Artificial neural network applied to diagnosis of lung cancer

Artificial neural network(ANN) approach was applied to classification of normal persons and lung cancer patients based on the metal content of hair and serum samples obtained by inductively coupled plasma atomic emission spectrometry (ICP-AES) for the two groups. This method was verified with independent prediction samples and can be used as an aiding means of the diagnosis of lung cancer. The case of predictive classification with one element missing in the prediction samples was studied in details, The significance of elements in hair and serum samples for classification prediction was also investigated.

Hypothesis Formation and Evaluation in Medical Diagnosis

This thesis describes some aspects of a computer system for doing medical diagnosis in the specialized field of kidney disease. Because such a system faces the spectre of combinatorial explosion, this discussion concentrates on heuristics which control the number of concurrent hypotheses and efficient "compiled" representations of medical knowledge. In particular, the differential diagnosis of hematuria (blood in the urine) is discussed in detail. A protocol of a simulated doctor/patient interaction is presented and analyzed to determine the crucial structures and processes involved in the diagnosis procedure. The data structure proposed for representing medical information revolves around elementary hypotheses which are activated when certain disposing of findings, activating hypotheses, evaluating hypotheses locally and combining hypotheses globally is examined for its heuristic implications. The thesis attempts to fit the problem of medical diagnosis into the framework of other Artifcial Intelligence problems and paradigms and in particular explores the notions of pure search vs. heuristic methods, linearity and interaction, local vs. global knowledge and the structure of hypotheses within the world of kidney disease.

Automatic diagnosis of task faults in flexible manufacturing systems

Hardy, N. W., Barnes, D. P., Lee, L. H. (1989). Automatic diagnosis of task faults in flexible manufacturing systems. Robotica, 7 (1):25-35

Taking advantage of an old concept, "illegitimate transcription", for a proposed novel method of genetic diagnosis of McArdle disease

McArdle disease is a metabolic disorder caused by pathogenic mutations in the PYGM gene. Timely diagnosis can sometimes be difficult with direct genomic analysis, which requires additional studies of cDNA from muscle transcripts. Although the "nonsense-mediated mRNA decay" (NMD) eliminates tissue-specific aberrant transcripts, there is some residual transcription of tissue-specific genes in virtually all cells, such as peripheral blood mononuclear cells (PBMCs).We studied a subset of the main types of PYGM mutations (deletions, missense, nonsense, silent, or splicing mutations) in cDNA from easily accessible cells (PBMCs) in 12 McArdle patients.Analysis of cDNA from PBMCs allowed detection of all mutations. Importantly, the effects of mutations with unknown pathogenicity (silent and splicing mutations) were characterized in PBMCs. Because the NMD mechanism does not seem to operate in nonspecific cells, PBMCs were more suitable than muscle biopsies for detecting the pathogenicity of some PYGM mutations, notably the silent mutation c.645G>A (p.K215=), whose effect in the splicing of intron 6 was unnoticed in previous muscle transcriptomic studies.We propose considering the use of PBMCs for detecting mutations that are thought to cause McArdle disease, particularly for studying their actual pathogenicity.

A qualitative analysis of parental coping with an early diagnosis of hearing loss in Ireland

The recent implementation of Universal Neonatal Hearing Screening (UNHS) in all 19 maternity hospitals across Ireland has precipitated early identification of paediatric hearing loss in an Irish context. This qualitative, grounded theory study centres on the issue of parental coping as families receive and respond to (what is typically) an unexpected diagnosis of hearing loss in their newborn baby. Parental wellbeing is of particular concern as the diagnosis occurs in the context of recovery from birth and at a time when the parent-child relationship is being established. As the vast majority of children with a hearing loss are born into hearing families with no prior history of deafness, parents generally have had little exposure to childhood hearing loss and often experience acute emotional vulnerability as they respond to the diagnosis. The researcher conducted in-depth interviews primarily with parents (and to a lesser extent with professionals), as well as a follow-up postal questionnaire for parents. Through a grounded theory analysis of data, the researcher subsequently fashioned a four-stage model depicting the parental journey of receiving and coping with a diagnosis. The four stages (entitled Anticipating, Confirming, Adjusting and Normalising) are differentiated by the chronology of service intervention and defined by the overarching parental experience. Far from representing a homogenous trajectory, this four-stage model is multifaceted and captures a wide diversity of parental experiences ranging from acute distress to resilient hopefulness

Antiendomysial and antihuman recombinant tissue transglutaminase antibodies in the diagnosis of coeliac disease: a biopsy-proven European multicentre study.

OBJECTIVE: To investigate the value of serum antitissue transglutaminase IgA antibodies (IgA-TTG) and IgA antiendomysial antibodies (IgA-EMA) in the diagnosis of coeliac disease in cohorts from different geographical areas in Europe. The setting allowed a further comparison between the antibody results and the conventional small-intestinal histology. METHODS: A total of 144 cases with coeliac disease [median age 19.5 years (range 0.9-81.4)], and 127 disease controls [median age 29.2 years (range 0.5-79.0)], were recruited, on the basis of biopsy, from 13 centres in nine countries. All biopsy specimens were re-evaluated and classified blindly a second time by two investigators. IgA-TTG were determined by ELISA with human recombinant antigen and IgA-EMA by an immunofluorescence test with human umbilical cord as antigen. RESULTS: The quality of the biopsy specimens was not acceptable in 29 (10.7%) of 271 cases and a reliable judgement could not be made, mainly due to poor orientation of the samples. The primary clinical diagnosis and the second classification of the biopsy specimens were divergent in nine cases, and one patient was initially enrolled in the wrong group. Thus, 126 coeliac patients and 106 controls, verified by biopsy, remained for final analysis. The sensitivity of IgA-TTG was 94% and IgA-EMA 89%, the specificity was 99% and 98%, respectively. CONCLUSIONS: Serum IgA-TTG measurement is effective and at least as good as IgA-EMA in the identification of coeliac disease. Due to a high percentage of poor histological specimens, the diagnosis of coeliac disease should not depend only on biopsy, but in addition the clinical picture and serology should be considered.

Human oesophagus: A convenient antigenic substrate for the determination of anti-endomysium antibodies in the serological diagnosis of coeliac disease

SCOPUS: ar.j

Development of a new blood test based on the helper lymphocytes Th-17 response for the diagnosis of allergies to dental metals: Preliminary results

info:eu-repo/semantics/nonPublished

Development of a new blood test for the diagnosis of the allergies to dental metals

Congrès du GIRSO, Lille, avril 2011

Evaluation of a WHO-Validated Serotype-Specific Serological Assay for the Diagnosis of Pneumococcal Etiology in Children with Community-Acquired Pneumonia.

BACKGROUND: The etiologic diagnosis of community-acquired pneumonia (CAP) remains challenging in children because blood cultures have low sensitivity. Novel approaches are needed to confirm the role of Streptococcus pneumoniae. METHODS: In this study, pneumococcal aetiology was determined by serology using a subset of blood samples collected during a prospective multicentre observational study of children <15 years of age hospitalised in Belgium with X-ray-confirmed CAP. Blood samples were collected at admission and 3-4 weeks later. Pneumococcal (P)-CAP was defined in the presence of a positive blood or pleural fluid culture. Serotyping of Streptococcus pneumoniae isolates was done with the Quellung reaction. Serological diagnosis was assessed for nine serotypes using World Health Organization validated IgG and IgA serotype-specific enzyme-linked immunosorbent assays (ELISAs). RESULTS: Paired admission/convalescent sera from 163 children were evaluated by ELISA (35 with proven P-CAP and 128 with non proven P-CAP). ELISA detected pneumococci in 82.8% of patients with proven P-CAP. The serotypes identified were the same as with the Quellung reaction in 82% and 59% of cases by IgG ELISA and IgA ELISA, respectively. Overall, ELISA identified a pneumococcal aetiology in 55% of patients with non-proven P-CAP. Serotypes 1 (51.6%), 7F (19%), and 5 (15.7%) were the most frequent according to IgG ELISA. CONCLUSIONS: In conclusion, the serological assay allows recognition of pneumococcal origin in 55% of CAP patients with negative culture. This assay should improve the diagnosis of P-CAP in children and could be a useful tool for future epidemiological studies on childhood CAP etiology.

Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis.

As more diagnostic testing options become available to physicians, it becomes more difficult to combine various types of medical information together in order to optimize the overall diagnosis. To improve diagnostic performance, here we introduce an approach to optimize a decision-fusion technique to combine heterogeneous information, such as from different modalities, feature categories, or institutions. For classifier comparison we used two performance metrics: The receiving operator characteristic (ROC) area under the curve [area under the ROC curve (AUC)] and the normalized partial area under the curve (pAUC). This study used four classifiers: Linear discriminant analysis (LDA), artificial neural network (ANN), and two variants of our decision-fusion technique, AUC-optimized (DF-A) and pAUC-optimized (DF-P) decision fusion. We applied each of these classifiers with 100-fold cross-validation to two heterogeneous breast cancer data sets: One of mass lesion features and a much more challenging one of microcalcification lesion features. For the calcification data set, DF-A outperformed the other classifiers in terms of AUC (p < 0.02) and achieved AUC=0.85 +/- 0.01. The DF-P surpassed the other classifiers in terms of pAUC (p < 0.01) and reached pAUC=0.38 +/- 0.02. For the mass data set, DF-A outperformed both the ANN and the LDA (p < 0.04) and achieved AUC=0.94 +/- 0.01. Although for this data set there were no statistically significant differences among the classifiers' pAUC values (pAUC=0.57 +/- 0.07 to 0.67 +/- 0.05, p > 0.10), the DF-P did significantly improve specificity versus the LDA at both 98% and 100% sensitivity (p < 0.04). In conclusion, decision fusion directly optimized clinically significant performance measures, such as AUC and pAUC, and sometimes outperformed two well-known machine-learning techniques when applied to two different breast cancer data sets.