Multiagent realization of prediction-based diagnosis and loss prevention

A multiagent diagnostic system implemented in a Protege-JADE-JESS environment interfaced with a dynamic simulator and database services is described in this paper. The proposed system architecture enables the use of a combination of diagnostic methods from heterogeneous knowledge sources. The process ontology and the process agents are designed based on the structure of the process system, while the diagnostic agents implement the applied diagnostic methods. A specific completeness coordinator agent is implemented to coordinate the diagnostic agents based on different methods. The system is demonstrated on a case study for diagnosis of faults in a granulation process based on HAZOP and FMEA analysis.

Computational methods for the detection of facial palsy

We are developing a telemedicine application which offers automated diagnosis of facial (Bell's) palsy through a Web service. We used a test data set of 43 images of facial palsy patients and 44 normal people to develop the automatic recognition algorithm. Three different image pre-processing methods were used. Machine learning techniques (support vector machine, SVM) were used to examine the difference between the two halves of the face. If there was a sufficient difference, then the SVM recognized facial palsy. Otherwise, if the halves were roughly symmetrical, the SVM classified the image as normal. It was found that the facial palsy images had a greater Hamming Distance than the normal images, indicating greater asymmetry. The median distance in the normal group was 331 (interquartile range 277-435) and the median distance in the facial palsy group was 509 (interquartile range 334-703). This difference was significant (P

Diagnosis of diabetes mellitus: case of different cutoff values: A data mining approach

Objective: An estimation of cut-off points for the diagnosis of diabetes mellitus (DM) based on individual risk factors. Methods: A subset of the 1991 Oman National Diabetes Survey is used, including all patients with a 2h post glucose load >= 200 mg/dl (278 subjects) and a control group of 286 subjects. All subjects previously diagnosed as diabetic and all subjects with missing data values were excluded. The data set was analyzed by use of the SPSS Clementine data mining system. Decision Tree Learners (C5 and CART) and a method for mining association rules (the GRI algorithm) are used. The fasting plasma glucose (FPG), age, sex, family history of diabetes and body mass index (BMI) are input risk factors (independent variables), while diabetes onset (the 2h post glucose load >= 200 mg/dl) is the output (dependent variable). All three techniques used were tested by use of crossvalidation (89.8%). Results: Rules produced for diabetes diagnosis are: A- GRI algorithm (1) FPG>=108.9 mg/dl, (2) FPG>=107.1 and age>39.5 years. B- CART decision trees: FPG >=110.7 mg/dl. C- The C5 decision tree learner: (1) FPG>=95.5 and 54, (2) FPG>=106 and 25.2 kg/m2. (3) FPG>=106 and =133 mg/dl. The three techniques produced rules which cover a significant number of cases (82%), with confidence between 74 and 100%. Conclusion: Our approach supports the suggestion that the present cut-off value of fasting plasma glucose (126 mg/dl) for the diagnosis of diabetes mellitus needs revision, and the individual risk factors such as age and BMI should be considered in defining the new cut-off value.

Evaluation of routine microbiological techniques for establishing the diagnosis of catheter-related bloodstream infection caused by coagulase-negative staphylococci

Microbiological diagnosis of catheter-related bloodstream infection (CR-BSI) is often based on isolation of indistinguishable micro-organisms from an explanted catheter tip and blood culture, confirmed by antibiograms. Whether phenotypic identification of coagulase-negative staphylococci (CoNS) allows an accurate diagnosis of CR-BSI to be established was evaluated. Eight patients with a diagnosis of CR-BSI had CoNS isolated from pure blood cultures and explanted catheter tips which were considered as indistinguishable strains by routine microbiological methods. For each patient, an additional three colonies of CoNS isolated from the blood and five from the catheter tip were subcultured and further characterized by antibiogram profiles, analytical profile index (API) biotyping and PFGE. PFGE distinguished more strains of CoNS compared to API biotyping or antibiograms (17, 10 and 11, respectively). By PFGE, indistinguishable micro-organisms were only isolated from pure blood and catheter tip cultures in four out of eight (50%) patients thus supporting the diagnosis of CR-BSI. In another patient, indistinguishable micro-organisms were identified in both cultures; however, other strains of CoNS were also present. The remaining three patients had multiple strains of CoNS, none of which were indistinguishable in the tip and blood cultures, thus questioning the diagnosis of CR-BSI. Phenotypic characterization of CoNS lacked discriminatory power. Current routine methods of characterizing a limited number of pooled colonies may generate misleading results as multiple strains may be present in the cultures. Multiple colonies should be studied using a rapid genotypic characterization method to confirm or refute the diagnosis of CR-BSI. © 2007 SGM.

Patients in waiting:A qualitative study of type 2 diabetes patients' perceptions of diagnosis

Objective. Our aim was to examine how diagnosis is perceived by a sample of newly diagnosed type 2 diabetes patients. Methods. A qualitative study was carried out in the Lothian region of Scotland using in-depth interviews of 40 newly diagnosed type 2 diabetes patients recruited from 16 general practices in four Local Health Care Co-operatives and three hospital clinics. Purposive selection ensured that the sample's demographic characteristics were broadly representative of newly diagnosed type 2 diabetes patients in Lothian/Scotland. Results. Clarity, timing and authority of the diagnosis delivery were highly salient for patients. Many patients perceived their GP as unwilling to deliver/confirm the diagnosis. Patients who were not referred to hospital were unclear why a referral had not taken place. Those referred perceived confirmation of diagnosis by the consultant as a central reason. Waiting for a hospital appointment could be problematic for patients. Most wanted the diagnosis confirmed before they felt confident making lifestyle changes. Input from health services during the period prior to the hospital visit was highly valued. Waiting was taken by some asymptomatic patients to indicate that they did not have the condition. Others used a lengthy period of waiting to confirm their view that they had a 'milder' or 'less serious' form of diabetes than other patients. Conclusions. Adequate input from practitioners is needed to ensure that diagnosis is fully exploited as a crucial period in which patients learn to adapt to their condition. Being explicit about the diagnosis at first contact may avoid the problem of patients feeling 'in limbo' or uncertain whether they have type 2 diabetes. Practitioners should convey to patients that post-diagnosis/initial care is a process, stages of this process should be clarified to avoid misunderstanding and services should be integrated during this interim period to best effect. © Oxford University Press 2004; all rights reserved.

Has DRG payment influenced the technical efficiency and productivity of diagnostic technologies in Portuguese public hospitals? An empirical analysis using parametric and non‐parametric methods

The use of Diagnosis Related Groups (DRG) as a mechanism for hospital financing is a currently debated topic in Portugal. The DRG system was scheduled to be initiated by the Health Ministry of Portugal on January 1, 1990 as an instrument for the allocation of public hospital budgets funded by the National Health Service (NHS), and as a method of payment for other third party payers (e.g., Public Employees (ADSE), private insurers, etc.). Based on experience from other countries such as the United States, it was expected that implementation of this system would result in more efficient hospital resource utilisation and a more equitable distribution of hospital budgets. However, in order to minimise the potentially adverse financial impact on hospitals, the Portuguese Health Ministry decided to gradually phase in the use of the DRG system for budget allocation by using blended hospitalspecific and national DRG casemix rates. Since implementation in 1990, the percentage of each hospitals budget based on hospital specific costs was to decrease, while the percentage based on DRG casemix was to increase. This was scheduled to continue until 1995 when the plan called for allocating yearly budgets on a 50% national and 50% hospitalspecific cost basis. While all other nonNHS third party payers are currently paying based on DRGs, the adoption of DRG casemix as a National Health Service budget setting tool has been slower than anticipated. There is now some argument in both the political and academic communities as to the appropriateness of DRGs as a budget setting criterion as well as to their impact on hospital efficiency in Portugal. This paper uses a twostage procedure to assess the impact of actual DRG payment on the productivity (through its components, i.e., technological change and technical efficiency change) of diagnostic technology in Portuguese hospitals during the years 1992–1994, using both parametric and nonparametric frontier models. We find evidence that the DRG payment system does appear to have had a positive impact on productivity and technical efficiency of some commonly employed diagnostic technologies in Portugal during this time span.

The serological diagnosis of staphylococcal infective endocarditis

Objectives: Establishing the diagnosis of infective endocarditis (IE) can be difficult when blood cultures remain sterile or echocardiography is inconclusive. Staphylococcus aureus is a common aetiological microorganism in IE and is associated with severe valvular destruction and increased mortality. Early diagnosis using culture and antibiotic independent tests would be preferable to allow prompt antibiotic administration. We have developed and evaluated 2 serological assays for the rapid identification of a staphylococcal aetiology in infective endocarditis. The assays measure IgG against whole cells of S. aureus and IgG against lipid S, a novel extracellular antigen released by Gram-positive microorganisms. Methods: Serum was collected from 130 patients with IE and 94 control patients. IgG against whole cells of S. aureus and against lipid S was measured by enzyme linked immunosorbent assay (ELISA). Results: Anti-lipid S IgG titres were higher in IE caused by Gram-positive microorganisms than in controls (p < 0.0001) and higher in staphylococcal IE than in both controls and IE caused by other microorganisms (p = 0.0003). Anti-whole cell staphylococcal IgG was significantly higher in serum from patients with staphylococcal IE than in IE caused by other microorganisms and control samples (p < 0.0001). Conclusion: High anti-whole cell IgG titres are predictive of a staphylococcal aetiology in IE. Elevated serum anti-lipid S IgG titres are predictive of Gram-positive infection compared to controls, very high titres being associated with staphylococcal IE. © 2005 The British Infection Society.

Evaluation of PCR in the molecular diagnosis of endocarditis

Objective. Infective endocarditis (IE) is diagnosed by the Duke criteria, which can be inconclusive particularly when blood cultures are negative. This study investigated the application of polymerase chain reaction (PCR) to identify bacterial DNA in excised valvular tissue, and its role in establishing the diagnosis of IE. Methods. Ninety-eight patients undergoing valve replacement surgery were studied. Twenty-eight patients were confirmed as definite for endocarditis by the Duke criteria; nine were considered as possible and 61 had no known or previous microbial infection of the endocardium. A broad-range PCR technique was used to amplify prokaryotic 16S rRNA genes present within homogenised heart valve tissue. Subsequent DNA sequencing of the PCR amplicon allowed identification of the infecting microorganism. Results. PCR results demonstrated the presence of bacterial DNA in the heart valves obtained from 14 out of 20 (70%) definite IE patients with positive blood cultures preoperatively. The causative microorganism for one patient with definite culture negative endocarditis was identified by PCR. Two out of nine (22%) of the valves from possible endocarditis patients also had bacterial DNA present converting them into the definite criteria whereas in the valves of seven out of nine (78%) of these patients no bacterial DNA was detected. Conclusion. The application of PCR to the explanted valves in patients with possible or confirmed diagnosis can augment the Duke criteria thereby improving post-surgical antimicrobial therapeutic options. © 2003 The British Infection Society. Published by Elsevier Ltd. All rights reserved.

Looking at Alzheimer's disease: Part 1 symptoms, diagnosis and changes in the brain

In this, the first of a series of articles, the natural history of Alzheimer's disease will be discussed as well as the methods of diagnosis and the pathological changes which underlie the symptoms.

The prevention and diagnosis of central venous catheter-related infection

The potential source of CVC colonisation was assessed. Isolates of coagulase-negative staphylococci (CoNS) recovered from the skin and CVC components of 3 cardiothoracic surgery patients were characterised by pulsed-field gel electrophoresis (PFGE). The genetic heterogeneity of CoNS isolated from the skin was demonstrated and specific genotypes implicated in catheter colonisation. In addition, phenotypic and genotypic typing techniques were assessed for their ability to characterise strains of CoNS recovered from 33 patients who developed catheter-related bloodstream infection (CR-BSI) on a bone marrow transplant (BMT) unit and Siaphylococcus aureus recovered from 6 cardiothoracic surgery patients with surgical site infection (SSI) following median sternotomy. This epidemiological investigation revealed that common strains of CoNS and 51 aureus where not associated with infection in patients with CR-BSI or sternal SSI during the study period. Furthermore, there was no correlation between phenotypic and genotypic characterisation results. The variable expression of phenotypic traits within strains of staphylococci was evident whilst PFGE and randomly amplified polymorphic DNA (RAPD) were highly discriminatory for the molecular characterisation of S. aureus and CoNS. This was highlighted in 8 stem cell transplant (SCT) patients whereby it was demonstrated that routine identification and characterisation of CoNS by phenotypic techniques may not be adequate for the diagnosis of CR-BSI by current guidelines. The potential of the lipid S ELISA to facilitate the diagnosis of CR-BSI in 38 haematology/SCT patients and sternal SSI in 57 cardiothoracic surgery patients was also assessed. The ELISA proved to be a sensitive test for the rapid serodiagnosis of infection due to staphylococci in immunocompetent patients. The acridine orange leucocyte cytospin test (AOLC) was also evaluated for the rapid diagnosis of CR-BSI in 16 haematology/SCT patients with Hickman CVC in situ. Although the sensitivity of the test was low, it may provide a useful adjunct to conventional methods for the in situ sampling of catheters to predict and diagnose CR-BSI, preventing the unnecessary removal of CVC.