Prediction of response to anti-TNFα using integrative computational approaches in Crohn's disease-Needle in a haystack or a promising biomarker?

In the January issue of Cell Reports Medicine, Gerassy-Vainberg et al.1 demonstrate the utility of integrative methods to reveal molecular mechanisms associated with anti-tumor necrosis factor-alpha therapy response in patients with inflammatory conditions.

Inspiring diverse researchers in Virginia: Cultivating research excellence through a career-building program

Historically underrepresented groups in biomedical research have continued to experience low representation despite shifting demographics. Diversity fosters inclusive, higher quality, and innovative team science. One avenue for diversifying research teams is integrating diversity-focused initiatives into Clinical and Translational Science Award (CTSA) Programs, such as the integrated Translational Health Research Institute of Virginia (iTHRIV). In 2020, iTHRIV participated in Building Up, developed by the University of Pittsburgh CTSA, and intended to increase representation and improve career support for underrepresented groups in the biomedical workforce. Drawing lessons from this study, iTHRIV implemented the "inspiring Diverse Researchers in Virginia" (iDRIV) program. This yearlong program provided education, coaching, mentoring, and sponsorship for underrepresented early career investigators in the biomedical workforce. To date, 24 participants have participated in the program across three cohorts. Participants have been predominantly female (92%), with 33% identifying as Hispanic/Latinx, 29% as Black, and 13% as Asian. Notably, 38% of scholars have subsequently achieved at least one accomplishment, such as receiving a local research honor or award and an extramural funding award from a foundation or federal agency. The iTHRIV iDRIV program serves as a model for providing career support to developing investigators from underrepresented backgrounds, with the overall goal of improving patient health.

Effects of empagliflozin on progression of chronic kidney disease: a prespecified secondary analysis from the empa-kidney trial

BACKGROUND

Sodium-glucose co-transporter-2 (SGLT2) inhibitors reduce progression of chronic kidney disease and the risk of cardiovascular morbidity and mortality in a wide range of patients. However, their effects on kidney disease progression in some patients with chronic kidney disease are unclear because few clinical kidney outcomes occurred among such patients in the completed trials. In particular, some guidelines stratify their level of recommendation about who should be treated with SGLT2 inhibitors based on diabetes status and albuminuria. We aimed to assess the effects of empagliflozin on progression of chronic kidney disease both overall and among specific types of participants in the EMPA-KIDNEY trial.

METHODS

EMPA-KIDNEY, a randomised, controlled, phase 3 trial, was conducted at 241 centres in eight countries (Canada, China, Germany, Italy, Japan, Malaysia, the UK, and the USA), and included individuals aged 18 years or older with an estimated glomerular filtration rate (eGFR) of 20 to less than 45 mL/min per 1·73 m2, or with an eGFR of 45 to less than 90 mL/min per 1·73 m2 with a urinary albumin-to-creatinine ratio (uACR) of 200 mg/g or higher. We explored the effects of 10 mg oral empagliflozin once daily versus placebo on the annualised rate of change in estimated glomerular filtration rate (eGFR slope), a tertiary outcome. We studied the acute slope (from randomisation to 2 months) and chronic slope (from 2 months onwards) separately, using shared parameter models to estimate the latter. Analyses were done in all randomly assigned participants by intention to treat. EMPA-KIDNEY is registered at ClinicalTrials.gov, NCT03594110.

FINDINGS

Between May 15, 2019, and April 16, 2021, 6609 participants were randomly assigned and then followed up for a median of 2·0 years (IQR 1·5-2·4). Prespecified subgroups of eGFR included 2282 (34·5%) participants with an eGFR of less than 30 mL/min per 1·73 m2, 2928 (44·3%) with an eGFR of 30 to less than 45 mL/min per 1·73 m2, and 1399 (21·2%) with an eGFR 45 mL/min per 1·73 m2 or higher. Prespecified subgroups of uACR included 1328 (20·1%) with a uACR of less than 30 mg/g, 1864 (28·2%) with a uACR of 30 to 300 mg/g, and 3417 (51·7%) with a uACR of more than 300 mg/g. Overall, allocation to empagliflozin caused an acute 2·12 mL/min per 1·73 m2 (95% CI 1·83-2·41) reduction in eGFR, equivalent to a 6% (5-6) dip in the first 2 months. After this, it halved the chronic slope from -2·75 to -1·37 mL/min per 1·73 m2 per year (relative difference 50%, 95% CI 42-58). The absolute and relative benefits of empagliflozin on the magnitude of the chronic slope varied significantly depending on diabetes status and baseline levels of eGFR and uACR. In particular, the absolute difference in chronic slopes was lower in patients with lower baseline uACR, but because this group progressed more slowly than those with higher uACR, this translated to a larger relative difference in chronic slopes in this group (86% [36-136] reduction in the chronic slope among those with baseline uACR <30 mg/g compared with a 29% [19-38] reduction for those with baseline uACR ≥2000 mg/g; ptrend<0·0001).

INTERPRETATION

Empagliflozin slowed the rate of progression of chronic kidney disease among all types of participant in the EMPA-KIDNEY trial, including those with little albuminuria. Albuminuria alone should not be used to determine whether to treat with an SGLT2 inhibitor.

FUNDING

Boehringer Ingelheim and Eli Lilly.

Impact of primary kidney disease on the effects of empagliflozin in patients with chronic kidney disease: secondary analyses of the EMPA-KIDNEY trial

BACKGROUND

The EMPA-KIDNEY trial showed that empagliflozin reduced the risk of the primary composite outcome of kidney disease progression or cardiovascular death in patients with chronic kidney disease mainly through slowing progression. We aimed to assess how effects of empagliflozin might differ by primary kidney disease across its broad population.

METHODS

EMPA-KIDNEY, a randomised, controlled, phase 3 trial, was conducted at 241 centres in eight countries (Canada, China, Germany, Italy, Japan, Malaysia, the UK, and the USA). Patients were eligible if their estimated glomerular filtration rate (eGFR) was 20 to less than 45 mL/min per 1·73 m2, or 45 to less than 90 mL/min per 1·73 m2 with a urinary albumin-to-creatinine ratio (uACR) of 200 mg/g or higher at screening. They were randomly assigned (1:1) to 10 mg oral empagliflozin once daily or matching placebo. Effects on kidney disease progression (defined as a sustained ≥40% eGFR decline from randomisation, end-stage kidney disease, a sustained eGFR below 10 mL/min per 1·73 m2, or death from kidney failure) were assessed using prespecified Cox models, and eGFR slope analyses used shared parameter models. Subgroup comparisons were performed by including relevant interaction terms in models. EMPA-KIDNEY is registered with ClinicalTrials.gov, NCT03594110.

FINDINGS

Between May 15, 2019, and April 16, 2021, 6609 participants were randomly assigned and followed up for a median of 2·0 years (IQR 1·5-2·4). Prespecified subgroupings by primary kidney disease included 2057 (31·1%) participants with diabetic kidney disease, 1669 (25·3%) with glomerular disease, 1445 (21·9%) with hypertensive or renovascular disease, and 1438 (21·8%) with other or unknown causes. Kidney disease progression occurred in 384 (11·6%) of 3304 patients in the empagliflozin group and 504 (15·2%) of 3305 patients in the placebo group (hazard ratio 0·71 [95% CI 0·62-0·81]), with no evidence that the relative effect size varied significantly by primary kidney disease (pheterogeneity=0·62). The between-group difference in chronic eGFR slopes (ie, from 2 months to final follow-up) was 1·37 mL/min per 1·73 m2 per year (95% CI 1·16-1·59), representing a 50% (42-58) reduction in the rate of chronic eGFR decline. This relative effect of empagliflozin on chronic eGFR slope was similar in analyses by different primary kidney diseases, including in explorations by type of glomerular disease and diabetes (p values for heterogeneity all >0·1).

INTERPRETATION

In a broad range of patients with chronic kidney disease at risk of progression, including a wide range of non-diabetic causes of chronic kidney disease, empagliflozin reduced risk of kidney disease progression. Relative effect sizes were broadly similar irrespective of the cause of primary kidney disease, suggesting that SGLT2 inhibitors should be part of a standard of care to minimise risk of kidney failure in chronic kidney disease.

FUNDING

Boehringer Ingelheim, Eli Lilly, and UK Medical Research Council.

Inspiring Diverse Researchers in Virginia: Cultivating Research Excellence Through a Career Building Program

Historically underrepresented groups in biomedical research have continued to experience low representation despite shifting demographics. Diversity fosters inclusive, higher quality, and innovative team science. One avenue for diversifying research teams is integrating diversity-focused initiatives into Clinical and Translational Science Award (CTSA) Programs, such as the integrated Translational Health Research Institute of Virginia (iTHRIV). In 2020, iTHRIV participated in Building Up, developed by the University of Pittsburgh CTSA, intended to increase representation and improve career support for underrepresented groups in the biomedical workforce. Drawing lessons from this study, iTHRIV implemented the "inspiring Diverse Researchers in Virginia" (iDRIV) program. This year-long program provided education, coaching, mentoring, and sponsorship for underrepresented early-career investigators in the biomedical workforce. To date, 24 participants have participated in the program across three cohorts. Participants have been predominantly female (92%), with 33% identifying as Hispanic/Latinx, 29% as Black, and 13% Asian. Notably, 38% of scholars have subsequently achieved at least one accomplishment, such as receiving a local research honor or award and an extramural funding award from a foundation or federal agency. The iTHRIV iDRIV program serves as a model for providing career support to developing investigators from underrepresented backgrounds, with the overall goal of improving patient health.

The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning

Introduction

Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five challenges to address. Challenge #1: VCE data are stochastic and contains significant artifact. Challenge #2: VCE interpretation is cost-intensive. Challenge #3: VCE data are inherently imbalanced. Challenge #4: Existing VCE AIMLT are computationally cumbersome. Challenge #5: Clinicians are hesitant to accept AIMLT that cannot explain their process.

Methods

An anatomic landmark detection model was used to test the application of convolutional neural networks (CNNs) to the task of classifying VCE data. We also created a tool that assists in expert annotation of VCE data. We then created more elaborate models using different approaches including a multi-frame approach, a CNN based on graph representation, and a few-shot approach based on meta-learning.

Results

When used on full-length VCE footage, CNNs accurately identified anatomic landmarks (99.1%), with gradient weighted-class activation mapping showing the parts of each frame that the CNN used to make its decision. The graph CNN with weakly supervised learning (accuracy 89.9%, sensitivity of 91.1%), the few-shot model (accuracy 90.8%, precision 91.4%, sensitivity 90.9%), and the multi-frame model (accuracy 97.5%, precision 91.5%, sensitivity 94.8%) performed well.

Discussion

Each of these five challenges is addressed, in part, by one of our AI-based models. Our goal of producing high performance using lightweight models that aim to improve clinician confidence was achieved.

Impact of diarrhoea and acute respiratory infection on environmental enteric dysfunction and growth of malnourished children in Pakistan: a longitudinal cohort study

Background

Diarrhoea and acute respiratory infections (ARI) are assumed to be major drivers of growth and likely contribute to environmental enteric dysfunction (EED), which is a precursor to childhood malnutrition. In the present study, we checked the correlation between diarrhoeal/ARI burden and EED using a novel duodenal histological index.

Methods

Between November 2017 and July 2019, a total of 365 infants with weight-for-height Z scores (WHZ score) of <-2 were enrolled, and 51 infants with WHZ scores of >0 and height-for-age Z scores (HAZ scores) of >-1 were selected as age-matched healthy controls. Morbidity was assessed weekly and categorised as the total number of days with diarrhoea and acute respiratory infection (ARI) from enrolment until two years of age and was further divided into four quartiles in ascending order.

Findings

The HAZ declined until two years of age regardless of morbidity burden, and WHZ and weight-for-age Z scores (WAZ scores) were at their lowest at six months. Sixty-three subjects who had a WHZ score <-2 and failed to respond to nutritional and educational interventions were further selected at 15 months to investigate their EED histological scores with endoscopy further. EED histological scores of the subjects were higher with increasing diarrhoeal frequency yet remained statistically insignificant (p = 0.810).

Interpretation

There was not a clear correlation between diarrhoea and ARI frequency with growth faltering, however, children with the highest frequency of diarrhoea had the highest EED histological scores and growth faltering.

Funding

Bill and Melinda Gates Foundation and The National Institutes of Health.

Standard RUTF vs. locally-made RUSF for acutely malnourished children: A quasi-experimental comparison of the impact on growth and compliance in a rural community of Pakistan

BACKGROUND

The reduction in severe and moderate acute malnutrition (SAM and MAM) rates in Pakistan has been sub-optimal compared to other low-and middle-income countries (LMICs). Specially-formulated products have been designed globally to manage SAM and MAM, such as ready-to-use therapeutic food (RUTF) and ready-to-use supplementary food (RUSF), with variable efficacies. RUTF is primarily produced and patented in industrialized countries, raising supply challenges in resource-constrained regions with a high burden of acute malnutrition. RUSF minimizes costs by using locally-available ingredients while providing similar nutritional value. In this study, we compared the efficacy, side effects, and compliance of two months of supplementation with either RUTF or RUSF.

METHODS

Children aged nine months in the rural district of Matiari, Pakistan, with a weight-for-height z-score (WHZ) <-2 received either RUTF (500 kcal sachet) for two months in 2015 or RUSF (520 kcal sachet) for two months in 2018.

RESULTS

The RUSF group had a higher height gain and mid-upper arm circumferences (MUAC) score. Higher compliance was noted with lower side effects in the RUSF group. A higher compliance rate did correlate with the growth parameters in respective groups.

CONCLUSION

Our study found that both RUTF and RUSF partially improve the anthropometric status of acutely malnourished children, with neither being superior to the other.

Machine and deep learning in inflammatory bowel disease

PURPOSE OF REVIEW

The Management of inflammatory bowel disease (IBD) has evolved with the introduction and widespread adoption of biologic agents; however, the advent of artificial intelligence technologies like machine learning and deep learning presents another watershed moment in IBD treatment. Interest in these methods in IBD research has increased over the past 10 years, and they offer a promising path to better clinical outcomes for IBD patients.

RECENT FINDINGS

Developing new tools to evaluate IBD and inform clinical management is challenging because of the expansive volume of data and requisite manual interpretation of data. Recently, machine and deep learning models have been used to streamline diagnosis and evaluation of IBD by automating review of data from several diagnostic modalities with high accuracy. These methods decrease the amount of time that clinicians spend manually reviewing data to formulate an assessment.

SUMMARY

Interest in machine and deep learning is increasing in medicine, and these methods are poised to revolutionize the way that we treat IBD. Here, we highlight the recent advances in using these technologies to evaluate IBD and discuss the ways that they can be leveraged to improve clinical outcomes.

The effect of photodynamic therapy on the salivary flow rate, IgA concentration and C-reactive protein levels in active smokers: a case-control study

OBJECTIVE

This study aimed to evaluate the effect of photodynamic therapy (PDT) on the salivary flow rate, secretory immunoglobulin A, and C-reactive protein levels in active smokers.

PATIENTS AND METHODS

The present study is a prospective case-control study. Twenty active smokers were allocated to two groups randomly of ten participants each: the experimental group was irradiated while the control was exposed to sham irradiation by turning off the equipment. In the experimental group, methylene blue mediated PDT was applied both intra- and extra-orally over the major and minor salivary glands using a diode laser. 780 nm wavelength and 4 J/cm2 of energy were used to irradiate the 10 points of major salivary glands (6 for parotid and 2 for submandibular glands and 2 for sublingual glands). On the other hand, 660 nm was used to apply 10 J/cm2 of energy over the minor salivary glands at numerous points. The samples of the stimulated and unstimulated saliva were collected from both groups to assess the SFR. ELISA method was used to assess the level of salivary IgA levels, statistical analysis was done using a one-way ANOVA, and a p-value of <0.05 was considered significant.

RESULTS

The results showed a significant increment in salivary and secretory immunoglobulin A levels of subjects undergone photodynamic therapy. C-reactive protein levels were significantly decreased in subjects exposed to irradiation.

CONCLUSIONS

The present study concludes that photodynamic therapy significantly improves the salivary flow rate, secretory Immunoglobulin A, and oral health quality of life in smokers. The inflammatory salivary marker C-reactive protein, which is usually raised in smokers, is also reduced.

Environmental enteric dysfunction: gut and microbiota adaptation in pregnancy and infancy

Environmental enteric dysfunction (EED) is a subclinical syndrome of intestinal inflammation, malabsorption and barrier disruption that is highly prevalent in low- and middle-income countries in which poverty, food insecurity and frequent exposure to enteric pathogens impair growth, immunity and neurodevelopment in children. In this Review, we discuss advances in our understanding of EED, intestinal adaptation and the gut microbiome over the 'first 1,000 days' of life, spanning pregnancy and early childhood. Data on maternal EED are emerging, and they mirror earlier findings of increased risks for preterm birth and fetal growth restriction in mothers with either active inflammatory bowel disease or coeliac disease. The intense metabolic demands of pregnancy and lactation drive gut adaptation, including dramatic changes in the composition, function and mother-to-child transmission of the gut microbiota. We urgently need to elucidate the mechanisms by which EED undermines these critical processes so that we can improve global strategies to prevent and reverse intergenerational cycles of undernutrition.

Provision of smoking cessation support for patients following a diagnosis of cancer in Ireland

There is growing evidence that smoking cessation (SC) improves outcomes following diagnosis of cancer. Notwithstanding adverse outcomes, a significant number of those diagnosed with cancer continue to smoke. Our objective was to document the SC services provided for patients with cancer by specialist adult cancer hospitals across Ireland, a country with a stated tobacco endgame goal. A cross-sectional survey based on recent national clinical guidelines was used to determine SC care delivery across eight adult cancer specialist hospitals, and one specialist radiotherapy centre. Qualtrics was used. The response rate was 88.9% with data reported from seven cancer hospitals and one specialist radiotherapy centre, all indicating they had some SC related provision (100%). Stop smoking medications were provided to cancer inpatients in two hospitals, at outpatients and attending day ward services in one hospital. Smokers with cancer were referred automatically to the SC service in two hospitals at diagnosis. While stop smoking medications were available 24 h a day in five hospitals, most did not stock all three (Nicotine Replacement Therapy, Bupropion, Varenicline). One hospital advised they had data on uptake of SC services for smokers with cancer but were unable to provide detail. There is considerable variation in SC information and services provided to cancer patients across adult cancer specialist centres in Ireland, reflecting the suboptimal practice of smoking cessation for patients with cancer found in the limited international audits. Such audits are essential to demonstrate service gaps and provide a baseline for service improvement.

Essential Fatty Acid Deficiency Associates with Growth Faltering and Environmental Enteric Dysfunction in Children

Environmental enteric dysfunction (EED) is characterized by intestinal inflammation, malabsorption and growth-faltering in children with heightened exposure to gut pathogens. The aim of this study was to characterize serum non-esterified fatty acids (NEFA), in association with childhood undernutrition and EED, as potential biomarkers to predict growth outcomes. The study comprised a cohort of undernourished rural Pakistani infants (n = 365) and age-matched controls followed prospectively up to 24 months of age. Serum NEFA were quantified at ages 3–6 and 9 months and correlated with growth outcomes, serum bile acids and EED histopathological biomarkers. Serum NEFA correlated with linear growth-faltering and systemic and gut biomarkers of EED. Undernourished children exhibited essential fatty acid deficiency (EFAD), with low levels of linoleic acid and total n-6 polyunsaturated fatty acids, compensated by increased levels of oleic acid and increased elongase and desaturase activities. EFAD correlated with reduced anthropometric Z scores at 3–6 and 9 months of age. Serum NEFA also correlated with elevated BA and liver dysfunction. Essential fatty acid depletion and altered NEFA metabolism were highly prevalent and associated with acute and chronic growth-faltering in EED. The finding suggests that targeting early interventions to correct EFAD and promote FA absorption in children with EED may facilitate childhood growth in high-risk settings.

Quantitative Morphometry and Machine Learning Model to Explore Duodenal and Rectal Mucosal Tissue of Children with Environmental Enteric Dysfunction

Environmental enteric dysfunction (EED) is a subclinical enteropathy prevalent in resource-limited settings, hypothesized to be a consequence of chronic exposure to environmental enteropathogens, resulting in malnutrition, growth failure, neurocognitive delays, and oral vaccine failure. This study explored the duodenal and colonic tissues of children with EED, celiac disease, and other enteropathies using quantitative mucosal morphometry, histopathologic scoring indices, and machine learning-based image analysis from archival and prospective cohorts of children from Pakistan and the United States. We observed villus blunting as being more prominent in celiac disease than in EED, as shorter lengths of villi were observed in patients with celiac disease from Pakistan than in those from the United States, with median (interquartile range) lengths of 81 (73, 127) µm and 209 (188, 266) µm, respectively. Additionally, per the Marsh scoring method, celiac disease histologic severity was increased in the cohorts from Pakistan. Goblet cell depletion and increased intraepithelial lymphocytes were features of EED and celiac disease. Interestingly, the rectal tissue from cases with EED showed increased mononuclear inflammatory cells and intraepithelial lymphocytes in the crypts compared with controls. Increased neutrophils in the rectal crypt epithelium were also significantly associated with increased EED histologic severity scores in duodenal tissue. We observed an overlap between diseased and healthy duodenal tissue upon leveraging machine learning image analysis. We conclude that EED comprises a spectrum of inflammation in the duodenum, as previously described, and the rectal mucosa, warranting the examination of both anatomic regions in our efforts to understand and manage EED.

Impact of enteropathogens on faltering growth in a resource-limited setting

Introduction

Environmental enteropathy is an important contributor to childhood malnutrition in the developing world. Chronic exposure to fecal pathogens leads to alteration in intestinal structure and function, resulting in impaired gut immune function, malabsorption, and growth faltering leading to environmental enteropathy.

Methods

A community-based intervention study was carried out on children till 24 months of age in Matiari district, Pakistan. Blood and fecal specimens were collected from the enrolled children aged 3-6 and 9 months. A real-time PCR-based TaqMan array card (TAC) was used to detect enteropathogens.

Results

Giardia, Campylobacter spp., enteroaggregative Escherichia coli (EAEC), Enteropathogenic Escherichia coli (EPEC), Enterotoxigenic Escherichia coli (ETEC), and Cryptosporidium spp. were the most prevailing enteropathogens in terms of overall positivity at both time points. Detection of protozoa at enrollment and 9 months was negatively correlated with rate of change in height-for-age Z (ΔHAZ) scores during the first and second years of life. A positive association was found between Giardia, fecal lipocalin (LCN), and alpha 1-Acid Glycoprotein (AGP), while Campylobacter spp. showed positive associations with neopterin (NEO) and myeloperoxidase (MPO).

Conclusion

Protozoal colonization is associated with a decline in linear growth velocity during the first 2 years of life in children living in Environmental enteric dysfunction (EED) endemic settings. Mechanistic studies exploring the role of cumulative microbial colonization, their adaptations to undernutrition, and their influence on gut homeostasis are required to understand symptomatic enteropathogen-induced growth faltering.

Smoking cessation for cancer patients through the lens of cancer specialists: challenges & solutions

Background

The benefits of smoking cessation (SC) for cancer patients are widely recognised. However, there has been a limited emphasis on SC in this context and it continues to be a challenge for cancer patients. As part of a larger feasibility study aiming to develop a structured SC pathway for cancer patients in Ireland, this qualitative study explored the SC practices, experiences and opinions of oncology healthcare professionals (HCPs).

Methods

Semi-structured interviews were conducted with 18 HCPs from lung, breast, cervical, head and neck and general oncology, across 4 specialist adult cancer hospitals in Ireland. Interview transcripts were analysed using thematic analysis.

Results

Four key themes emerged:

(1) Frequently ask and advise but infrequently assist: most HCPs ask about smoking and many advise about available supports, but few refer patients to SC services. Where offered, referrals were to hospital SC services and/or nicotine replacement therapy was prescribed; no HCP prescribed varenicline or bupropion. Barriers included lack of time, ill-defined referral pathways and lack of knowledge.

(2) Increased willingness but differing ability to quit: most patients were interested in quitting post diagnosis and had varying support needs, linked to cancer stage, social circumstances and stress levels.

(3) Need for an integrated or parallel service: all HCPs suggested that a structured and defined referral pathway will facilitate SC.

(4) Motivational counselling and pharmacotherapy combination: many HCPs suggested face to face as the best mode of intervention initially, with regular follow ups and ongoing support virtually, started pre-treatment, with an empathetic and empowering approach with provision of both motivational counselling and SC pharmacotherapy.

Conclusions

Smoking post cancer diagnosis has serious implications for cancer treatment and prognosis but is frequently overlooked. These findings will inform the design of a SC pathway for cancer patients.

Key messages

• Despite increased willingness to quit, there is inadequate and inconsistent SC support provision for cancer patients.

• Tailored SC support should be an integral part of comprehensive cancer care.

Image-Level Uncertainty in Pseudo-Label Selection for Semi-Supervised Segmentation

Advancements in deep learning techniques have proved useful in biomedical image segmentation. However, the large amount of unlabeled data inherent in biomedical imagery, particularly in digital pathology, creates a semi-supervised learning paradigm. Specifically, because of the time consuming nature of producing pixel-wise annotations and the high cost of having a pathologist dedicate time to labeling, there is a large amount of unlabeled data that we wish to utilize in training segmentation algorithms. Pseudo-labeling is one method to leverage the unlabeled data to increase overall model performance. We adapt a method used for image classification pseudo-labeling to select images for segmentation pseudo-labeling and apply it to 3 digital pathology datasets. To select images for pseudo-labeling, we create and explore different thresholds for confidence and uncertainty on an image level basis. Furthermore, we study the relationship between image-level uncertainty and confidence with model performance. We find that the certainty metrics do not consistently correlate with performance intuitively, and abnormal correlations serve as an indicator of a model's ability to produce pseudo-labels that are useful in training. Clinical relevance - The proposed approach adapts image-level confidence and uncertainty measures for segmentation pseudo-labeling on digital pathology datasets. Increased model performance enables better disease quantification for histopathology.

Infant Nutrition in Low- and Middle-Income Countries

The burden of infant malnutrition is greatest in low- and middle-income countries (LMICs). Infant malnutrition is defined based on distinct subcategories, among them stunting (low-height-for-age) and wasting (low-weight-for-height). Some experts are shifting more toward understanding the interplay between these overlapping phenotypes and other confounding factors such as maternal nutrition and environmental hygiene. Current guidelines emphasize appropriate breastfeeding and nutrition within the 1000 days from conception to a child's second birthday to optimize early development. Future research directed toward better biomarkers of malnutrition before acute clinical symptoms develop will help direct targeted efforts toward at-risk populations.

022 Updated safety of cladribine tablets in multiple sclerosis patients: integrated safety analysis and post-approval data

Background

This analysis updates on the previously reported serious treatment emergent adverse event (TEAE) profile of cladribine tablets (CT) 10mg (cumulative dose 3.5mg/kg [CT3.5] over 2 years) following integration of final data from the PREMIERE registry and post-approval safety data from worldwide sources.

Methods

The monotherapy oral cohort (CT3.5, N=923, patient-years [PY]=3936.69; placebo, N=641, PY=2421.47) was derived from the CLARITY, CLARITY Extension and ORACLE-MS trials plus the PREMIERE registry. Adjusted adverse event incidences-per-100PY (Adj-AE-per-100PY) were calculated, cumulative to end of PREMIERE (October 2018).

Results

Patient characteristics were balanced between groups. Adj-AE-per-100PY for ≥1 serious TEAE were:

3.80 (CT3.5), 3.05 (placebo); for serious lymphopenia (preferred term [PT]): 0.10 (CT3.5), 0 (placebo); for serious infections and infestations (system organ class): 0.60 (CT3.5), 0.42 (placebo); for serious herpes zoster (PT): 0.05 (CT3.5), 0 (placebo); and malignant tumours: 0.26 (CT3.5), 0.12 (placebo). Post-approval sources reported 1622 AEs in the Periodic Benefit-Risk Evaluation Report (275 were serious); none repre- sented a new safety signal.

Conclusions

No new major safety findings for cladribine tablets were identified in this finalised integrated dataset containing final data from the PREMIERE registry. Findings are consistent with previously published integrated safety analyses. No new safety signals were identified from post-approval safety data. CLARITY:NCT00213135. CLARITY Extension:NCT00641537. ORACLE-MS:NCT00725985. PREMIERE:NCT01013350

g.giovannoni@qmul.ac.uk

Distance from Healthcare Facilities Is Associated with Increased Morbidity of Acute Infection in Pediatric Patients in Matiari, Pakistan

The relationship between environmental factors and child health is not well understood in rural Pakistan. This study characterized the environmental factors related to the morbidity of acute respiratory infections (ARIs), diarrhea, and growth using geographical information systems (GIS) technology. Anthropometric, address and disease prevalence data were collected through the SEEM (Study of Environmental Enteropathy and Malnutrition) study in Matiari, Pakistan. Publicly available map data were used to compile coordinates of healthcare facilities. A Pearson correlation coefficient (r) was used to calculate the correlation between distance from healthcare facilities and participant growth and morbidity. Other continuous variables influencing these outcomes were analyzed using a random forest regression model. In this study of 416 children, we found that participants living closer to secondary hospitals had a lower prevalence of ARI (r = 0.154, p < 0.010) and diarrhea (r = 0.228, p < 0.001) as well as participants living closer to Maternal Health Centers (MHCs): ARI (r = 0.185, p < 0.002) and diarrhea (r = 0.223, p < 0.001) compared to those living near primary facilities. Our random forest model showed that distance has high variable importance in the context of disease prevalence. Our results indicated that participants closer to more basic healthcare facilities reported a higher prevalence of both diarrhea and ARI than those near more urban facilities, highlighting potential public policy gaps in ameliorating rural health.

Deep Learning Methods for Anatomical Landmark Detection in Video Capsule Endoscopy Images

Video capsule endoscope (VCE) is an emerging technology that allows examination of the entire gastrointestinal (GI) tract with minimal invasion. While traditional endoscopy with biopsy procedures are the gold standard for diagnosis of most GI diseases, they are limited by how far the scope can be advanced in the tract and are also invasive. VCE allows gastroenterologists to investigate GI tract abnormalities in detail with visualization of all parts of the GI tract. It captures continuous real time images as it is propelled in the GI tract by gut motility. Even though VCE allows for thorough examination, reviewing and analyzing up to eight hours of images (compiled as videos) is tedious and not cost effective. In order to pave way for automation of VCE-based GI disease diagnosis, detecting the location of the capsule would allow for a more focused analysis as well as abnormality detection in each region of the GI tract. In this paper, we compared four deep Convolutional Neural Network models for feature extraction and detection of the anatomical part within the GI tract captured by VCE images. Our results showed that VGG-Net has superior performance with the highest average accuracy, precision, recall and, F1-score compared to other state of the art architectures: GoogLeNet, AlexNet and, ResNet.

Bile Acid Profiling Reveals Distinct Signatures in Undernourished Children with Environmental Enteric Dysfunction

BACKGROUND

Intestinal inflammation and malabsorption in environmental enteric dysfunction (EED) are associated with early childhood growth faltering in impoverished settings worldwide.

OBJECTIVES

The goal of this study was to identify candidate biomarkers associated with inflammation, EED histology, and as predictors of later growth outcomes by focusing on the liver-gut axis by investigating the bile acid metabolome.

METHODS

Undernourished rural Pakistani infants (n = 365) with weight-for-height Z score (WHZ) < -2 were followed up to the age of 24 mo and monitored for growth, infections, and EED. Well-nourished local children (n = 51) were controls, based on consistent WHZ > 0 and height-for-age Z score (HAZ) > -1 on 2 consecutive visits at 3 and 6 mo. Serum bile acid (sBA) profiles were measured by tandem MS at the ages of 3-6 and 9 mo and before nutritional intervention. Biopsies and duodenal aspirates were obtained following upper gastrointestinal endoscopy from a subset of children (n = 63) that responded poorly to nutritional intervention. BA composition in paired plasma and duodenal aspirates was compared based on the severity of EED histopathological scores and correlated to clinical and growth outcomes.

RESULTS

Remarkably, >70% of undernourished Pakistani infants displayed elevated sBA concentrations consistent with subclinical cholestasis. Serum glycocholic acid (GCA) correlated with linear growth faltering (HAZ, r = -0.252 and -0.295 at the age of 3-6 and 9 mo, respectively, P <0.001) and biomarkers of inflammation. The proportion of GCA positively correlated with EED severity for both plasma (rs = 0.324 P = 0.02) and duodenal aspirates (rs = 0.307 P = 0.06) in children with refractory wasting that underwent endoscopy, and the proportion of secondary BA was low in both undernourished and EED children.

CONCLUSIONS

Dysregulated bile acid metabolism is associated with growth faltering and EED severity in undernourished children. Restoration of intestinal BA homeostasis may offer a novel therapeutic target for undernutrition in children with EED. This trial was registered at clinicaltrials.gov as NCT03588013.

Good perception of own lifestyle associated with poor attendance at Diabetic RetinaScreen Programme

Background

Untreated diabetic retinopathy is the most common cause of sight loss in people of working age. The Diabetic RetinaScreen programme (DRS) is the national diabetic retinopathy screening programme in Ireland which commenced in 2013 with aim to prevent diabetic retinopathy and subsequent blindness, through free screening and ophthalmology services. High uptake is crucial for the effectiveness of the programme. This study aimed to determine the sociodemographic, lifestyle and healthcare factors associated with attendance at the DRS programme in Ireland, using data from a national cohort study, the Irish Longitudinal Study on Ageing (TILDA).

Methods

The TILDA wave-4 dataset (anonymised) was utilised for the current study. Questions on DRS invitation and attendance formed part of the wave 4 study questionnaire. Multivariate logistic regression was used to examine independent factors associated with attendance. SPSS was used for analysis.

Results

418 respondents (7.3%) were invited to DRS and 373 (89.2%) attended. Among all those who were invited to DRS, 244 (58.4%) were male and 174 (41.6%) were female. The mean age was 69.8 years (53-84 years). Following multivariate logistic regression, following a good diet/taking exercise (OR = 0.29, 95% CI 0.10-0.82) was negatively associated with attendance, after adjustment for age, male gender, higher education and medical card.

Conclusions

Recognising factors linked with uptake is important to develop goal directed strategies. Interestingly those who stated they followed a good diet & took exercise and were compliant with DM prevention were less likely to attend DRS. Previous research has also indicated that a higher physical activity level is associated with higher self-perceived health status

Key messages

Persons with DM with good compliance to diet and exercise were found to have poor attendance at the DRS programme. Targeted advertising is required to raise awareness of diabetic retinopathy.

Application of Artificial Intelligence to Clinical Practice in Inflammatory Bowel Disease - What the Clinician Needs to Know

Artificial intelligence [AI] techniques are quickly spreading across medicine as an analytical method to tackle challenging clinical questions. What were previously thought of as highly complex data sources, such as images or free text, are now becoming manageable. Novel analytical methods merge the latest developments in information technology infrastructure with advances in computer science. Once primarily associated with Silicon Valley, AI techniques are now making their way into medicine, including in the field of inflammatory bowel diseases [IBD]. Understanding potential applications and limitations of these techniques can be difficult, in particular for busy clinicians. In this article, we explain the basic terminologies and provide a particular focus on the foundations behind state-of-the-art AI methodologies in both imaging and text. We explore the growing applications of AI in medicine, with a specific focus on IBD to inform the practising gastroenterologist and IBD specialist. Finally, we outline possible future uses of these technologies in daily clinical practice.

Machine Learning Predictive Outcomes Modeling in Inflammatory Bowel Diseases

There is a rising interest in use of big data approaches to personalize treatment of inflammatory bowel diseases (IBDs) and to predict and prevent outcomes such as disease flares and therapeutic nonresponse. Machine learning (ML) provides an avenue to identify and quantify features across vast quantities of data to produce novel insights in disease management. In this review, we cover current approaches in ML-driven predictive outcomes modeling for IBD and relate how advances in other fields of medicine may be applied to improve future IBD predictive models. Numerous studies have incorporated clinical, laboratory, or omics data to predict significant outcomes in IBD, including hospitalizations, outpatient corticosteroid use, biologic response, and refractory disease after colectomy, among others, with considerable health care dollars saved as a result. Encouraging results in other fields of medicine support efforts to use ML image analysis-including analysis of histopathology, endoscopy, and radiology-to further advance outcome predictions in IBD. Though obstacles to clinical implementation include technical barriers, bias within data sets, and incongruence between limited data sets preventing model validation in larger cohorts, ML-predictive analytics have the potential to transform the clinical management of IBD. Future directions include the development of models that synthesize all aforementioned approaches to produce more robust predictive metrics.

Gut integrity and duodenal enteropathogen burden in undernourished children with environmental enteric dysfunction

Environmental enteric dysfunction (EED) is a subclinical condition of intestinal inflammation, barrier dysfunction and malabsorption associated with growth faltering in children living in poverty. This study explores association of altered duodenal permeability (lactulose, rhamnose and their ratio) with higher burden of enteropathogen in the duodenal aspirate, altered histopathological findings and higher morbidity (diarrhea) that is collectively associated with linear growth faltering in children living in EED endemic setting. In a longitudinal birth cohort, 51 controls (WHZ > 0, HAZ > −1.0) and 63 cases (WHZ< -2.0, refractory to nutritional intervention) were recruited. Anthropometry and morbidity were recorded on monthly bases up to 24 months of age. Dual sugar assay of urine collected after oral administration of lactulose and rhamnose was assessed in 96 children from both the groups. Duodenal histopathology (n = 63) and enteropathogen analysis of aspirate via Taqman array card (n = 60) was assessed in only cases. Giardia was the most frequent pathogen and was associated with raised L:R ratio (p = 0.068). Gastric microscopy was more sensitive than duodenal aspirate in H. pylori detection. Microscopically confirmed H. pylori negatively correlated with HAZ at 24 months (r = −0.313, p = 0.013). Regarding histopathological parameters, goblet cell reduction significantly correlated with decline in dual sugar excretion (p< 0.05). Between cases and controls, there were no significant differences in the median (25^th, 75^th percentile) of urinary concentrations (μg/ml) of lactulose [27.0 (11.50, 59.50) for cases vs. 38.0 (12.0, 61.0) for controls], rhamnose [66.0 (28.0, 178.0) vs. 86.5 (29.5, 190.5)] and L:R ratio [0.47 (0.24, 0.90) vs. 0.51 (0.31, 0.71)] respectively. In multivariable regression model, 31% of variability in HAZ at 24 months of age among cases and controls was explained by final model including dual sugars. In conclusion, enteropathogen burden is associated with altered histopathological features and intestinal permeability. In cases and controls living in settings of endemic enteropathy, intestinal permeability test may predict linear growth. However, for adoption as a screening tool for EED, further validation is required due to its complex intestinal pathophysiology.

EED is a subclinical condition of compromised gut integrity secondary to frequent and repeated exposure to enteropathogens in global settings with a high prevalence of undernutrition. In this study, we reported association of gut mucosal architecture with a dual sugar intestinal permeability assay (lactulose-rhamnose) in Pakistani children. In the presence of duodenal enteropathogens, features such as chronic inflammation, intra-epithelial lymphocytosis, enterocyte injury and Paneth cell reduction were consistently observed. When comparing undernourished cases and controls living in the same setting, we found urinary excretion of the sugars was similar among groups; however, variability in HAZ among children at 24 months was partially explained by a model that includes excretion values.

Safety of emergency, elective and day case operating during the winter period at East Suffolk and North Essex NHS Foundation Trust: lessons from the outcomes of 4,254 surgical patients from the first COVID-19 wave

BACKGROUND

There is limited evidence on perioperative outcomes of surgical patients during the COVID-19 pandemic to inform continued operating into the winter period.

METHODS

We retrospectively analysed the rate of 30-day COVID-19 transmission and mortality of all surgical patients in the three hospitals in our trust in the East of England during the first lockdown in March 2020. All patients who underwent a swab were swabbed on or 24 hours prior to admission.

RESULTS

There were 4,254 patients and an overall 30-day mortality of 0.99%. The excess surgical mortality in our region was 0.29%. There were 39 patients who were COVID-19 positive within 30 days of admission, 12 of whom died. All 12 were emergency admissions with a length of stay longer than 24 hours. There were three deaths among those who underwent day case surgery, one of whom was COVID-19 negative, and the other two were not swabbed but not suspected to have COVID-19. There were two COVID-19 positive elective cases and none in day case elective or emergency surgery. There were no COVID-19 positive deaths in elective or day case surgery.

CONCLUSIONS

There was a low rate of COVID-19 transmission and mortality in elective and day case operations. Our data have allowed us to guide patients in the consent process and provided the evidence base to restart elective and day case operating with precautions and regular review. A number of regions will be similarly affected and should perform a review of their data for the winter period and beyond.

Artificial Intelligence-based Analytics for Diagnosis of Small Bowel Enteropathies and Black Box Feature Detection

OBJECTIVES

Striking histopathological overlap between distinct but related conditions poses a disease diagnostic challenge. There is a major clinical need to develop computational methods enabling clinicians to translate heterogeneous biomedical images into accurate and quantitative diagnostics. This need is particularly salient with small bowel enteropathies; environmental enteropathy (EE) and celiac disease (CD). We built upon our preliminary analysis by developing an artificial intelligence (AI)-based image analysis platform utilizing deep learning convolutional neural networks (CNNs) for these enteropathies.

METHODS

Data for the secondary analysis was obtained from three primary studies at different sites. The image analysis platform for EE and CD was developed using CNNs including one with multizoom architecture. Gradient-weighted class activation mappings (Grad-CAMs) were used to visualize the models' decision-making process for classifying each disease. A team of medical experts simultaneously reviewed the stain color normalized images done for bias reduction and Grad-CAMs to confirm structural preservation and biomedical relevance, respectively.

RESULTS

Four hundred and sixty-one high-resolution biopsy images from 150 children were acquired. Median age (interquartile range) was 37.5 (19.0-121.5) months with a roughly equal sex distribution; 77 males (51.3%). ResNet50 and shallow CNN demonstrated 98% and 96% case-detection accuracy, respectively, which increased to 98.3% with an ensemble. Grad-CAMs demonstrated models' ability to learn different microscopic morphological features for EE, CD, and controls.

CONCLUSIONS

Our AI-based image analysis platform demonstrated high classification accuracy for small bowel enteropathies which was capable of identifying biologically relevant microscopic features and emulating human pathologist decision-making process. Grad-CAMs illuminated the otherwise "black box" of deep learning in medicine, allowing for increased physician confidence in adopting these new technologies in clinical practice.

Mucosal Genomics Implicate Lymphocyte Activation and Lipid Metabolism in Refractory Environmental Enteric Dysfunction

BACKGROUND & AIMS

Environmental enteric dysfunction (EED) limits the Sustainable Development Goals of improved childhood growth and survival. We applied mucosal genomics to advance our understanding of EED.

METHODS

The Study of Environmental Enteropathy and Malnutrition (SEEM) followed 416 children from birth to 24 months in a rural district in Pakistan. Biomarkers were measured at 9 months and tested for association with growth at 24 months. The duodenal methylome and transcriptome were determined in 52 undernourished SEEM participants and 42 North American controls and patients with celiac disease.

RESULTS

After accounting for growth at study entry, circulating insulin-like growth factor-1 (IGF-1) and ferritin predicted linear growth, whereas leptin correlated with future weight gain. The EED transcriptome exhibited suppression of antioxidant, detoxification, and lipid metabolism genes, and induction of anti-microbial response, interferon, and lymphocyte activation genes. Relative to celiac disease, suppression of antioxidant and detoxification genes and induction of antimicrobial response genes were EED-specific. At the epigenetic level, EED showed hyper-methylation of epithelial metabolism and barrier function genes, and hypo-methylation of immune response and cell proliferation genes. Duodenal coexpression modules showed association between lymphocyte proliferation and epithelial metabolic genes and histologic severity, fecal energy loss, and wasting (weight-for-length/height Z < -2.0). Leptin was associated with expression of epithelial carbohydrate metabolism and stem cell renewal genes. Immune response genes were attenuated by giardia colonization.

CONCLUSIONS

Children with reduced circulating IGF-1 are more likely to experience stunting. Leptin and a gene signature for lymphocyte activation and dysregulated lipid metabolism are implicated in wasting, suggesting new approaches for EED refractory to nutritional intervention. ClinicalTrials.gov, Number: NCT03588013. (https://clinicaltrials.gov/ct2/show/NCT03588013).

Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy

Probe-based confocal laser endomicroscopy (pCLE) allows for real-time diagnosis of dysplasia and cancer in Barrett's esophagus (BE) but is limited by low sensitivity. Even the gold standard of histopathology is hindered by poor agreement between pathologists. We deployed deep-learning-based image and video analysis in order to improve diagnostic accuracy of pCLE videos and biopsy images. Blinded experts categorized biopsies and pCLE videos as squamous, non-dysplastic BE, or dysplasia/cancer, and deep learning models were trained to classify the data into these three categories. Biopsy classification was conducted using two distinct approaches-a patch-level model and a whole-slide-image-level model. Gradient-weighted class activation maps (Grad-CAMs) were extracted from pCLE and biopsy models in order to determine tissue structures deemed relevant by the models. 1970 pCLE videos, 897,931 biopsy patches, and 387 whole-slide images were used to train, test, and validate the models. In pCLE analysis, models achieved a high sensitivity for dysplasia (71%) and an overall accuracy of 90% for all classes. For biopsies at the patch level, the model achieved a sensitivity of 72% for dysplasia and an overall accuracy of 90%. The whole-slide-image-level model achieved a sensitivity of 90% for dysplasia and 94% overall accuracy. Grad-CAMs for all models showed activation in medically relevant tissue regions. Our deep learning models achieved high diagnostic accuracy for both pCLE-based and histopathologic diagnosis of esophageal dysplasia and its precursors, similar to human accuracy in prior studies. These machine learning approaches may improve accuracy and efficiency of current screening protocols.

Deep learning systems detect dysplasia with human-like accuracy using histopathology and probe-based confocal laser endomicroscopy

Probe-based confocal laser endomicroscopy (pCLE) allows for real-time diagnosis of dysplasia and cancer in Barrett's esophagus (BE) but is limited by low sensitivity. Even the gold standard of histopathology is hindered by poor agreement between pathologists. We deployed deep-learning-based image and video analysis in order to improve diagnostic accuracy of pCLE videos and biopsy images. Blinded experts categorized biopsies and pCLE videos as squamous, non-dysplastic BE, or dysplasia/cancer, and deep learning models were trained to classify the data into these three categories. Biopsy classification was conducted using two distinct approaches-a patch-level model and a whole-slide-image-level model. Gradient-weighted class activation maps (Grad-CAMs) were extracted from pCLE and biopsy models in order to determine tissue structures deemed relevant by the models. 1970 pCLE videos, 897,931 biopsy patches, and 387 whole-slide images were used to train, test, and validate the models. In pCLE analysis, models achieved a high sensitivity for dysplasia (71%) and an overall accuracy of 90% for all classes. For biopsies at the patch level, the model achieved a sensitivity of 72% for dysplasia and an overall accuracy of 90%. The whole-slide-image-level model achieved a sensitivity of 90% for dysplasia and 94% overall accuracy. Grad-CAMs for all models showed activation in medically relevant tissue regions. Our deep learning models achieved high diagnostic accuracy for both pCLE-based and histopathologic diagnosis of esophageal dysplasia and its precursors, similar to human accuracy in prior studies. These machine learning approaches may improve accuracy and efficiency of current screening protocols.

Advancing Eosinophilic Esophagitis Diagnosis and Phenotype Assessment with Deep Learning Computer Vision

Eosinophilic Esophagitis (EoE) is an inflammatory esophageal disease which is increasing in prevalence. The diagnostic gold-standard involves manual review of a patient's biopsy tissue sample by a clinical pathologist for the presence of 15 or greater eosinophils within a single high-power field (400× magnification). Diagnosing EoE can be a cumbersome process with added difficulty for assessing the severity and progression of disease. We propose an automated approach for quantifying eosinophils using deep image segmentation. A U-Net model and post-processing system are applied to generate eosinophil-based statistics that can diagnose EoE as well as describe disease severity and progression. These statistics are captured in biopsies at the initial EoE diagnosis and are then compared with patient metadata: clinical and treatment phenotypes. The goal is to find linkages that could potentially guide treatment plans for new patients at their initial disease diagnosis. A deep image classification model is further applied to discover features other than eosinophils that can be used to diagnose EoE. This is the first study to utilize a deep learning computer vision approach for EoE diagnosis and to provide an automated process for tracking disease severity and progression.

Self-Attentive Adversarial Stain Normalization

Hematoxylin and Eosin (H&E) stained Whole Slide Images (WSIs) are utilized for biopsy visualization-based diagnostic and prognostic assessment of diseases. Variation in the H&E staining process across different lab sites can lead to significant variations in biopsy image appearance. These variations introduce an undesirable bias when the slides are examined by pathologists or used for training deep learning models. Traditionally proposed stain normalization and color augmentation strategies can handle the human level bias. But deep learning models can easily disentangle the linear transformation used in these approaches, resulting in undesirable bias and lack of generalization. To handle these limitations, we propose a Self-Attentive Adversarial Stain Normalization (SAASN) approach for the normalization of multiple stain appearances to a common domain. This unsupervised generative adversarial approach includes self-attention mechanism for synthesizing images with finer detail while preserving the structural consistency of the biopsy features during translation. SAASN demonstrates consistent and superior performance compared to other popular stain normalization techniques on H&E stained duodenal biopsy image data.

Artificial Intelligence and Its Role in Identifying Esophageal Neoplasia

Randomized trials have demonstrated that ablation of dysplastic Barrett's esophagus can reduce the risk of progression to cancer. Endoscopic resection for early stage esophageal adenocarcinoma and squamous cell carcinoma can significantly reduce postoperative morbidity compared to esophagectomy. Unfortunately, current endoscopic surveillance technologies (e.g., high-definition white light, electronic, and dye-based chromoendoscopy) lack sensitivity at identifying subtle areas of dysplasia and cancer. Random biopsies sample only approximately 5% of the esophageal mucosa at risk, and there is poor agreement among pathologists in identifying low-grade dysplasia. Machine-based deep learning medical image and video assessment technologies have progressed significantly in recent years, enabled in large part by advances in computer processing capabilities. In deep learning, sequential layers allow models to transform input data (e.g., pixels for imaging data) into a composite representation that allows for classification and feature identification. Several publications have attempted to use this technology to help identify dysplasia and early esophageal cancer. The aims of this reviews are as follows: (a) discussing limitations in our current strategies to identify esophageal dysplasia and cancer, (b) explaining the concepts behind deep learning and convolutional neural networks using language appropriate for clinicians without an engineering background, (c) systematically reviewing the literature for studies that have used deep learning to identify esophageal neoplasia, and (d) based on the systemic review, outlining strategies on further work necessary before these technologies are ready for "prime-time," i.e., use in routine clinical care.

Adolescents' knowledge of a peer's non-suicidal self-injury and own non-suicidal self-injury and suicidality

OBJECTIVE

Some research suggests that suicidal ideation and attempt among adolescents may be contagious - that is adolescents who are exposed to peers' suicidal behaviour are more likely to experience suicidal ideation or attempt suicide themselves. Less is known about the potential contagion effect of non-suicidal self-injury (NSSI). Our objective was to determine whether knowledge of a friend's NSSI is associated with adolescent's own non-suicidal self-injury and suicidal behaviours.

METHODS

Data from 1483 youth ages 14-17 years were obtained from the 2014 Ontario Child Health Study, a cross-sectional population-based survey of children and adolescents in Ontario, Canada. Logistic regression models were used to examine associations between knowledge of a friend's NSSI and adolescents' own self-reported self-injurious and suicidal behaviours. Interactions with gender, age group and presence of a mental disorder were investigated.

RESULTS

Knowledge of a friend's non-suicidal self-injury was significantly associated with the adolescent's own non-suicidal self-injury (OR = 2.03, 95% CI 1.05-3.90), suicidal ideation (OR = 3.08, 95% CI 1.50-6.30) and suicide attempt (OR = 2.87, 95% CI 1.20-6.87).

CONCLUSION

These findings suggest an apparent contagion effect for non-suicidal self-injury. Awareness of a friend's self-injurious behaviours is associated with an adolescent's own self-injury and suicidality. Interventions aimed at preventing NSSI and suicidality should consider prevention of possible contagion at the school and/or community level.

Machine learning model demonstrates stunting at birth and systemic inflammatory biomarkers as predictors of subsequent infant growth - a four-year prospective study

BACKGROUND

Stunting affects up to one-third of the children in low-to-middle income countries (LMICs) and has been correlated with decline in cognitive capacity and vaccine immunogenicity. Early identification of infants at risk is critical for early intervention and prevention of morbidity. The aim of this study was to investigate patterns of growth in infants up through 48 months of age to assess whether the growth of infants with stunting eventually improved as well as the potential predictors of growth.

METHODS

Height-for-age z-scores (HAZ) of children from Matiari (rural site, Pakistan) at birth, 18 months, and 48 months were obtained. Results of serum-based biomarkers collected at 6 and 9 months were recorded. A descriptive analysis of the population was followed by assessment of growth predictors via traditional machine learning random forest models.

RESULTS

Of the 107 children who were followed up till 48 months of age, 51% were stunted (HAZ < - 2) at birth which increased to 54% by 48 months of age. Stunting status for the majority of children at 48 months was found to be the same as at 18 months. Most children with large gains started off stunted or severely stunted, while all of those with notably large losses were not stunted at birth. Random forest models identified HAZ at birth as the most important feature in predicting HAZ at 18 months. Of the biomarkers, AGP (Alpha- 1-acid Glycoprotein), CRP (C-Reactive Protein), and IL1 (interleukin-1) were identified as strong subsequent growth predictors across both the classification and regressor models.

CONCLUSION

We demonstrated that children most children with stunting at birth remained stunted at 48 months of age. Value was added for predicting growth outcomes with the use of traditional machine learning random forest models. HAZ at birth was found to be a strong predictor of subsequent growth in infants up through 48 months of age. Biomarkers of systemic inflammation, AGP, CRP, IL1, were also strong predictors of growth outcomes. These findings provide support for continued focus on interventions prenatally, at birth, and early infancy in children at risk for stunting who live in resource-constrained regions of the world.

Semi-Supervised Classification of Noisy, Gigapixel Histology Images

One of the greatest obstacles in the adoption of deep neural networks for new medical applications is that training these models typically require a large amount of manually labeled training samples. In this body of work, we investigate the semi-supervised scenario where one has access to large amounts of unlabeled data and only a few labeled samples. We study the performance of MixMatch and FixMatch-two popular semi-supervised learning methods-on a histology dataset. More specifically, we study these models' impact under a highly noisy and imbalanced setting. The findings here motivate the development of semi-supervised methods to ameliorate problems commonly encountered in medical data applications.

Deep Learning for Whole-Slide Tissue Histopathology Classification: A Comparative Study in the Identification of Dysplastic and Non-Dysplastic Barrett's Esophagus

The gold standard of histopathology for the diagnosis of Barrett's esophagus (BE) is hindered by inter-observer variability among gastrointestinal pathologists. Deep learning-based approaches have shown promising results in the analysis of whole-slide tissue histopathology images (WSIs). We performed a comparative study to elucidate the characteristics and behaviors of different deep learning-based feature representation approaches for the WSI-based diagnosis of diseased esophageal architectures, namely, dysplastic and non-dysplastic BE. The results showed that if appropriate settings are chosen, the unsupervised feature representation approach is capable of extracting more relevant image features from WSIs to classify and locate the precursors of esophageal cancer compared to weakly supervised and fully supervised approaches.

Potential for Standardization and Automation for Pathology and Endoscopy in Inflammatory Bowel Disease

Automated image analysis methods have shown potential for replicating expert interpretation of histology and endoscopy images, which traditionally require highly specialized and experienced reviewers. Inflammatory bowel disease (IBD) diagnosis, severity assessment, and treatment decision-making require multimodal expert data interpretation and integration, which could be significantly aided by applications of machine learning analyses. This review introduces fundamental concepts of machine learning for imaging analysis and highlights research and development of automated histology and endoscopy interpretation in IBD. Proof-of-concept studies strongly suggest that histologic and endoscopic images can be interpreted with similar accuracy as knowledge experts. Encouraging results support the potential of automating existing disease activity scoring instruments with high reproducibility, speed, and accessibility, therefore improving the standardization of IBD assessment. Though challenges surrounding ground truth definitions, technical barriers, and the need for extensive multicenter evaluation must be resolved before clinical implementation, automated image analysis is likely to both improve access to standardized IBD assessment and advance the fundamental concepts of how disease is measured.

Pneumocystis jirovecii Pneumonia in Neurologic Disorders: Is Prophylaxis Necessary?

Background

The incidence of Pneumocystis jirovecii pneumonia (PJP) in patients with underlying neurologic conditions is not well established, and the necessity of PJP prophylaxis for immunocompromised patients with neurologic disorders is uncertain.

Methods

Single-center retrospective analysis of non-HIV PJP patients at a tertiary referral center from 2007 to 2016 to determine the incidence of PJP in patients with primary neurologic disorders.

Results

The study included 142 patients with PJP without HIV. Twenty patients had primary neurologic diagnoses, and 122 had non-neurologic conditions. Associated neurologic diagnoses included brain malignancies (N = 14), myasthenia gravis (MG) (N = 2), myopathy (N = 2), neuromyelitis optica (NMO) (N = 1), and CNS vasculitis (N = 1). Estimated incidences of PJP were 0.7% for patients with NMO and 0.3% for patients with MG for the 10-year study period, whereas 4.6% of patients with NMO and 3.8% of patients with MG were placed on PJP prophylaxis. A survey of 24 neurologists who prescribe immunotherapy or chemotherapy confirmed an infrequent occurrence of PJP in their practice. Malignancy or parenchymal organ failure was present in 90% of neurologic patients with PJP, and coexisting infections occurred in 45%.

Conclusions

The overall incidence of PJP in patients with non-neoplastic neurologic disorders is exceedingly low, raising doubt about the value of routine PJP prophylaxis in neurologic patients outside neuro-oncology. PJP infection occurs frequently in patients with malignancy or parenchymal organ failure, indicating that overall health status may serve as a predisposing factor for PJP.

Celiac Disease Screening for High-Risk Groups: Are We Doing It Right?

Celiac disease (CD) is an immune-mediated enteropathy triggered by dietary ingestion of gluten in genetically susceptible patients. CD is often diagnosed by a "case-finding" approach of symptomatic patients. In recent times, the diagnostic paradigm has shifted to investigate patients who may be asymptomatic, but are at high risk of developing CD due to shared genetic susceptibilities. These high-risk groups include first-degree relatives of CD patients and patients with Type 1 diabetes mellitus, autoimmune thyroid disease, Down's syndrome, and Turner syndrome. Moreover, CD is often diagnosed as the cause of iron deficiency anemia or unexplained chronic diarrhea. Although screening for CD with serological tests is not recommended for the general population, it should be considered in these special populations. In this review, we explore screening for CD among high-risk groups in light of recent research and development in the CD arena.

Time to regain birth weight predicts neonatal growth velocity: A single-center experience

BACKGROUND

Failure to Thrive (FTT) describes the development of an inappropriate pattern of growth, generally secondary to inadequate nutritional intake, and is associated with several negative outcomes. We describe key features among neonates with FTT as well as the variables that predicted their growth after birth at a Neonatal Intensive Care Unit.

METHODS

A retrospective single center study of 340 patients grouped into FTT (n = 100) and non-FTT (n = 240) was conducted. FTT was defined as having a weight <10th percentile on the Fenton 2013 curve at the time of discharge. For analyzing growth velocity, 204 patients were grouped into 4 quartiles based on their calculated growth velocity (grams/kilograms/day [g/kg/day]; 4th quartile had the highest velocity). Multivariate regression models were used to identify predictors of growth velocity.

RESULTS

When comparing FTT vs. non-FTT patients, lower birth weights (1897.9 ± 561.4 vs. 2445.9 ± 783.0 g, t_(255.1) = -7.2, p < 0.001) and higher growth velocities (9.2 ± 3.9 vs. 8.0 ± 4.1 g/kg/day, t_(153.6) = 2.2, p = 0.03) were noted. Among patients with higher growth velocities, birth weights were lower (1st to 4th quartiles: 2474.0 ± 677.0, 2000.0 ± 297.0, 1715.0 ± 285.0, 1533.0 ± 332.0 g, F_{(3, 200)} = 46.5, p < 0.001, adjusted R² = 0.4). Days to regain birth weight was the most consistent predictor of growth velocity in our overall patient sample (β [SE] = -0.3 [0.03], p < 0.001) and in the lowest growth velocity quartile subgroup (β [SE] = -0.3 [0.04], p < 0.001).

CONCLUSIONS

Days to regain birth weight was consistently the strongest predictor of neonatal growth velocity along with difference in gender positive predicting growth velocity in the total sample. This highlights the importance of the first week of life in growth pattern establishment.

How close is the axillary nerve to the inferior glenoid? A magnetic resonance study of normal and arthritic shoulders

INTRODUCTION

Axillary nerve injury is a major complication of shoulder surgery during glenoid exposure. The aim of this study was to measure the mean distance between the inferior glenoid and the axillary nerve in healthy shoulders and then to compare this distance between osteoarthritic and rotator cuff deficient glenohumeral joints.

METHODS

The magnetic resonance images of 50 patients with normal glenohumeral joints were reviewed. The infra-glenoid tubercle was determined as a fixed point and the distance to the axillary nerve was measured. Two separate assessors measured on the same sagittal sections. With a study power of 80%, the sample needed in each comparison group was 28 patients. Measurements were then performed on scans in patients with osteoarthritis and cuff tear arthropathy. The mean distance was compared between groups.

RESULTS

The mean distance between the infra-glenoid tubercle and axillary nerve was 12mm (standard deviation, SD, 5.6mm) in normal shoulders, 10.6mm (SD 5.4mm) in shoulders with osteoarthritis and 9.7mm (SD 3.7mm) in those with cuff tear arthropathy. For this sample size of 50 patients with a confidence interval of 95%, the mean range is 12mm (95% CI 10.4-13.6). A comparison between normal shoulder and osteoarthritis showed a p-value of 0.3, and between normal and cuff tear arthropathy a p-value of 0.06. This was not statistically significant.

CONCLUSIONS

The axillary nerve lies on average 12mm from the infra-glenoid tubercle. The presence of inferior osteophytes in glenohumeral osteoarthritis and the proximal migration of humeral head in cuff tear arthropathy does not seem to alter the course of the nerve significantly in relation to the inferior glenoid tubercle.

HMIC: Hierarchical Medical Image Classification, A Deep Learning Approach

Image classification is central to the big data revolution in medicine. Improved information processing methods for diagnosis and classification of digital medical images have shown to be successful via deep learning approaches. As this field is explored, there are limitations to the performance of traditional supervised classifiers. This paper outlines an approach that is different from the current medical image classification tasks that view the issue as multi-class classification. We performed a hierarchical classification using our Hierarchical Medical Image classification (HMIC) approach. HMIC uses stacks of deep learning models to give particular comprehension at each level of the clinical picture hierarchy. For testing our performance, we use biopsy of the small bowel images that contain three categories in the parent level (Celiac Disease, Environmental Enteropathy, and histologically normal controls). For the child level, Celiac Disease Severity is classified into 4 classes (I, IIIa, IIIb, and IIIC).