Clinical Decision Analysis

1976 ◽  
Vol 15 (04) ◽  
pp. 216-224 ◽  
Author(s):  
Th. R. Taylor
Keyword(s):  
Decision Theory ◽  
Decision Analysis ◽  
Clinical Decision ◽  
Computer Assisted ◽  
Major Objective ◽  
Routine Patient Care ◽  
Clinical Diagnoses ◽  
Basic Concepts ◽  
Assisted Diagnosis

Attempts have been made for almost two decades to use computers to make clinical diagnoses. Interest in such techniques persists despite little practical success in their application to routine patient care. The explanation of this lack of success is complex and includes (i) lack of understanding of the decisionmaking process itself and (ii) the need for a theoretical framework within which such systems can be developed. A major objective of this paper is to illustrate the contribution that the concepts and techniques associated with Decision Theory can make to both of these problems.After attempting to analyse the deficiencies of current approaches to computer-assisted diagnosis the paper discusses some of the basic concepts of decision theory. It then illustrates the role of decision theory in studies using different forms of clinical decision analysis.Finally the paper indicates the relevance of decision analysis to medical education and to the provision of health care.

Clinical Decision Analysis

1976 ◽  
Vol 15 (04) ◽  
pp. 216-224
Author(s):  
Th. R. Taylor
Keyword(s):  
Decision Theory ◽  
Decision Analysis ◽  
Clinical Decision ◽  
Computer Assisted ◽  
Major Objective ◽  
Routine Patient Care ◽  
Clinical Diagnoses ◽  
Basic Concepts ◽  
Assisted Diagnosis

Attempts have been made for almost two decades to use computers to make clinical diagnoses. Interest in such techniques persists despite little practical success in their application to routine patient care. The explanation of this lack of success is complex and includes (i) lack of understanding of the decisionmaking process itself and (ii) the need for a theoretical framework within which such systems can be developed. A major objective of this paper is to illustrate the contribution that the concepts and techniques associated with Decision Theory can make to both of these problems.After attempting to analyse the deficiencies of current approaches to computer-assisted diagnosis the paper discusses some of the basic concepts of decision theory. It then illustrates the role of decision theory in studies using different forms of clinical decision analysis.Finally the paper indicates the relevance of decision analysis to medical education and to the provision of health care.

scholarly journals Deep Transfer Learning for Improved Detection of Keratoconus using Corneal Topographic Maps

2021 ◽  
Author(s):  
Ali H. Al-Timemy ◽  
Nebras H. Ghaeb ◽  
Zahraa M. Mosa ◽  
Javier Escudero
Keyword(s):  
Transfer Learning ◽  
Learning Strategy ◽  
Clinical Decision ◽  
Topographic Maps ◽  
Computer Assisted ◽  
Clinical Knowledge ◽  
Average Accuracy ◽  
Assisted Diagnosis ◽  
Improved Accuracy ◽  
Fine Tune

Abstract Clinical keratoconus (KCN) detection is a challenging and time-consuming task. In the diagnosis process, ophthalmologists must revise demographic and clinical ophthalmic examinations. The latter include slit-lamb, corneal topographic maps, and Pentacam indices (PI). We propose an Ensemble of Deep Transfer Learning (EDTL) based on corneal topographic maps. We consider four pretrained networks, SqueezeNet (SqN), AlexNet (AN), ShuffleNet (SfN), and MobileNet-v2 (MN), and fine-tune them on a dataset of KCN and normal cases, each including four topographic maps. We also consider a PI classifier. Then, our EDTL method combines the output probabilities of each of the five classifiers to obtain a decision based on the fusion of probabilities. Individually, the classifier based on PI achieved 93.1% accuracy, whereas the deep classifiers reached classification accuracies over 90% only in isolated cases. Overall, the average accuracy of the deep networks over the four corneal maps ranged from 86% (SfN) to 89.9% (AN). The classifier ensemble increased the accuracy of the deep classifiers based on corneal maps to values ranging (92.2% to 93.1%) for SqN and (93.1% to 94.8%) for AN. Including in the ensemble-specific combinations of corneal maps’ classifiers and PI increased the accuracy to 98.3%. Moreover, visualization of first learner filters in the networks and Grad-CAMs confirmed that the networks had learned relevant clinical features. This study shows the potential of creating ensembles of deep classifiers fine-tuned with a transfer learning strategy as it resulted in an improved accuracy while showing learnable filters and Grad-CAMs that agree with clinical knowledge. This is a step further towards the potential clinical deployment of an improved computer-assisted diagnosis system for KCN detection to help ophthalmologists to confirm the clinical decision and to perform fast and accurate KCN treatment.

Cargo Mechanics (Application of Seakeeping--Revisited)

1986 ◽  
Vol 23 (03) ◽  
pp. 230-241
Author(s):  
Bruce L. Hutchison
Keyword(s):  
Risk Analysis ◽  
Decision Theory ◽  
Reliability Theory ◽  
Ship Motions ◽  
Basic Concepts

The basic concepts of modern risk and reliability theory are reviewed. Application of these concepts to topics arising in the analysis of ship motions, cargo sea-fastening design and voyage risk studies is explored. The role of risk analysis in decision theory is briefly discussed and the paper concludes with a suggested program of analysis for marine activities and enterprises subject to sea-action induced risk.

Computer-Assisted Clinical Decision-Making

1973 ◽  
Vol 12 (01) ◽  
pp. 45-51 ◽  
Author(s):  
G. A. GOBRY
Keyword(s):  
Decision Making ◽  
Decision Theory ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Computer Assisted ◽  
New Approaches ◽  
Computer Aided ◽  
Clinical Problems

This paper discusses some research in computer-aided! clinical decision-making. Experience with formal (decision theory) models is discussed and the limitations of these models are noted.It is argued that new approaches are needed to solve complex clinical problems, and one such approach is discussed.

scholarly journals Decision Theory as Practice: Crafting Rationality in Organizations

2010 ◽  
Vol 31 (11) ◽  
pp. 1531-1566 ◽  
Author(s):  
Laure Cabantous ◽  
Jean-Pascal Gond ◽  
Michael Johnson-Cramer
Keyword(s):  
Social Construction ◽  
Decision Theory ◽  
Decision Analysis ◽  
Rational Choice ◽  
Rational Choice Theory ◽  
Choice Theory ◽  
The Social ◽  
Wide Range

This paper explores the underlying practices whereby rationality — as defined in rational choice theory — is achieved within organizations. The qualitative coding of 58 case study reports produced by decision analysts, working in a wide range of settings, highlights how organizational actors can make decisions in accord with the axioms of rational choice theory. Our findings describe the emergence of ‘decision-analysis’ as a field and reveal the complex and fragile socio-technical infrastructure underlying the craft of rationality, the central role of calculability, and the various forms of bricolage that decision analysts deploy to make rational decisions happen. Overall, this research explores the social construction of rationality and identifies the practices sustaining the performativity of rational choice theory within organizations.

scholarly journals Rationality as the condition of individual rights in David Gauthier’s Morals by Agreement

2021 ◽  
pp. 7-22
Author(s):  
Marcin Saar
Keyword(s):  
Game Theory ◽  
Decision Theory ◽  
Individual Rights ◽  
David Gauthier ◽  
Lockean Proviso ◽  
Basic Concepts

The topic of this paper is the foundation for individual rights proposed by David Gauthier in his seminal 1986 book Morals by Agreement, and particularly the role of conception of rationality in this foundation. The foundation of rights is a part of Gauthier’s broader enterprise: to ground morals in rationality – more specifically, in the economic conception of rationality. Because of the importance of this conception for the whole of Gauthier’s project, we reconstruct first the conception of rationality which can be found in decision theory and game theory, presenting simultaneously in a relatively non-technical way some basic concepts of the aforementioned disciplines. We proceed then to reconstruction of the foundation of rights itself – it turns on Gauthier’s interpretation of the so-called “Lockean proviso.” Lastly, we turn to the connection between rationality and foundation of rights. It is to be found in the narrow compliance – the disposition to enter only into cooperation which satisfies conditions of fairness set out in part by the Lockean proviso.

scholarly journals Behavioral multi-criteria decision analysis: further elaborations on the todim method

2012 ◽  
Vol 37 (1) ◽  
pp. 3-8 ◽  
Author(s):  
Luiz Flavio Autran Monteiro Gomes ◽  
Xavier Ignacio González
Keyword(s):  
Decision Theory ◽  
Decision Analysis ◽  
Prospect Theory ◽  
Reference Point ◽  
Short Communication ◽  
Cumulative Prospect Theory ◽  
Behavioral Decision Theory ◽  
Behavioral Decision ◽  
Todim Method

Abstract.This short communication reviews the role of the TODIM method within behavioral decision theory and presents its genesis. Two important aspects of the method such as generalizing that method towards cumulative prospect theory and the choice of a reference point are further clarified.

Collection of Ego-Centered Network Data with Computer-Assisted Interviews

Methodology ◽  
2006 ◽  
Vol 2 (1) ◽  
pp. 7-15 ◽  
Author(s):  
Joachim Gerich ◽  
Roland Lehner
Keyword(s):  
Survey Methods ◽  
A Priori ◽  
Dynamic Structure ◽  
Computer Assisted ◽  
Network Data ◽  
Great Effort ◽  
Self Administration ◽  
Face To Face ◽  
Full Network

Although ego-centered network data provide information that is limited in various ways as compared with full network data, an ego-centered design can be used without the need for a priori and researcher-defined network borders. Moreover, ego-centered network data can be obtained with traditional survey methods. However, due to the dynamic structure of the questionnaires involved, a great effort is required on the part of either respondents (with self-administration) or interviewers (with face-to-face interviews). As an alternative, we will show the advantages of using CASI (computer-assisted self-administered interview) methods for the collection of ego-centered network data as applied in a study on the role of social networks in substance use among college students.

Sign in / Sign up

Export Citation Format

Share Document