The Design and Testing of a New Approach to Computer-aided Differential Diagnosis

1983 ◽  
Vol 22 (03) ◽  
pp. 156-166 ◽  
Author(s):  
Dana Ludwig ◽  
D. Heilbronn
Keyword(s):  
Statistical Models ◽  
Medical Diagnosis ◽  
Logistic Regression Model ◽  
Medical Knowledge ◽  
Bayes Rule ◽  
Causal Network ◽  
New Approach ◽  
Linear Discriminant ◽  
Computer Aided ◽  
Design And Testing

An algorithm is presented for making diagnostic inferences on the basis of a causal network model of medical knowledge. The algorithm is based on Bayes Rule, but is unique in the way that it accounts for the presence of conditional non-independence of observations and for the presence of multiple diseases in the same patient. An evaluation of the system is performed on a database of patients with chest pain. In this evaluation, the diagnostic accuracy of the system is found to be inferior to that of a logistic regression model and comparable to that of a linear discriminant function. In a review of selected cases from this database, the system can be shown to provide inferences that are not possible with other simpler statistical models. The practicality of this and other computer aids to medical diagnosis is discussed.

scholarly journals Sparse Functional Linear Discriminant Analysis

Biometrika ◽  
2021 ◽  
Author(s):  
Juhyun Park ◽  
Jeongyoun Ahn ◽  
Yongho Jeon
Keyword(s):  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Real Data ◽  
New Approach ◽  
Linear Discriminant ◽  
Finite Samples ◽  
Regularization Problem ◽  
Bayes Error ◽  
Functional Setting ◽  
Regularized Solution

Abstract Functional linear discriminant analysis offers a simple yet efficient method for classification, with the possibility of achieving a perfect classification. Several methods are proposed in the literature that mostly address the dimensionality of the problem. On the other hand, there is a growing interest in interpretability of the analysis, which favors a simple and sparse solution. In this work, we propose a new approach that incorporates a type of sparsity that identifies nonzero sub-domains in the functional setting, offering a solution that is easier to interpret without compromising performance. With the need to embed additional constraints in the solution, we reformulate the functional linear discriminant analysis as a regularization problem with an appropriate penalty. Inspired by the success of ℓ1-type regularization at inducing zero coefficients for scalar variables, we develop a new regularization method for functional linear discriminant analysis that incorporates an L1-type penalty, ∫ |f|, to induce zero regions. We demonstrate that our formulation has a well-defined solution that contains zero regions, achieving a functional sparsity in the sense of domain selection. In addition, the misclassification probability of the regularized solution is shown to converge to the Bayes error if the data are Gaussian. Our method does not presume that the underlying function has zero regions in the domain, but produces a sparse estimator that consistently estimates the true function whether or not the latter is sparse. Numerical comparisons with existing methods demonstrate this property in finite samples with both simulated and real data examples.

Computer-aided 3-D simulation and prediction of craniofacial surgery: a new approach

2001 ◽  
Vol 29 (3) ◽  
pp. 156-158 ◽  
Author(s):  
Sabine Girod ◽  
Matthias Teschner ◽  
Uwe Schrell ◽  
Beate Kevekordes ◽  
Bernd Girod
Keyword(s):  
Craniofacial Surgery ◽  
New Approach ◽  
Computer Aided

DECISION MAKING BY VARIABLE CONTRIBUTION IN DISCRIMINANT, LOGIT, AND REGRESSION ANALYSES

2004 ◽  
Vol 03 (02) ◽  
pp. 265-279 ◽  
Author(s):  
STAN LIPOVETSKY ◽  
MICHAEL CONKLIN
Keyword(s):  
Decision Making ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Statistical Models ◽  
Regression Analyses ◽  
Discriminant Functions ◽  
Multivariate Statistical ◽  
Linear Discriminant ◽  
Variable Contribution ◽  
Linear Aggregate

Comparative contribution of predictors in multivariate statistical models is widely used for decision making on the importance of the variables for the aims of analysis and prediction. However, the analysis can be made difficult because of the predictors' multicollinearity that distorts estimates for coefficients in the linear aggregate. To solve the problem of the robust evaluation of the predictors' contribution, we apply the Shapley Value regression analysis that provides consistent results in the presence of multicollinearity both for regression and discriminant functions. We also show how the linear discriminant function can be constructed as a multiple regression, and how the logistic regression can be approximated by linear regression that helps to obtain the variables contribution in the linear aggregate.

ASYMMETRIES IN UNIVERSAL GRAMMAR The Role of Method and Statistics

2000 ◽  
Vol 22 (2) ◽  
pp. 209-228 ◽  
Author(s):  
John C. Paolillo
Keyword(s):  
Logistic Regression ◽  
Statistical Analysis ◽  
Statistical Models ◽  
Logistic Regression Model ◽  
Universal Grammar ◽  
Nonnative Speakers ◽  
Potential Explanation ◽  
Differential Learning ◽  
Grammaticality Judgments

Felix (1988) claimed to demonstrate that UG-based knowledge of grammaticality causes nonnative speakers (NNSs) to have more accurate grammaticality judgments on sentences that are ungrammatical according to UG than on those that are grammatical. Birdsong (1994) criticized the methodology employed, noting that it ignores “response bias” (a propensity to judge sentences as ungrammatical) as a potential explanation. Felix and Zobl (1994) dismissed this criticism as merely methodological. In this paper, Birdsong's criticism is upheld by considering a statistical model of the data. At the same time, a more complete logistic regression model allows a fuller statistical analysis, revealing tentative support for the asymmetry claim, as well as differential learning states for different constructions and a tendency toward transfer avoidance. These theoretically significant effects were unnoticed in the earlier discussion of this research. For SLA research on grammaticality judgments to proceed fruitfully, appropriate statistical models need to be considered in designing the research.

scholarly journals Fundamental Research on Hydraulic Systems Driven by Alternating Flow

10.14311/1606 ◽  
2012 ◽  
Vol 52 (4) ◽  
Author(s):  
Ioan-Lucian Marcu ◽  
Daniel-Vasile Banyai
Keyword(s):  
Volume Of Fluid ◽  
Hydraulic Systems ◽  
Hydraulic Motor ◽  
New Approach ◽  
Three Phase ◽  
Fundamental Research ◽  
Design And Testing

This paper presents a new approach to rotary hydraulic systems, and the functional principles of rotary hydraulic systems that can work using alternating flows. Hydraulic transmissions using alternating flows are based on bidirectional displacement of a predefined volume of fluid through the connection pipes between the alternating flow, the pressure energy generator and the motor. The paper also presents some considerations regarding the basic calculation formulas, the design and testing principles for a hydraulic motor driven by alternating flow, and also a three-phase rotary hydraulic motor.

Sign in / Sign up

Export Citation Format

Share Document