Australasian Medical Journal
Not a member yet
1482 research outputs found
Sort by
Lamin C gene-mutation and ventricular dysrrhythmia
No full textLamin A/C gene-related cardiomyopathy is associated with progressive heart failure and malignant arrhythmias. Current guidelines advise the use of implantable defibrillators to prevent arrhythmogenic sudden cardiac death only in situations where there is evidence of severe left ventricular dysfunction. We describe a case of a woman with genetically confirmed Lamin C deficiency with preserved left ventricular function in whom an implantable defibrillator was inserted and within a month of implantation was used to terminate symptomatic ventricular tachycardia
Incidence of Ovarian Pregnancy is in the increasing trend? Two case reports
No full textOvarian pregnancy is a rare event occurring in 1-3% of all ectopic pregnancies. Increased reporting might be due to the wider use of intra-uterine devices, ovulatory drugs and assisted reproductive techniques. Though ovarian pregnancy has a distinct pathology, it can be a source of clinical and intraoperative diagnostic difficulty. We report two cases of ovarian pregnancy – one primary and one secondary – that came to our notice within six months span. Unlike tubal ectopic and secondary ovarian pregnancies, patients with primary ovarian pregnancy are likely to experience success in future intra-uterine conception and negligible risk
Incorporating feature ranking and evolutionary methods for the classification of high-dimensional DNA microarray gene expression data
Get PDFBackgroundDNA microarray gene expression classification poses a challenging task to the machine learning domain. Typically, the dimensionality of gene expression data sets could go from several thousands to over 10,000 genes. A potential solution to this issue is using feature selection to reduce the dimensionality.AimThe aim of this paper is to investigate how we can use feature quality information to improve the precision of microarray gene expression classification tasks. Method We propose two evolutionary machine learning models based on the eXtended Classifier System (XCS) and a typical feature selection methodology. The first one, which we call FS-XCS, uses feature selection for feature reduction purposes. The second model is GRD-XCS, which uses feature ranking to bias the rule discovery process of XCS.ResultsThe results indicate that the use of feature selection / ranking methods is essential for tackling high-dimensional classification tasks, such as microarray gene expression classification. However, the results also suggest that using feature ranking to bias the rule discovery process performs significantly better than using the feature reduction method. In other words, using feature quality information to develop a smarter learning procedure is more efficient than reducing the feature set. ConclusionOur findings have shown that extracting feature quality information can assist the learning process and improve classification accuracy. On the other hand, relying exclusively on the feature quality information might potentially decrease the classification performance (e.g., using feature reduction). Therefore, we recommend a hybrid approach that uses feature quality information to direct the learning process by highlighting the more informative features, but at the same time not restricting the learning process to explore other features
Automated Classification of Limb Fractures from Free-Text Radiology Reports using a Clinician-informed Gazetteer Methodology
Get PDFBackgroundTimely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to dispersed information resources and a vast amount of manual processing of unstructured information, accurate point-of-care diagnosis is often difficult. AimsThe aim of this research is to report initial experimental evaluation of a clinician-informed automated method for the issue of initial misdiagnoses associated with delayed receipt of unstructured radiology reports. Method A method was developed that resembles clinical reasoning for identifying limb abnormalities. The method consists of a gazetteer of keywords related to radiological findings; the method classifies an X-ray report as abnormal if it contains evidence contained in the gazetteer. A set of 99 narrative reports of radiological findings was sourced from a tertiary hospital. Reports were manually assessed by two clinicians and discrepancies were validated by a third expert ED clinician; the final manual classification generated by the expert ED clinician was used as ground truth to empirically evaluate the approach.ResultsThe automated method that attempts to individuate limb abnormalities by searching for keywords expressed by clinicians achieved an F-measure of 0.80 and an accuracy of 0.80.ConclusionWhile the automated clinician-driven method achieved promising performances, a number of avenues for improvement were identified using advanced natural language processing (NLP) and machine learning techniques
Detection of Metallo-beta-lactamase producing Pseudomonas aeruginosa in Intensive care units
Get PDFBackgroundMetallo-beta-lactamase (MBL) producing Pseudomonas aeruginosa has emerged as a threat to hospital infection control, due to its multi-drug resistance, especially in intensive care units (ICUs). AimsThis study was carried out to detect MBL producing P. aeruginosa isolates from medical and surgical ICUs, to compare and evaluate different phenotypic methods currently in use and to determine antibiograms.Method A prospective study was undertaken to detect MBLs in P. aeruginosa isolates obtained from various clinical samples. A total of 49 strains were recovered from patients admitted in inpatient wards and ICUs, and screened for imipenem resistance by Kirby Bauer disk diffusion method. Detection of MBLs was further done by imipenem-EDTA disk synergy test and combined disk test.ResultsOut of 49 isolates, 11 isolates (22.4 per cent) were imipenem resistant. All 11 imipenem resistant P. aeruginosa strains, when further tested, were positive for MBL production by combined disk test, but, only eight showed positive results by imipenem-EDTA disk synergy test.ConclusionMBL production was the main resistance mechanism in the 11 carbapenem resistant P. aeruginosa isolates collected, with multidrug resistance associating significantly with MBL production in P. aeruginosa from our institution
Letter to the Editor
Get PDFIntroduction: A medical humanities (MH) module, Sparshanam has been conducted for all first year undergraduate medical students at KIST Medical College, Nepal, since 2008. Knowledge, attitude and perceived skills in empathy, what it means to be sick in Nepal, the doctor, the patient, the family, doctor-patient relationship and professional values in medicine were studied at the beginning and conclusion of the module conducted from December 2011 to March 2012.
Methods: A questionnaire was developed to study respondents’ perception regarding knowledge, attitude and perceived skill levels in the areas mentioned above. Total scores in different areas and overall score were calculated. All scores were normally distributed (one sample Kolmogorov-Smirnov test). Scores among different subgroups of respondents and before and after the module were compared using appropriate tests (
