MEDUSA: A Fuzzy Expert System for Medical Diagnosis of Acute Abdominal Pain

A practical review and taxonomy of fuzzy expert systems: methods and applications

Purpose

Expert systems are computer-based systems that mimic the logical processes of human experts or organizations to give advice in a specific domain of knowledge. Fuzzy expert systems use fuzzy logic to handle uncertainties generated by imprecise, incomplete and/or vague information. The purpose of this paper is to present a comprehensive review of the methods and applications in fuzzy expert systems.

Design/methodology/approach

The authors have carefully reviewed 281 journal publications and 149 conference proceedings published over the past 37 years since 1982. The authors grouped the journal publications and conference proceedings separately accordingly to the methods, application domains, tools and inference systems.

Findings

The authors have synthesized the findings and proposed useful suggestions for future research directions. The authors show that the most common use of fuzzy expert systems is in the medical field.

Originality/value

Fuzzy logic can be used to manage uncertainty in expert systems and solve problems that cannot be solved effectively with conventional methods. In this study, the authors present a comprehensive review of the methods and applications in fuzzy expert systems which could be useful for practicing managers developing expert systems under uncertainty.

Artificial intelligence (AI) and global health: how can AI contribute to health in resource-poor settings?

The field of artificial intelligence (AI) has evolved considerably in the last 60 years. While there are now many AI applications that have been deployed in high-income country contexts, use in resource-poor settings remains relatively nascent. With a few notable exceptions, there are limited examples of AI being used in such settings. However, there are signs that this is changing. Several high-profile meetings have been convened in recent years to discuss the development and deployment of AI applications to reduce poverty and deliver a broad range of critical public services. We provide a general overview of AI and how it can be used to improve health outcomes in resource-poor settings. We also describe some of the current ethical debates around patient safety and privacy. Despite current challenges, AI holds tremendous promise for transforming the provision of healthcare services in resource-poor settings. Many health system hurdles in such settings could be overcome with the use of AI and other complementary emerging technologies. Further research and investments in the development of AI tools tailored to resource-poor settings will accelerate realising of the full potential of AI for improving global health.

Knowledge discovery in clinical decision support systems for pain management: a systematic review

OBJECTIVE

The occurrence of pain accounts for billions of dollars in annual medical expenditures; loss of quality of life and decreased worker productivity contribute to indirect costs. As pain is highly subjective, clinical decision support systems (CDSSs) can be critical for improving the accuracy of pain assessment and offering better support for clinical decision-making. This review is focused on computer technologies for pain management that allow CDSSs to obtain knowledge from the clinical data produced by either patients or health care professionals.

METHODS AND MATERIALS

A comprehensive literature search was conducted in several electronic databases to identify relevant articles focused on computerised systems that constituted CDSSs and include data or results related to pain symptoms from patients with acute or chronic pain, published between 1992 and 2011 in the English language. In total, thirty-nine studies were analysed; thirty-two were selected from 1245 citations, and seven were obtained from reference tracking.

RESULTS

The results highlighted the following clusters of computer technologies: rule-based algorithms, artificial neural networks, nonstandard set theory, and statistical learning algorithms. In addition, several methodologies were found for content processing such as terminologies, questionnaires, and scores. The median accuracy ranged from 53% to 87.5%.

CONCLUSIONS

Computer technologies that have been applied in CDSSs are important but not determinant in improving the systems' accuracy and the clinical practice, as evidenced by the moderate correlation among the studies. However, these systems play an important role in the design of computerised systems oriented to a patient's symptoms as is required for pain management. Several limitations related to CDSSs were observed: the lack of integration with mobile devices, the reduced use of web-based interfaces, and scarce capabilities for data to be inserted by patients.

A hybrid decision support model to discover informative knowledge in diagnosing acute appendicitis

Background

The aim of this study is to develop a simple and reliable hybrid decision support model by combining statistical analysis and decision tree algorithms to ensure high accuracy of early diagnosis in patients with suspected acute appendicitis and to identify useful decision rules.

Methods

We enrolled 326 patients who attended an emergency medical center complaining mainly of acute abdominal pain. Statistical analysis approaches were used as a feature selection process in the design of decision support models, including the Chi-square test, Fisher's exact test, the Mann-Whitney U-test (p < 0.01), and Wald forward logistic regression (entry and removal criteria of 0.01 and 0.05, or 0.05 and 0.10, respectively). The final decision support models were constructed using the C5.0 decision tree algorithm of Clementine 12.0 after pre-processing.

Results

Of 55 variables, two subsets were found to be indispensable for early diagnostic knowledge discovery in acute appendicitis. The two subsets were as follows: (1) lymphocytes, urine glucose, total bilirubin, total amylase, chloride, red blood cell, neutrophils, eosinophils, white blood cell, complaints, basophils, glucose, monocytes, activated partial thromboplastin time, urine ketone, and direct bilirubin in the univariate analysis-based model; and (2) neutrophils, complaints, total bilirubin, urine glucose, and lipase in the multivariate analysis-based model. The experimental results showed that the model with univariate analysis (80.2%, 82.4%, 78.3%, 76.8%, 83.5%, and 80.3%) outperformed models using multivariate analysis (71.6%, 69.3%, 73.7%, 69.7%, 73.3%, and 71.5% with entry and removal criteria of 0.01 and 0.05; 73.5%, 66.0%, 80.0%, 74.3%, 72.9%, and 73.0% with entry and removal criteria of 0.05 and 0.10) in terms of accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under ROC curve, during a 10-fold cross validation. A statistically significant difference was detected in the pairwise comparison of ROC curves (p < 0.01, 95% CI, 3.13-14.5; p < 0.05, 95% CI, 1.54-13.1). The larger induced decision model was more effective for identifying acute appendicitis in patients with acute abdominal pain, whereas the smaller induced decision tree was less accurate with the test data.

Conclusions

The decision model developed in this study can be applied as an aid in the initial decision making of clinicians to increase vigilance in cases of suspected acute appendicitis.

Fuzzy logic based expert system for the treatment of mobile tooth

The aim of this research work is to design an expert system to assist dentist in treating the mobile tooth. There is lack of consistency among dentists in choosing the treatment plan. Moreover, there is no expert system currently available to verify and support such decision making in dentistry. A Fuzzy Logic based expert system has been designed to accept imprecise and vague values of dental sign-symptoms related to mobile tooth and the system suggests treatment plan(s). The comparison of predictions made by the system with those of the dentist is conducted. Chi-square Test of homogeneity is conducted and it is found that the system is capable of predicting accurate results. With this system, dentist feels more confident while planning the treatment of mobile tooth as he can verify his decision with the expert system. The authors also argue that Fuzzy Logic provides an appropriate mechanism to handle imprecise values of dental domain.

Prospective evaluation of the MET-AP system providing triage plans for acute pediatric abdominal pain

BACKGROUND

Children with acute abdominal pain (AP) are frequently assessed in the Emergency Department (ED). Though the majority of patients have benign causes, uncertainty during the physician's initial assessment may result in unnecessary tests and prolonged observation before a definitive disposition decision can be made. A rule-based mobile clinical decision support system, Mobile Emergency Triage-Abdominal Pain (MET-AP), has been developed to recommend an appropriate triage plan (discharge, consult surgery or observe/investigate) early in the ED visit, with the goal of promoting ED efficiencies and improved patient outcomes.

OBJECTIVE

To prospectively evaluate the accuracy of MET-AP to recommend the correct triage plan when used during the initial assessment by staff emergency physicians (EPs) and residents in a tertiary care pediatric ED.

DESIGN

Prospective cohort study. Staff EPs and/or residents examined children, aged 1-16 years, with acute, non-traumatic AP of less than 10 days duration. Details of their initial assessment, along with their blinded prediction of the correct triage plan, were recorded electronically. Inter-observer assessments were collected, where possible. Telephone and chart follow-up at 10-14 days was conducted to determine the patient's outcome/diagnosis, and thus the gold standard triage plan appropriate for the patient's visit.

MEASUREMENTS

Accuracy of MET-AP to recommend the correct triage plan (i.e., to match the gold standard plan); accuracy of physicians to predict the correct triage plan; inter-observer agreement between staff EPs and residents for each clinical attribute recorded within MET-AP.

RESULTS

Over 8 months, 574 patients with AP completed follow-up (10% appendicitis, 13% other pathology, 77% benign/resolving conditions). For patient assessments by the staff EP (n=457), the MET-AP recommendation was correct for 72% of patients (95% CI's: 67.9-76.1), while the physician's prediction was correct in 70% of cases (65.9-74.2) (p=0.518). However, staff EP triage plans were more conservative than those generated by MET-AP, and a small number of patients whose triage plan should have been "consult surgery" would have been "discharged" by MET-AP. For resident assessments (n=339), MET-AP and physician accuracies were slightly lower, but not statistically different from staff results or from each other. Inter-observer agreement on most attributes was moderate to near perfect.

CONCLUSION

MET-AP shows promise in recommending the correct triage plan with similar overall accuracy to experienced pediatric EPs, but requires further research to improve accuracy and safety. MET-AP can be used on all pediatric ED patients with AP and is capable of producing a triage plan recommendation without requiring a complete set of patient information.

Evaluation of the decision support computer program for cancer pain management

PURPOSE/OBJECTIVES

To evaluate a decision support computer program (DSCP) for cancer pain management.

DESIGN

An Internet intervention study to evaluate the usage profile, accuracy, and acceptance of the DSCP.

SETTING

Internet and community settings.

SAMPLE

122 nurses working with patients with cancer were recruited through the Internet through a convenience sampling method.

METHODS

The instruments included tools for registration and for evaluation of the DSCP. To evaluate the DSCP, the usage profile was measured by counting the total number of cases in which the participants used the DSCP; accuracy was measured by determining whether the decision support from the DSCP was appropriate and accurate; and acceptance was measured using the Questionnaire for User Interaction Satisfaction.

MAIN RESEARCH VARIABLES

Usage profile, accuracy, and acceptance of the DSCP.

FINDINGS

Participants used the DSCP an average of 1.49 times per person (SD = 1.16). Eighty-eight percent of the participants evaluated the DSCP as appropriate and accurate. The mean scores of overall satisfaction in four major areas of the computer program ranged from 7.46-9.69.

CONCLUSIONS

The DSCP could provide accurate and acceptable computerized evidence-based practice guidelines for cancer pain management.

IMPLICATIONS FOR NURSING

The findings suggest that researchers should develop decision support systems in multiple aspects and dimensions of cancer pain experience and that hand-held devices would increase the usability of the DSCP.

Assessing likelihood ratio of clinical symptoms: handling vagueness

Clinical symptoms including homeopathic symptoms are often vague. There is reluctance to assess clinical symptoms as diagnostic instruments because they are hard to define. Still, clinical symptoms appear effective in daily practice. Expert systems and neural networks handle vague data successfully. Theoretical considerations predict the kind of problems we may expect. There is a difference between quantitative and qualitative vagueness. Vague data cause problems if we try to prove a hypothesis because of expectation bias. We assess likelihood ratio of homeopathic symptoms only to improve the method.

Fuzzy logic and nursing

In empiricism, there are only two answers for a question: black or white. Yet, subjective meanings of human behaviours and responses toward health and illness cannot be simply explained with black and white. Gray zones are needed because they are characterized by complexity and require a contextual understanding. In this paper, we present and suggest fuzzy logic as an example of theoretical bases that help transcend the conflicts between objectivity and subjectivity, respect gray zones between black and white answers for questions, and provide a contextual understanding of complex nursing phenomenon. A historical review of fuzzy logic is followed by a definition of fuzzy logic. Then, fuzzy logic is discussed in terms of its compatibility with nursing epistemological views and philosophical thoughts. Fuzzy logic agrees with three categories of epistemological views of nursing, including correspondence, coherence and pragmatism. Fuzzy logic also agrees with four major philosophical thoughts in nursing, including postempiricism, pragmatism, feminism, and postmodernism. Based on the discussion, we propose that fuzzy logic be further explored, used and developed in research and practice in the nursing areas/situations/phenomena that are characterized by complexity, ambiguousness, and vagueness.

Decision support computer program for cancer pain management

The purpose of the study was to develop an initial version of computer software that could assist nurses' decision making about cancer pain reported by women from diverse cultural groups. This cross-sectional study included two phases: (1) data collection and (2) development of computer software. Data were collected using an Internet survey and e-mail group discussions of 19 faculty members from 10 countries who were self-identified experts in oncology nursing. The data were analyzed using descriptive statistics and content analysis. The findings indicated ethnic, gender, geographic, and age differences in cancer pain descriptions. Based on the collected data, a decision support computer program for cancer pain management, including (1) a knowledge base generation module, (2) a decision-making module, and (3) a self-adaptation module, was developed. Based on the study findings, suggestions for future research and practice related to cancer pain and expert systems were proposed.

Supporting decisions in medical applications: the knowledge management perspective

In the medical domain, different knowledge types are typically available. Operative knowledge, collected during every day practice, and reporting expert's skills, is stored in the hospital information system (HIS). On the other hand, well-assessed, formalised medical knowledge is reported in textbooks and clinical guidelines. We claim that all this heterogeneous information should be secured and distributed, and made available to physicians in the right form, at the right time, in order to support decision making: in our view, therefore, a decision support system cannot be conceived as an independent tool, able to substitute the human expert on demand, but should be integrated with the knowledge management (KM) task. From the methodological viewpoint, case based reasoning (CBR) has proved to be a very well suited reasoning paradigm for managing knowledge of the operative type. On the other hand, rule based reasoning (RBR) is historically one of the most successful approaches to deal with formalised knowledge. To take advantage of all the available knowledge types, we propose a multi modal reasoning (MMR) methodology, that integrates CBR and RBR, for supporting context detection, information retrieval and decision support. Our methodology has been successfully tested on an application in the field of diabetic patients management.

A proposed hierarchical fuzzy inference system for the diagnosis of arthritic diseases

Development of computer-based medical inference systems is always confronted with some difficulties. In this paper, difficulties of designing an inference system for the diagnosis of arthritic diseases are described, including variations of disease manifestations under various situations and conditions. Furthermore, the need for a huge knowledge base would result in low efficiency of the inference system. We proposed a hierarchical model of the fuzzy inference system as a possible solution. With such a model, the diagnostic process is divided into two levels. The first level of the diagnosis reduces the scope of diagnosis to be processed by the second level. This will reduce the amount of input and mapping for the whole diagnostic process. Fuzzy relational theory is the core of this system and it is used in both levels to improve the accuracy.

Cased-Based Reasoning for medical knowledge-based systems

In this paper we present the results of the MIE/GMDS-2000 Workshop 'Case-Based Reasoning for Medical Knowledge-based Systems'. While in many domains Cased-Based Reasoning (CBR) has become a successful technique for knowledge-based systems, in the medical field attempts to apply the complete CBR cycle are rather exceptional. Some systems have recently been developed, which on the one hand use only parts of the CBR method, mainly the retrieval, and on the other hand enrich the method by a generalisation step to fill the knowledge gap between the specificity of single cases and general rules. And some systems rely on integrating CBR and other problem solving methodologies. In this paper we discuss the appropriateness of CBR for medical knowledge-based systems, point out problems, limitations and possible ways to cope with them.

Managing uncertainty in diagnosis of acute coronaric ischemia

The paper presents the reasoning mechanism of COR, a knowledge-based system (KBS) able to provide support for the diagnosis of coronaric ischemia by integrating the interpretation of chest pain, 12-lead ECG, and bio-marker concentrations. Chest pain features are collected interactively through a questionnaire. The ECG signal is acquired in SCP format. Any set of bio-markers can be considered. Data input is incremental and possibly incomplete. Reasoning is based on revised uncertainty calculus, which allows a formal treatment of verbally expressed uncertainty concerning both input data and diagnostic rules. Each diagnosis is supplemented by a linguistic label, expressing the plausibility of the disease identified, given the symptoms observed.

Using fuzzy logic to predict response to citalopram in alcohol dependence

INTRODUCTION

The prediction of patient response to new pharmacotherapies for alcohol dependence has usually not been successful with standard statistical techniques. We hypothesized that fuzzy logic, a qualitative computational approach, could predict response to 40 mg/day citalopram and 40 mg/day citalopram with a brief psychosocial intervention in alcohol-dependent patients.

METHODS

Two data sets were formed with patients from our studies who received 40 mg/day citalopram alone (n = 34) or 40 mg/day citalopram and a brief psychosocial intervention (n = 28). The output variable, "response," was the percentage decrease in alcohol intake from baseline. Input variables included age, gender, baseline alcohol intake, and levels of anxiety, depression, alcohol dependence, and alcohol-related problems.

RESULTS

A fuzzy rulebase was created from the data of 26 randomly chosen patients who received 40 mg/day citalopram and was used to predict the responses of the remaining eight patients. Eight rules related response with depression, anxiety, alcohol dependence, alcohol-related problems, age, and baseline alcohol intake. The average magnitude of the error in the predictions (RMSE) was 2.6 with a bias (ME) of 0.6. Predicted and actual response correlated (r = 0.99; p < 0.001). A fuzzy rulebase was created from the data of 28 randomly chosen patients who received 40 mg/day citalopram and a brief psychosocial intervention and was used to predict the responses of the remaining five patients. Six rules related response with age, anxiety, depression, alcohol dependence, and baseline alcohol intake with good predictive performance (RMSE = 6.4; ME = -1.5; r = 0.96; p < 0.01).

CONCLUSIONS

This study indicates that fuzzy logic modeling can predict response to pharmacotherapies for alcohol dependence.

Fuzzy logic pharmacokinetic modeling: application to lithium concentration prediction

INTRODUCTION

We hypothesized that fuzzy logic could be used for pharmacokinetic modeling. Our objectives were to develop and evaluate a model for predicting serum lithium concentrations with fuzzy logic.

METHODS

Steady-state pharmacokinetic data had been previously collected in 10 elderly patients (age range, 67 to 80 years) with depression who were receiving lithium once daily. Each patient had serial serum lithium concentration determinations over one 24-hour period. The resulting 137 data sets initially consisted of five input variables (age, weight, serum creatinine, lithium dose, and time since last dose) and one output variable (serum lithium concentration; range, 0.2 to 1.24 mmol/L).

RESULTS

A fuzzy rulebase was created with 87 randomly chosen data sets, and predictions of serum lithium concentration were made on the basis of the remaining 50 data sets. All of the input variables except age and weight were identified as contributing to the fuzzy logic model. The average magnitude of the error in the predictions was 0.13 mmol/L (root mean squared error) with a bias (mean of the prediction errors) of 0.03 mmol/L.

CONCLUSIONS

This study indicates that the use of fuzzy logic for pharmacokinetic modeling of lithium for serum concentration predictions is feasible.