Time dedicated to physical activity among medical residents: are there differences based on gender or specialty type?

INTRODUCTION

Physical activity (PA) is associated with positive health outcomes such as prevention of chronic diseases, psychological well-being and improved work performance. Medical residents are subjected to sleep deprivation, extended work schedule and high burnout prevalence. These conditions may lead to the neglect of personal health and the restriction of time dedicated to PA. The objective of the present study was to analyze the time dedicated to PA of medical residents, comparing women vs men residents and surgical vs clinical residents.

METHODS

It is a cross-sectional study performed in a Spanish third-level university hospital. All medical residents from our institution were invited to voluntarily participate in the study answering a web-based questionnaire on June 2022. Data regarding demographics, residency and PA practice was recorded.

RESULTS

The response rate was 20.73% (114/550). The 32.5% of the residents considered themselves to be physically inactive and mean time dedicated to PA in a regular week was 3.62 ± 2.22 h. Men residents dedicated more time to PA than women residents (4.23 ± 2.42 h vs 3.14 ± 1.95 h, p = 0.012) and surgical residents dedicated more time than clinical residents (4.33 ± 2.36 h vs 3.23 ± 2.05 h, p = 0.01).

CONCLUSIONS

One third of the medical residents consider themself physically inactive. Women and clinical residents practice PA less time than men and surgical residents. Efforts should be made to encourage PA among residents, especially in women and non-surgeons.

Addressing healthcare disparities in homeless neurosurgical patients: A comprehensive literature review on strategies for equitable care and improved outcomes

Background

Homelessness is a growing concern in the US, with 3.5 million people experiencing it annually and 600,000 on any given night. Homeless individuals face increased vulnerability to 30-day hospital readmissions and higher mortality rates, straining the healthcare system and exacerbating existing disparities. This study aims to inform neurosurgeons on evidence-based strategies to reduce readmission and mortality rates among homeless patients by reviewing the literature on the impact of medical respite on 30-day readmission rates. The study aims to gauge the efficacy of medical respite in reducing hospital readmissions and improving health outcomes for homeless individuals.

Methods

A comprehensive literature search was conducted across PubMed, Embase/Medline, and Cochrane databases, as well as consulting the National Institute for Medical Respite Care and the Department of Health Care Access and Information. Ten articles were chosen from an initial 296 to investigate the impact of respite programs on readmission rates among homeless patients.

Results

Homeless patients experience high readmission rates due to various factors. Interventions such as respite programs and a comprehensive approach to healthcare can lower these rates. Collaboration between hospitals and medical respites has proven particularly effective.

Conclusion

Inadequate healthcare for homeless individuals leads to increased readmissions, longer hospital stays, and higher costs. Medical respites are a viable solution, but limited resources hamper their effectiveness. Therefore, it is crucial to facilitate cooperation between hospitals, respites, and other entities. Future research should focus on disparity in neurosurgical procedures and explore alternative services. An interdisciplinary approach is key to addressing healthcare inequalities.

Leukocyte differential gene expression prognostic value for high versus low seizure frequency in temporal lobe epilepsy

BACKGROUND

This study was performed to test the hypothesis that systemic leukocyte gene expression has prognostic value differentiating low from high seizure frequency refractory temporal lobe epilepsy (TLE).

METHODS

A consecutive series of patients with refractory temporal lobe epilepsy was studied. Based on a median baseline seizure frequency of 2.0 seizures per month, low versus high seizure frequency was defined as ≤ 2 seizures/month and > 2 seizures/month, respectively. Systemic leukocyte gene expression was analyzed for prognostic value for TLE seizure frequency. All differentially expressed genes were analyzed, with Ingenuity® Pathway Analysis (IPA®) and Reactome, to identify leukocyte gene expression and biological pathways with prognostic value for seizure frequency.

RESULTS

There were ten males and six females with a mean age of 39.4 years (range: 16 to 62 years, standard error of mean: 3.6 years). There were five patients in the high and eleven patients in the low seizure frequency cohorts, respectively. Based on a threshold of twofold change (p < 0.001, FC > 2.0, FDR < 0.05) and expression within at least two pathways from both Reactome and Ingenuity® Pathway Analysis (IPA®), 13 differentially expressed leukocyte genes were identified which were all over-expressed in the low when compared to the high seizure frequency groups, including NCF2, HMOX1, RHOB, FCGR2A, PRKCD, RAC2, TLR1, CHP1, TNFRSF1A, IFNGR1, LYN, MYD88, and CASP1. Similar analysis identified four differentially expressed genes which were all over-expressed in the high when compared to the low seizure frequency groups, including AK1, F2R, GNB5, and TYMS.

CONCLUSIONS

Low and high seizure frequency TLE are predicted by the respective upregulation and downregulation of specific leukocyte genes involved in canonical pathways of neuroinflammation, oxidative stress and lipid peroxidation, GABA (γ-aminobutyric acid) inhibition, and AMPA and NMDA receptor signaling. Furthermore, high seizure frequency-TLE is distinguished prognostically from low seizure frequency-TLE by differentially increased specific leukocyte gene expression involved in GABA inhibition and NMDA receptor signaling. High and low seizure frequency patients appear to represent two mechanistically different forms of temporal lobe epilepsy based on leukocyte gene expression.

Emotional intelligence in neurosurgery: Mitigating burnout and enhancing performance

Background

This study underscores the high burnout rates among physicians, particularly surgical residents, attributing it to the demanding health-care ecosystem. It highlights the negative impacts of burnout, such as medical errors and increased health-care costs, while exploring the potential mitigating role of emotional intelligence (EI) and mindfulness. The research aimed to analyze the existing literature on EI in neurosurgery, focusing on its relationship with physician burnout and its potential role in healthcare leadership and residency training programs.

Methods

A comprehensive literature review was conducted using multiple databases, including PubMed, OVID Embase, and OVID Medline, using the keywords "Emotional Intelligence" and "neurosurgery." The search duration spanned from each database's inception to June 2023.

Results

The review highlighted various studies emphasizing the importance of integrating EI and mindfulness training into medical education and leadership, suggesting that a balance between technical competencies and interpersonal skills are critical. It identified personal integrity, effective communication, professional ethics, pursuit of excellence, relationship building, and critical thinking as key competencies for health-care leadership.

Conclusion

EI and a growth mindset play a critical role in managing burnout, enhancing job satisfaction and performance, and promoting effective healthcare leadership. The review, however, acknowledges certain limitations such as small sample sizes, single-institution experiences, potential biases, and inconsistencies in burnout parameters and EI measurement tools. Despite these, it points toward potential areas for future investigation and highlights the importance of standardized EI measurement tools and robust quantitative assessment methods.

Accuracy of Artificial Intelligence in Estimating Best-Corrected Visual Acuity From Fundus Photographs in Eyes With Diabetic Macular Edema

Importance

Best-corrected visual acuity (BCVA) is a measure used to manage diabetic macular edema (DME), sometimes suggesting development of DME or consideration of initiating, repeating, withholding, or resuming treatment with anti-vascular endothelial growth factor. Using artificial intelligence (AI) to estimate BCVA from fundus images could help clinicians manage DME by reducing the personnel needed for refraction, the time presently required for assessing BCVA, or even the number of office visits if imaged remotely.

Objective

To evaluate the potential application of AI techniques for estimating BCVA from fundus photographs with and without ancillary information.

Design, Setting, and Participants

Deidentified color fundus images taken after dilation were used post hoc to train AI systems to perform regression from image to BCVA and to evaluate resultant estimation errors. Participants were patients enrolled in the VISTA randomized clinical trial through 148 weeks wherein the study eye was treated with aflibercept or laser. The data from study participants included macular images, clinical information, and BCVA scores by trained examiners following protocol refraction and VA measurement on Early Treatment Diabetic Retinopathy Study (ETDRS) charts.

Main Outcomes

Primary outcome was regression evaluated by mean absolute error (MAE); the secondary outcome included percentage of predictions within 10 letters, computed over the entire cohort as well as over subsets categorized by baseline BCVA, determined from baseline through the 148-week visit.

Results

Analysis included 7185 macular color fundus images of the study and fellow eyes from 459 participants. Overall, the mean (SD) age was 62.2 (9.8) years, and 250 (54.5%) were male. The baseline BCVA score for the study eyes ranged from 73 to 24 letters (approximate Snellen equivalent 20/40 to 20/320). Using ResNet50 architecture, the MAE for the testing set (n = 641 images) was 9.66 (95% CI, 9.05-10.28); 33% of the values (95% CI, 30%-37%) were within 0 to 5 letters and 28% (95% CI, 25%-32%) within 6 to 10 letters. For BCVA of 100 letters or less but more than 80 letters (20/10 to 20/25, n = 161) and 80 letters or less but more than 55 letters (20/32 to 20/80, n = 309), the MAE was 8.84 letters (95% CI, 7.88-9.81) and 7.91 letters (95% CI, 7.28-8.53), respectively.

Conclusions and Relevance

This investigation suggests AI can estimate BCVA directly from fundus photographs in patients with DME, without refraction or subjective visual acuity measurements, often within 1 to 2 lines on an ETDRS chart, supporting this AI concept if additional improvements in estimates can be achieved.

Better Social-emotional Behavior in Young Nepali Children is Associated with Household Wealth, Child Age, and Family Participation in a Community Development Intervention

Background Mental health and behavior problems are under-recognized in low- and middleincome countries, especially in young children. Early identification of these problems could encourage governments to address the shortages of child mental health professionals and promote early intervention programs to help children achieve their full developmental potential. Objective Describe the social-emotional development of young rural Nepali children; explore risk factors for poor development. Method The study was embedded in a longitudinal intervention trial comparing control households with those who received training in family nutrition+livestock management (Partial Package) or family nutrition+livestock management+community mobilization (Full Package). At midline, enumerators completed a 145-item household questionnaire, child anthropometry, and Administered the Ages and Stages Questionnaire-Social-Emotional (ASQ-SE) to all enrolled children age 33-47 months (n=310). Bivariate and regression analyses examined the relationship of child and household risk factors to administered the Ages and Stages QuestionnaireSocial-Emotional scores. Result Administered the Ages and Stages Questionnaire-Social-Emotional scores were below age cutoffs in 24% of children, suggesting worse social-emotional development. In bivariate analyses and the adjusted linear regression model, older child age, greater household wealth, and Full Package Intervention status were all associated with better social-emotional development scores. Partial Package Intervention status was associated with worse scores. Conclusion The Administered the Ages and Stages Questionnaire-Social-Emotional is a potential tool to assess child social-emotional development in the context of household and community level interventions. Further work is necessary to validate the administered the Ages and Stages Questionnaire-Social-Emotional and similar tools in Nepal, and to better understand the prevalence of challenges to optimal socialemotional development in young children in order to use this information to design and monitor needed interventions.

Periplasmic stress contributes to a tradeoff between protein secretion and cell growth in E. Coli Nissile

Maximizing protein secretion is an important target in the design of engineered living systems. In this paper, we characterize a tradeoff between cell growth and per cell protein secretion in the curli biofilm secretion system of E Coli Nissile 1917. Initial characterization using 24-hour continuous growth and protein production monitoring confirms decreased growth rates at high induction leading to a local maximum in total protein production at intermediate induction. Propidium iodide staining at the endpoint indicates that cellular death is a dominant cause of growth reduction. Assaying variants with combinatorial constructs of inner and outer membrane secretion tags, we find that diminished growth at high production is specific to secretory variants associated with accumulation of protein containing the outer membrane transport tag in the periplasmic space. RNA sequencing experiments indicate upregulation of known periplasmic stress response genes in the highly secreting variant, further implicating periplasmic stress in the growth-secretion tradeoff. Overall, these results motivate additional strategies for optimizing total protein production and longevity of secretory engineered living systems.

Spinal cord stimulation for genitofemoral neuropathy: A case report and review of the literature

Background:

Chronic testicular pain due to genitofemoral neuropathy often becomes refractory to conservative medical therapy. Neurostimulation is a potentially useful treatment option, should the neuropathic pain remain refractory to more invasive procedures such as orchiectomy. We provide a case report of spinal cord stimulation (SCS) for successful treatment of genitofemoral neuropathy and have also reviewed the literature to find similar cases which required a similar treatment paradigm.

Case Description:

A 42-year-old male underwent SCS for refractory testicular and groin pain. SCS through a four-column, 2 × 8 contact neurostimulator paddle lead, was implanted in the mid-thoracic-9 (T9) vertebral level, providing > 50% testicular pain relief with a decrease in visual analog scale scores from 8–10/10 to 3–4/10. The patient required one adjustment to the stimulation parameters at the time of the 6 weeks follow-up visit due to over-stimulation. He then continued to experience >50% resolution in pain 9 months later. A review of the literature yielded only two similar cases that successfully utilized SCS for treatment of chronic testicular pain.

Conclusion:

SCS should be considered as a possible treatment option for patients with chronic testicular pain localized to the genitofemoral nerve distribution.

Assessment of germinal matrix hemorrhage on head ultrasound with deep learning algorithms

BACKGROUND

Germinal matrix hemorrhage-intraventricular hemorrhage is among the most common intracranial complications in premature infants. Early detection is important to guide clinical management for improved patient prognosis.

OBJECTIVE

The purpose of this study was to assess whether a convolutional neural network (CNN) can be trained via transfer learning to accurately diagnose germinal matrix hemorrhage on head ultrasound.

MATERIALS AND METHODS

Over a 10-year period, 400 head ultrasounds performed in patients ages 6 months or younger were reviewed. Key sagittal images at the level of the caudothalamic groove were obtained from 200 patients with germinal matrix hemorrhage and 200 patients without hemorrhage; all images were reviewed by a board-certified pediatric radiologist. One hundred cases were randomly allocated from the total for validation and an additional 100 for testing of a CNN binary classifier. Transfer learning and data augmentation were used to train the model.

RESULTS

The median age of patients was 0 weeks old with a median gestational age of 30 weeks. The final trained CNN model had a receiver operating characteristic area under the curve of 0.92 on the validation set and accuracy of 0.875 on the test set, with 95% confidence intervals of [0.86, 0.98] and [0.81, 0.94], respectively.

CONCLUSION

A CNN trained on a small set of images with data augmentation can detect germinal matrix hemorrhage on head ultrasounds with strong accuracy.

TARA: Training and Representation Alteration for AI Fairness and Domain Generalization

We propose a novel method for enforcing AI fairness with respect to protected or sensitive factors. This method uses a dual strategy performing training and representation alteration (TARA) for the mitigation of prominent causes of AI bias. It includes the use of representation learning alteration via adversarial independence to suppress the bias-inducing dependence of the data representation from protected factors and training set alteration via intelligent augmentation to address bias-causing data imbalance by using generative models that allow the fine control of sensitive factors related to underrepresented populations via domain adaptation and latent space manipulation. When testing our methods on image analytics, experiments demonstrate that TARA significantly or fully debiases baseline models while outperforming competing debiasing methods that have the same amount of information-for example, with (% overall accuracy, % accuracy gap) = (78.8, 0.5) versus the baseline method's score of (71.8, 10.5) for Eye-PACS, and (73.7, 11.8) versus (69.1, 21.7) for CelebA. Furthermore, recognizing certain limitations in current metrics used for assessing debiasing performance, we propose novel conjunctive debiasing metrics. Our experiments also demonstrate the ability of these novel metrics in assessing the Pareto efficiency of the proposed methods.

Transrectal ultrasound-guided prostate needle biopsy remains a safe method in confirming a prostate cancer diagnosis: a multicentre Australian analysis of infection rates

PURPOSE

Worldwide, transrectal ultrasound-guided prostate needle remains the most common method of diagnosing prostate cancer. Due to high infective complications reported, some have suggested it is now time to abandon this technique in preference of a trans-perineal approach. The aim of this study was to report on the infection rates following transrectal ultrasound-guided prostate needle biopsy in multiple Australian centres.

MATERIALS AND METHODS

Data were collected from seven Australian centres across four states and territories that undertake transrectal ultrasound-guided prostate needle biopsies for the diagnosis of prostate cancer, including major metropolitan and regional centres. In four centres, the data were collected prospectively. Rates of readmissions due to infection, urosepsis resulting in intensive care admission and mortality were recorded.

RESULTS

12,240 prostate biopsies were performed in seven Australian centres between July 1998 and December 2020. There were 105 readmissions for infective complications with rates between centres ranging from 0.19 to 2.60% and an overall rate of 0.86%. Admission to intensive care with sepsis ranged from 0 to 0.23% and overall 0.03%. There was no mortality in the 12,240 cases.

CONCLUSION

Infective complications following transrectal ultrasound-guided prostate needle biopsies are very low, occurring in less than 1% of 12,240 biopsies. Though this study included a combination of both prospective and retrospective data and did not offer a comparison with a trans-perineal approach, TRUS prostate biopsy is a safe means of obtaining a prostate cancer diagnosis. Further prospective studies directly comparing the techniques are required prior to abandoning TRUS based upon infectious complications.

18F-Sodium fluoride positron emission tomography, aortic disease activity and ischaemic stroke risk

Background

Arterial 18F-sodium fluoride (18F-NaF) activity on positron emission tomography (PET) is a marker of active microcalcification and atherosclerosis. Coronary 18F-NaF activity (CMA) predicts coronary artery disease progression and subsequent myocardial infarction.

Objective

To investigate whether aortic 18F-NaF activity (AMA) predicts thoracic aortic atherosclerotic disease progression and subsequent ischaemic stroke or myocardial infarction in patients with established cardiovascular disease.

Methods

In a post-hoc observational cohort study, we evaluated AMA and CMA in patients with stable coronary artery disease (n=239) or aortic stenosis (n=158) who had underwent thoracic 18F-NaF PET and computed tomography (CT). We assessed the associations between AMA or CMA and progression of calcified atherosclerotic plaque in both thoracic aortic and coronary territories on follow up CT, as well as subsequent ischaemic stroke or myocardial infarction.

Results

In 141 and 231 patients with repeat aortic and coronary CT imaging respectively at 12.7±2.7 months, AMA correlated with log progression of thoracic aortic calcium scores (r=0.21, p=0.011), volume (r=0.29, p&lt;0.01) and mass (r=0.29, P&lt;0.01) as well as log coronary calcium score progression (r=0.21, p=0.03). CMA correlated with log coronary (r=0.42, p&lt;0.01), but not log aortic (p&gt;0.80) calcium score progression. In 397 patients, 16 had an ischaemic stroke and 25 had a myocardial infarction after 4.7±1.6 years. After adjusting for clinical risk factors, CMA and calcium scoring, AMA was associated with stroke (hazard ratio, 1.71 [95% confidence interval 1.00–2.90], p=0.048]). AMA was superior to clinical risk and calcium scores in identifying patients with stroke (c-statistic 0.76 versus 0.58 versus 0.63 respectively, p&lt;0.05). Survival analysis demonstrated that AMA was associated with ischaemic stroke (p&lt;0.001) but not myocardial infarction (p=0.45), whereas CMA was associated with myocardial infarction (p&lt;0.001) but not stroke (p=0.39).

Conclusions

In patients with established cardiovascular disease, AMA is associated with progression of aortic atherosclerosis and future ischaemic stroke. Arterial 18F-NaF identifies localised areas of atherosclerotic disease activity that relate to regional atherothrombotic events.

Funding Acknowledgement

Type of funding sources: Other. Main funding source(s): British Heart Foundation AMA, disease progression and outcomesVariables associated with stroke

Sex and age differences in patients with acute coronary syndrome and non-obstructive coronary arteries: presentation and outcome

Aims

A substantial number of patients present with acute coronary syndrome (ACS) and non-obstructive coronary arteries. Sex and age differences in these patients are not well understood. This study aims to evaluate the impact of sex and age on clinical presentation and outcome in patients with ACS and non-obstructive coronary arteries, with either an ischaemic or non-ischaemic cause.

Methods and results

Consecutive patients with an ACS and non-obstructive coronary arteries (n=719) from a single tertiary centre underwent comprehensive cardiovascular magnetic resonance (CMR) imaging with late gadolinium enhancement (LGE). The primary endpoint was all-cause mortality. CMR was performed at a median time of 30 days after presentation and identified a diagnosis in 74% of patients. Patients with an ischaemic or non-ischaemic aetiology (n=529) on CMR were followed prospectively. All-cause mortality was 11% over a median follow up of 4.9 years, with no significant difference between sexes (11% versus 11% p=0.732). Women were more likely to have an ischaemic aetiology on CMR (40% v 31%, p=0.037). Age group (HR 1.48, p=0.002), log peak troponin (HR 0.78, p=0.033) and LVEF (HR 0.98, p=0.032) were independent predictors of mortality. Men aged &gt;60 years with a non-ischaemic aetiology on their CMR were at higher risk of death than women &gt;60 years (p=0.003).

Conclusions

There is no difference in all-cause mortality between sexes in patients presenting with ACS and non-obstructive coronary arteries but increasing age is an important predictor of mortality in both sexes.

Funding Acknowledgement

Type of funding sources: None. Sex differences in CMR diagnosisSex, age and mortality

Sex and age differences in patients with a working diagnosis of myocardial infarction with non-obstructive coronary arteries (MINOCA): presentation and outcome

Funding Acknowledgements

Type of funding sources: Private grant(s) and/or Sponsorship. Main funding source(s): Rosetrees Trust James Tudor Foundation

Background Myocardial infarction with non-obstructive coronary arteries (MINOCA) is an increasingly recognised working diagnosis. Sex and age differences in MINOCA are not well understood.

Purpose  This study aims to evaluate the impact of sex and age in patients with MINOCA due to ischaemic and non-ischaemic causes on clinical presentation and outcome.

Methods and Results Consecutive patients with a working diagnosis of MINOCA (n = 719) from a single tertiary centre who underwent comprehensive cardiovascular magnetic resonance (CMR) imaging with late gadolinium enhancement (LGE) were followed prospectively. The primary endpoint was all-cause mortality.  CMR was performed at a median time of 30 days after presentation and identified a diagnosis in 74% of patients. Men were more likely to have a non-ischaemic cause on CMR (55% v. 41%, p &lt; 0.001) and less likely to have a normal/non-specific scan (21% v. 32%, p = 0.001, figure 1).  All-cause mortality was 9.5% over a median follow up of 4.9 years, with no significant difference between sexes (8.7% versus 10.1% p = 0.456).  Age group (HR 1.61, p &lt; 0.001) and LVEF (HR 0.98, p = 0.020) were independent predictors of mortality. Men aged &gt;60 years with a non-ischaemic aetiology on their CMR were at higher risk of death than women with non-ischaemic causes &gt;60 years (p = 0.003, figure 2).

Conclusions There is no difference in all-cause mortality between sexes in MINOCA but increasing age is the most important predictor of mortality in both sexes.

Low-Shot Deep Learning of Diabetic Retinopathy With Potential Applications to Address Artificial Intelligence Bias in Retinal Diagnostics and Rare Ophthalmic Diseases

Importance

Recent studies have demonstrated the successful application of artificial intelligence (AI) for automated retinal disease diagnostics but have not addressed a fundamental challenge for deep learning systems: the current need for large, criterion standard-annotated retinal data sets for training. Low-shot learning algorithms, aiming to learn from a relatively low number of training data, may be beneficial for clinical situations involving rare retinal diseases or when addressing potential bias resulting from data that may not adequately represent certain groups for training, such as individuals older than 85 years.

Objective

To evaluate whether low-shot deep learning methods are beneficial when using small training data sets for automated retinal diagnostics.

Design, Setting, and Participants

This cross-sectional study, conducted from July 1, 2019, to June 21, 2020, compared different diabetic retinopathy classification algorithms, traditional and low-shot, for 2-class designations (diabetic retinopathy warranting referral vs not warranting referral). The public domain EyePACS data set was used, which originally included 88 692 fundi from 44 346 individuals. Statistical analysis was performed from February 1 to June 21, 2020.

Main Outcomes and Measures

The performance (95% CIs) of the various AI algorithms was measured via receiver operating curves and their area under the curve (AUC), precision recall curves, accuracy, and F1 score, evaluated for different training data sizes, ranging from 5120 to 10 samples per class.

Results

Deep learning algorithms, when trained with sufficiently large data sets (5120 samples per class), yielded comparable performance, with an AUC of 0.8330 (95% CI, 0.8140-0.8520) for a traditional approach (eg, fined-tuned ResNet), compared with low-shot methods (AUC, 0.8348 [95% CI, 0.8159-0.8537]) (using self-supervised Deep InfoMax [our method denoted as DIM]). However, when far fewer training images were available (n = 160), the traditional deep learning approach had an AUC decreasing to 0.6585 (95% CI, 0.6332-0.6838) and was outperformed by a low-shot method using self-supervision with an AUC of 0.7467 (95% CI, 0.7239-0.7695). At very low shots (n = 10), the traditional approach had performance close to chance, with an AUC of 0.5178 (95% CI, 0.4909-0.5447) compared with the best low-shot method (AUC, 0.5778 [95% CI, 0.5512-0.6044]).

Conclusions and Relevance

These findings suggest the potential benefits of using low-shot methods for AI retinal diagnostics when a limited number of annotated training retinal images are available (eg, with rare ophthalmic diseases or when addressing potential AI bias).

Addressing Artificial Intelligence Bias in Retinal Diagnostics

Purpose

This study evaluated generative methods to potentially mitigate artificial intelligence (AI) bias when diagnosing diabetic retinopathy (DR) resulting from training data imbalance or domain generalization, which occurs when deep learning systems (DLSs) face concepts at test/inference time they were not initially trained on.

Methods

The public domain Kaggle EyePACS dataset (88,692 fundi and 44,346 individuals, originally diverse for ethnicity) was modified by adding clinician-annotated labels and constructing an artificial scenario of data imbalance and domain generalization by disallowing training (but not testing) exemplars for images of retinas with DR warranting referral (DR-referable) from darker-skin individuals, who presumably have greater concentration of melanin within uveal melanocytes, on average, contributing to retinal image pigmentation. A traditional/baseline diagnostic DLS was compared against new DLSs that would use training data augmented via generative models for debiasing.

Results

Accuracy (95% confidence intervals [CIs]) of the baseline diagnostics DLS for fundus images of lighter-skin individuals was 73.0% (66.9% to 79.2%) versus darker-skin of 60.5% (53.5% to 67.3%), demonstrating bias/disparity (delta = 12.5%; Welch t-test t = 2.670, P = 0.008) in AI performance across protected subpopulations. Using novel generative methods for addressing missing subpopulation training data (DR-referable darker-skin) achieved instead accuracy, for lighter-skin, of 72.0% (65.8% to 78.2%), and for darker-skin, of 71.5% (65.2% to 77.8%), demonstrating closer parity (delta = 0.5%) in accuracy across subpopulations (Welch t-test t = 0.111, P = 0.912).

Conclusions

Findings illustrate how data imbalance and domain generalization can lead to disparity of accuracy across subpopulations, and show that novel generative methods of synthetic fundus images may play a role for debiasing AI.

Translational Relevance

New AI methods have possible applications to address potential AI bias in DR diagnostics from fundus pigmentation, and potentially other ophthalmic DLSs too.

18F-sodium fluoride coronary uptake in patients with coronary artery bypass grafts

 

18F-Sodium fluoride (18F-NaF) positron emission tomography (PET) provides an assessment of active calcification (microcalcification) across a wide range of cardiovascular conditions including coronary artery disease, carotid and penile atherosclerosis, aortic and mitral valve disease, and abdominal aortic aneurysms. To date the significance of 18F-NaF uptake in patients with coronary artery bypass grafts (CABG) is unknown.

We aimed to characterize 18F-NaF activity in CABG patients.

We performed 18F-NaF PET (30-min long single bed position acquisition 1h after a 250mB injection of 18F-NaF) and coronary CT angiography in patients with multivessel coronary artery disease and followed them for fatal or non-fatal myocardial infarction over 42 [31,49] months. On motion-corrected datasets we quantified the whole-vessel coronary 18F-NaF PET uptake (the coronary microcalcification activity (CMA)) by measuring the activity of voxels above the background (right atrium activity) + 2 * standard deviations threshold. All study subjects underwent a comprehensive baseline clinical assessment including evaluation of their cardiovascular risk factor profile with the SMART [Secondary Manifestations of Arterial Disease] risk score calculated, and the coronary calcium burden assessed with calcium scoring (CCS).

Among 293 study participants (65±9 years; 84% male), 48 (16%) had a history of CABG. Although the majority 124/128 (97%) of coronary bypass grafts showed no uptake, 4 saphenous vein grafts presented with a CMA&gt;0 (range: 2.5–11.5, Figure). While a similar proportion of patients with and without prior CABG showed increased coronary 18F-NaF uptake (CMA&gt;0) (58.3% versus 71.4%, p=0.11) overall prior-CABG subjects had higher CMA (2.0 [0.3, 6.6] versus 0.6 [0, 2.7], p=0.001) and CCS (1135 [631, 2120] versus 225 [59, 542], p&lt;0.001), respectively. In line with the differences in the calcification activity and the coronary calcium burden, the SMART risk scores were higher in CABG patients (23 [17, 28] versus 17 [12, 24], p=0.01), and these patients were also older (68±8 versus 64±8, p=0.01). Despite the aforementioned differences the incidence of myocardial infarction 5/48 (9%) versus 15/245 (6%) and MACE 6/48 (12%) versus 34/245 (14%) during follow-up between subjects with and without prior CABG was similar (p=0.44 and p=0.80, respectively).

CABG patients have a higher coronary microcalcification activity on 18F-NaF PET than multivessel coronary artery disease patients without prior CABG. Despite evidence of higher 18F-NaF uptake there is no difference in outcome between these two groups.

Figure 1. 18F-NaF uptake in CABG patients. (A) 63-year old male with prominent uptake in stented saphenous vein bypass grafts and native coronary arteries who experienced a non-fatal non ST elevation myocardial infarction during follow-up. (B) 70-year old male with evident uptake in native coronary arteries and only little 18F-NaF activity within coronary bypasses.

Funding Acknowledgement

Type of funding source: Other. Main funding source(s): National Heart, Lung, and Blood Institute/National Institute of Health (NHLBI/NIH), British Heart Foundation

How relevant is the ISCHEMIA trial to a rapid access chest pain clinic cohort of patients?

Background

The ISCHEMIA trial demonstrated that optimal medical therapy (OMT) is not inferior to an early interventional approach for stable angina. This could significantly impact on clinical practice. This study aimed to check the relevance of the ISCHEMIA trial in a real-world population of patients referred to a tertiary centre with recent onset chest pain (CP).

Methods

In this registry study, electronic notes of all patients assessed in a Rapid Access Chest Pain Clinic (RACPC) within a 12-month period (2018–19) were reviewed. Patients were selected if they met key ISCHEMIA trial inclusion criteria.

Results

2416 patients were assessed, 378 (15.6%) presented with typical anginal CP, 1357 (56.2%) had atypical CP and 681 (28.2%) had non anginal CP.

Of the typical CP group, 158 patients were excluded (91 known CAD, 62 ACS, 2 eGFR &lt;30mL/min, 3 severe LVSD). This resulted in 220 patients, representing 58.2% of the typical chest pain population and 9.1% of all patients seen in RACPC. These patients had a median age of 60 years, 96 (44%) female, 119 (54.1%) had high cholesterol, 44 (20%) had diabetes, 115 (52.3%) had hypertension, 104 (47.3%) had a family history of ischaemic heart disease, and 32 (14.5%) were current smokers.

Of these 220 patients, 48 (21.8%) had a CT coronary angiogram (CTCA) requested as their first line investigation (42 completed) with 1 (2.4%) patients result suggestive of significant left main stem (LMS) disease. 15 (6.8%) patients had stress echocardiography requested as their first line investigation (13 completed), 4 (31%) were positive for inducible ischaemia. 3 (1.4%) patients had stress CMR requested as their first line investigation (2 completed), both were negative. 143 (65%) patients had an invasive coronary angiogram (ICA) requested as their first line investigation (112 completed). 8 patients had severe LMS disease and were referred for surgical opinion. A further 11 patients were referred for surgical opinion due to multivessel disease or aberrant coronary anatomy. In total 24 (21.4%) patients were treated with PCI following ICA as their first line investigation.

All patients were started on medical therapy for presumed CAD with up-titration while awaiting investigations. The median wait time for a CTCA was 55 days compared to 165.5 days for ICA.

Two patients (0.9%) from the cohort of 220 patients died during the follow up period, compared to 2.5% of patients admitted from RACPC with an ACS diagnosis.

Conclusion

Patients present with undifferentiated chest pain, consequently the outcomes of the ISCHEMIA trial must be considered cautiously. Within our cohort of 2416 patients, only 9% of patients met key inclusion criteria of the trial. Ultimately, only 19.5% patients with typical chest pain were revascularised, unlike 80% of patients in the invasive arm of ISCHEMIA. It is unclear how the results of the ISCHEMIA trial will impact on UK practice, but it is clear that OMT plays a central role.

Funding Acknowledgement

Type of funding source: None

Crop production in the USA is frequently limited by a lack of pollinators

Most of the world's crops depend on pollinators, so declines in both managed and wild bees raise concerns about food security. However, the degree to which insect pollination is actually limiting current crop production is poorly understood, as is the role of wild species (as opposed to managed honeybees) in pollinating crops, particularly in intensive production areas. We established a nationwide study to assess the extent of pollinator limitation in seven crops at 131 locations situated across major crop-producing areas of the USA. We found that five out of seven crops showed evidence of pollinator limitation. Wild bees and honeybees provided comparable amounts of pollination for most crops, even in agriculturally intensive regions. We estimated the nationwide annual production value of wild pollinators to the seven crops we studied at over $1.5 billion; the value of wild bee pollination of all pollinator-dependent crops would be much greater. Our findings show that pollinator declines could translate directly into decreased yields or production for most of the crops studied, and that wild species contribute substantially to pollination of most study crops in major crop-producing regions.

Ion thrusters for electric propulsion: Scientific issues developing a niche technology into a game changer

The transition from old space to new space along with increasing commercialization has a major impact on space flight, in general, and on electric propulsion (EP) by ion thrusters, in particular. Ion thrusters are nowadays used as primary propulsion systems in space. This article describes how these changes related to new space affect various aspects that are important for the development of EP systems. Starting with a historical overview of the development of space flight and of the technology of EP systems, a number of important missions with EP and the underlying technologies are presented. The focus of our discussion is the technology of the radio frequency ion thruster as a prominent member of the gridded ion engine family. Based on this discussion, we give an overview of important research topics such as the search for alternative propellants, the development of reliable neutralizer concepts based on novel insert materials, as well as promising neutralizer-free propulsion concepts. In addition, aspects of thruster modeling and requirements for test facilities are discussed. Furthermore, we address aspects of space electronics with regard to the development of highly efficient electronic components as well as aspects of electromagnetic compatibility and radiation hardness. This article concludes with a presentation of the interaction of EP systems with the spacecraft.

The Neural Sulcus of the Cervical Vertebrae: A Review of Its Anatomy and Surgical Perspectives

The neural sulcus is a bony channel that spans the transverse process in the subaxial cervical spine. It is located between the anterior and posterior tubercles on either side of the transverse foramen, housing the spinal nerve as it passes through the intervertebral foramina. Although numerous studies have evaluated the anatomy of the cervical spine, very little data on detailed anatomy of the neural sulcus and its implication in cervical spine surgery exist. Here, we review the anatomy of the neural sulcus and surgical considerations. The neural sulcus has important surgical implications, and knowledge of its anatomy is important in considering and planning posterior cervical segmented instrumentation. This increases the ability of the neurosurgeon to choose the best suitable surgical approach to the subaxial cervical spine, allowing good outcomes for the patient.

Assessment of Deep Generative Models for High-Resolution Synthetic Retinal Image Generation of Age-Related Macular Degeneration

Importance

Deep learning (DL) used for discriminative tasks in ophthalmology, such as diagnosing diabetic retinopathy or age-related macular degeneration (AMD), requires large image data sets graded by human experts to train deep convolutional neural networks (DCNNs). In contrast, generative DL techniques could synthesize large new data sets of artificial retina images with different stages of AMD. Such images could enhance existing data sets of common and rare ophthalmic diseases without concern for personally identifying information to assist medical education of students, residents, and retinal specialists, as well as for training new DL diagnostic models for which extensive data sets from large clinical trials of expertly graded images may not exist.

Objective

To develop DL techniques for synthesizing high-resolution realistic fundus images serving as proxy data sets for use by retinal specialists and DL machines.

Design, Setting, and Participants

Generative adversarial networks were trained on 133 821 color fundus images from 4613 study participants from the Age-Related Eye Disease Study (AREDS), generating synthetic fundus images with and without AMD. We compared retinal specialists' ability to diagnose AMD on both real and synthetic images, asking them to assess image gradability and testing their ability to discern real from synthetic images. The performance of AMD diagnostic DCNNs (referable vs not referable AMD) trained on either all-real vs all-synthetic data sets was compared.

Main Outcomes and Measures

Accuracy of 2 retinal specialists (T.Y.A.L. and K.D.P.) for diagnosing and distinguishing AMD on real vs synthetic images and diagnostic performance (area under the curve) of DL algorithms trained on synthetic vs real images.

Results

The diagnostic accuracy of 2 retinal specialists on real vs synthetic images was similar. The accuracy of diagnosis as referable vs nonreferable AMD compared with certified human graders for retinal specialist 1 was 84.54% (error margin, 4.06%) on real images vs 84.12% (error margin, 4.16%) on synthetic images and for retinal specialist 2 was 89.47% (error margin, 3.45%) on real images vs 89.19% (error margin, 3.54%) on synthetic images. Retinal specialists could not distinguish real from synthetic images, with an accuracy of 59.50% (error margin, 3.93%) for retinal specialist 1 and 53.67% (error margin, 3.99%) for retinal specialist 2. The DCNNs trained on real data showed an area under the curve of 0.9706 (error margin, 0.0029), and those trained on synthetic data showed an area under the curve of 0.9235 (error margin, 0.0045).

Conclusions and Relevance

Deep learning-synthesized images appeared to be realistic to retinal specialists, and DCNNs achieved diagnostic performance on synthetic data close to that for real images, suggesting that DL generative techniques hold promise for training humans and machines.

Use of Deep Learning for Detailed Severity Characterization and Estimation of 5-Year Risk Among Patients With Age-Related Macular Degeneration

Importance

Although deep learning (DL) can identify the intermediate or advanced stages of age-related macular degeneration (AMD) as a binary yes or no, stratified gradings using the more granular Age-Related Eye Disease Study (AREDS) 9-step detailed severity scale for AMD provide more precise estimation of 5-year progression to advanced stages. The AREDS 9-step detailed scale's complexity and implementation solely with highly trained fundus photograph graders potentially hampered its clinical use, warranting development and use of an alternate AREDS simple scale, which although valuable, has less predictive ability.

Objective

To describe DL techniques for the AREDS 9-step detailed severity scale for AMD to estimate 5-year risk probability with reasonable accuracy.

Design, Setting, and Participants

This study used data collected from November 13, 1992, to November 30, 2005, from 4613 study participants of the AREDS data set to develop deep convolutional neural networks that were trained to provide detailed automated AMD grading on several AMD severity classification scales, using a multiclass classification setting. Two AMD severity classification problems using criteria based on 4-step (AMD-1, AMD-2, AMD-3, and AMD-4 from classifications developed for AREDS eligibility criteria) and 9-step (from AREDS detailed severity scale) AMD severity scales were investigated. The performance of these algorithms was compared with a contemporary human grader and against a criterion standard (fundus photograph reading center graders) used at the time of AREDS enrollment and follow-up. Three methods for estimating 5-year risk were developed, including one based on DL regression. Data were analyzed from December 1, 2017, through April 15, 2018.

Main Outcomes and Measures

Weighted κ scores and mean unsigned errors for estimating 5-year risk probability of progression to advanced AMD.

Results

This study used 67 401 color fundus images from the 4613 study participants. The weighted κ scores were 0.77 for the 4-step and 0.74 for the 9-step AMD severity scales. The overall mean estimation error for the 5-year risk ranged from 3.5% to 5.3%.

Conclusions and Relevance

These findings suggest that DL AMD grading has, for the 4-step classification evaluation, performance comparable with that of humans and achieves promising results for providing AMD detailed severity grading (9-step classification), which normally requires highly trained graders, and for estimating 5-year risk of progression to advanced AMD. Use of DL has the potential to assist physicians in longitudinal care for individualized, detailed risk assessment as well as clinical studies of disease progression during treatment or as public screening or monitoring worldwide.

Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks

Importance

Age-related macular degeneration (AMD) affects millions of people throughout the world. The intermediate stage may go undetected, as it typically is asymptomatic. However, the preferred practice patterns for AMD recommend identifying individuals with this stage of the disease to educate how to monitor for the early detection of the choroidal neovascular stage before substantial vision loss has occurred and to consider dietary supplements that might reduce the risk of the disease progressing from the intermediate to the advanced stage. Identification, though, can be time-intensive and requires expertly trained individuals.

Objective

To develop methods for automatically detecting AMD from fundus images using a novel application of deep learning methods to the automated assessment of these images and to leverage artificial intelligence advances.

Design, Setting, and Participants

Deep convolutional neural networks that are explicitly trained for performing automated AMD grading were compared with an alternate deep learning method that used transfer learning and universal features and with a trained clinical grader. Age-related macular degeneration automated detection was applied to a 2-class classification problem in which the task was to distinguish the disease-free/early stages from the referable intermediate/advanced stages. Using several experiments that entailed different data partitioning, the performance of the machine algorithms and human graders in evaluating over 130 000 images that were deidentified with respect to age, sex, and race/ethnicity from 4613 patients against a gold standard included in the National Institutes of Health Age-related Eye Disease Study data set was evaluated.

Main Outcomes and Measures

Accuracy, receiver operating characteristics and area under the curve, and kappa score.

Results

The deep convolutional neural network method yielded accuracy (SD) that ranged between 88.4% (0.5%) and 91.6% (0.1%), the area under the receiver operating characteristic curve was between 0.94 and 0.96, and kappa coefficient (SD) between 0.764 (0.010) and 0.829 (0.003), which indicated a substantial agreement with the gold standard Age-related Eye Disease Study data set.

Conclusions and Relevance

Applying a deep learning-based automated assessment of AMD from fundus images can produce results that are similar to human performance levels. This study demonstrates that automated algorithms could play a role that is independent of expert human graders in the current management of AMD and could address the costs of screening or monitoring, access to health care, and the assessment of novel treatments that address the development or progression of AMD.