Search

Objective. Bariatric surgery effectively treats non-alcoholic fatty liver disease (NAFLD). The glutamate-serine-glycine (GSG) index has emerged as a non-invasive diagnostic marker for NAFLD, but its ability to monitor treatment response remains unclear. This study investigates the GSG index's ability to monitor NAFLD's response to bariatric surgery. Methodology. Ten NAFLD participants were studied at baseline and 6 months post-bariatric surgery. Blood samples were collected for serum biomarkers and metabolomic profiling. Hepatic steatosis [proton density fat fraction (PDFF)] and fibroinflammation (cT1) were quantified with multiparametric magnetic resonance imaging (mpMRI), and hepatic stiffness with magnetic resonance elastography (MRE). Amino acids and acylcarnitines were measured with mass spectrometry. Statistical analyses included paired Student’s t-test, Wilcoxon-signed rank test, and Pearson’s correlation. Results. Eight participants provided complete data. At baseline, all had hepatic steatosis (BMI 39.3 ± 5.6 kg/m2, PDFF ≥ 5%). Post-surgery reductions in PDFF (from 12.4 ± 6.7% to 6.2 ± 2.8%, p = 0.013) and cT1 (from 823.3 ± 85.4ms to 757.5 ± 41.6ms, p = 0.039) were significant, along with the GSG index (from 0.272 ± 0.03 to 0.157 ± 0.05, p = 0.001). Conclusion. The GSG index can potentially be developed as a marker for monitoring the response of patients with NAFLD to bariatric surgery.

Introduction: Tuberculosis (TB) remains endemic in Singapore. Singapore’s clinical practice guidelines for the management of tuberculosis were first published in 2016. Since then, there have been major new advances in the clinical management of TB, ranging from diagnostics to new drugs and treatment regimens. The National TB Programme convened a multidisciplinary panel to update guidelines for the clinical management of drug-susceptible TB infection and disease in Singapore, contextualising current evidence for local practice. Method: Following the ADAPTE framework, the panel systematically reviewed, scored and synthesised English-language national and international TB clinical guidelines published from 2016, adapting recommendations for a prioritised list of clinical decisions. For questions related to more recent advances, an additional primary literature review was conducted via a targeted search approach. A 2-round modified Delphi process was implemented to achieve consensus for each recommendation, with a final round of edits after consultation with external stakeholders. Results: Recommendations for 25 clinical questions spanning screening, diagnosis, selection of drug regimen, monitoring and follow-up of TB infection and disease were formulated. The availability of results from recent clinical trials led to the inclusion of shorter treatment regimens for TB infection and disease, as well as consensus positions on the role of newer technologies, such as computer-aided detection-artificial intelligence products for radiological screening of TB disease, next-generation sequencing for drug-susceptibility testing, and video observation of treatment. Conclusion: The panel updated recommendations on the management of drug-susceptible TB infection and disease in Singapore.

Objectives Telemedicine is firmly established in the healthcare landscape of many countries. Acute respiratory infections are the most common reason for telemedicine consultations. A throat examination is important for diagnosing bacterial pharyngitis, but this is challenging for doctors during a telemedicine consultation. A solution could be for patients to upload images of their throat to a web application. This study aimed to develop a deep learning model for the automated diagnosis of exudative pharyngitis. Thereafter, the model will be deployed online. Methods We used 343 throat images (139 with exudative pharyngitis and 204 without pharyngitis) in the study. ImageDataGenerator was used to augment the training data. The convolutional neural network models of MobileNetV3, ResNet50, and EfficientNetB0 were implemented to train the dataset, with hyperparameter tuning. Results All three models were trained successfully; with successive epochs, the loss and training loss decreased, and accuracy and training accuracy increased. The EfficientNetB0 model achieved the highest accuracy (95.5%), compared to MobileNetV3 (82.1%) and ResNet50 (88.1%). The EfficientNetB0 model also achieved high precision (1.00), recall (0.89) and F1-score (0.94). Conclusions We trained a deep learning model based on EfficientNetB0 that can diagnose exudative pharyngitis. Our model was able to achieve the highest accuracy, at 95.5%, out of all previous studies that used machine learning for the diagnosis of exudative pharyngitis. We have deployed the model on a web application that can be used to augment the doctor’s diagnosis of exudative pharyngitis.

Abstract Artificial intelligence (AI) has demonstrated the ability to extract insights from data, but the fairness of such data-driven insights remains a concern in high-stakes fields. Despite extensive developments, issues of AI fairness in clinical contexts have not been adequately addressed. A fair model is normally expected to perform equally across subgroups defined by sensitive variables (e.g., age, gender/sex, race/ethnicity, socio-economic status, etc.). Various fairness measurements have been developed to detect differences between subgroups as evidence of bias, and bias mitigation methods are designed to reduce the differences detected. This perspective of fairness, however, is misaligned with some key considerations in clinical contexts. The set of sensitive variables used in healthcare applications must be carefully examined for relevance and justified by clear clinical motivations. In addition, clinical AI fairness should closely investigate the ethical implications of fairness measurements (e.g., potential conflicts between group- and individual-level fairness) to select suitable and objective metrics. Generally defining AI fairness as “equality” is not necessarily reasonable in clinical settings, as differences may have clinical justifications and do not indicate biases. Instead, “equity” would be an appropriate objective of clinical AI fairness. Moreover, clinical feedback is essential to developing fair and well-performing AI models, and efforts should be made to actively involve clinicians in the process. The adaptation of AI fairness towards healthcare is not self-evident due to misalignments between technical developments and clinical considerations. Multidisciplinary collaboration between AI researchers, clinicians, and ethicists is necessary to bridge the gap and translate AI fairness into real-life benefits.

Summary: This paper describes the development of a deep learning model for prediction of hip fractures on pelvic radiographs (X-rays). Developed using over 40,000 pelvic radiographs from a single institution, the model demonstrated high sensitivity and specificity when applied to a test set of emergency department radiographs. This study approximates the real-world application of a deep learning fracture detection model by including radiographs with sub-optimal image quality, other non-hip fractures, and metallic implants, which were excluded from prior published work. The study also explores the effect of ethnicity on model performance, as well as the accuracy of visualization algorithm for fracture localization.

Background: Traditional methods of research registry development for rare conditions such as peritoneal surface malignancies (PSM) are often hindered by poor patient accrual and need for significant manpower resources. We develop a novel pipeline using natural language processing (NLP) to accelerate this process and demonstrate its real-world application in the identification of PSM patients, as well as characterisation of referral patterns in this cohort. Materials and methods: A training set comprising 100 radiological reports of abdomen and pelvis computed tomography scans was used to develop a rule-based NLP system able to classify reports based on the presence or absence of PSM. The algorithm was applied to a test set of 10,261 reports to identify all patients with PSM for registry creation. The registry was subsequently linked to electronic medical records, and the referral patterns of patients evaluated. Results: The algorithm identified 251 reports as positive for PSM from a total of 10,261 reports, of which 239 were concordant with manual review. Performance was excellent with a specificity of 90%, positive predictive value of 95%, and accuracy of 96%. From these, 228 unique patients were identified for registry inclusion after corroboration with pathological findings. Only 27.6% of patients were found to have been referred to and reviewed by PSM specialist surgeons. For those without a PSM specialist consult, 39.4% were managed by medical oncology, 11.5% by colorectal surgery, 7.3% by gastroenterology, 5.4% by internal medicine, and 29.1% by various other miscellaneous medical and surgical subspecialties. Conclusion: NLP is a useful tool in automated pipelines that can greatly contribute to registry creation, as well as research and quality improvement efforts.

Background. Bariatric surgery is the most effective treatment for morbid obesity and reduces the severity of nonalcoholic fatty liver disease (NAFLD) in the long term. Less is known about the effects of bariatric surgery on liver fat, inflammation, and fibrosis during the early stages following bariatric surgery. Aims. This exploratory study utilises advanced imaging methods to investigate NAFLD and fibrosis changes during the early metabolic transitional period following bariatric surgery. Methods. Nine participants with morbid obesity underwent sleeve gastrectomy. Multiparametric MRI (mpMRI) and magnetic resonance elastography (MRE) were performed at baseline, during the immediate (1 month), and late (6 months) postsurgery period. Liver fat was measured using proton density fat fraction (PDFF), disease activity using iron-correct T1 (cT1), and liver stiffness using MRE. Repeated measured ANOVA was used to assess longitudinal changes and Dunnett’s method for multiple comparisons. Results. All participants (Age 45.1±9.0 years, BMI 39.7±5.3 kg/m2) had elevated hepatic steatosis at baseline (PDFF >5%). In the immediate postsurgery period, PDFF decreased significantly from 14.1±7.4% to 8.9±4.4% (p=0.016) and cT1 from 826.9±80.6 ms to 768.4±50.9 ms (p=0.047). These improvements continued to the later postsurgery period. Bariatric surgery did not reduce liver stiffness measurements. Conclusion. Our findings support using MRI as a noninvasive tool to monitor NAFLD in patient with morbid obesity during the early stages following bariatric surgery.

Background Survival Radiology (SR) is a flagship annual full-day in-person radiology workshop targeted at final year medical students in Singapore to prepare them for internship. Previous in-person editions have consistently received positive reviews from 2014 to 2019. However, the COVID-19 pandemic necessitated a rapid online pivot for its sixth edition in 2020. Objectives This study aims to (a) identify key success factors of a traditional in-person medical student radiology workshop, (b) describe the rapid online pivot in 2020 and (c) to identify key success factors for online educational initiatives. Methods Post-workshop survey responses of SR from 2014 to 2020 were evaluated. Likert-scale data were quantitatively analysed, while free-text responses were qualitatively analysed. Results A total of 1248 post-workshop surveys (2014–2020 workshops) and 266 free-text responses (2020 workshop) were received from 2640 participants over the years. Progressive changes that sustained or improved participant feedback for in-person SR workshops included adoption of a case-based approach, utility of ‘live’ audience response systems and incorporation of quizzes with a favourable overall feedback rating of 4.42–4.89 from 2014 to 2019. The webinar version of SR in 2020 became the best-rated edition since inception with a rating of 4.9. Qualitative analysis of feedback from SR 2020 showed that the participants preferred the webinar model, online modes of engagement and interactivity. Conclusion Our experience shows that it is not only possible to successfully pivot online for such workshops, but that blended educational formats utilising online engagements supplemented by in-person activities will be well-received by ‘Generation Z’ learners even after the COVID-19 pandemic.

Introduction Urgent radiological studies obtained during on-call hours are often preliminarily read by on-call residents before consultant radiologists finalise the reports at a later time. Such provisional radiology reports provide important information to guide initial patient management. This study aims to determine discrepancy rates between provisional reports and final interpretations, and to assess the clinical significance of such discrepancies. Methods This retrospective quality assurance project reviewed a total of 1218 cross-sectional imaging studies of the body (thorax, abdomen and pelvis) done between July 2015 and May 2016 during on-call hours. The studies included 1201 Computed tomography (CT) scans and 17 Magnetic Resonance Imaging (MRI) scans. Studies with incomplete or unavailable reports were excluded. Conclusions of both the provisional and final reports of each study were reviewed for concordance, with reference to the full report if needed. Discrepancies were graded according to the ACR 2016 RADPEER scoring system. Results There were 1210 studies with complete reports. Discrepant reports were noted in 183 (15.1%) studies. Of these, 89 (7.3%) were assessed to be clinically significant and the majority of these (55) were due to interpretations which should be made most of the time. CT of the abdomen and pelvis were the most prone to discrepant reports, accounting for 148 cases (80.9%). Conclusion The majority of preliminary reports for on-call body scans were concordant with final interpretations. The discrepancy rates for provisional body scan reports provided by residents while on call were comparable to those previously reported in literature.

Objective: To evaluate the efficacy of multiparametric magnetic resonance imaging (mp-MRI) using Prostate Imaging Reporting and Data System version 2.0 (PI-RADSv2) definitions in detecting organ-confined prostate cancer. Methods: All patients who underwent radical prostatectomy between January 1, 2014 and December 30, 2014 were identified. All underwent mp-MRI within 180 days before surgery. Those with prior pelvic irradiation or androgen deprivation therapy were excluded. Fully embedded, whole-mount histopathology was centrally reviewed and correlated with imaging for tumour location, Gleason score (GS) and stage. Results: There were 39 patients included, of which 35 (90%) had mp-MRI done post-biopsy. A total of 93 cancer foci were identified on whole-mount pathology, of which mp-MRI detected 63 (68%). Of those detected by mp-MRI, 14 were PI-RADS 3 (n = 6 for GS 6, n = 8 for GS 7, no GS ≥ 8) and 49 were PI-RADS 4–5 (n = 7 for GS 6, n = 33 for GS 7, and n = 9 for GS ≥ 8). There were 30 (32%) cancer foci missed by mp-MRI (n = 15 for GS 6, n = 13 for GS 7 and n = 2 for GS ≥ 8). A lesion classified as PI-RADS 4–5 predicted a higher grade cancer on pathology as compared to PI-RADS 3 (for GS 7 lesions, odds ratio [OR] = 3.53, 95% CI: 0.93–13.45, p = 0.064). The mp-MRI size detection limit was 20 mm2 and 100 mm2 for 50% and 75% probability of cancer, respectively. In associating with radiological and pathologic stage, the weighted Kappa value was 0.69 (p

Singapore is a small tropical island city-state with limited natural resources that has achieved remarkable healthcare outcomes through effective long-term planning and judicious investment in human resources and technology. A full-range of medical imaging services is available in the country, with integrated care delivered to patients through a network of both government and private hospitals. Training in diagnostic radiology, interventional radiology, nuclear medicine and diagnostic radiography continue to evolve in Singapore, with an aim to further increase the range of subspecialty medical imaging services available and address projected challenges for the healthcare system in the future, such as an aging population. Continued government investment in technology and biomedical imaging is expected to further expand the scope and depth of medical imaging services in the future.

Abdominal pain is a symptom that is commonly encountered in clinical practice. Evaluation of abdominal pain involves the exclusion of a myriad of possible diagnosis. This case illustrates an uncommon cause of abdominal pain and vomiting in a 55-year-old female with diagnostic radiological features.

Abstract We aimed to test the sensitivity of naso-oropharyngeal saliva and self-administered nasal (SN) swab compared to nasopharyngeal (NP) swab for COVID-19 testing in a large cohort of migrant workers in Singapore. We also tested the utility of next-generation sequencing (NGS) for diagnosis of COVID-19. Saliva, NP and SN swabs were collected from subjects who presented with acute respiratory infection, their asymptomatic roommates, and prior confirmed cases who were undergoing isolation at a community care facility in June 2020. All samples were tested using RT-PCR. SARS-CoV-2 amplicon-based NGS with phylogenetic analysis was done for 30 samples. We recruited 200 subjects, of which 91 and 46 were tested twice and thrice respectively. In total, 62.0%, 44.5%, and 37.7% of saliva, NP and SN samples were positive. Cycle threshold (Ct) values were lower during the earlier period of infection across all sample types. The percentage of test-positive saliva was higher than NP and SN swabs. We found a strong correlation between viral genome coverage by NGS and Ct values for SARS-CoV-2. Phylogenetic analyses revealed Clade O and lineage B.6 known to be circulating in Singapore. We found saliva to be a sensitive and viable sample for COVID-19 diagnosis.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.