Management of blunt pancreatic trauma in children

Purpose  Blunt abdominal trauma is the major cause of abdominal injury in children. Because of the retroperitoneal location, insidious signs and symptoms and the lack of sensitivity with common imaging modalities often lead to difficulties in making an accurate diagnosis. The most common complication is the formation of a pancreatic fistula, pancreatitis and a pancreatic pseudocyst, which usually manifests within 3 or 4 weeks after injury. Methods  The case records of seven children (4 male, 3 female) treated for blunt pancreatic injury in the department of pediatric surgery, University Hospital, Split were reviewed. Results  The treatment modalities were selected according to the grade of the pancreatic injury, hemodynamic status and associated injuries. Because all of the patients were classified as grade I or II according to the American Association for the Surgery of Trauma (AAST) classification, a conservative treatment was selected for all seven patients. In four patients the conservative treatment resulted in the total regression of the clinical, biochemical and radiological signs within four weeks (AAST grade I). In the other three patients, pancreatic pseudocysts arose within 3 or 4 weeks after the injury (AAST grade II). Conclusions  The status of the main pancreatic duct and the location of the pancreatic injury constitute the basis of the AAST scoring system. This scale should be used as a guide to selecting a surgical or conservative strategy. Based on these data, two factors appear to be the most important determinants of the treatment strategy for children with pancreatic injury: the grade of the pancreatic injury, which is determined according to the status of the main pancreatic duct and the clinical status of the patient.     

Electroencephalographic staging of hepatic encephalopathy by an artificial neural network and an expert system

AIM OF THE STUDY: To provide an objective EEG assessment of hepatic encephalopathy (HE), we set up and tested an entirely automatic procedure based on an artificial neural network-expert system software (ANNESS). PATIENTS AND METHODS: A training set sample of 50 EEG (group A) and a test sample of 50 EEG (group B) of 100 cirrhotic patients were considered. The EEGs had been visually classified by an expert electroencephalographer, using a modified five-degree Parsons-Simith classification of HE. The efficiency of the ANNESS, trained in group A, was tested in group B. RESULTS: Both the ANNESS and the visually-based classifications were found to be correlated to liver insufficiency, as assessed by the Child-Pugh score (Spearman's coefficient rho=0.485, P<0.0001; rho=0.489, P<0.0001, respectively) and by the biochemical indexes of hepatic function (bilirubin: rho=0.31 vs. 0.27; albumin: rho=-0.13 vs. -0.18; prothrombin time rho=-0.35 vs. -0.52). The classifications were found to be correlated to each other (rho=0.84 P<0.0001, Cohen's kappa=0.55). However, the ANNESS overestimated grade 2 EEG alterations. CONCLUSION: An ANNESS-based classification of EEG in HE provided data comparable with a visually-based classification, except for mild alterations (class 2) that tended to be overestimated. Further optimization of automatic EEG staging of HE is desirable, as well as a prospective clinical evaluation.     

Backpropagation Artificial Neural Network Detects Changes in Electro-Encephalogram Power Spectra of Syncopic Patients

This paper presents an effective application of backpropagation artificial neural network (ANN) in differentiating electroencephalogram (EEG) power spectra of syncopic and normal subjects. Digitized 8-channel EEG data were recorded with standard electrodes placement and amplifier settings from five confirmed syncopic and five normal subjects. The preprocessed EEG signals were fragmented in two-second artifact free epochs for calculation and analysis of changes due to syncope. The results revealed significant increase in percentage δ and α (p<0.5 or better) with significant reduction in percentage θ activity (p<0.05). The backpropagation ANN used for classification contains 60 nodes in input layer, weighted from power spectrum data from 0 to 30 Hz, 18 nodes in hidden layer and an output node. The ANN was found effective in differentiating the EEG power spectra from syncopic EEG power spectra and the normal EEG power spectra with an accuracy of 88.87% (85.75% for syncopic and 92% for normal). Certificate of Originality—This is to certify that the article submitted for publication in ‘Journal of Medical Systems’ has not been publ-ished, nor is being considered for publication, elsewhere. (Rakesh Kumar Sinha)     

Sequence-based protein structure prediction using a reduced state-space hidden Markov model

This work describes the use of a hidden Markov model (HMM), with a reduced number of states, which simultaneously learns amino acid sequence and secondary structure for proteins of known three-dimensional structure and it is used for two tasks: protein class prediction and fold recognition. The Protein Data Bank and the annotation of the SCOP database are used for training and evaluation of the proposed HMM for a number of protein classes and folds. Results demonstrate that the reduced state-space HMM performs equivalently, or even better in some cases, on classifying proteins than a HMM trained with the amino acid sequence. The major advantage of the proposed approach is that a small number of states is employed and the training algorithm is of low complexity and thus relatively fast.     

Learning and modeling biosignatures from tissue images

Ideally biosignatures can be detected at the early infection phase and used both for developing diagnostic patterns and for prognostic triage. Such biosignatures are important for vaccine validation and to provide risk stratification to a population such as for the identification of individuals who are exposed to biological or chemical agents and who are at high risk for developing an infection. The research goal is to detect broad based biosignature models and is initially focused on developing effective computer-augmented pathology tied to animal models developed at the University of New Mexico (UNM). Using lung tissue from infected and nai ve mice, feature extraction from images of the tissue under a specialized microscope, and Bayesian networks to analyze the data sets of features, we were able to differentiate normal from diseased samples and viral from bacterial samples in mid to late stages of infection. This effort has shown the potential effectiveness of computer-augmented pathology in this application. The extended research intends to couple analysis of serum, microarray analysis of organs, proteomic data and the pathology. The rational for the current invasive procedure on animal models is to facilitate the development of data analysis and machine learning techniques that can eventually be generalized to the task of discovering non-invasive and early stage biosignatures for human models.