An Assessment of Imbalanced Control Chart Pattern Recognition by Artificial Neural Networks

Manual detection of abnormality in control data is an annoying work which requires a specialized person. Automatic detection might be simpler and effective. Various methodologies such as ANN, SVM, Fuzzy Logic, etc. have been implemented into the control chart patterns to detect abnormal patterns in real time. In general, control chart data is imbalanced, meaning the rate of minority class (abnormal pattern) is much lower than the rate of normal class (normal pattern). To take this fact into consideration, authors implemented a weighting strategy in conjunction with ANN and investigated the performance of weighted ANN for several abnormal patterns, then compared its performance with regular ANN. This comparison is also made under different conditions, for example, abnormal and normal patterns are separable, partially separable, inseparable and the length of data is fixed as being 10,20, and 30 for each. Based on numerical results, weighting policy can better predict in some of the cases in terms of classifying samples belonging to minority class to the correct class.

A novel RSW&TST framework of MCPs detection for abnormal pattern recognition on large-scale time series and pathological signals in epilepsy

To quickly and efficiently recognize abnormal patterns from large-scale time series and pathological signals in epilepsy, this paper presents here a preliminary RSW&TST framework for Multiple Change-Points (MCPs) detection based on the Random Slide Window (RSW) and Trigeminal Search Tree (TST) methods. To avoid the remaining local optima, the proposed framework applies a random strategy for selecting the size of each slide window from a predefined collection, in terms of data feature and experimental knowledge. For each data segment to be diagnosed in a current slide window, an optimal path towards a potential change point is detected by TST methods from the top root to leaf nodes with O(log3(N)). Then, the resulting MCPs vector is assembled by means of TST-based single CP detection on data segments within each of the slide windows. In our experiments, the RSW&TST framework was tested by using large-scale synthetic time series, and then its performance was evaluated by comparing it with existing binary search tree (BST), Kolmogorov-Smirnov (KS)-statistics, and T-test under the fixed slide window (FSW) approach, as well as the integrated method of wild binary segmentation and CUSUM test (WBS&CUSUM). The simulation results indicate that our RSW&TST is both more efficient and effective, with a higher hit rate, shorter computing time, and lower missed, error and redundancy rates. When the proposed RSW&TST framework is executed for MCPs detection on pathological ECG (electrocardiogram)/EEG (electroencephalogram) recordings of people in epileptic states, the abnormal patterns are roughly recognized in terms of the number and position of the resultant MCPs. Furthermore, the severity of epilepsy is roughly analyzed based on the strength and period of signal fluctuations among multiple change points in the stage of a sudden epileptic attack. The purpose of our RSW&TST framework is to provide an encouraging platform for abnormal pattern recognition through MCPs detection on large-scale time series quickly and efficiently.

The rat rotenone model reproduces the abnormal pattern of central catecholamine metabolism found in Parkinson's disease

Background: Recent reports indicate that Parkinson's disease (PD) involves specific functional abnormalities in residual neurons—decreased vesicular sequestration of cytoplasmic catecholamines via the vesicular monoamine transporter (VMAT) and decreased aldehyde dehydrogenase (ALDH) activity. This double hit builds up the autotoxic metabolite 3,4-dihydroxyphenylacetaldehyde (DOPAL), the focus of the catecholaldehyde hypothesis for the pathogenesis of PD. An animal model is needed that reproduces this abnormal catecholamine neurochemical pattern. Methods: Adult rats received subcutaneous vehicle or rotenone (2 mg/kg/day via a minipump) for 10 days. Locomotor activity was recorded and striatal tissue sampled for catechol contents and catechol ratios that indicate the above abnormalities. Results: Compared to vehicle, rotenone reduced locomotor activity (p=0.002), decreased tissue dopamine concentrations (p=0.00001), reduced indices of vesicular sequestration (3,4-dihydroxyphenylacetic acid (DOPAC)/dopamine) and ALDH activity (DOPAC/DOPAL) (p=0.0025, p=0.036), and increased DOPAL levels (p=0.04). Conclusions: The rat rotenone model involves functional abnormalities in catecholaminergic neurons that replicate the pattern found in PD putamen. These include a vesicular storage defect, decreased ALDH activity, and DOPAL buildup. The rat rotenone model provides a suitable in vivo platform for studying the catecholaldehyde hypothesis.

Hand Movement Based Message Transmission and Body Physical Parameters Remote Monitoring Device for Disabled People

The main focus of the proposed model is to manifest a system that is reliable and also effective interms of communication between Disabled/paralyzed people with the caretaker. When it comes to looking after the disabled or paralytic people who are in large numbers such as in old age homes, Non-Governmental Organizations, and hospitals, it is considerably difficult to monitor the patients based on their needs immediately. To overcome this difficulty a simple yet effective module is developed to establish the communication between the patient (Transmitter) and caretaker (receiver) by mounting a device on the hand of the patient so that by simple movements made using the hand aspecific message is communicated to the device which is in a form of a board consisting of the LCD screen and voice module to indicate the message and the board is held by the caretaker separately. The transmission mode is wireless and the range is about 10 meters. The physical parameters of the patient’s body are measured and monitored remotely. When there is any abnormal pattern in the parameters such as pulse rate and temperature it is indicated to the caretaker immediately.

Classification of Functional Movement Disorders with Resting State fMRI

Functional movement disorder (FMD) is a type of functional neurological disorder characterized by abnormal movements that patients do not recognize as self-generated. Prior imaging studies show a complex pattern of altered activity, linking regions of the brain involved in emotional responses, motor control, and agency. This study aimed to better characterize these relationships by building a classifier via support vector machine (SVM) to accurately classify 61 FMD patients from 59 healthy controls using features derived from resting state functional MRI (rs-fMRI). First, we selected 66 seed regions based on prior related studies, then calculated the full correlation matrix between them, before performing recursive feature elimination to winnow the feature set to the most predictive features and building the classifier. We identified 29 features of interest that were highly predictive of FMD condition, classifying patients from controls with 80% accuracy. The features selected by the model highlight the importance of the interconnected relationship between areas associated with emotion, reward and sensorimotor integration, potentially mediating relationships between regions associated with motor function, attention and executive function. Exploratory machine learning was able to identify this distinctive, abnormal pattern, suggesting that alterations in functional linkages between these regions may be a consistent feature of the condition in many FMD patients.

Caspase-1 Inhibition Impacts the Formation of Chondrogenic Nodules, and the Expression of Markers Related to Osteogenic Differentiation and Lipid Metabolism

Caspase-1, as the main pro-inflammatory cysteine protease, was investigated mostly with respect to inflammation-related processes. Interestingly, caspase-1 was identified as being involved in lipid metabolism, which is extremely important for the proper differentiation of chondrocytes. Based on a screening investigation, general caspase inhibition impacts the expression of Cd36 in chondrocytes, the fatty acid translocase with a significant impact on lipid metabolism. However, the engagement of individual caspases in the effect has not yet been identified. Therefore, the hypothesis that caspase-1 might be a candidate here appears challenging. The primary aim of this study thus was to find out whether the inhibition of caspase-1 activity would affect Cd36 expression in a chondrogenic micromass model. The expression of Pparg, a regulator Cd36, was examined as well. In the caspase-1 inhibited samples, both molecules were significantly downregulated. Notably, in the treated group, the formation of the chondrogenic nodules was apparently disrupted, and the subcellular deposition of lipids and polysaccharides showed an abnormal pattern. To further investigate this observation, the samples were subjected to an osteogenic PCR array containing selected markers related to cartilage/bone cell differentiation. Among affected molecules, Bmp7 and Gdf10 showed a significantly increased expression, while Itgam, Mmp9, Vdr, and Rankl decreased. Notably, Rankl is a key marker in bone remodeling/homeostasis and thus is a target in several treatment strategies, including a variety of fatty acids, and is balanced by its decoy receptor Opg (osteoprotegerin). To evaluate the effect of Cd36 downregulation on Rankl and Opg, Cd36 silencing was performed using micromass cultures. After Cd36 silencing, the expression of Rankl was downregulated and Opg upregulated, which was an inverse effect to caspase-1 inhibition (and Cd36 upregulation). These results demonstrate new functions of caspase-1 in chondrocyte differentiation and lipid metabolism-related pathways. The effect on the Rankl/Opg ratio, critical for bone maintenance and pathology, including osteoarthritis, is particularly important here as well.

CHEST RADIOGRAPHIC FINDINGS IN PEDIATRIC HOSPITALIZED PATIENTS WITH COVID-19 INFECTION

Background: This study aims to evaluate the COVID-19 related chest radiographic ndings in hospitalised paediatric patients in tertiary care hospital. Method: In this retrospective study, we included 52 RT-PCR COVID-19 positive hospitalized paediatric patients who presented with moderate to severe COVID-19 related symptoms or patients admitted in medical/surgical wards and found to be RT PCR positive during screening process as per our hospital policy. Results: Only Consolidation was seen in 8 (22.3%) patients. Interstitial markings and peribronchial thickening without consolidation was seen in 12 (33.3%) patients. Consolidation with interstitial markings were seen in 16 (44.4%) patients. Most common distribution pattern of consolidation/interstitial markings was central seen in 24 (66.7%) patients followed by mixed ( peripheral and central) seen in 8(22.3%) patients and peripheral in 4 (11%) patient. Pleural effusion was present in 4(11%) patient. Pneumothorax was present in 2(5.5%) patient. Conclusion: Imaging ndings of COVID-19 pneumonia have been less studied in paediatric population due to its asymptomatic/mild clinical presentation and poor sensitivity of RTPCR test in detecting COVID-19 infection. We found central and mixed chest radiographic pattern as most common abnormal pattern in paediatric population which is in contrast to the peripheral pattern seen in adult population.

Studies of Some Haemostatic Variables in Preeclamptic Women in Owerri, Imo State, Nigeria

Preeclampsia is a serious and life-threatening pregnancy complication. In this study, the levels of haemostatic parameters were measured in preeclamptic women in Owerri, Imo State. A total of 120 pregnant women aged 18-45 years at 20-40 weeks of pregnancy were recruited; 60 were preeclamptic women (test group) while 60 were normotensive pregnant women (control group). Preeclampsia was determined by the presence of ≥2+ protein in the urine using combi 2 dipstick for urinalysis and sphygmomanometer blood pressure reading of ≥ 140/90 mmHg. From the demographic data obtained in the studied subject through questionnaire, it showed that nulliparity and family history of high blood pressure were the most dominant risk factor of preeclampsia. The mean haemostatic parameters (PT, APTT, Fibrinogen, D-dimer and t-PA) of the test group were 12.3±0.94sec, 32.17±3.38sec, 627.31±106.93mg/ld, 2.23±0.50mg/l, 2.65±0.57ng/ml respectively, while the control group were 11.76±0.97sec, 28.69±2.64sec, 554±124.81 mg/dl, 1.89±0.44mg/l and 2.37±0.66 ng/ml respectively. There was a significant difference between the haemostatic parameter of the test group when compared with the control group. The results indicated that although anaemia and activation of coagulation and fibrinolysis occur within the peripheral circulation of both preeclamptic and normotensive pregnancy, an abnormal pattern of haemostasis occurs more in preeclamptic women.

Mining Knowledge of Respiratory Rate Quantification and Abnormal Pattern Prediction

The described application of granular computing is motivated because cardiovascular disease (CVD) remains a major killer globally. There is increasing evidence that abnormal respiratory patterns might contribute to the development and progression of CVD. Consequently, a method that would support a physician in respiratory pattern evaluation should be developed. Group decision-making, tri-way reasoning, and rough set–based analysis were applied to granular computing. Signal attributes and anthropomorphic parameters were explored to develop prediction models to determine the percentage contribution of periodic-like, intermediate, and normal breathing patterns in the analyzed signals. The proposed methodology was validated employing k-nearest neighbor (k-NN) and UMAP (uniform manifold approximation and projection). The presented approach applied to respiratory pattern evaluation shows that median accuracies in a considerable number of cases exceeded 0.75. Overall, parameters related to signal analysis are indicated as more important than anthropomorphic features. It was also found that obesity characterized by a high WHR (waist-to-hip ratio) and male sex were predisposing factors for the occurrence of periodic-like or intermediate patterns of respiration. It may be among the essential findings derived from this study. Based on classification measures, it may be observed that a physician may use such a methodology as a respiratory pattern evaluation-aided method.

Liver lymphatic anatomy and role in systemic lymphatic disease

Objectives To characterize hepatic to systemic lymphatic connections in patients with systemic lymphatic disease using intra-hepatic lymphangiography and to compare outcomes after lymphatic intervention. Methods In this retrospective study, patients with intra-hepatic lymphangiography from May 2014 – April 2019 at our institution were included. Imaging review was performed and hepatic lymphatic connections and flow patterns were characterized. Clinical data were reviewed and comparisons between patients undergoing lymphatic intervention with or without abnormal hepatic lymphatics were performed. Results During the study period, 105 patients underwent intra-hepatic lymphangiography. Primary clinical presentation included ascites (19/105), chylothorax (27/105), plastic bronchitis (PB) (17/105), and protein losing enteropathy (PLE) (42/105). Five categories of hepatic lymphatic connections and flow patterns were identified (%): normal (25%, 26/105), hepatoperitoneal (12%, 13/105), hepatopulmonary (10.5%, 11/105), hepatomesenteric (7.5%, 8/105), and hepatoduodenal (41%, 43/105) with four patients having more than one abnormal pattern. A comparison between clinical presentation and imaging category revealed an increased likelihood of having ascites with hepatoperitoneal (p < .0001), chylothorax/PB with hepatopulmonary (p = .01), and PLE with hepatoduodenal (p < .001) connections. Seventy-six patients had a lymphatic intervention, 24% with normal, and 76% with abnormal liver lymphatics. There was no difference in length of hospital stay or mortality between the two groups, but there was a prolonged time to symptom resolution (p = .006) and persistent symptoms after 6 months (5% vs 44%, p = .002) in the group with abnormal liver lymphatics. Conclusion We identified five liver lymphatic imaging categories with a substantial correlation to presenting lymphatic disease. Abnormal imaging patterns correlated with increased morbidity. Evaluation of liver lymphatics should be considered in patients with a systemic lymphatic disease if central lymphatic imaging is normal. Key Points • We identified five liver lymphatic imaging patterns: normal, hepatoperitoneal, hepatomesenteric, hepatopulmonary, and hepatoduodenal. • Imaging patterns were correlated with disease presentation (normal – chylothorax/PB, hepatoperitoneal – ascites/chylothorax, hepatopulmonary – chylothorax/PB, hepatoduodenal – PLE). • Abnormal imaging patterns correlated with increased morbidity.