Diagnostic and prognostic decision support systems

Diagnostic decision support systems provide a quantitative evaluation of diagnostic evidence and the capability to combine diagnostic evidence in such a manner that a numeric measure of certainty in a final diagnostic recommendation results. Generally, expert systems serve to establish a diagnostic decision, inference networks allow a detailed analysis of the diagnostic value of diagnostic clues, case-based reasoning systems are designed to provide a prognostic assessment targeted to an individual patient. In all of these systems, symbolic information, i.e., traditional diagnostic, linguistic terms and concepts are processed and quantitatively evaluated.     

An industrial process view of information delivery to support clinical decision making: implications for systems design and process measures

Clinical decision making is driven by information in the form of patient data and clinical knowledge. Currently prevalent systems used to store and retrieve this information have high failure rates, which can be traced to well-established system constraints. The authors use an industrial process model of clinical decision making to expose the role of these constraints in increasing variability in the delivery of relevant clinical knowledge and patient data to decision-making clinicians. When combined with nonmodifiable human cognitive and memory constraints, this variability in information delivery is largely responsible for the high variability of decision outcomes. The model also highlights the supply characteristics of information, a view that supports the application of industrial inventory management concepts to clinical decision support. Finally, the clinical decision support literature is examined from a process-improvement perspective with a focus on decision process components related to information retrieval. Considerable knowledge gaps exist related to clinical decision support process measurement and improvement.     

Rule-based consultation systems]

This paper overviews the architecture of rule-based consultation systems and illustrates how such systems work by an Antibiotic Advisor. Knowledge representation and the inference engine implemented in the program are briefly described along with a sample consultation with the system. The paper is concluded with an analysis of the advantages and limitations of rule-based reasoning in clinical decision support.     

Transfer of radiocaesium in sensitive agricultural environments after the Chernobyl fallout in Sweden: III. County of V?sternorrland

Clinicians are faced with the difficulty of filtering large quantities of information and incorporating evidence to make safe and accurate diagnostic, therapeutic and management decisions. One solution to this difficulty is the development of evidence-based decision support tools designed to provide relevant and up-to-date evidence to clinicians. However, as investigations of medical decision making have found that hypothesis generation and clinical reasoning differ as a function of expertise, the gathering, interpretation and use of evidence against hypotheses depends on the prior knowledge of the clinician. The specific focus of the study is to understand how clinical evidence is gathered and evaluated during diagnostic reasoning. Verbal data during clinical interactions with physicians, residents and final year medical students were collected and transcribed. The dialogues were analyzed using three levels of coding: cognitive, epistemological and linguistic pragmatic perspectives. Results show that: (a) the ability to index and use adequate evidence by physicians, residents and students is a function of the early generation of accurate hypotheses: and (b) strategies for resolving inconsistent evidence differ as a function of medical expertise. The relationship between these findings and its application for the development of adequate knowledge-based systems for indexing and retrieval is discussed.     

A psychiatric diagnostic system integrating probabilistic and categorical reasoning

We describe a diagnostic support system for clinical psychiatry and its evaluation results. The system has two inter-related components: a rule-based reasoning part associated with uncertainty, and a deterministic part, that uses heuristics to perform categorical reasoning. The system includes the 30 groups of psychiatric diagnoses which are classified under the categories 290 to 319 of the DSM-III-R and the ICD-9. There are, in fact, 1508 rules relating 208 clinical findings with 257 diagnoses. The reasoning strategy is based on selecting and differentiating diagnostic categories in a hierarchical classification tree. The system is intended to be used for education of medical students, and to help non-specialist clinicians, residents in psychiatry, or experts with few years of experience in decision making. We tested the diagnostic performance of the system using case reports extracted from a specialized journal. In 52.8% of the cases, the correct diagnosis was ranked as the first hypothesis using only the rule-based part. In combination with the deterministic strategy, the correct diagnosis could be made for 73.6% of the analyzed cases.     

MEDUSA: a fuzzy expert system for medical diagnosis of acute abdominal pain

Even today, the diagnosis of acute abdominal pain represents a serious clinical problem. The medical knowledge in this field is characterized by uncertainty, imprecision and vagueness. This situation lends itself especially to be solved by the application of fuzzy logic. A fuzzy logic-based expert system for diagnostic decision support is presented (MEDUSA). The representation and application of uncertain and imprecise knowledge is realized by fuzzy sets and fuzzy relations. The hybrid concept of the system enables the integration of rule-based, heuristic and case-based reasoning on the basis of imprecise information. The central idea of the integration is to use case-based reasoning for the management of special cases, and rule-based reasoning for the representation of normal cases. The heuristic principle is ideally suited for making uncertain, hypothetical inferences on the basis of fuzzy data and fuzzy relations.     

Decisions and the evolution of memory: Multiple systems, multiple functions.

Memory evolved to supply useful, timely information to the organism's decision-making systems. Therefore, decision rules, multiple memory systems, and the search engines that link them should have coevolved to mesh in a coadapted, functionally interlocking way. This adaptationist perspective suggested the scope hypothesis: When a generalization is retrieved from semantic memory, episodic memories that are inconsistent with it should be retrieved in tandem to place boundary conditions on the scope of the generalization. Using a priming paradigm and a decision task involving person memory, the authors tested and confirmed this hypothesis. The results support the view that priming is an evolved adaptation. They further show that dissociations between memory systems are not--and should not be--absolute: Independence exists for some tasks but not others. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

The two stage case-based reasoning technology research on the basis of the expert decision

In some domain expert’s decision-making is intelligent output by comprehensive analysis and reasoning for the numerous decision-making factors,constraints and the goal in their domain,it is the concentrated expression of domain knowledge.Be aimed at field knowledge induction;sum up the exploration with systematization method,the two stages case-based reasoning(CBR) technology on the basis of the expert decision cased is present.The main idea,according to the characteristic of problem,analysis and decision process of field expert is carried out case-reasoning by two steps,and the field knowledge can be classified,induction and accumulated from different angles by multi case libraries.This technology includes two aspects,first,through two state case-based reasoning mechanisms to achieve area of decision-making process simulation;second,the CBR service in two more cases of library design process.First,two stage case-based reasoning mechanism,the first stage case-based reasoning to analyze the main level,clear nature of the problem,type,degree and character as the main content;the second stage case reasoning takes first order case reasoning result as basis then,the case reasoning,gives to making policy holding out being that purpose is in progress to out a decision-making suggestion once again.Secondly,in many cases the design of the library,to serve two-stage case-based reasoning process,the design of the four case libraries:First, property type case library,is a static case base can be modified,the effect is to performance differences between actual case and plan case of the qualitative distinction,indicate difference type attribute;Second, hierarchic quantization case library,is a static case base can be modified,the effect is to performance differences between actual case and plan case the quantitative distinction between the scope,indicate degree, size that the type issues in some difference etc.Three are that decision-making supports case library,is a static case base can be modified,the effect is similar enumeration all possible decision-makings content, indicate the decision-making that field expert possibility carries out;Four are decision match case library,is a self-study and dynamic case library,the effect is the library recording history decision-making case,is used to gain the decision-making scheme specifically for current reality achievement case is similar,to provide the support making policy,to learn composing in reply the case accumulating the new decision-making at the same time.The method is based on real business needs for research and development obtained after the conclusion,the paper shows through examples of the technology industry has a good adaptability,practicality and effectiveness.     

A model of response time effects in symbolic comparison.

A cognitive process model is developed that predicts the 3 major symbolic comparison response time effects (distance, end, and semantic congruity) found in the results of the linear syllogistic reasoning task. The model includes a simple connectionist learning component and dual evidence accumulation decision-making components. It assumes that responses can be based either on information concerning the positional difference between the presented stimulus items or on information concerning the endpoint status of each of these items. The model provides an excellent quantitative account of the mean correct response times obtained from 16 participants who performed paired comparisons of 6 ordered symbolic stimuli (3-letter names). (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Social influence on group moral decisions: The interactive effects of moral reasoning and sex role orientation.

In this study, we examined the effects of moral reasoning level and sex role orientation on social influence in group decision making. We predicted that these two individual difference constructs would have an interactive effect such that people who are compatible or nonconflicted on the two dimensions would have more influence on a group task with moral implications than would people who are conflicted. All subjects individually completed a distributive decision task that required ranking terminally ill patients for access to a life-saving kidney machine. They then met in small groups and reached a group decision on the same task. The subjects' moral reasoning level and sex role orientation—assessed via the Rest Defining Issues Test (Rest, 1979) and the Bem Sex Role Inventory (Bem, 1974), respectively—were used to predict influence on the group decision. Influence was measured in three ways: similarity between individual and group ranks, self-rated influence, and selection of the most influential group member. The results of all three influence measures provided support for the interactive hypothesis. In the discussion we consider the implications of the data for individual difference models of moral reasoning, the need for further understanding of goal competition and personality conflict, and the importance of considering the impact of moral factors on group decision-making processes. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Economic evaluation of diagnostic technology. Methodological challenges and viable solutions

The principles of economic evaluation are increasingly accepted by clinicians and policy makers as evidence from a significant number of studies becomes available to support their decisions. However, methods of assessment still need to be improved. This paper reports a comprehensive review of methodological challenges in the economic evaluation of diagnostic technology, where such challenges are more evident. This review formed the basis for a prioritized research agenda, with four main areas: modeling techniques for dealing with complexity; measures of the opportunity cost of shared resources; techniques for eliciting decision makers' utility functions for diagnostic tests; and ways of assessing the robustness of decisions. A number of methodological solutions are proposed, aimed at capturing elements and relationships that are usually neglected and fully recognizing the presence of an inductive cognitive component in decision-making processes.     

Evolutionary Fuzzy Neural Inference System for Decision Making in Geotechnical Engineering

Problems in geotechnical engineering are full of uncertain, vague, and incomplete information. In most instances, successfully solving such problems depends on experts’ knowledge and experience. The primary object of this research was to develop an evolutionary fuzzy neural inference system (EFNIS) to imitate the decision-making processes in the human brain in order to facilitate geotechnical expert decision making. First, an evolutionary fuzzy neural inference model (EFNIM) was constructed by combining the genetic algorithm (GA), fuzzy logic (FL), and neural network (NN). In the proposed model, GA is primarily concerned with optimizing parameters required in the fuzzy neural network; FL with imprecision and approximate reasoning; and NN with learning and curve fitting. This research then integrates the EFNIM with an object-oriented computer technique to develop an EFNIS. Finally, the potential to apply the proposed system to practical geotechnical decision making is validated using two real problems, namely estimating slurry wall duration and selecting retaining wall construction methods.     

REILP Approach for Uncertainty-Based Decision Making in Civil Engineering

The civil and environmental decision-making processes are plagued with uncertain, vague, and incomplete information. Interval linear programming (ILP) is a widely applied mathematical programming method in assisting civil and environmental decision making under uncertainty. However, the existing ILP decision approach is found to be ineffective in generating operational schemes for practical decision support due to a lack of linkage between decision risk and system return. In addition, the interpretation of the ILP solutions represented as the lower and upper bounds of decision variables can cause problems of infeasibility and nonoptimality in the resulted implementation schemes. This study proposed a risk explicit ILP (REILP) approach to overcome the limitations of existing ILP approaches. The REILP explicitly reflects the tradeoffs between risk and system return for a decision-making problem under an interval-type uncertainty environment. A risk function was defined to enable finding solutions which maximize system return while minimizing system risk, hence leading to crisp solutions that are feasible and optimal for practical decision making. A numerical experiment on land-use decision making under total maximum daily load was conducted to illustrate the REILP approach. The model results show that the REILP approach is able to efficiently explore the interval uncertainty space and generate an optimal decision front that directly reflects the tradeoff between decision risks and system return, allowing decision makers to make effective decision based on the risk-reward information generated by the REILP modeling analysis.     

Monitoring and Evaluation Scheme using the Multiple-Criteria-Decision-Making Technique: Application to Irrigation Projects

The application of monitoring and evaluation (M&E) systems to assess agricultural projects has received some attention in recent years. These systems provide valuable information for managers and decision makers by analyzing the implementation process, the progress of trends, and the long-term and short-term effectiveness of these projects. An algorithm is developed to monitor and evaluate drip and pressure irrigation projects in Iran. Different indicators are identified and the framework of an integrated evaluation system is demonstrated using an analytical hierarchy process for multiple-criteria-decision making. There is much subjective information that is quantified and normalized in order to remove any bias in evaluators’ assessment of qualitative measures or sensitivity to linguistic expressions. The application of this system to rank projects in different regions (zones) in Iran is also presented in this paper. The results have shown the significant value of such systems in providing information and input for different decision-making levels.     

Site Layout Planning using Nonstructural Fuzzy Decision Support System

Site layout planning can affect productivity and is crucial to project success. However, as construction is heterogeneous in the nature of its organizations, project designs, time constraints, environmental effects, etc., site layout planning for each project becomes unique. Affected by many uncertainties (variables) and variations, site layout planning is a typical multiobjective problem. To facilitate the decision-making process for these problems, a nonstructural fuzzy decision support system (NSFDSS) is proposed. NSFDSS integrates both experts’ judgment and computer decision modeling, making it suitable for the appraisal of complicated construction problems. The system allows assessments based on pairwise comparisons of alternatives using semantic operators that can provide a reliable assessment result even under the condition of insufficient precise information.     

Assessment of psychosocial stressors and maladjustment among foreign students of the University of the Ryukyus

Hormone replacement therapy: determinants of women's decisions. The purpose of this qualitative study was to explore the decision-making process used by menopausal women initiating or remaining on hormone replacement therapy (HRT), stopping HRT, or never starting HRT. Eight focus groups, composed of women reflecting these categories, were conducted. Four major themes or spheres of influence emerged as important in the women's decision-making process: the woman's internal influence--the interface between her perceptions and feelings including the symptoms of menopause, the benefits realized by HRT usage, and the experiences of negative side effects; interpersonal relationships, including the patient-physician relationship, family, friends and information networks; external influences, such as ageism and sexism; and consequences resulting from whichever treatment decision was chosen. A new concept was elucidated called "weighted influence" to underscore the dynamic interplay among the spheres. As information about HRT continues to grow and change, an understanding and application of these spheres of influence can assist physicians in engaging in a dialogue with their patients that allows individual evaluation and application of this new information.     

Case-Based Reasoning Approach in Bid Decision Making

Since contractors' bidding behaviors are affected by numerous factors related both to the specific features of the project and dynamically changed situations, bidding decision problems are highly unstructured. No clear rules can be found in delivering a bidding decision. In this problem domain, decisions are commonly made based upon intuition and past experience. Case-based reasoning (CBR) is a subbranch of artificial intelligence. It solves new problems by matching against similar problems that have been encountered and resolved in the past. It is a useful tool in dealing with complex and unstructured problems, which are difficult if not impossible to be theoretically modeled. This paper presents a case-based reasoning bidding system that helps contractors with the dynamic information varying with the specific features of the job and the new situation. In this system, bid cases are represented by sets of attributes derived from a preliminary survey of several experienced bidders, focusing, respectively, on two reasoning subgoals: (1) Risk; and (2) competition. Through the system, similar cases can be retrieved to assess the possible level of competition and risk margin. A hypothetical example is explained and evaluated to demonstrate the feasibility of the method. The effectiveness of this system is tested by a Monte Carlo simulation in comparison to the conventional statistical method.     

基于粗糙商集的模糊隶属度集值统计算法

模糊隶属度无统一算法,定义存在分歧.根据模糊概念"内涵明确,外延不明确"的特点,定义隶属度为不同外延对内涵的从属程度.在信息系统中,概念的外延用对象表示,内涵由属性表示,由此提出了求解隶属度的新算法:由原始统计数据组成初始信息系统,用粗糙集理论求得其商集并构建集值信息系统;该集值信息系统对应的条件概率空间中的条件概率即为隶属度.广义上信息系统可分为信息系统(无决策属性)和目标信息系统(有决策属性)两类.隶属度也可分为两类:第一类外延对象为内涵属性本身值,如年龄对青年人的隶属度(信息系统);第二类外延对象为不同于内涵属性的另一属性值,如边坡工程安全系数对稳定状态的隶属度(目标信息系统).计算以上两个实例,前者与已有结论作对比验证,后者与函数选择、经典统计方法及贝叶斯公理作对比验证,可知结果可靠,算法可行.