One-half of the world’s population lives in cities and towns; this is expected to increase to 70% by 2050. One in three urban dwellers lives in slums. As the urban population grows, so does the number of urban poor. Out of a billion children living in urban areas, approximately 300 million are suffering from exclusion or are at risk of exclusion. Urban poor children are devoid of basic rights of survival, development and protection and are marginalised in challenging conditions in overcrowded settlements. Rapid urbanisation and the consequent increase in urban population is one of the biggest challenges that developing countries, including India are facing. Thirty per cent (that is, 367.5 million) of India’s population of 1.23 billion live in urban areas. Moreover, this figure is increasing rapidly and is expected to reach 432 million (40%) by 2021. Rapid urbanisation has unfortunately outpaced development, and a large proportion (43 million) live in substandard conditions in slums. Now is the time to pay attention to the basic rights of the urban poor, especially the urban poor children, the most vulnerable group at the launching of 12th Five-Year Plan & National Urban Health Mission (NUHM) in India.
Urban poor; slum children; urban children
Malignant melanoma of the conjunctiva is a rare tumour of middle and old age. It is seen predominantly in whites, and is rare in those of pigmented ethnicity. Its clinical presentation varies, and making a clinical diagnosis may be difficult. The tumour is potentially fatal and displays a high rate of recurrence, which can be attributed to delay in diagnosis, as well as inadequate surgical approach. The literature on this melanoma is scanty, even in the West, particularly regarding the precise surgical technique.
We report a case of malignant melanoma of the conjunctiva which showed a local recurrence one year after the primary surgery. However, there was no evidence of distant metastasis on either occasion. This case highlights the need for care in making a diagnosis, meticulous attention to the surgical technique, and careful follow-up to detect further disease activity.
De novo; Conjunctival malignant melanoma; Local recurrence
DNA 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.
The aim of this paper is to investigate how we can use feature quality information to improve the precision of microarray gene expression classification tasks.
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.
The results indicate that the use of feature selection/ranking methods is essential for tackling highdimensional 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.
Our 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.
Classification; high-dimensional data; feature ranking; microarray gene expression profiling; eXtended Classifier System; XCS; GRD-XCS; guided rule discovery XCS; evolutionary algorithms
Stroke is one of the major diseases with human mortality. Recent clinical research has indicated that early changes in common physiological variables represent a potential therapeutic target, thus the manipulation of these variables may eventually yield an effective way to optimise stroke recovery.
We examined correlations between physiological parameters of patients during the first 48 hours after a stroke, and their stroke outcomes after three months. We wanted to discover physiological determinants that could be used to improve health outcomes by supporting the medical decisions that need to be made early on a patient’s stroke experience.
We applied regression-based machine learning techniques to build a prediction algorithm that can forecast threemonth outcomes from initial physiological time series data during the first 48 hours after stroke. In our method, not only did we use statistical characteristics as traditional prediction features, but we also adopted trend patterns of time series data as new key features.
We tested our prediction method on a real physiological data set of stroke patients. The experiment results revealed an average high precision rate: 90%. We also tested prediction methods only considering statistical characteristics of physiological data, and concluded an average precision rate: 71%.
We demonstrated that using trend pattern features in prediction methods improved the accuracy of stroke outcome prediction. Therefore, trend patterns of physiological time series data have an important role in the early treatment of patients with acute ischaemic stroke.
Stroke outcome prediction; Time series data; Machine Learning
An ageing population and higher rates of chronic disease increase the demand on health services. The Australian Institute of Health and Welfare reports a 3.6% per year increase in total elective surgery admissions over the past four years.1 The newly introduced National Elective Surgery Target (NEST) stresses the need for efficiency and necessitates the development of improved planning and scheduling systems in hospitals.
To provide an overview of the challenges of elective surgery scheduling and develop a prediction based methodology to drive optimal management of scheduling processes.
Our proposed two stage methodology initially employs historic utilisation data and current waiting list information to manage case mix distribution. A novel algorithm uses current and past perioperative information to accurately predict surgery duration. A NEST-compliance guided optimisation algorithm is then used to drive allocation of patients to the theatre schedule.
It is expected that the resulting improvement in scheduling processes will lead to more efficient use of surgical suites, higher productivity, and lower labour costs, and ultimately improve patient outcomes.
Accurate prediction of workload and surgery duration, retrospective and current waitlist as well as perioperative information, and NEST-compliance driven allocation of patients are employed by our proposed methodology in order to deliver further improvement to hospital operating facilities.
Surgery scheduling; Predictive optimisation; Waiting list
Cancer monitoring and prevention relies on the critical aspect of timely notification of cancer cases. However, the abstraction and classification of cancer from the free-text of pathology reports and other relevant documents, such as death certificates, exist as complex and time-consuming activities.
In this paper, approaches for the automatic detection of notifiable cancer cases as the cause of death from free-text death certificates supplied to Cancer Registries are investigated.
A number of machine learning classifiers were studied. Features were extracted using natural language techniques and the Medtex toolkit. The numerous features encompassed stemmed words, bi-grams, and concepts from the SNOMED CT medical terminology. The baseline consisted of a keyword spotter using keywords extracted from the long description of ICD-10 cancer related codes.
Death certificates with notifiable cancer listed as the cause of death can be effectively identified with the methods studied in this paper. A Support Vector Machine (SVM) classifier achieved best performance with an overall Fmeasure of 0.9866 when evaluated on a set of 5,000 freetext death certificates using the token stem feature set. The SNOMED CT concept plus token stem feature set reached the lowest variance (0.0032) and false negative rate (0.0297) while achieving an F-measure of 0.9864. The SVM classifier accounts for the first 18 of the top 40 evaluated runs, and entails the most robust classifier with a variance of 0.001141, half the variance of the other classifiers.
The selection of features significantly produced the most influences on the performance of the classifiers, although the type of classifier employed also affects performance. In contrast, the feature weighting schema created a negligible effect on performance. Specifically, it is found that stemmed tokens with or without SNOMED CT concepts create the most effective feature when combined with an SVM classifier.
Death certificates; Cancer Registry; cancer monitoring and reporting; machine learning; natural language processing; SNOMED CT
Timely 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.
The 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.
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.
The 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.
While 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.
Limb fractures; emergency department; radiology reports; classification; rule-based method; machine learning
Electroencephalogram (EEG) signal analysis is indispensable in epilepsy diagnosis as it offers valuable insights for locating the abnormal distortions in the brain wave. However, visual interpretation of the massive amounts of EEG signals is time-consuming, and there is often inconsistent judgment between experts.
This study proposes a novel and reliable seizure detection system, where the statistical features extracted from the discrete wavelet transform are used in conjunction with an improved wavelet neural network (WNN) to identify the occurrence of seizures.
Experimental simulations were carried out on a well-known publicly available dataset, which was kindly provided by the Epilepsy Center, University of Bonn, Germany. The normal and epileptic EEG signals were first pre-processed using the discrete wavelet transform. Subsequently, a set of statistical features was extracted to train a WNNs-based classifier.
The study has two key findings. First, simulation results showed that the proposed improved WNNs-based classifier gave excellent predictive ability, where an overall classification accuracy of 98.87% was obtained. Second, by using the 10th and 90th percentiles of the absolute values of the wavelet coefficients, a better set of EEG features can be identified from the data, as the outliers are removed before any further downstream analysis.
The obtained high prediction accuracy demonstrated the feasibility of the proposed seizure detection scheme. It suggested the prospective implementation of the proposed method in developing a real time automated epileptic diagnostic system with fast and accurate response that could assist neurologists in the decision making process.
Epileptic seizure detection; fuzzy C-means clustering; Kmeans clustering; type-2 fuzzy C-means clustering; wavelet neural network
We report a case of Kingella kingae endocarditis in a patient with a history of recent respiratory tract infection and dental extraction. This case is remarkable for embolic and vasculitic phenomena in association with a large valve vegetation and valve perforation. Kingella kingae is an organism known to cause endocarditis, however early major complications are uncommon. Our case of Kingella endocarditis behaved in a virulent fashion necessitating a combined approach of intravenous antibiotic therapy and a valve replacement. It highlights the importance of expedited investigation for endocarditis in patients with Kingella bacteraemia.
Kingella kingae; Endocarditis; Mitral Valve Rupture
Leprosy (Hansen’s disease) is caused by the obligate intracellular organism Mycobacterium leprae. It is an infectious, chronic granulomatous disease transmitted through close contact. The latest current data shows that in 2010, eleven new cases of leprosy were reported to the National Notifiable Diseases Surveillance System in Australia. We report the case of a patient with untreated chronic lepromatous leprosy diagnosed in Queensland, 2012. Delay in diagnosis may have been due to the rarity of this condition.
Leprosy; Aboriginal; deformity
Ventilator associated pneumonia (VAP) is a type of nosocomial pneumonia associated with increased morbidity and mortality. Knowledge about the incidence and risk factors is necessary to implement preventive measures to reduce mortality in these patients.
A prospective study was conducted at a tertiary care teaching hospital for a period of 20 months from November 2009 to July 2011. Patients who were on mechanical ventilation (MV) for more than 48 hours were monitored at frequent intervals for development of VAP using clinical and microbiological criteria until discharge or death.
Of the 76 patients, 18 (23.7%) developed VAP during their ICU stay. The incidence of VAP was 53.25 per 1,000 ventilator days. About 94% of VAP cases occurred within the first week of MV. Early-onset and late-onset VAP was observed in 72.2% and 27.8%, respectively. Univariate analysis showed chronic lung failure, H2 blockers usage, and supine head position were significant risk factors for VAP. Logistic regression revealed supine head position as an independent risk factor for VAP.
VAP occurred in a sizeable number of patients on MV. Chronic lung failure, H2 blockers usage, and supine head position were the risk factors associated with VAP. Awareness about these risk factors can be used to inform simple and effective preventive measures.
VAP; incidence; risk factors
Accredited pharmacists conduct home medicines reviews (HMRs) to detect and resolve potential drug-related problems (DRPs). A commercial expert system, Medscope Review Mentor (MRM), has been developed to assist pharmacists in the detection and resolution of potential DRPs.
This study compares types of DRPs identified with the commercial system which uses multiple classification ripple down rules (MCRDR) with the findings of pharmacists.
HMR data from 570 reviews collected from accredited pharmacists was entered into MRM and the DRPs were identified. A list of themes describing the main concept of each DRP identified by MRM was developed to allow comparison with pharmacists. Theme types, frequencies, similarity and dissimilarity were explored.
The expert system was capable of detecting a wide range of potential DRPs: 2854 themes; compared to pharmacists: 1680 themes. The system identified the same problems as pharmacists in many patient cases. Ninety of 119 types of themes identifiable by pharmacists were also identifiable by software. MRM could identify the same problems in the same patients as pharmacists for 389 problems, resulting in a low overlap of similarity with an averaged Jaccard Index of 0.09
MRM found significantly more potential DRPs than pharmacists. MRM identified a wide scope of DRPs approaching the range of DRPs that were identified by pharmacists. Differences may be associated with system consistency and perhaps human oversight or human selective prioritisation. DRPs identified by the system were still considered relevant even though the system identified a larger number of problems.
Clinical decision support system; MCRDR; home medicines review; pharmacy practice
A 55-year-old male patient presented with gradual progressive outward and downward deviation of right eye since last two years, with history of a similar complaint 10 years ago when he was diagnosed as having neurofibroma of the orbit. Computed Tomography imaging revealed a large, multilobulated, heterogeneous, soft tissue density mass lesion in the retro bulbar region on the medial side of right orbit suggestive of a neurofibroma. Excision and histopathology confirmed it to be a recurrence of neurofibroma of the orbit.
Recurrent; neurofibroma; orbit
We report a case of a right radial pseudoaneurysm due to assault. The pseudoaneurysm was treated successfully with prolonged ultrasound-guided compression for more than 300 minutes over multiple sittings coupled with the use of a compression device. We believe that if initial compression fails, a prolonged ultrasound-guided compression repair coupled with a compression device can greatly improve the success rates and can negate the use of more invasive procedures to treat pseudoaneurysms.
Pseudoaneurysm; Ultrasound-Guided Compression Repair (UGCR); Prolonged Compression; Radial Artery
The number of medical practitioners in the developed world has increased but in relative terms their incomes have decreased. Published comments suggest that some doctors are dissatisfied with what they earn. However doctors are still perceived as having a high status in society. Publicly available data suggests that doctors chose to live and work in affluent suburbs where arguably the need for their skills is less than that in neighbouring deprived areas. The gender balance in medicine is also changing with more women entering the workforce and a greater acceptance of parttime working arrangements. In some countries doctors have relinquished the responsibility for emergency out of hours care in general practice and personal continuity of care is no longer on offer. The profession is also challenged by policy makers’ enthusiasm for guidelines while the focus on multidisciplinary teamwork makes it more likely that patients will routinely be able to consult professionals other than medical practitioners. At the same time the internet has changed patient expectations so that health care providers will be expected to deploy information technology to satisfy patients. Medicine still has a great deal to offer. Information may be readily available on the internet, but it is not an independently sufficient, prerequisite for people to contend with the physical and psychological distress associated with disease and disability. We need to understand and promote the crucial role doctors play in society at a time of tremendous change in the attitudes to, and within, the profession.
Doctors; profession; income; working hours
We report an interaction between erythromycin and simvastatin resulting in life-threatening rhabdomyolysis in an elderly patient. Drugs that inhibit CYP3A4 enzyme can cause elevated serum levels of statins which amplifies the risk of statin-induced rhabdomyolysis. Physicians should be aware of potential drug interactions of statins, which are widely used in the community.
Rhabdomyolysis; Drug interaction; Statins; Macrolides
We describe a case of a 40-year-old male patient who was found to have multiple myeloma with spontaneous tumour lysis syndrome (TLS), following a compression fracture of the L–2 vertebrae. Multiple myeloma was confirmed by bone marrow analysis and the M–band on serum protein electrophoresis. Hyperuricaemia (26.2 mg/dL), hyperkalaemia (> 7.0 mEq/L), hyperphosphatemia (16.2 mg of phosphorus/dL), normocalcemia and acute kidney injury, prior to anticancer treatment suggested spontaneous TLS. Inciting events for tumour lysis, such as chemotherapy, dehydration and exposure to steroids were absent. Patient received hydration, hypourecemic drugs and haemodialysis. This case report highlights the rare presentation of multiple myeloma with spontaneous TLS.
Hyperphosphatemia; hyperkalaemia; hyperuricaemia; normocalcaemia; renal failure
A total of 275 million tobacco users live throughout India and are in need of tobacco cessation services. However, the preparation of physicians to deliver this service at primary care health facilities remains unknown.
The study aimed to examine the primary care physicians’ preparedness to deliver tobacco cessation services in two Indian states.
Researchers surveyed physicians working in primary care public health facilities, primarily in rural areas using a semistructured interview schedule. Physicians’ preparedness was defined in the study as those possessing knowledge of tobacco cessation methods and exhibiting a positive attitude towards the benefits of tobacco cessation counselling as well as being willing to be part of tobacco prevention or cessation program.
Overall only 17% of physicians demonstrated adequate preparation to provide tobacco cessation services at primary care health facilities in both the States. The findings revealed minimal tobacco cessation training during formal medical education (21.3%) and on-the-job training (18.9%). Factors, like sex and age of service provider, type of health facility, location of health facility and number of patients attended by the service provider, failed to show significance during bivariate and regression analysis. Preparedness was significantly predicted by state health system.
The study highlights a lack of preparedness of primary care physicians to deliver tobacco cessation services. Both the curriculum in medical school and on-the-job training require an addition of a learning component on tobacco cessation. The addition of this component will enable existing primary care facilities to deliver tobacco cessation services.
Tobacco cessation; service delivery; primary care; physicians; India
Wellens’ syndrome is a condition in which electrocardiographic (ECG) changes indicate critical proximal left anterior descending artery narrowing occurring during the chest pain-free period. Due to the severity of the obstruction, if such cases are managed by early invasive revascularisation therapy, a major threat in the form of a massive myocardial infarction or sudden death may be averted. We present the case of a patient with previous chest pain, whose ECG showing subtle ischemic changes was initially overlooked. A repeat ECG taken during the painless period showed a biphasic T wave, suggestive of Wellen’s’ syndrome. This was confirmed by an immediate coronary angiogram.
Wellens’ syndrome; left anterior descending artery obstruction; electrocadiographic changes; revascularisation
Past reports on trends of alcohol consumption and related harm have generally been descriptive in nature and have not provided evidence of whether changes over time are significant.
We investigated whether: (i) the risk of alcohol-attributable hospitalisation and death between 1994 and 2005 for three different age groups changed significantly across all Australian jurisdictions; and (ii) the relative rates of hospitalisation for males and females changed over time.
Estimates of alcohol-attributable hospitalisations and deaths were calculated using the aetiologic fraction method. Hospitalisations and deaths were grouped by age: 15-29 years, 30-44 years and 45+ years. Risk estimates and risk differences were analysed using Poisson regression.
Risk of alcohol-attributable hospital separations increased nationally and across most jurisdictions throughout the study period. Male and female rates converged over time. Alcohol-attributable deaths decreased nationally across the three age groups and across several jurisdictions beginning in the mid-1990s.
Nationally, alcohol-attributable deaths declined while hospitalisations rose. However, states with higher population density tended to drive national rates, with considerable variation by jurisdiction. The conditions which dominated hospitalisations (e.g. alcohol dependence, falls) differed substantially from those underlying alcoholattributable deaths (e.g. alcoholic liver cirrhosis, road crashes). Jurisdictional variation in death and hospitalisations rates as well as changes over time may be partly due to differences in: regulation of alcohol supply; patterns and levels of alcohol consumption; the nature and effectiveness of law enforcement; demographic characteristics of general and sub-populations; and medical health services and screening for chronic conditions.
Alcohol; aetiologic fraction; mortality; morbidity; risk; epidemiology
Thrombolysis remains the only approved therapy for acute ischaemic stroke (AIS); however, its utilisation is reported to be low.
This study aimed to determine the reasons for the low utilisation of thrombolysis in clinical practice.
Five metropolitan hospitals comprising two tertiary referral centres and three district hospitals conducted a retrospective, cross-sectional study. Researchers identified patients discharged with a principal diagnosis of AIS over a 12-month time period (July 2009–July 2010), and reviewed the medical record of systematically chosen samples.
The research team reviewed a total of 521 records (48.8% females, mean age 74.4 ± 14 years, age range 5-102 years) from the 1261 AIS patients. Sixty-nine per cent of AIS patients failed to meet eligibility criteria to receive thrombolysis because individuals arrived at the hospital later than 4.5 hours after the onset of symptoms. The factors found to be positively associated with late arrival included confusion at onset, absence of a witness at onset and waiting for improvement of symptoms. However, factors negatively associated with late arrival encompassed facial droop, slurred speech and immediately calling an ambulance. Only 14.7% of the patients arriving within 4.5 hours received thrombolysis. The main reasons for exclusion included such factors as rapidly improving symptoms (28.2%), minor symptoms (17.2%), patient receiving therapeutic anticoagulation (6.7%) and severe stroke (5.5%).
A late patient presentation represents the most significant barrier to utilising thrombolysis in the acute stroke setting. Thrombolysis continues to be currently underutilised in potentially eligible patients, and additional research is needed to identify more precise criteria for selecting patients for thrombolysis.
Tissue Plasminogen Activator (tPA); Alteplase; Thrombolysis; Stroke; Cerebrovascular accident
Suprapubic cartilaginous cyst (SPCC) is a rare condition known to occur in postmenopausal multiparous women. It is due to the degeneration of the pubic symphysis. Due to its slow progression and rarity in occurrence, it is often misdiagnosed. Presentation includes a painless mass in the suprapubic region, urinary retention, recurrent urinary tract infections, dysuria and dyspareunia. Knowledge of this condition is of great importance, as this is a benign condition that is managed conservatively, thereby avoiding unnecessary procedures. Surgical resection has not shown to have any additional benefit. Once suspected, MRI is ideal for diagnosis. This case report discusses a SPCC with punctuate calcifications and a locule of gas within it. This is the first documented case of a SPCC with punctuate calcifications.
Suprapubic cartilaginous cyst; suprapubic cyst; painless valvular mass; symphysis pubis degeneration