiling and floor effects were modest, and 25 of the 27 proposed items grouped into 2 factors (positive impacts, negative impacts, this latter factor being potentially subdivided into limitations versus hassles and burdens). Each factor had a high degree of internal consistency (Cronbach's alpha 0.78-0.91). The limitations and hassles factors consistently correlated with the SF-36 scales measuring generic quality of life, while the positive psychological impact scale correlated with age and time on anticoagulation. The intra-class correlation coefficient for test-retest reliability was 0.80. CONCLUSIONS: The DASS has demonstrated reasonable psychometric properties to date. Further validation is ongoing. To the degree that dissatisfaction with anticoagulation leads to decreased adherence, poorer INR control, and poor clinical outcomes, the DASS has the potential to help identify reasons for dissatisfaction (and positive satisfaction), and thus help to develop interventions to break this cycle. As an instrument designed to be applicable across multiple models of anticoagulation management, the DASS could be crucial in the scientific comparison between those models of care.

Do You Want to Hear the Bad News? The Value of Diagnostic Tests for Alzheimer's Disease.

OBJECTIVE: The diagnosis of Alzheimer's disease (AD) remains difficult. Lack of diagnostic certainty or possible distress related to a positive result from diagnostic testing could limit the application of new testing technologies. The objective of this paper is to quantify respondents' preferences for obtaining AD diagnostic tests and to estimate the perceived value of AD test information. METHODS: Discrete-choice experiment and contingent-valuation questions were administered to respondents in Germany and the United Kingdom. Choice data were analyzed by using random-parameters logit. A probit model characterized respondents who were not willing to take a test. RESULTS: Most respondents indicated a positive value for AD diagnostic test information. Respondents who indicated an interest in testing preferred brain imaging without the use of radioactive markers. German respondents had relatively lower money-equivalent values for test features compared with respondents in the United Kingdom. CONCLUSIONS: Respondents preferred less invasive diagnostic procedures and tests with higher accuracy and expressed a willingness to pay up to €700 to receive a less invasive test with the highest accuracy.

Validation of the Food-Linked Virtual Response task.

This research validates a computerized dietary selection task (Food-Linked Virtual Response or FLVR) for use in studies of food consumption. In two studies, FLVR task responses were compared with measures of health consciousness, mood, body mass index, personality, cognitive restraint toward food, and actual food selections from a buffet table. The FLVR task was associated with variables which typically predict healthy decision-making and was unrelated to mood or body mass index. Furthermore, the FLVR task predicted participants' unhealthy selections from the buffet, but not overall amount of food. The FLVR task is an inexpensive, valid, and easily administered option for assessing momentary dietary decisions.