Fuzzy based optimized itemset mining in high dimensional transactional database using adaptable FCM

One of the extremely deliberated data mining processes is HUIM (High Utility Itemset Mining). Its applications include text mining, e-learning bioinformatics, product recommendation, online click stream analysis, and market basket analysis. Likewise lot of potential applications availed in the HUIM. However, HUIM techniques could find erroneous patterns because they don’t look at the correlation of the retrieved patterns. Numerous approaches for mining related HUIs have been presented as an outcome. The computational expense of these methods continues to be problematic, both in terms of time and memory utilization. A technique for extracting weighted temporal designs is therefore suggested to rectify the identified issue in HUIM. Preprocessing of time series-based information into fuzzy item sets is the first step of the suggested technique. These feed the Graph Based Ant Colony Optimization (GACO) and Fuzzy C Means (FCM) clustering methodologies used in the Improvised Adaptable FCM (IAFCM) method. The suggested IAFCM technique achieves two objectives: optimal item placement in clusters using GACO; and ii) IAFCM clustering and information decrease in FCM cluster. The proposed technique yields high-quality clusters by GACO. Weighted sequential pattern mining, which considers facts of patterns with the highest weight and low frequency in a repository that is updated over a period, is used to locate the sequential patterns in these clusters. The outcomes of this methodology make evident that the IAFCM with GACO improves execution time when compared to other conventional approaches. Additionally, it enhances information representation by enhancing accuracy while using a smaller amount of memory.

Deep Learning Approach for Emotion Recognition Analysis in Text Streams

Social media sites employ various approaches to track feelings, including diagnosing neurological problems, including fear, in people or assessing a population public sentiment. One essential obstacle for automatic emotion recognition principles is variable with fluctuating limitations, language, and interpretation shifts. Therefore, in this paper, a deep learning-based emotion recognition (DL-EM) system has been proposed to describe the various relational effects in emotional groups. A soft classification method is suggested to quantify the tendency and allocate a message to each emotional class. A supervised framework for emotions in text streaming messages is developed and tested. Two of the major activities are offline teaching assignments and interactive emotion classification techniques. The first challenge offers templates in text responses to describe sentiment. The second activity includes implementing a two-stage framework to identify live broadcasts of text messages for dedicated emotion monitoring.

Association mapping of drought tolerance and agronomic traits in rice (Oryza sativa L.) landraces

BACKGROUND

Asian cultivars were predominantly represented in global rice panel selected for sequencing and to identify novel alleles for drought tolerance. Diverse genetic resources adapted to Indian subcontinent were not represented much in spite harboring useful alleles that could improve agronomic traits, stress resilience and productivity. These rice accessions are valuable genetic resource in developing rice varieties suited to different rice ecosystem that experiences varying drought stress level, and at different crop stages. A core collection of rice germplasm adapted to Southwestern Indian peninsular genotyped using SSR markers and characterized by contrasting water regimes to associate genomic regions for physiological, root traits and yield related traits. Genotyping-By-Sequencing of selected accessions within the diverse panel revealed haplotype variation in genic content within genomic regions mapped for physiological, morphological and root traits.

RESULTS

Diverse rice panel (99 accessions) were evaluated in field and measurements on plant physiological, root traits and yield related traits were made over five different seasons experiencing varying drought stress intensity at different crop stages. Traits like chlorophyll stability index, leaf rolling, days to 50% flowering, chlorophyll content, root volume and root biomass were identified as best predictors of grain yield under stress. Association mapping revealed genetic variation among accessions and revealed 14 genomic targets associated with different physiological, root and plant production traits. Certain accessions were found to have beneficial allele to improve traits, plant height, root length and spikelet fertility, that contribute to the grain yield under stress. Genomic characterization of eleven accessions revealed haplotype variation within key genomic targets on chromosomes 1, 4, 6 and 11 for potential use as molecular markers to combine drought avoidance and tolerance traits. Genes mined within the genomic QTL intervals identified were prioritized based on tissue specific expression level in publicly available rice transcriptome data.

CONCLUSION

The genetic and genomic resources identified will enable combining traits with agronomic value to optimize yield under stress and hasten trait introgression into elite cultivars. Alleles associated with plant height, specific leaf area, root length from PTB8 and spikelet fertility and grain weight from PTB26 can be harnessed in future rice breeding program.

Chronic musculoskeletal pain among elderly in rural Tamil Nadu: Mixed-method study

Objectives

(1) To determine the prevalence of chronic pain of musculoskeletal origin at different body sites among elderly (≥60 years). (2) To study the determinants of chronic pain and the healthcare seeking behavior among elderly with chronic pain. (3) To explore the perceptions of chronic pain among elderly.

Materials and Methods

This study was done in 55 field practice villages of the Rural Health Training Centre (RHTC) of the Department of Community Medicine, SMVMCH, Puducherry. An Exploratory Mixed-Method study design, where a qualitative phase (in-depth interviews [IDI]) followed the quantitative phase (Survey). A representative sample of 850 respondents was selected by two-stage cluster sampling. A trained investigator did a house-to-house visit and interviewed selected elderly respondents by using predesigned and pretested questionnaire. The intensity of chronic pain was measured using the Functional Rating Scale and Numeric Rating Scale. The manual content analysis was done for qualitative data. Multiple logistic regression was performed on quantitative data.

Results

Qualitative data were described under two broad themes: (1) perceptions of elderly people about chronic pain and 2) healthcare seeking and coping mechanisms. Prevalence of chronic pain among the elderly respondents was found to be 47.6%. Most common site for chronic pain was knee joint (64.5%) followed by a low backache (21.7%). Most of the older people with chronic pain had mild-to-moderate and tolerable pain. Two predictors for chronic pain were the age of the respondent (adjusted OR -1.03, 95% CI = 1.01-1.05) and the presence of at least one chronic morbidity (adjusted OR -1.37, 95% CI = 1.03-1.82).

Conclusions and Recommendations

Since the chronic pain was found to be associated with aging and the presence of at least one of the chronic morbidities, it is crucial for treating community physicians to consider the comorbid conditions while managing chronic pain in elderly. Considering the complex nature of chronic pain in old age, the primary care physician should be trained in drug and context-specific nondrug interventions to address the biomedical causes and other cognitive-behavior factors, respectively, through active support from their family and neighborhood.

Lower incidence of inappropriate shock therapy in patients with combined cardiac resynchronisation therapy defibrillators (CRT-D) compared with patients with non-CRT defibrillators (ICDs)

INTRODUCTION

A significant number of patients experience inappropriate shock therapy (IST) from implantable cardioverter-defibrillators (ICD). An increasing number of patients with advanced heart failure receive combined ICD and cardiac resynchronisation therapy devices (CRT-D). The incidence of IST in this group is less well described. We aimed to assess the incidence and predictors of IST in CRT-D patients.

METHODS

A retrospective cohort study of prospectively collected data on patients who received an ICD and CRT-D between October 2007 and January 2009 at our institution were studied. The primary outcome measures were the IST event rate and all-cause mortality.

RESULTS

A total of 185 patients with ICD/CRT-D (100/85) were included in the analysis. Eighteen patients experienced 35 episodes of IST during the follow-up (21 ± 13 months). There was a significantly lower IST cumulative event rate in the CRT-D vs. ICD group, 5% (CI: 1-13%) vs. 19% (95% CI: 11-30%) by 24 months, (p = 0.017). The majority of the IST was caused by atrial arrhythmias with atrial fibrillation accounting for 28 episodes of IST in nine patients. Multivariate analysis using Cox hazard model including baseline characteristics and coexisting appropriate shock therapy showed that a history of atrial fibrillation/flutter was the strongest independent predictor of IST with a hazard ratio of 3.53 (p = 0.019).

CONCLUSION

Patients with CRT-D had a significantly lower incidence of IST compared with patients receiving an ICD. Given that atrial arrhythmia remained the commonest trigger for IST, our finding lends support to the hypothesis that CRT may reduce atrial fibrillation burden in patients receiving CRT-D.

Trends, indications and outcomes of cardiac implantable device system extraction: a single UK centre experience over the last decade

BACKGROUND

The rising number of device implantation has seen a parallel in the rising numbers of lead extraction. Herein we have analysed our experience in cardiac device and lead extraction in a single tertiary centre over the last decade.

METHOD

Retrospective analysis of all consecutive patients undergoing lead extractions performed between 2001 and 2010. Procedural success and complications as defined by the Heart Rhythm Society policy.

RESULTS

A total of 745 leads were extracted with a procedural success of 98.9% [382 cases; partial success in 6.9% (26) cases] and failure in 1.1% (4). Major complication rate was 1% (four cases) and minor complication rate was 3.6%. By both univariate and multivariate analysis only duration of lead implantation was an indicator for success (p < 0.0001). The mean implantation time for failed lead extraction was 203 ± 64 months compared with 71.8 ± 16.5 months in the successful cohort (p < 0.0001). Laser-assisted extraction was required in 176 cases. With regard to extraction indication, lead malfunction/recall showed a significant increase during the study period (p = 0.03). On time trend analysis the rise in coronary sinus (CS) lead extraction over time was significant. (p = 0.02) Despite a trend for increased laser use over time this did not achieve statistical significance, p = 0.06.

CONCLUSIONS

A decade's experience of percutaneous lead extraction suggests that a high procedural success rate with a low complication rate is achieved in a high-volume centre. During this time, an increase in both defibrillator and CS lead explantation and a rising trend in laser assistance with almost 50% of cases needing laser usage were observed.

Inadvertent identification of the left pericardiophrenic vein following laser lead extraction to guide left ventricular lead placement

Phrenic nerve stimulation (PNS) is a frequent occurrence in patients implanted with a cardiac resynchronization therapy device. We present a case where identification of the left pericardiophrenic vein, which runs alongside the phrenic nerve, was used to guide left ventricular lead placement in order to minimize the risk of PNS.

Male gender and chronic obstructive pulmonary disease predict a poor clinical response in patients undergoing cardiac resynchronisation therapy

AIMS

Current guidelines advocate cardiac resynchronisation therapy (CRT) in patients with class III/IV New York Heart Association (NYHA) heart failure, depressed left ventricular function and a broad QRS. However, a significant proportion of patients do not derive any benefit from CRT. The aim of this study was to identify clinical, electrocardiographic and echocardiographic predictors of response to CRT.

METHODS

A retrospective analysis of patients undergoing CRT in our institution was performed. A favourable clinical response to CRT was defined as an improvement in NYHA Heart failure class of ≥ 1 and lack of hospitalisation with heart failure. Comparisons were made between responders and non-responders in terms of baseline characteristics and potential predictors of CRT response (QRS width, presence of left bundle branch block, atrial fibrillation, evidence of mechanical dyssynchrony on echocardiography and LV lead position).

RESULTS

A total of 164 patients had full follow-up data. The mean follow-up was 293 days. Of patients undergoing CRT, 90 (58.9%) had a favourable clinical response to CRT. Predictors of a lack of clinical response to CRT were male gender (p = 0.012) and chronic obstructive pulmonary disease (COPD) (0.008). Pre-implant echocardiographic dyssynchrony assessment appeared not to predict response to CRT (p = 0.87); however, there was a trend towards a positive response in those patients with significant dyssynchrony (p = 0.09) defined as interventricular delay > 40 ms or maximal LV delay of > 80 ms.

CONCLUSION

Male gender and coexisting COPD were shown to be independent predictors of non-response to CRT in this cohort of patients fulfilling current criteria for CRT.

Can iron status be improved in each of the three trimesters? A community-based study

OBJECTIVE

Intervention with iron supplementation, deworming, and information, education and communication (IEC) to improve the haematological status among each of the three trimesters of pregnant women in a rural community.

DESIGN

A community-based study was carried out using a two-group pre-post experimental design in a rural community.

SETTING

Two rural blocks in Vellore district were selected for the study. KV Kuppam block with a population of 120,000 and the adjacent Gudiyatham block with a population of 132,000 served as study and control areas for the study.

SUBJECTS

Using a multistage sampling, initially 50% of the panchayats, the local village administrative units, were randomly selected and all pregnant women were the subjects. In the pre-intervention survey 458 and 387 pregnant women had haemoglobin tested and the post-intervention survey covered 403 and 425 pregnant women in the study and control areas, respectively. Similarly serum ferritin was tested in a randomly selected sub-sample with 254 and 191 pregnant women before intervention and in 216 and 223 pregnant women after intervention in both study and control areas, respectively.

INTERVENTION

Iron supplementation and deworming were provided to all pregnant women in the study area from the fourth month of their pregnancy. An intensive information, education and communication was carried out with facts on anaemia and diet modification to each pregnant woman, using a one-to-one approach in the community, and a group method in the mobile clinics. This was carried out for a period of 18 months.

RESULTS

A significant decrease in the prevalence of anaemia was found, from 56.1% to 25.07% (P<0.001), 73. 4% to 49.2% (P<0.001) and 68.8% to 56.8% (P<0.01) among women in the first, second and third trimesters, respectively, in the intervention area. Significant (P<0.001) increases in the mean haemoglobin of 0.85 g/dl (95% CI 10.18-10.84, 11.09-11.63), 0.59 g/dl (95% CI 9.98-10.34, 10.55-10.95) and 0.36 g/dl (95% CI 9.93-10. 33, 10.25-10.73) were also observed in each of the groups.

CONCLUSION

A comprehensive community-based intervention with iron supplementation, helminthic treatment and increase in knowledge using IEC through effective strategies can improve the haematological status of pregnant women in each trimester.