Computerized three-class classification of MRI-based prognostic markers for breast cancer

The purpose of this study is to investigate whether computerized analysis using three-class Bayesian artificial neural network (BANN) feature selection and classification can characterize tumor grades (grade 1, grade 2 and grade 3) of breast lesions for prognostic classification on DCE-MRI. A database of 26 IDC grade 1 lesions, 86 IDC grade 2 lesions and 58 IDC grade 3 lesions was collected. The computer automatically segmented the lesions, and kinetic and morphological lesion features were automatically extracted. The discrimination tasks-grade 1 versus grade 3, grade 2 versus grade 3, and grade 1 versus grade 2 lesions-were investigated. Step-wise feature selection was conducted by three-class BANNs. Classification was performed with three-class BANNs using leave-one-lesion-out cross-validation to yield computer-estimated probabilities of being grade 3 lesion, grade 2 lesion and grade 1 lesion. Two-class ROC analysis was used to evaluate the performances. We achieved AUC values of 0.80?±?0.05, 0.78?±?0.05 and 0.62?±?0.05 for grade 1 versus grade 3, grade 1 versus grade 2, and grade 2 versus grade 3, respectively. This study shows the potential for (1) applying three-class BANN feature selection and classification to CADx and (2) expanding the role of DCE-MRI CADx from diagnostic to prognostic classification in distinguishing tumor grades.     

Computerized classification of nuclear profiles in non-Hodgkin's lymphomas

The authors present experimental technics for the diagnosis of non-Hodgkin's lymphomas, based on instrumental classification of nuclear profiles using a video-based system for computerized interactive morphometry (CIM). In their system, the real time video image of a specimen is superimposed to a graphics overlay generated by a computer, consisting of a test area with four visual markers for random sampling of cells and a menu with several options to send direct commands to the system. Using a touch-sensitive screen mounted on a video monitor as an interactive peripheral, a trained observer traces 100 randomly selected lymphoid cells, counts mitoses in 25 microscopic fields, and categorizes the lesion as diffuse or nodular. Each cell is instrumentally classified into either small cell noncleaved, small cell cleaved, or large, based on the length of their nuclear profiles, their enclosed nuclear area, and a circularity factor. Thereafter the computer provides a "diagnosis," based on hierarchic analysis of the data. The morphometric data are also interpreted by alternate statistical methods of discriminatory classificatory analysis that provide a diagnosis and a probability statement derived from matching unknown cases with a data base. Forty-two lymphoid lesions have been categorized with the CIM system. Studies of interobserver and intraobserver variations in data collection are discussed. The potential advantages of CIM for the objective classification of non-Hodgkin's lymphomas are discussed.     

Computerized EEG pattern classification by adaptive segmentation and probability-density-function classification. Description of the method

A phenomenological model for the representation of clinical EEGs is proposed. It assumes each individual record to consist of a few repetitive patterns which are described sufficiently by their power spectra. An algorithm for automatic EEG evaluation is described. It consists of two steps, a segmentation process which isolates the elementary patterns, and a clustering procedure which groups similar patterns with each other. Results are represented in graphical form. Diagnostic classification is not attempted. An appendix highlights the advantages of autoregressive modelling for EEG spectral analysis and, in particular, the estimation of the power contained in the various "rhythms".     

Computerized diagnostic decision support system for the classification of preinvasive cervical squamous lesions

Previous studies have revealed considerable interobserver and intraobserver variation in the histological classification of preinvasive cervical squamous lesions. The aim of the present study was to develop a decision support system (DSS) for the histological interpretation of these lesions. Knowledge and uncertainty were represented in the form of a Bayesian belief network that permitted the storage of diagnostic knowledge and, for a given case, the collection of evidence in a cumulative manner that provided a final probability for the possible diagnostic outcomes. The network comprised 8 diagnostic histological features (evidence nodes) that were each independently linked to the diagnosis (decision node) by a conditional probability matrix. Diagnostic outcomes comprised normal; koilocytosis; and cervical intraepithelial neoplasia (CIN) I, CIN II, and CIN III. For each evidence feature, a set of images was recorded that represented the full spectrum of change for that feature. The system was designed to be interactive in that the histopathologist was prompted to enter evidence into the network via a specifically designed graphical user interface (i-Path Diagnostics, Belfast, Northern Ireland). Membership functions were used to derive the relative likelihoods for the alternative feature outcomes, the likelihood vector was entered into the network, and the updated diagnostic belief was computed for the diagnostic outcomes and displayed. A cumulative probability graph was generated throughout the diagnostic process and presented on screen. The network was tested on 50 cervical colposcopic biopsy specimens, comprising 10 cases each of normal, koilocytosis, CIN I, CIN II, and CIN III. These had been preselected by a consultant gynecological pathologist. Using conventional morphological assessment, the cases were classified on 2 separate occasions by 2 consultant and 2 junior pathologists. The cases were also then classified using the DSS on 2 occasions by the 4 pathologists and by 2 medical students with no experience in cervical histology. Interobserver and intraobserver agreement using morphology and using the DSS was calculated with kappa statistics. Intraobserver reproducibility using conventional unaided diagnosis was reasonably good (kappa range, 0.688 to 0.861), but interobserver agreement was poor (kappa range, 0.347 to 0.747). Using the DSS improved overall reproducibility between individuals. Using the DSS, however, did not enhance the diagnostic performance of junior pathologists when comparing their DSS-based diagnosis against an experienced consultant. However, the generation of a cumulative probability graph also allowed a comparison of individual performance, how individual features were assessed in the same case, and how this contributed to diagnostic disagreement between individuals. Diagnostic features such as nuclear pleomorphism were shown to be particularly problematic and poorly reproducible. DSSs such as this therefore not only have a role to play in enhancing decision making but also in the study of diagnostic protocol, education, self-assessment, and quality control.     

Computerized classification of congenital malformations using a modified Bayesian approach

The diagnostic classification of children with dysmorphic features involves over 200 syndromes and 232 findings, with an average of about 15 findings per syndrome. A knowledge base expressed in terms of Boolean combinations of findings is impractical. The normal Bayesian method requires a very large incidence matrix with the vast majority of cells being zero. A modified Bayesian method is proposed in which each syndrome is described in terms of its associated findings, whose incidence P (S/D) are designated as essential (0.90), prevalent (0.90), occasional (0.70) or rare (0.15), whilst P(S/-D) ranged from (0.08) to (0.10). The Bayesian calculation determines the probability of the presence P(D/S) or the absence P(-D/S) of each syndrome. The differential diagnosis consisted of all syndromes whose presence has a probability greater than 0.85. One hundred and thirty-one cases from the Hanna Khoushi Developmental Pediatrics Center at Haifa's Rothschild Hospital were considered. Of the 42 cases for which the center's specialists reached a diagnosis, the system listed the correct diagnosis for 91%. The system reached a diagnosis in about half of the remaining 89 cases. The medical literature is arranged by syndrome whilst the computer allows a case by case approach, thereby avoiding the need for the physician to consider each syndrome to see if it fits his case. This study shows that our modified Bayesian analysis is a valid method for shortening the physician's search in an area of great diagnostic complexity.     

Computerized analysis of mammographic parenchymal patterns for assessing breast cancer risk: effect of ROI size and location

The long-term goal of our research is to develop computerized radiographic markers for assessing breast density and parenchymal patterns that may be used together with clinical measures for determining the risk of breast cancer and assessing the response to preventive treatment. In our earlier studies, we found that women at high risk tended to have dense breasts with mammographic patterns that were coarse and low in contrast. With our method, computerized texture analysis is performed on a region of interest (ROI) within the mammographic image. In our current study, we investigate the effect of ROI size and ROI location on the computerized texture features obtained from 90 subjects (30 BRCA1/BRCA2 gene-mutation carriers and 60 age-matched women deemed to be at low risk for breast cancer). Mammograms were digitized at 0.1 mm pixel size and various ROI sizes were extracted from different breast regions in the craniocaudal (CC) view. Seventeen features, which characterize the density and texture of the parenchymal patterns, were extracted from the ROIs on these digitized mammograms. Stepwise feature selection and linear discriminant analysis were applied to identify features that differentiate between the low-risk women and the BRCA1/BRCA2 gene-mutation carriers. ROC analysis was used to assess the performance of the features in the task of distinguishing between these two groups. Our results show that there was a statistically significant decrease in the performance of the computerized texture features, as the ROI location was varied from the central region behind the nipple. However, we failed to show a statistically significant decrease in the performance of the computerized texture features with decreasing ROI size for the range studied.     

Mechanistic immunological based classification of rheumatoid arthritis

The classical autoimmunity paradigm in rheumatoid arthritis (RA) is strongly supported by immunogenetics suggesting follicular helper T-cell responses driving high titre specific autoantibodies that pre-dates disease onset. Using the immunological disease continuum model of inflammation against self with “pure” adaptive and innate immune disease at opposite boundaries, we propose a novel immune mechanistic classification describing the heterogeneity within RA. Mutations or SNPs in autoinflammatory genes including MEFV and NOD2 are linked to seronegative RA phenotypes including some so called palindromic RA cases. However, just as innate and adaptive immunity are closely functionally integrated, some ACPA+ RA cases have superimposed “autoinflammatory” features including abrupt onset attacks, severe attacks, self-limiting attacks, relevant autoinflammatory mutations or SNPs and therapeutic responses to autoinflammatory pathway therapies including colchicine and IL-1 pathway blockade. An emergent feature from this classification that non-destructive RA phenotypes, both innate and adaptive, have disease epicentres situated in the extracapsular tissues. This mixed innate and adaptive immunopathogenesis may be the key to understanding severe disease flares, resistant disease subsets that are unresponsive to standard therapy and for therapies that target the autoinflammatory component of disease that are not currently considered by expert therapeutic recommendations.     

定量CT在评估类风湿性关节炎相关间质性肺病中的应用

目的:探究胸部CT定量分析对于类风湿性关节炎相关间质性肺病（RA-ILD）患者肺间质改变早期诊断及病情评估的价值。方法:收集临床确诊RA患者105例,同时收集胸部CT无间质改变的非结缔组织病患者对照组80例。测量两组研究对象肺总体积（TLV）,利用定量CT肺部密度直方图计算CT值为-200~-700 HU的肺体积占全肺体积百分比（LAA-200~-700%）、CT值小于-950 HU的肺体积占全肺体积百分比（LAA-950%）、主动脉直径（AD）、肺动脉干直径（PAD）、主肺动脉干比值（AD/PAD）、左肺下叶直径2 mm支气管周围血管数量及面积（视区范围80 mm2）。比较RA患者组与对照组的测量值差异。结果:RA患者组与对照组相比,TLV、LAA-200~-700%、PAD、左肺下叶直径为2 mm的支气管视区范围为80 mm2时肺血管数量及面积均存在差异,其中RA患者组TLV为（4 047.60±1 160.11） mL,小于对照组（4 507.30±1 207.50） mL;LAA-200~-700%为14.42%±8.62%,大于对照组10.40%±3.87%,PAD为（26.39±3.59） mm,大于对照组（25.27±2.57） mm;RA组左肺下叶直径为2 mm支气管层面视区范围为80 mm2时肺血管数量为13.3±6.28,面积为（105.48±59.07） mm2;对照组血管数量为17.06±4.70,血管面积为（164.88±46.02） mm2,差异有统计学意义（P<0.001）。结论:RA-ILD患者肺部与对照组相比有差异,定量CT能有效识别评估RA-ILD早期肺血管改变。     

Thrombin-antithrombin III complex, proinflammatory cytokines, and fibrinolytic indices for assessing the severity of inflammation in pleural effusions

This study investigated coagulation-related variables, proinflammatory cytokines, and fibrinolytic indices to assess the severity of inflammation in patients with pleural effusions. Tuberculous pleural fluids revealed significantly higher concentrations of tumor necrosis factor-α (TNF-α) and plasminogen activator inhibitor type I (PAI-1) than did malignant and pneumonic pleural fluids. Among the coagulation-related variables, thrombin-antithrombin III complex (TAT) exhibited the largest difference in mean values between pleural fluids and blood samples (125.4 ± 45.1 vs 14.3 ± 20.3 ng/ml, p <0.05). Inflammatory parameters were more closely associated with TAT than tissue type plasminogen activator (tPA), PAI-1, and D-dimers. TAT levels in the severe inflammation group (153.8 ± 45.6 ng/ml) were significantly above those in the mild inflammation group (105.6 ± 38.5 ng/ml, p <0.05); however, no significant differences were observed in PAI-1 and D-dimers levels between the two groups. In conclusion, TNF-α and PAI-1 are important indicators in patients with tuberculous pleural effusions, and measurement of TAT is useful for assessing the severity of inflammation in pleural fluids.     

Computerized classification of suspicious regions in chest radiographs using subregion Hotelling observers.

We propose to investigate the use of subregion Hotelling observers (SRHOs) in conjunction with perceptrons for the computerized classification of suspicious regions in chest radiographs for being nodules requiring follow up. Previously, 239 regions of interest (ROIs), each containing a suspicious lesion with proven classification, were collected. We chose to investigate the use of SRHOs as part of a multilayer classifier to determine the presence of a nodule. Each SRHO incorporates information about signal, background, and noise correlation for classification. For this study, 225 separate Hotelling observers were set up in a grid across each ROI. Each separate observer discriminates an 8 by 8 pixel area. A round robin sampling scheme was used to generate the 225 features, where each feature is the output of the individual observers. These features were then rank ordered by the magnitude of the weights of a perceptron. Once rank ordered, subsets of increasing number of features were selected to be used in another perceptron. This perceptron was trained to minimize mean squared error and the output was a continuous variable representing the likelihood of the region being a nodule. Performance was evaluated by receiver operating characteristic (ROC) analysis and reported as the area under the curve (Az). The classifier was optimized by adding additional features until the Az declined. The optimized subset of observers then were combined using a third perceptron. A subset of 80 features was selected which gave an Az of 0.972. Additionally, at 98.6% sensitivity, the classifier had a specificity of 71.3% and increased the positive predictive value from 60.7% to 84.1 %. Preliminary results suggest that using SRHOs in combination with perceptrons can provide a successful classification scheme for pulmonary nodules. This approach could be incorporated into a larger computer aided detection system for decreasing false positives.     

Group education for patients with rheumatoid arthritis

Patients with rheumatoid arthritis must learn to adjust their exercise, rest and medication to the varying activity of the disease. Patient education can help patients in making the right decisions about adjustments in their treatment regimen and in attaining “self-management” behaviors. We developed a group education program based on social learning theory and the ‘Arthritis Self Management Course’ developed in the USA by Lorig. Goal of the program is the strengthening of self-efficacy, outcome expectations and self-management behaviors of RA patients which may lead to better health status. The program has been evaluated in an experimental design. We established significant positive effects of the group training on functional disability, joint tenderness, practice of relaxation and physical exercises, self-management behavior, outcome expectations, self-efficacy function and knowledge. After 14 months we still found effects on practice of physical exercises, self-efficacy function and knowledge.     

Health Attitude Survey. A scale for assessing somatizing patients

The authors designed an instrument, the Health Attitude Survey, to assess somatization, and administered it to over 1,000 patients attending a general medicine clinic. Within this population, a series of somatizing patients and control patients were identified for purposes of developing and testing the instrument. The 27-item scale was rapidly administered and acceptable to the patients. Based on comparisons with other measures of somatization, the instrument appeared to be a valid measure of the attitudes and perceptions of somatizing patients, and it distinguished these patients from the control subjects. The measure showed acceptable predictive value and may prove useful in clinical settings, where rapid screening is desired.     

Laser evoked potentials for assessing sensory neuropathy in human patients

Sensory neuropathy usually impairs tactile sensations related to large myelinated afferents (Abeta) as well as thermal-pain sense related to small myelinated (Adelta) and unmyelinated (C) afferents. By selectively affecting large or small fibres, some sensory neuropathies may also provoke a dissociated sensory loss. Standard nerve conduction studies and somatosensory evoked potentials assess Abeta-fibre function only. Laser pulses selectively excite free nerve endings in the superficial skin layers and evoke Adelta-related brain potentials (LEPs). From earlier studies and new cases we collected data on 270 patients with sensory neuropathy. LEPs often disclosed subclinical dysfunction of Adelta fibres and proved a sensitive and reliable diagnostic tool for assessing small-fibre function in sensory neuropathy.     

Development and classification of a robust inventory of near real-time outcome measurements for assessing information technology interventions in health care

ObjectiveTo develop and classify an inventory of near real-time outcome measures for assessing information technology (IT) interventions in health care and assess their relevance as perceived by experts in the field.Materials and methodsTo verify the robustness and coverage of a previously published inventory of measures and taxonomy, we conducted semi-structured interviews with clinical and administrative leaders from a large care delivery system to collect suggestions of outcome measures that can be calculated with data available in electronic format for near real-time monitoring of EHR implementations. We combined these measures with the most commonly reported in the literature. We then conducted two online surveys with subject-matter experts to collect their perceptions of the relevance of the measures, and identify other potentially relevant measures.ResultsWith input from experienced health care leaders and informaticists, we developed an inventory of 102 outcome measures. These measures were classified into a taxonomy of commonly used measures around the categories of quality, productivity, and safety. Safety measures were rated as most relevant by subject-matter experts, especially those measuring medication processes. Clinician satisfaction and measures assessing mean time to complete tasks and time spent on electronic documentation were also rated as highly relevant.DiscussionBy expanding the coverage of our previously published inventory and taxonomy, we expect to help providers, health IT vendors and researchers to more effectively and consistently monitor the impact of EHR implementations in near real-time, and report more standardized outcomes in future studies. We identified several measures not commonly assessed by previous studies of IT implementations, especially those of safety and productivity, which deserve more attention from the broader informatics community.ConclusionOur inventory of measures and taxonomy will help researchers identify gaps in their measurement approaches and report more standardized measurements of IT interventions that could be shared among researchers, hopefully facilitating comparison across future studies and increasing our understanding of the impact of IT interventions in health care.     

Cholesterol and serotonin indices in depressed and suicidal patients

BACKGROUND: Prolactin and cortisol responses to d-fenfluramine challenge of central serotonin are reduced in depressed and suicidal patients. Low serum cholesterol levels are also reported in suicidal behavior. Thus, we examined for a relationship between serum cholesterol and fenfluramine challenge responses in patients with depression and/or attempted suicide. METHODS: We studied 12 patients and six controls. Blood was drawn for baseline serum cholesterol and the d-fenfluramine challenge test performed. RESULTS: Serum cholesterol levels were significantly lower in suicidal patients than in either non-suicidal patients or controls. However, neither the prolactin nor cortisol responses to d-fenfluramine correlated significantly with serum cholesterol levels. CONCLUSION: No relationship was found between serum cholesterol and these peripheral indices of serotonergic function.