The unintended consequences of artificial intelligence in paediatric radiology.

Over the past decade, there has been a dramatic rise in the interest relating to the application of artificial intelligence (AI) in radiology. Originally only 'narrow' AI tasks were possible; however, with increasing availability of data, teamed with ease of access to powerful computer processing capabilities, we are becoming more able to generate complex and nuanced prediction models and elaborate solutions for healthcare. Nevertheless, these AI models are not without their failings, and sometimes the intended use for these solutions may not lead to predictable impacts for patients, society or those working within the healthcare profession. In this article, we provide an overview of the latest opinions regarding AI ethics, bias, limitations, challenges and considerations that we should all contemplate in this exciting and expanding field, with a special attention to how this applies to the unique aspects of a paediatric population. By embracing AI technology and fostering a multidisciplinary approach, it is hoped that we can harness the power AI brings whilst minimising harm and ensuring a beneficial impact on radiology practice.

Analysis of the Trends of Methicillin-Resistant Staphylococcus aureus in Gauteng Public Hospitals from 2009 to 2018.

Most investigations into the distribution of methicillin resistant Staphylococcus aureus (MRSA) have focused exclusively on bloodborne infections within individual health care institutions for shorter time periods. This has limited the analysis of a community-spread pathogen to snapshots within the hospital domain. Therefore, in this study we determined the demographic and geographical patterns of MRSA infections and their fluctuation in 10 years within all public hospitals in Gauteng, South Africa. A retrospective analysis of S. aureus samples was done by deduplicating samples in two groups. The sample groups were placed into subsets with respect to demographic and geographical fields and compared across the studied period. Logistic regression was utilized to determine odds ratios for resistant infections in univariate and multivariable configurations. A total of 66,071 unique infectious events were identified from the 148,065 samples received over a 10-year period, out of which 14,356 were identified as bacteremia. MRSA bacteremia rates in Gauteng peaked in 2015 and have since decreased. Within Gauteng, metropolitan areas have the greatest burden of MRSA with children under 5 years of age and males being most affected. Medical wards have the highest S. aureus bacteremia rates, while intensive care units have the highest MRSA bacteremia rates. Patient age, admitting ward, and geographical district are the most important associated factors of resistance. MRSA acquisition rates have shown tremendous growth since 2009 but have since spiked and subsequently decreased. This may be due to the initiation of the National Guidelines on Antimicrobial Stewardship and Infectious Disease Surveillance. Further studies to determine the trajectory of infections are required to support these claims. IMPORTANCE S. aureus is the leading cause of a variety of devastating clinical conditions, including infective endocarditis, bacteremia, and pleuropulmonary infections. It is an important pathogen responsible for substantial morbidity and mortality. MRSA is a variant of interest originally responsible for difficult to treat hospital-acquired infections that has since achieved community spread throughout the world. Most investigations into the distribution of MRSA have focused exclusively on bloodborne infections within individual health care institutions for shorter periods. This has limited the analysis of a community-spread pathogen to snapshots within the hospital domain. This study sought to determine the demographic and geographical patterns of MRSA infections as well as how these have fluctuated over time within all public hospitals. This will also help in understanding the epidemiology and resistance trends of S. aureus, which will help clinicians to understand the clinical prospective and policy makers to design guidelines and strategies for treating such infections.

D-dimers in omicron versus delta: A retrospective analysis.

Background: Infection with SARS-CoV-2 has shown to cause an increase in D-dimers, which correlate with severity and prognosis for in-hospital mortality. The B.1.617.2 (delta) variant is known to cause a raised D-dimer level, with data on D-dimers in the B.1.1.529 (omicron) variant being scarce. Objectives: To determine the effect of age, gender and SARS-CoV-2 variant on the D-dimer in South Africans admitted to tertiary medical centres from May 2021 to December 2021. Method: The study was performed retrospectively on 16 010 adult patients with a SARS-CoV-2 infection. Age, gender, SARS-CoV-2 PCR and D-dimer levels on admission were collected from two national laboratories. Admissions from 01 May 2021 to 31 October 2021 were classified as B.1.617.2, whereas admissions from 01 November 2021 to 23 December 2021 were classified as B.1.1.529 infections. Results: Omicron infections had a median D-dimer level of 0.54 µg/mL (95% CI: 0.32, 1.08, p < 0.001). Multivariable regression analysis showed that infection with omicron had a 34.30% (95% CI: 28.97, 39.23) reduction in D-dimer values, compared with delta infections. Middle aged, aged and aged over 80 years had D-dimer results greater than the adult baseline (42.6%, 95% CI: 38.0, 47.3, 124.6%, 95% CI: 116.0, 133.7 and 216.1%, 95% CI: 199.5, 233.3). Males on average had a 7.1% (95% CI: 4.6, 9.6) lower D-dimer level than females. Conclusion: Infection with the B.1.1.529 variant, compared with B.1.617.2 variant, had significantly lower D-dimer levels, with age being a more significant predictor of D-dimer levels, than gender and SARS-CoV-2 variant of infection. Contribution: This study provides novel insight into the hypercoagulable impact of various SARS-CoV-2 variants, which can guide the management of patients.

The role of machine learning in HIV risk prediction.

Despite advances in reducing HIV-related mortality, persistently high HIV incidence rates are undermining global efforts to end the epidemic by 2030. The UNAIDS Fast-track targets as well as other preventative strategies, such as pre-exposure prophylaxis, have been identified as priority areas to reduce the ongoing transmission threatening to undermine recent progress. Accurate and granular risk prediction is critical for these campaigns but is often lacking in regions where the burden is highest. Owing to their ability to capture complex interactions between data, machine learning and artificial intelligence algorithms have proven effective at predicting the risk of HIV infection in both high resource and low resource settings. However, interpretability of these algorithms presents a challenge to the understanding and adoption of these algorithms. In this perspectives article, we provide an introduction to machine learning and discuss some of the important considerations when choosing the variables used in model development and when evaluating the performance of different machine learning algorithms, as well as the role emerging tools such as Shapely Additive Explanations may play in helping understand and decompose these models in the context of HIV. Finally, we discuss some of the potential public health and clinical use cases for such decomposed risk assessment models in directing testing and preventative interventions including pre-exposure prophylaxis, as well as highlight the potential integration synergies with algorithms that predict the risk of sexually transmitted infections and tuberculosis.

Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs.

Chest X-rays are a vital diagnostic tool in the workup of many patients. Similar to most medical imaging modalities, they are profoundly multi-modal and are capable of visualising a variety of combinations of conditions. There is an ever pressing need for greater quantities of labelled images to drive forward the development of diagnostic tools; however, this is in direct opposition to concerns regarding patient confidentiality which constrains access through permission requests and ethics approvals. Previous work has sought to address these concerns by creating class-specific generative adversarial networks (GANs) that synthesise images to augment training data. These approaches cannot be scaled as they introduce computational trade offs between model size and class number which places fixed limits on the quality that such generates can achieve. We address this concern by introducing latent class optimisation which enables efficient, multi-modal sampling from a GAN and with which we synthesise a large archive of labelled generates. We apply a Progressive Growing GAN (PGGAN) to the task of unsupervised X-ray synthesis and have radiologists evaluate the clinical realism of the resultant samples. We provide an in depth review of the properties of varying pathologies seen on generates as well as an overview of the extent of disease diversity captured by the model. We validate the application of the Fréchet Inception Distance (FID) to measure the quality of X-ray generates and find that they are similar to other high-resolution tasks. We quantify X-ray clinical realism by asking radiologists to distinguish between real and fake scans and find that generates are more likely to be classed as real than by chance, but there is still progress required to achieve true realism. We confirm these findings by evaluating synthetic classification model performance on real scans. We conclude by discussing the limitations of PGGAN generates and how to achieve controllable, realistic generates going forward. We release our source code, model weights, and an archive of labelled generates.