Artificial Intelligence Applied to Gastrointestinal Diagnostics: A Review.

Artificial intelligence (AI), a discipline encompassed by data science, has seen recent rapid growth in its application to healthcare and beyond, and is now an integral part of daily life. Uses of AI in gastroenterology include the automated detection of disease and differentiation of pathology subtypes and disease severity. Although a majority of AI research in gastroenterology focuses on adult applications, there are a number of pediatric pathologies that could benefit from more research. As new and improved diagnostic tools become available and more information is retrieved from them, AI could provide physicians a method to distill enormous amounts of data into enhanced decision-making and cost saving for children with digestive disorders. This review provides a broad overview of AI and examples of its possible applications in pediatric gastroenterology.

Study of Environmental Enteropathy and Malnutrition (SEEM) in Pakistan: protocols for biopsy based biomarker discovery and validation.

BACKGROUND: Environmental Enteropathy (EE), characterized by alterations in intestinal structure, function, and immune activation, is believed to be an important contributor to childhood undernutrition and its associated morbidities, including stunting. Half of all global deaths in children < 5 years are attributable to under-nutrition, making the study of EE an area of critical priority. METHODS: Community based intervention study, divided into two sub-studies, 1) Longitudinal analyses and 2) Biopsy studies for identification of EE features via omics analyses. Birth cohorts in Matiari, Pakistan established: moderately or severely malnourished (weight for height Z score (WHZ) < - 2) children, and well-nourished (WHZ > 0) children. Blood, urine, and fecal samples, for evaluation of potential biomarkers, will be collected at various time points from all participants (longitudinal analyses). Participants will receive appropriate educational and nutritional interventions; non-responders will undergo further evaluation to determine eligibility for further workup, including upper gastrointestinal endoscopy. Histopathological changes in duodenal biopsies will be compared with duodenal biopsies obtained from USA controls who have celiac disease, Crohn's disease, or who were found to have normal histopathology. RNA-Seq will be employed to characterize mucosal gene expression across groups. Duodenal biopsies, luminal aspirates from the duodenum, and fecal samples will be analyzed to define microbial community composition (omic analyses). The relationship between histopathology, mucosal gene expression, and community configuration will be assessed using a variety of bioinformatic tools to gain better understanding of disease pathogenesis and to identify mechanism-based biomarkers. Ethical review committees at all collaborating institutions have approved this study. All results will be made available to the scientific community. DISCUSSION: Operational and ethical constraints for safely obtaining intestinal biopsies from children in resource-poor settings have led to a paucity of human tissue-based investigations to understand and reverse EE in vulnerable populations. Furthermore, EE biomarkers have rarely been correlated with gold standard histopathological confirmation. The Study of Environmental Enteropathy and Malnutrition (SEEM) is designed to better understand the pathophysiology, predictors, biomarkers, and potential management strategies of EE to inform strategies to eradicate this debilitating pathology and accelerate progress towards the 2030 Sustainable Development Goals. TRIAL REGISTRATION: Retrospectively registered; clinicaltrials.gov ID NCT03588013 .

Single Ventricular Assist Device Care and Outcomes for Failed Stage I Palliation: A Single-Center Decade of Experience.

Single ventricular assist device (SVAD) use before and after stage I palliation (S1P) is increasing with limited data on outcomes. To address this knowledge gap, we conducted a single-center retrospective review to assess pre- and post-SVAD clinical status, complications, and outcomes. We leveraged a granular, longitudinal, local database that captures end-organ support, procedural interventions, hematologic events, laboratory data, and antithrombotic strategy. We identified 25 patients between 2013 and 2023 implanted at median age of 53 days (interquartile range [IQR] = 16-130); 80% had systemic right ventricles and underwent S1P. Median SVAD days were 54 (IQR = 29-86), and 40% were implanted directly from ECMO. Compared to preimplant, there was a significant reduction in inotrope use ( p = 0.013) and improved weight gain ( p = 0.008) post-SVAD. Complications were frequent including bleeding (80%), stroke (40%), acute kidney injury (AKI) (40%), infection (36%), and unanticipated catheterization (56%). Patients with in-hospital mortality had significantly more bleeding complications ( p = 0.02) and were more likely to have had Blalock-Thomas-Taussig shunts pre-SVAD ( p = 0.028). Survival to 1 year postexplant was 40% and included three recovered and explanted patients. At 1 year posttransplant, all survivors have technology dependence or neurologic injury. This study highlights the clinical outcomes and ongoing support required for successful SVAD use in failed single-ventricle physiology before or after S1P.

Accuracy of STOP-Bang Questionnaire in Predicting Difficult Mask Ventilation: An Observational Study.

Introduction Difficulty with bag-mask ventilation after the induction of general anesthesia and muscle relaxation places the patient at risk for a prolonged period of apnea and hypoxia and thus, at an increased risk of morbidity and mortality. This study was designed to assess the accuracy of the STOP-Bang questionnaire in predicting difficult mask ventilation (DMV) in patients receiving general anesthesia for elective surgical procedures. Methods It was a prospective cross-sectional, observational study conducted at a university teaching hospital. A total of 530 patients undergoing surgery under general anesthesia with endotracheal intubation were enrolled. STOP-Bang questionnaire was filled at pre-operative anesthesia assessment. Ease or difficulty of mask ventilation was assessed and documented by a senior resident responsible for intraoperative anesthetic management. Results Out of 530 patients, 139 (26.22%) had a STOP-Bang score of ≥ 3, of whom 55 (39.5%) were found to have DMV. Out of 391 patients with a STOP-Bang score of < 3, only 29 patients (7.5%) had DMV (P ≤0.001). Snoring, high blood pressure, BMI more than 35 kg/m2, age more than 50 years, neck circumference more than 40 cm, and male gender were significantly associated with DMV. The accuracy of the STOP-Bang questionnaire in predicting difficult mask ventilation was 78.68% (95% CI 74.99-81.95) with a negative predictive value of 92.58%. The sensitivity and specificity were found to be 65.48% and 81.17% respectively. Conclusion STOP-Bang score has a high negative predictive value and can be very useful in ruling out the possibility of difficult mask ventilation.

Diagnosis of Celiac Disease and Environmental Enteropathy on Biopsy Images Using Color Balancing on Convolutional Neural Networks.

Celiac Disease (CD) and Environmental Enteropathy (EE) are common causes of malnutrition and adversely impact normal childhood development. CD is an autoimmune disorder that is prevalent worldwide and is caused by an increased sensitivity to gluten. Gluten exposure destructs the small intestinal epithelial barrier, resulting in nutrient mal-absorption and childhood under-nutrition. EE also results in barrier dysfunction but is thought to be caused by an increased vulnerability to infections. EE has been implicated as the predominant cause of under-nutrition, oral vaccine failure, and impaired cognitive development in low-and-middle-income countries. Both conditions require a tissue biopsy for diagnosis, and a major challenge of interpreting clinical biopsy images to differentiate between these gastrointestinal diseases is striking histopathologic overlap between them. In the current study, we propose a convolutional neural network (CNN) to classify duodenal biopsy images from subjects with CD, EE, and healthy controls. We evaluated the performance of our proposed model using a large cohort containing 1000 biopsy images. Our evaluations show that the proposed model achieves an area under ROC of 0.99, 1.00, and 0.97 for CD, EE, and healthy controls, respectively. These results demonstrate the discriminative power of the proposed model in duodenal biopsies classification.

Cholestasis affects enteral tolerance and prospective weight gain in the NICU.

BACKGROUND: Intestinal Failure-Associated Liver Disease is characterized by cholestasis and hepatic dysfunction due to parenteral nutrition (PN) therapy. We described key features of cholestatic infants receiving PN to assess overall outcomes in this population at our institution. METHODS: This is a retrospective single center study of 163 neonates grouped into cholestatic (n = 63) and non-cholestatic (n = 100) as defined by peak conjugated bilirubin of ≥2.0 mg/dL or < 0.8 mg/dL, respectively. Univariate and multiple regression models were used to study associations between variables and outcomes of interest. RESULTS: Lower Apgar scores (4 ± 3 vs. 6 ± 3, p-value = <0.005 at 1 min; 6 ± 2 vs. 7 ± 2, p < 0.005 at 5 min) and lower birth weight (adj ß [SE] = 0.62 [0.27], p-value = 0.024) were risk factors for developing cholestasis. Cholestatic infants were more likely to have had gastrointestinal surgery (31 [49%] vs. 15 [15%], p-value <0.005), received PN for a longer duration (40 ± 39 days vs. 11 ± 7 days, p-value <0.005), and started enteral feeds later in life (86 ± 23 days vs. 79 ± 20 days, p-value <0.005) when compared to non-cholestatic infants. Weight percentiles in cholestatic infants were lower both at hospital discharge (14 ± 19 vs. 24 ± 22, p-value <0.005) and at 6 months of age (24 ± 28 vs. 36 ± 31, p-value = 0.05). CONCLUSIONS: Cholestasis in the NICU is a multifactorial process, but it has a long lasting effect on prospective weight gain in infants who receive PN in the NICU. This finding highlights the importance of follow-up for adequate growth and the potential benefit from aggressive nutritional support.

Assessment of Machine Learning Detection of Environmental Enteropathy and Celiac Disease in Children.

Importance: Duodenal biopsies from children with enteropathies associated with undernutrition, such as environmental enteropathy (EE) and celiac disease (CD), display significant histopathological overlap. Objective: To develop a convolutional neural network (CNN) to enhance the detection of pathologic morphological features in diseased vs healthy duodenal tissue. Design, Setting, and Participants: In this prospective diagnostic study, a CNN consisting of 4 convolutions, 1 fully connected layer, and 1 softmax layer was trained on duodenal biopsy images. Data were provided by 3 sites: Aga Khan University Hospital, Karachi, Pakistan; University Teaching Hospital, Lusaka, Zambia; and University of Virginia, Charlottesville. Duodenal biopsy slides from 102 children (10 with EE from Aga Khan University Hospital, 16 with EE from University Teaching Hospital, 34 with CD from University of Virginia, and 42 with no disease from University of Virginia) were converted into 3118 images. The CNN was designed and analyzed at the University of Virginia. The data were collected, prepared, and analyzed between November 2017 and February 2018. Main Outcomes and Measures: Classification accuracy of the CNN per image and per case and incorrect classification rate identified by aggregated 10-fold cross-validation confusion/error matrices of CNN models. Results: Overall, 102 children participated in this study, with a median (interquartile range) age of 31.0 (20.3-75.5) months and a roughly equal sex distribution, with 53 boys (51.9%). The model demonstrated 93.4% case-detection accuracy and had a false-negative rate of 2.4%. Confusion metrics indicated most incorrect classifications were between patients with CD and healthy patients. Feature map activations were visualized and learned distinctive patterns, including microlevel features in duodenal tissues, such as alterations in secretory cell populations. Conclusions and Relevance: A machine learning-based histopathological analysis model demonstrating 93.4% classification accuracy was developed for identifying and differentiating between duodenal biopsies from children with EE and CD. The combination of the CNN with a deconvolutional network enabled feature recognition and highlighted secretory cells' role in the model's ability to differentiate between these histologically similar diseases.