Sentimental analysis from imbalanced code-mixed data using machine learning approaches

Knowledge discovery from various perspectives has become a crucial asset in almost all fields. Sentimental analysis is a classification task used to classify the sentence based on the meaning of their context. This paper addresses class imbalance problem which is one of the important issues in sentimental analysis. Not much works focused on sentimental analysis with imbalanced class label distribution. The paper also focusses on another aspect of the problem which involves a concept called "Code Mixing". Code mixed data consists of text alternating between two or more languages. Class imbalance distribution is a commonly noted phenomenon in a code-mixed data. The existing works have focused more on analyzing the sentiments in a monolingual data but not in a code-mixed data. This paper addresses all these issues and comes up with a solution to analyze sentiments for a class imbalanced code-mixed data using sampling technique combined with levenshtein distance metrics. Furthermore, this paper compares the performances of various machine learning approaches namely, Random Forest Classifier, Logistic Regression, XGBoost classifier, Support Vector Machine and Naïve Bayes Classifier using F1- Score.

Prevalence of early hip OA features on MRI in high-impact athletes. The femoroacetabular impingement and hip osteoarthritis cohort (FORCe) study

OBJECTIVE

To compare early hip osteoarthritis (OA) features on magnetic resonance imaging (MRI) in high-impact athletes with and without hip and/or groin pain, and to evaluate associations between early hip OA features, the International Hip Outcome Tool (iHOT33) and Copenhagen Hip and Groin Outcome Score (HAGOS).

DESIGN

This case-control study evaluated data of the femoroacetabular impingement and hip osteoarthritis cohort (FORCe). One hundred and eighty-two symptomatic (hip and/or groin pain >6 months and positive flexion-adduction-internal-rotation (FADIR) test) and 55 pain-free high-impact athletes (soccer or Australian football (AF)) without definite radiographic hip OA underwent hip MRI. The Scoring Hip Osteoarthritis with MRI (SHOMRI) method quantified and graded the severity of OA features. Each participant completed the iHOT33 and HAGOS.

RESULTS

Hip and/or groin pain was associated with higher total SHOMRI (0-96) (mean difference 1.4, 95% CI: 0.7-2.2), labral score (adjusted incidence rate ratio (aIRR) 1.33, 95% CI: 1.1-1.6). Differences in prevalence of cartilage defects, labral tears and paralabral cysts between symptomatic and pain-free participants were inconclusive. There was a lower prevalence of effusion-synovitis in symptomatic participants when compared to pain-free participants (adjusted odds ratio (aOR) 0.46 (95% CI: 0.3-0.8). Early hip OA features were not associated with iHOT33 or HAGOS.

CONCLUSIONS

A complex and poorly understood relationship exists between hip and/or groin pain and early hip OA features present on MRI in high-impact athletes without radiographic OA. Hip and/or groin pain was associated with higher SHOMRI and labral scores.

Emergence of Maruca vitrata as a Major Pest of Food Legumes and Evolution of Management Practices in Asia and Africa

Legume pod borer, Maruca vitrata, has emerged as a major pest on food legumes in Asia and Africa. It is an oligophagous pest, feeding on over 70 species in Fabaceae. We examine the species complex in Asia, Africa, Oceania, and the Americas, with an emphasis on molecular taxonomy. Studies on pheromone production and perception suggest the existence of pheromone polymorphism, especially in Asia and Africa. No Maruca-resistant varieties are available in the major food legumes including cowpea, pigeonpea, mungbean, and yard-long bean. Legume growers use chemical pesticides indiscriminately, leading to the development of pesticide resistance. However recent developments in habitat management, classical biocontrol with more efficient parasitoids, biopesticides, and judicious use of insecticides pave the way for sustainable management of M. vitrata, which can reduce the pesticide misuse. Active engagement of the private sector and policy makers can increase the adoption of integrated pest management approaches in food legumes.

Evaluation of Different Bacterial Wilt Resistant Eggplant Rootstocks for Grafting Tomato

Bacterial wilt (BW) is one of the most economically important diseases of tomato and eggplant in the tropics and subtropics, and grafting onto resistant rootstocks can provide an alternative and effective solution to manage soil-borne bacterial in these crops. This study was conducted to evaluate the BW resistance and agronomic potential of newly identified eggplant accessions as rootstocks for tomato grafting. Five BW resistant eggplant accessions (VI041809A, VI041943, VI041945, VI041979A, and VI041984) from the World Vegetable Center were evaluated as rootstocks for grafting with two different fresh market tomato cultivars (Victoria and TStarE) as scion under open field conditions in Taiwan. Graft compatibility using the tube grafting method as well as BW wilting percentage, disease index, fruit yield and quality parameters were assessed. All the rootstocks showed good graft compatibility (93% and above) and grafted plants showed low wilting percentage (0.0–20.0%) and disease index (0.0–20.8%) following inoculation with BW. Yield for the eggplant rootstock grafted tomato plants was higher compared to the non-grafted tomatoes and self-grafted tomato. Fruit quality was not affected by grafting, although some differences in antioxidant activities were observed. The new eggplant rootstocks can be considered as alternatives to the rootstocks currently used for commercial production of tomatoes during the hot-wet season.

Molecular analysis of Bacillus velezensis KB 2216, purification and biochemical characterization of alpha-amylase

Alpha-amylase producing strain KB 2216 was identified as Bacillus velezensis. The growth pattern showed that 72 h is the optimum incubation period of amylase production, which is a stationary period for the strain. By the purification process, maximum alpha-amylase activity was achieved up to 418.25 U/mL at 72 h of incubation, which was purified with 4.74 folds, 4230.32 U/mg specific activity, with 31.35% yield. The strain was found to produce an oligomeric alpha-amylase, namely Amy3. Amy3 was a trimeric macromolecule of 195 kDa with 62, 64, and 66 kDa subunits, as revealed by zymogram and SDS PAGE analyses. Amy3 was highly active at 55 °C and pH 5.5. It had shown the highest stability at pH 5.0-5.5 and between 0 ̊C and 4 ̊C. It did not require any metal cofactors, but it was inhibited by Ag²⁺, Hg²⁺ and Cd²⁺ divalent cations. Glucose and maltose were shown to be the end products of soluble starch digestion by Amy3. These interesting properties of Amy3 may be useful for many biotechnological applications in the future.

Enhanced Biosynthesis Synthesis of Copper Oxide Nanoparticles (CuO-NPs) for their Antifungal Activity Toxicity against Major Phyto-Pathogens of Apple Orchards

PURPOSE

The present study made an attempt to develop copper nanoparticles (Cu-NP) with antifungal property using green synthesis method. Copper oxide nanoparticles (CuO-NPs) botanically synthesized using Neem leaf extract (Azadirachta indica A. Juss) were characterized by using different techniques like; UV-visible spectrophotometry, FTIR, XRD, SEM and TEM.

METHODS

Materials were chosen the disease free and fresh Azadirachta indica A. Juss were collected and identified at Center of Biodiversity and Taxonomy. The plant samples were vigorously washed with distilled water then shade dried followed by sterilization with 0.1% mercuric chloride for 20 s and again it was washed with distilled water. 15 g powder form of plant material was added to 200 ml double distilled, CO₂ free and deionized water and kept in shaker at 80°C and 1500 rpm for six hours. After agitation, the extract was separated by regular centrifugation at 10,000 rpm followed by filtration by using whatmann filter paper. The final volume of 100 ml of supernatant was collected as pure extract and stored in cool place for further use.

RESULTS

The final results confirm a significant inhibition of CuO-NPs for the test fungi. Additionally, CuO-NPs demonstrated an enhanced effect when combined with Neem leaf extract. A total of 20-30% improvement in activity was noticed after combination, which correlates with commonly used synthetic fungicides. The toxicity results reveal that A. indica extract and their combined fractions with CuO-NP were less toxic to the test seeds of experimental plant while as bulk Cu followed by biosynthesized CuO-NPs influenced the germination rate as compared to control pots.

CONCLUSIONS

The study drops a concern of research and offers a promising route of developing Copper based green fungicides that can help to combat with modern issues of synthetic fungicides. An average size of 80 ± 15 nm monoclinic cupric oxide (CuO) and cubic cuprous oxides (Cu₂O) nanocrystals that existed in mixed form were successfully developed.

Evaluating satellite-based evapotranspiration estimates for hydrological applications in data-scarce regions: A case in Ethiopia

Water resource development opens up opportunities for improving smallholder farmer livelihoods in sub-Saharan Africa; however, implementation of water resource interventions to ensure sustainability hinges on the availability of sufficient quantity and quality data for monitoring, analysis and planning. Such data is often acquired through instrumentation of water resources (e.g. stream flow monitoring) or the use of hydrological models. In sub-Saharan Africa, data scarcity has limited the ability to monitor and make appropriate decisions for water resource allocation and use. Data derived from remote sensing has been considered a viable option to fill this gap; however, there is limited research in the region that evaluate the quality of the remotely sensed based datasets. This study evaluated actual evapotranspiration (AET) estimates derived from Advanced Very High Resolution Radiometer (AVHRR AET) images and Moderate Resolution Imaging Spectrometer (MOD16 AET) images using estimates from a grid-based Soil and Water Assessment Tool (SWAT). The SWAT model was set up for the entire country of Ethiopia, and calibrated and validated using observed streamflow at several meso-scale watersheds in which satisfactory model performance was obtained. AET estimates from the calibrated and validated SWAT model were then used to evaluate remotely sensed based AET for three landscapes. The AVHRR AET better agreed with the SWAT-simulated AET than the MOD16 AET, although the AVHRR AET overestimated the SWAT-simulated AET in all of the landscapes. Both remotely sensed AET products showed better agreement with the SWAT-simulated AET over agriculture dominated landscapes compared to grassland and forest dominated landscapes. The findings of the study suggest that remotely sensed based AET may help to fine-tune hydrological models in agricultural landscapes in data-scarce regions to improve studies on the impacts of water management interventions aiming to ensure environmental sustainability while enhancing agricultural production, and household income and nutrition.

Power Spectral Density Computation and Dominant Frequencies Identification from the Vibration Sensor Output under Random Vibration Environment

The objective of the modal and spectral analysis is to determine the vibration characteristics of structures such as natural frequencies, dominant frequencies and mode shapes. Such modal and spectral analyses have major relevance to the study of the dynamic properties of the structures undergoing dynamic vibration. Methods for the estimation of the power spectral density and identification of the dominant frequencies from the sensor responses under random vibrating environment are presented in this paper. Periodogram using FFT, Welch Method and MUSIC algorithm are used to analyse the known frequency sinusoids with additive white noise and output of the vibration sensor mounted on the test object. The resultant spectra obtained using the methods and their corresponding errors with the reference spectrum are analysed. The Welch method is further studied with three different windows, namely, Hann, Hamming and Blackman-Harris and with three different overlapping criteria viz. 0%, 25% and 50%. The same algorithm and methodology were adopted and compared in two different platforms: Mathematical Model Simulation and Hardware-In-Loop-Simulation. It is observed from the results that Welch Method with 25% overlap used in combination either with Hann or Blackman-Harris window yields more accurate results, compared to other combinations. Also, 25% overlap provides better execution time trade-off compared to 50% overlap.

Understanding the genetic aspects of resistance to antidepressants treatment

Major depression disorder (MDD) is an extremely prevalent disorder and is expected to be the second leading cause of disease burden by 2020 according to the World Health Organisation (WHO). Moreover, this disease burden is predicted to rise in the next 20 years. Antidepressant medications are vital in the therapy of major depression. However, approximately 30-60% of patients treated with current antidepressant drugs fail to attain remission of depressive symptoms leading to drug resistance. Such patients account for a disproportionately great burden of disease, as supported by cost, augmented disability, and suicidal incidents. Antidepressants resistance remains to challenge mental health care professionals, and more relevant research relating newer medications is necessitated to enhance the quality of life of patients with depression. Enhancement in response rates continues the major challenge in antidepressant research, thus a wealth of potentials still exists concerning the antidepressant resistance for the management of major depression. However, the mechanisms causing resistance to antidepressant treatment remain unknown. Hence, clinical and basic research in understanding the fundamental mechanism of antidepressant resistance should remain a key priority. One potential source accounting for these differences in treatment outcome is genetic variations. The pharmacological mechanisms behind antidepressant response are only partly known but genetic factors play a significant role. Future research of risk factors should assist to advance the understanding of the mechanisms underlying drug resistance in mood disorders and contribute to progress their therapeutic management. Thus, psychiatrists could rely on more effective approaches to treat depressive episodes, reducing the incidence of further drug resistance. This review critically summarises the author's view on many aspects of treatment resistance, specific genetic biomarkers, potential strategies and clinical relevance from both clinical and preclinical studies in drug resistance to antidepressant therapies. Finally, this will allow us to suggest possible recommendations and innovative treatment strategies to improve therapeutic outcomes in managing antidepressant resistance.

Sunlight-Driven Photocatalytic Degradation of Methyl Orange Based on Bismuth Ferrite (BiFeO₃) Heterostructures Composed of Interconnected Nanosheets

Herein, we report the facile microwave-assisted synthesis, characterization and photocatalytic degradation applications of Bismuth ferrite heterostructures composed of interconnected nanosheets (BHNs). The synthesized materials were subjected to several analytical studies such as scanning electron microscopy (SEM), transmission electron microscopy (TEM), X-ray diffraction (XRD), energy dispersive spectroscopy (EDS), Fourier transform infrared (FTIR) spectroscopy and UV-visible spectroscopy in order to examine the morphological, structural, optical and photo catalytic properties. The structural and morphological characterizations confirmed the rhombohedral perovskite crystal structure and the formation of heterostructures composed of interconnected nanosheets for the synthesized material. The compositional characterization revealed that the synthesized material is bismuth ferrite with high purity. The BHNs were further used as efficient photocatalyst for the photocatalytic degradation of highly hazardous pollutant methyl orange under sunlight irradiation. The sunlight driven photocatalytic experiments revealed ~86% photodegradation of methyl orange dye in 150 min. The presented work revealed that the synthesized BHNs are excellent material for the photocatalytic degradation of various organic contaminants and hazardous pollutants.

Visible-Light Driven Photocatalytic Degradation of Eosin Yellow (EY) Dye Based on NiO-WO₃ Nanoparticles

Herein, we report a simple synthesis, characterization and photocatalytic degradation application of composite NiO-WO₃ nanoparticles. The nanoparticles were synthesized by facile low-temperature method and characterized by several techniques such as X-ray diffraction (XRD), scanning electron microscopy (SEM), transmission electron microscopy (TEM) and UV-Vis diffuse reflectance spectra (DRS). The synthesized NiO-WO₃ nanoparticles were used as efficient photocatalyst for the photocatalytic degradation of Eosin yellow (EY) dye. Interestingly, the synthesized photocatalytic exhibited a significant visible-light driven photocatalytic degradation of Eosin yellow (EY) dye. Under optimized conditions (pH = 5, catalyst dosage = 3 μM and initial dye concentration= 1.0 g/L), the obtained photo degradation of EY dye was above 95% in 180 min under visible light irradiation. Remarkably, reusability of the prepared photocatalyst was also observed and the photo-degradation reactions follow the pseudo-first-order model.

SWAT ungauged: Water quality modeling in the Upper Mississippi River Basin

Improving model performance in ungauged basins has been a chronic challenge in watershed model application to understand and assess water quality impacts of agricultural conservation practices, land use change, and climate adaptation measures in large river basins. Here, we evaluate a modified version of SWAT2012 (referred to as SWAT-EC hereafter), which integrates an energy balanced soil temperature module (STM) and the CENTRUY-based soil organic matter algorithm, for simulating water quality parameters in the Upper Mississippi River Basin (UMRB), and compare it against the original SWAT2012. Model evaluation was performed for simulating streamflow, sediment, and nitrate-N (NO₃-N) and total nitrogen (TN) loadings at three stations near the outlets of UMRB. The model comparison was conducted without parameter calibration in order to assess their performance under ungauged conditions. The results indicate that SWAT-EC outperformed SWAT2012 for stream flow and NO₃-N and TN loading simulation on both monthly and annual scales. For sediment, SWAT-EC performed better than SWAT2012 on a monthly time step basis, but no noticeable improvement was found at the annual scale. In addition, the performance of the uncalibrated SWAT-EC was comparable to other calibrated SWAT models reported in previous publications with respect to sediment and NO₃-N loadings. These findings highlight the importance of advancing process representation in physically-based models to improve model credibility, particularly in ungauged basins.

Global soil, landuse, evapotranspiration, historical and future weather databases for SWAT Applications

Large-scale distributed watershed models are data-intensive, and preparing them consumes most of the research resources. We prepared high-resolution global databases of soil, landuse, actual evapotranspiration (AET), and historical and future weather databases that could serve as standard inputs in Soil and Water Assessment Tool (SWAT) models. The data include two global soil maps and their associated databases calculated with a large number of pedotransfer functions, two landuse maps and their correspondence with SWAT's database, historical and future daily temperature and precipitation data from five IPCC models with four scenarios; and finally, global monthly AET data. Weather data are 0.5° global grids text-formatted for direct use in SWAT models. The AET data is formatted for use in SWAT-CUP (SWAT Calibration Uncertainty Procedures) for calibration of SWAT models. The use of these global databases for SWAT models can speed up the model building by 75-80% and are extremely valuable in areas with limited or no physical data. Furthermore, they can facilitate the comparison of model results in different parts of the world.

Depression and self-harm from adolescence to young adulthood in sexual minorities compared with heterosexuals in the UK: a population-based cohort study

Background

There are few population-based cohort studies of the emergence, development, and persistence of mental health problems in sexual minorities compared with heterosexuals. We compared trajectories of depressive symptoms in sexual-minority adolescents and heterosexual adolescents from when they were aged 10 to 21 years, and examined self-harm at ages 16 and 21 years.

Methods

The study included 4828 adolescents born between April 1, 1991, and Dec 31, 1992, from the Avon Longitudinal Study of Parents and Children birth cohort (Bristol, UK) who reported their sexual orientation when aged 16 years. Depressive symptoms were assessed with the short Mood and Feelings Questionnaire at seven timepoints between ages 10 and 21 years. A self-harm questionnaire was completed at ages 16 and 21 years. Analyses were linear multilevel models with growth curves (depressive symptoms), logistic multilevel models (self-harm in the previous year at ages 16 and 21 years), and multinomial regression (lifetime self-harm with and without suicidal intent at age 21 years).

Findings

At age 10, depressive symptoms were higher in sexual minorities than in heterosexuals and increased with age to a larger extent. Depressive symptoms increased at each timepoint by 0·31 points in hetereosexuals, and by 0·49 points in sexual minorities. Sexual-minority adolescents were more likely than heterosexual adolescents to report self-harm in the previous year at ages 16 and 21 years, with no evidence that this estimate decreased with age. At aged 21, sexual minorities were more likely to report lifetime self-harm (ie, on at least one previous occasion) with suicidal intent than heterosexuals.

Interpretation

Mental health disparities between heterosexuals and sexual minorities are present early in adolescence and increase throughout the school years, persisting to young adulthood. Prevention of these mental health problems and early intervention must be a priority.

P5706Finding predictors and causes of cardiac surgery ICU readmission using machine learning and causal inference

Background

“Bounce-back” to the intensive care unit (ICU) occurs when patients return to the ICU for critical changes in clinical status within the same hospital admission. Bounce-backs post-cardiac surgery increase resource utilisation, total cost of care, are associated with higher mortality and morbidity. However, prediction of bounce-back has proved to be challenging. Previous work addressed the feasibility of predicting bounce-back, but these models required significant physician input to design and calibrate the predictive variables.

Purpose

We aimed to develop an automated machine learning model that would identify patients at risk of bounce-back by selecting the most relevant variables from those available before onset of bounce-back. Additionally, we highlight the differences between predictive and causal inference, to demonstrate that purely associative methods of prediction can mislead clinical decision-making.

Methods

Clinical records of adult cardiac surgery patients between 2011 to 2016 were collected from our institutional Society for Thoracic Surgeons (STS) database and our institutional electronic health record (EHR) system. For bounce-back prediction, an L1 regularised logistic regression model was applied, which also automatically determined important variables with highest prediction effect from the initial 151 variables. For causal inference, the g-computation algorithm was used to compare the differences between causal and predictive regression effects. We quantified the performance of our system on clinically relevant metrics such as specificity, sensitivity, and area under the ROC curve (AUC).

Results

Of the 6189 patients, 357 (5.7%) bounced back to the ICU. The prediction model achieved an AUC score of 0.75 (0.03) and 22% specificity at 95% sensitivity, Further analysis showed 79% of the false positive patients had faced other severe postoperative complications but none of the false negative patients had downstream complications. Subsequent causal analysis revealed that the actual causal effects of treatments differed from the predictive model estimates, e.g. administration of intra-operative tranexamic acid increased the probability of bounce-back by 13% but its causal effect on bounce-back after removing confounders was negligible (an increase of only 0.5%).

Conclusions

Our predictive machine-learning model can successfully predict patients at risk of ICU bounce-backs, using linked STS registry data with the comprehensive electronic health record. The prediction model automatically detects important subset of variables. In addition, we note that causal and predictive model estimates of the same parameters differed, indicating that reliance on predictive models for interventional clinical decision-making may not be appropriate.

Acknowledgement/Funding

National Institutes of Health, Office of Naval Research, Defense Advanced Research Projects Agency

Biopesticide based sustainable pest management for safer production of vegetable legumes and brassicas in Asia and Africa

Vegetables are one of the important crops which could alleviate poverty and malnutrition among the smallholder farmers in tropical Asia and Africa. However, a plethora of pests limit the productivity of these crops, leading to economic losses. Vegetable producers overwhelmingly rely on chemical pesticides in order to reduce pest-caused economic losses. However, over-reliance on chemical pesticides poses serious threats to human and environmental health. Hence, biopesticides offer a viable alternative to chemical pesticides in sustainable pest management programs. Baculoviruses such as nucleopolyhedrovirus (NPV) and granulovirus (GV) have been exploited as successful biological pesticides in agriculture, horticulture and forestry. Maruca vitrata multiple nucleocapsid NPV (MaviMNPV) was found to be a unique baculovirus specifically infecting pod borer on food legumes, and it has been successfully developed as a biopesticide in Asia and Africa. Entomopathogenic fungi also offer sustainable pest management options. Several strains of Metarhizium anisopliae and Beauveria bassiana have been tested and developed as biopesticides in Asia and Africa. This review specifically focuses on the discovery and development of entomopathogenic virus and fungi-based biopesticides against major pests of vegetable legumes and brassicas in Asia and Africa. © 2019 Society of Chemical Industry.

Microbiome digital signature of MCR genes - an in silico approach to study the diversity of methanogenic population in laboratory-developed and pilot-scale anaerobic digesters

The production of biogas by anaerobic digestion (AD) of organic/biological wastes has a firm place in sustainable energy production. A simple and cost-effective anaerobic jar at a laboratory scale is a prerequisite to study the microbial community involved in biomass conversion and releasing of methane gas. In this study, a simulation was carried out using a laboratory-modified anaerobic-jar-converted digester (AD1) with that of a commercial/pilot-scale anaerobic digester (AD2). Taxonomic profiling of biogas-producing communities by means of high-throughput methyl coenzyme-M reductase α-subunit (mcrA) gene amplicon sequencing provided high-resolution insights into bacterial and archaeal structures of AD assemblages and their linkages to fed substrates and process parameters. Commonly, the bacterial phyla Euryarchaeota, Chordata, Firmicutes and Proteobacteria appeared to dominate biogas communities in varying abundances depending on the apparent process conditions. Key micro-organisms identified from AD were Methanocorpusculum labreanum and Methanobacterium formicicum. Specific biogas production was found to be significantly correlating to Methanosarcinaceae. It can be implied from this study that the metagenomic sequencing data was able to dissect the microbial community structure in the digesters. The data gathered indicates that the anaerobic-jar system could throw light on the population dynamics of the methanogens at laboratory scale and its effectiveness at large-scale production of bio-methane. The genome sequence information of non-cultivable biogas community members, metagenome sequencing including assembly and binning strategies will be highly valuable in determining the efficacy of an anaerobic digester.

A review of the safety of MRI in cochlear implant patients with retained magnets

The number of patients with cochlear implants (CIs) is increasing due to expanding indications, and improving CI services. Furthermore, as the use of imaging increases in clinical medicine, it is increasingly likely that patients with CIs will require a magnetic resonance imaging (MRI) examination during their lifetime. Therefore it is important that clinicians are aware of the safety aspects and manufacturer recommendations for CI patients with retained magnets. This article summarises guidelines from all major CI manufacturers and reviews the published literature on the safety of MRI in CI patients with magnets in situ. The most commonly reported complication of MRI in CI patients was pain. Other significant complications included magnet displacement, depolarisation, and polarity reversal. Artefacts caused by the CI remain an issue, but may be reduced by the use of specific sequences. Manufacturer recommendations should be followed to reduce the risk of complications, although complications may occur even when guidelines are followed. For this reason, the indication for imaging these patients should be reviewed, and patients should be appropriately counselled and consented.