Optimal Model-free Approach Based on MDL and CHL for Active Brain Identification in fMRI Data Analysis.

BACKGROUND: Cluster analysis is a robust tool for exploring the underlining structures in data and grouping them with similar objects. In the researches of Functional Magnetic Resonance Imaging (fMRI), clustering approaches attempt to classify voxels depending on their time-course signals into a similar hemodynamic response over time. OBJECTIVE: In this work, a novel unsupervised learning approach is proposed that relies on using Enhanced Neural Gas (ENG) algorithm in fMRI data for comparison with Neural Gas (NG) method, which has yet to be utilized for that aim. The ENG algorithm depends on the network structure of the NG and concentrates on an efficacious prototype-based clustering approach. METHODS: The comparison outcomes on real auditory fMRI data show that ENG outperforms the NG and statistical parametric mapping (SPM) methods due to its insensitivity to the ordering of input data sequence, various initializations for selecting a set of neurons, and the existence of extreme values (outliers). The findings also prove its capability to discover the exact and real values of a cluster number effectively. RESULTS: Four validation indices are applied to evaluate the performance of the proposed ENG method with fMRI and compare it with a clustering approach (NG algorithm) and model-based data analysis (SPM). These validation indices include the Jaccard Coefficient (JC), Receiver Operating Characteristic (ROC), Minimum Description Length (MDL) value, and Minimum Square Error (MSE). CONCLUSION: The ENG technique can tackle all shortcomings of NG application with fMRI data, identify the active area of the human brain effectively, and determine the locations of the cluster center based on the MDL value during the process of network learning.

Clustering fMRI data with a robust unsupervised learning algorithm for neuroscience data mining.

BACKGROUND: Clustering approaches used in functional magnetic resonance imaging (fMRI) research use brain activity to divide the brain into various parcels with some degree of homogeneous characteristics, but choosing the appropriate clustering algorithms remains a problem. NEW METHOD: A novel application of the robust unsupervised learning approach is proposed in the current study. Robust growing neural gas (RGNG) algorithm was fed into fMRI data and compared with growing neural gas (GNG) algorithm, which has not been used for this purpose or any other medical application. Learning algorithms proposed in the current study are fed with real and free auditory fMRI datasets. RESULTS: The fMRI result obtained by running RGNG was within the expected outcome and is similar to those found with the hypothesis method in detecting active areas within the expected auditory cortices. COMPARISON WITH EXISTING METHOD(S): The fMRI application of the presented RGNG approach is clearly superior to other approaches in terms of its insensitivity to different initializations and the presence of outliers, as well as its ability to determine the actual number of clusters successfully, as indicated by its performance measured by minimum description length (MDL) and receiver operating characteristic (ROC) analysis. CONCLUSIONS: The RGNG can detect the active zones in the brain, analyze brain function, and determine the optimal number of underlying clusters in fMRI datasets. This algorithm can define the positions of the center of an output cluster corresponding to the minimal MDL value.

Validity and Reliability of Turkish Translation of Neuropathic Pain Impact on Quality-of-Life (NePIQoL) Questionnaire.

OBJECTIVES: The aim of this study was to adapt the "Neuropathic Pain Impact on Quality-of-Life Questionnaire" (NePIQoL) into Turkish and to test its validity and reliability in neuropathic pain patients. METHODS: We enrolled 200 chronic pain patients who admitted to the Neurology Department of Kirikkale University, Faculty of Medicine, in our study. Patients were diagnosed with neuropathic or nociceptive pain based on medical history, physical examination, electromyography and nerve conduction studies, laboratory examinations, and imaging techniques. Discriminant analysis was used to diagnose the neuropathic pain regarding sensitivity and specificity. The original version of the NePIQoL was translated into Turkish by standard procedures. RESULTS: Total NePIQoL scores were statistically different between neuropathic and nociceptive pain patients in both the first and second NePIQoL applications (P < 0.001). Cronbach's alpha coefficient of total 12 items of the first and second applications was 0.95. These results suggest a high validity level for the Turkish version of the NePIQoL. CONCLUSIONS: The Turkish version of NePIQoL appears to be reliable and valid for neuropathic pain impact on quality of life in patients with neuropathic pain.

Cognitive and behavioral characteristics of children with caustic ingestion.

BACKGROUND/AIM: Children with attention-deficit/hyperactivity disorder (AD/HD) have risk taking behavior and are more prone to sustaining injury. It is aimed to evaluate the cognitive and behavioral characteristics of children with caustic ingestion. PATIENTS AND METHODS: Ninety two children with a history of nonsuicidal caustic ingestion (CI, n=46) and healthy subjects (HS, n=46) admitted to pediatric surgery department were enrolled into the study. Patients in groups were evaluated for age, sex, number of siblings and educational status of the parents. Before filling the questionnaires, the children were undergone flexible endoscopy and treated accordingly. Conners Parents Rating Scale-revised long form (CPRS-R:L), validated for Turkish Children, was used to evaluate the cognitive and behavioral characteristics of children. Parents rate their child's behavior with a four-point Likert scale. Subscales of CPRS-R:L including cognitive problems/inattention (CG/I), hyperactivity (H), attention deficit hyperactivity disorder index (AD/HD-I), Conners' Global Index-discomfort-impulsivity (CGI-DI), DSM-IV-symptom subscale-inattention (DSMIV, SS-I), DSM-IV-symptom subscale-hyperactivity-impulsivity (DSM-IV, SS-HI), DSMIV-symptom subscale-total score (DSM-IV SS-T) were used to determine the severity of the AD/HD symptom. Demographic features and cognitive/behavioral characteristics of children with caustic ingestion were compared with healthy subjects. RESULTS: The median age of the patients was 4 (2-14 years) in both CI and HS groups. Female male ratio was 13:33 in CI and 12:34 in HS. Sixty seven percent of patients were preschool children (younger than 5 years of age) in both CI and HS groups. There was no difference between groups for number of siblings (p>0.05). Parents of HS group had higher educational status than parents in CI (p<0.05). When subscale scores of CPRS-R:L compared between CI and HS groups, CI group had higher CGI-DI scores than HS (p<0.05). Children younger than five years of age had higher scores of H, emotional instability and total CG/I in CI than HS group (p<0.05). CONCLUSION: Children with caustic ingestion had impulsiveness behavior when compared to healthy children. In addition to impulsivity, hyperactivity can be also assessed as a risk factor for caustic ingestion in children younger than 5years of age. We suggest that association between AD/HD behavior and risk of sustaining injuries was also confirmed for caustic ingestion in children.