Multi-task learning (MTL) aims to improve generalization performance by learning multiple related tasks simultaneously. While sometimes the underlying task relationship structure is known, often the structure needs to be estimated from data at hand. In this paper, we present a novel family of models for MTL, applicable to regression and classification problems, capable of learning the structure of task relationships. In particular, we consider a joint estimation problem of the task relationship structure and the individual task parameters, which is solved using alternating minimization. The task relationship structure learning component builds on recent advances in structure learning of Gaussian graphical models based on sparse estimators of the precision (inverse covariance) matrix. We illustrate the effectiveness of the proposed model on a variety of synthetic and benchmark datasets for regression and classification. We also consider the problem of combining climate model outputs for better projections of future climate, with focus on temperature in South America, and show that the proposed model outperforms several existing methods for the problem.

Purpose:The purpose of this study was to investigate the reliability and concurrent validity of active spinal mobility measurements using a gravity-based bubble inclinometer and an android application.Objective: This study was to examine the utility of an android application as a measurement tool in measurement of lumbar range of motion in low back pain patient Methods: It is a descriptive study design with a sample size of 30 patients. Results:Interclass correlation coefficients were used to analyze the ability of Samsung tab 2 and I handy application for measuring lumbar ROM in LBP patients. Conclusion:The I handy application has good Intra and inter-tester reliability and it can be used to measure the lumbar spine range of motion. Keywords MDC -Minimal detectable change, ROM -Range of motion, LBP-Low back pain

No abstract

Study DesignA retrospective, cross-sectional study of 213 patients who presented for abdominal computed tomography (CT) scans to assess coccygeal morphology in the Indian population.PurposeThere have been relatively few studies of coccygeal morphology in the normal population and none in the Indian population. We aimed to estimate coccygeal morphometric parameters in the Indian population.Overview of LiteratureCoccygeal morphology has been studied in European, American, Korean, and Egyptian populations, with few differences in morphology among populations.MethodsA retrospective analysis of 213 abdominal CT scans (114 males and 99 females; age, 7–88 years; mean age, 47.3 years) was performed to evaluate the number of coccygeal segments, coccyx type, sacrococcygeal and intercoccygeal fusion and subluxation, coccygeal spicules, sacrococcygeal straight length, and sacrococcygeal and intercoccygeal curvature angles. Results were analyzed for differences in morphology with respect to sex and coccyx type.ResultsTypes I and II coccyx were the most common. Most subjects had four coccygeal vertebrae; 93 subjects (43.66%) had partial or complete sacrococcygeal fusion. Intercoccygeal fusion was common, occurring in 193 subjects. Eighteen subjects had coccygeal spicules. The mean coccygeal straight length was 33.8 mm in males and 31.5 mm in females; the mean sacrococcygeal curvature angle was 116.6° in males and 111.6° in females; the mean intercoccygeal curvature angle was 140.94° in males and 145.10° in females.ConclusionsType I was the most common coccyx type in our study, as in Egyptian and Western populations. The number of coccygeal vertebrae and prevalence of sacrococcygeal and intercoccygeal fusion in the Indian population were similar to those in the Western population. The mean coccygeal straight length and mean sacrococcygeal curvature angle were higher in males, whereas the intercoccygeal curvature angle was higher in females. Information on similarities and differences in coccygeal morphology between different ethnic populations could be useful in imaging and treating patients presenting with coccydynia.

Background: There are many treatments given for mechanical Low back pain which includes Anti-inflammatory Drugs, Traction, Stretching However, studies involving Core muscle release technique for management of Mechanical Low back pain are limited to this date.Objective: To find out the efficacy Core muscle release technique for the management of mechanical low back pain. Study design: Quasi experimental study design. Subjects: 40 subjects with Core muscle release technique with low level laser therapy (LLLT) and Conventional physical therapy with Low level laser therapy, age group 20-40 years of males.Intervention: 20 subjects in the Group 1 received Core muscle release technique with low level laser therapy before and after-test and 20 subjects in Group 2 received Conventional Physical therapy and Low level laser therapy with before and after -test.Outcome measure: Numeric pain rating scale (NPRS), The Roland-Morris Low Back Pain and Disability Questionnaire (RMDQ), Active Lumbar range of movements like (Flexion, Extension, side flexion to right and left)Results: Statistical data analysis was done by using Paired 't' test which showed significant improvement in both group. Conclusion:Core muscle release technique with LLLT has significant result in the reduction of pain and functional activity in Mechanical Low back pain patients. KeywordsCore muscle release technique, Low level laser therapy, Mechanical low back pain