ART-EMAP: A neural network architecture for object recognition byevidence accumulation

A new neural network architecture is introduced for the recognition of pattern classes after supervised and unsupervised learning. Applications include spatio-temporal image understanding and prediction and 3D object recognition from a series of ambiguous 2D views. The architecture, called ART-EMAP, achieves a synthesis of adaptive resonance theory (ART) and spatial and temporal evidence integration for dynamic predictive mapping (EMAP). ART-EMAP extends the capabilities of fuzzy ARTMAP in four incremental stages. Stage 1 introduces distributed pattern representation at a view category field. Stage 2 adds a decision criterion to the mapping between view and object categories, delaying identification of ambiguous objects when faced with a low confidence prediction. Stage 3 augments the system with a field where evidence accumulates in medium-term memory. Stage 4 adds an unsupervised learning process to fine-tune performance after the limited initial period of supervised network training. Each ART-EMAP stage is illustrated with a benchmark simulation example, using both noisy and noise-free data.     

Effect of allowing for ethnic group in prenatal screening for Down's syndrome

We conducted a study to investigate ethnic group differences in levels of serum markers used in screening for Down's syndrome [serum alpha-fetoprotein (AFP), unconjugated oestriol (uE3), total human chorionic gonadotrophin (hCG), free alpha- and free beta-hCG, and dimeric inhibin-A], to estimate the extent to which maternal weight differences between ethnic groups explain these differences, and to estimate the effect of adjusting for ethnic group and maternal weight on screening performance. Serum measurements were taken from women who were screened prenatally for Down's syndrome. AFP, uE3, and hCG concentrations were available from 9462 white, 4215 black, and 4392 South Asian women with singleton pregnancies without Down's syndrome or neural tube defects between 15 and 22 weeks' gestational age. Frozen serum samples were available from a subset of 922 white, 449 black, and 135 South Asian women and were used for measurement of free alpha-hCG, free beta-hCG, and inhibin. Values were expressed as multiples of the median (MOM) for women of the same gestational age. There were statistically significant differences in the serum marker levels between ethnic groups that were not explained by differences in maternal weight. The main differences were found in black women compared with white women; black women had serum AFP levels 22 per cent higher (95 per cent confidence interval 20-24 per cent), total hCG levels 19 per cent higher (16-22 per cent), and free beta-hCG levels 12 per cent (3-21 per cent) higher. The other differences were less than 10 per cent. Adjusting for ethnic group only had a small estimated effect on screening performance: a maximum of about 0.5 per cent extra detection at a 5 per cent false-positive rate. At a fixed risk cut-off level, the false-positive rate will not be materially different between different ethnic groups. Adjusting serum markers for ethnic groups improves Down's syndrome screening performance to a very small extent. It is worthwhile because of its established value in AFP screening for open neural tube defects.     

Estimation of foetal brain dose from I-131 in the foetal thyroid

The ingestion of I-131 by pregnant women can have consequences for the developing foetus, in particular brain function. As the foetal thyroid accumulates iodine from the twelfth week of gestation onwards, the determination of foetal brain dose resulting from such I-131 accumulation is essential. Normal dosimetric methods fail to treat the case of foetus. Using an approximation method based on the MIRD approach, a foetal dose estimation scheme is developed to allow the determination of foetal brain dose from foetal thyroid irradiation. Dose values are obtained for the foetus based on the maternal intake of I-131. It was found that the choice of biokinetic model for the mother/foetus has a large impact on the determined dose estimate.     

Double coupling Edman chemistry for high-sensitivity automated protein sequencing

Capillary electrophoresis with laser-induced fluorescence detection (CE-LIF) is a promising new method for the analysis of protein sequencing products. It gives 10 zmol (1 zmol = 10(-21) mol) limits of detection (3 sigma) for fluorescein thiohydantoin (FTH) amino acids. We have developed a separation for the (FTH)-amino acid products generated from 18 of the 20 coded amino acids. The extremely low volume requirement associated with CE-LIF makes it incompatible with commercial sequencers. For this reason, we have also been developing a miniaturized sequencer that can be more easily coupled to our detection system. Both the CE-LIF system and the miniaturized sequencer are described.     

Factors related to rehospitalization within thirty days of discharge after coronary artery bypass grafting

BACKGROUND: Early rehospitalization after coronary artery bypass grafting (CABG) is an expensive and frequently adverse outcome. Rehospitalization rates after various surgical procedures have been used as an indicator of quality of care. Determining the extent to which rehospitalization rates reflect patient case mix and severity of illness rather than quality of care requires detailed information regarding the patients, the care they received, and the reasons for their rehospitalization. METHODS: We conducted a nested case control study comparing 110 CABG patients who were rehospitalized within 30 days after discharge with 224 control patients. Control patients were randomly selected from patients undergoing CABG during the same time frame as the cases and were matched on age, gender, and priority of surgery. A detailed chart review provided information regarding treatment in the postsurgical period, in addition to the preoperative information collected on all CABG patients as part of an ongoing regional prospective study. RESULTS: The overall rehospitalization rate was 13.8%. The most common reasons for rehospitalization included: wound infection (19%), atrial fibrillation (13%), pleural effusion (11%), and thromboembolic event (10%). Preoperative severity of illness and comorbidity accounted for 24% of the total variance. After adjustment for these factors, discharge hematocrit less than 30% (OR = 2.01, p = 0.018) and several discharge medications including: antiarrhythmics (OR = 3.26, p = 0.047), diuretics (OR = 2.18, p = 0.055), beta blockers (OR = 0.44, p = 0.036), and long length of stay (more than 7 days; OR = 2.09, p = 0.029) were the most important predictors of rehospitalization risk. CONCLUSIONS: Although the reasons for rehospitalization after CABG are heterogeneous and related to patient severity of illness as well as comorbid status, several of the most common are potentially preventable and related to quality of care. Rehospitalization was not related to early discharge.     

Approach to the patient with pulmonary disease

The approach to the HIV-infected patient with pulmonary disease is summarized by the algorithms in Figures 3 and 4. These are not intended to be followed in a rigid step-wise fashion. Rather, the practitioner's knowledge of the patient with his or her accompanying medical risks influences the path taken, including the depth and the speed of the evaluation. For example, the patient with cough who is afebrile and breathing at 18 breaths a minute, with a normal chest radiograph and a CD4 count of 350 cells/mm3, is reasonably treated with a macrolide or cephalosporin for bacterial bronchitis and clinical follow-up while awaiting cultures (see Fig. 4). A febrile patient with a cough productive of thin mucus, but known to have a CD4 count of 60 cells/mm3 should be started on anti-PCP therapy while being evaluated for PCP with an induced sputum and if nondiagnostic, a bronchoscope despite a normal chest radiograph. Screening can be as simple as placing an oximeter on the patient's finger in the clinic. If the oxygen saturation of a patient with a normal chest radiograph is low, then the patient should be hospitalized and begun on treatment for PCP while diagnostic evaluation is initiated. If the oxygen saturation is normal, the patient can be exercised to elicit desaturation. If there is no desaturation, PCP is unlikely. If the results are equivocal (i.e., a decrease in saturation, but less than 3%), rest and exercise arterial blood gases can be performed, along with a Dlco-Gallium scanning can be done in patients known to have abnormal Dlco or those who cannot exercise. Patients with focal infiltrates who have acute onset of symptoms (see Fig. 4) commonly have bacterial infections, but the possibility of PCP or TB should not be dismissed. Induced sputum should be examined if TB or PCP is suspected. Patients who are severely ill might go quickly to bronchoscopy without awaiting improvement on empiric therapy. The patient with diffuse infiltrates (see Fig. 4) needs no screening because the presence of disease is apparent from the radiograph. The diagnostic part quickly leads to bronchoscopy for these patients and the initiation of therapy for PCP when suspected. In patients with known pulmonary KS, gallium scanning can be helpful to rule out acute infection, but bronchoscopy is warranted if the patient is severely ill, or at high risk for PCP. This approach should avoid unnecessary procedures in patients with simple bacterial infections, without missing opportunistic infections and tumors.     

Transient conduction in a slab with chemical reaction

The heat-balance integral technique is used to analyse a one-dimensional transient conduction process. Heat is transferred by convection to the surface of a slab and when the surface temperature reaches a certain value, an endothermic reaction is triggered which propagates as an isothermal front in the same direction as the conduction front. Two possible routes to the fully developed heat transfer condition are treated in a way which allows the approximate temperature distribution in the slab to be predicted as a function of the main process variables.