Artificial intelligence in gastroenterology: A state-of-the-art review.

The development of artificial intelligence (AI) has increased dramatically in the last 20 years, with clinical applications progressively being explored for most of the medical specialties. The field of gastroenterology and hepatology, substantially reliant on vast amounts of imaging studies, is not an exception. The clinical applications of AI systems in this field include the identification of premalignant or malignant lesions (e.g., identification of dysplasia or esophageal adenocarcinoma in Barrett's esophagus, pancreatic malignancies), detection of lesions (e.g., polyp identification and classification, small-bowel bleeding lesion on capsule endoscopy, pancreatic cystic lesions), development of objective scoring systems for risk stratification, predicting disease prognosis or treatment response [e.g., determining survival in patients post-resection of hepatocellular carcinoma), determining which patients with inflammatory bowel disease (IBD) will benefit from biologic therapy], or evaluation of metrics such as bowel preparation score or quality of endoscopic examination. The objective of this comprehensive review is to analyze the available AI-related studies pertaining to the entirety of the gastrointestinal tract, including the upper, middle and lower tracts; IBD; the hepatobiliary system; and the pancreas, discussing the findings and clinical applications, as well as outlining the current limitations and future directions in this field.

Retrospective cohort study of clinical characteristics of 2199 hospitalised patients with COVID-19 in New York City.

OBJECTIVE: The COVID-19 pandemic is a global public health crisis, with over 33 million cases and 999 000 deaths worldwide. Data are needed regarding the clinical course of hospitalised patients, particularly in the USA. We aimed to compare clinical characteristic of patients with COVID-19 who had in-hospital mortality with those who were discharged alive. DESIGN: Demographic, clinical and outcomes data for patients admitted to five Mount Sinai Health System hospitals with confirmed COVID-19 between 27 February and 2 April 2020 were identified through institutional electronic health records. We performed a retrospective comparative analysis of patients who had in-hospital mortality or were discharged alive. SETTING: All patients were admitted to the Mount Sinai Health System, a large quaternary care urban hospital system. PARTICIPANTS: Participants over the age of 18 years were included. PRIMARY OUTCOMES: We investigated in-hospital mortality during the study period. RESULTS: A total of 2199 patients with COVID-19 were hospitalised during the study period. As of 2 April, 1121 (51%) patients remained hospitalised, and 1078 (49%) completed their hospital course. Of the latter, the overall mortality was 29%, and 36% required intensive care. The median age was 65 years overall and 75 years in those who died. Pre-existing conditions were present in 65% of those who died and 46% of those discharged. In those who died, the admission median lymphocyte percentage was 11.7%, D-dimer was 2.4 µg/mL, C reactive protein was 162 mg/L and procalcitonin was 0.44 ng/mL. In those discharged, the admission median lymphocyte percentage was 16.6%, D-dimer was 0.93 µg/mL, C reactive protein was 79 mg/L and procalcitonin was 0.09 ng/mL. CONCLUSIONS: In our cohort of hospitalised patients, requirement of intensive care and mortality were high. Patients who died typically had more pre-existing conditions and greater perturbations in inflammatory markers as compared with those who were discharged.

Molecular Imaging of Apoptosis in Atherosclerosis by Targeting Cell Membrane Phospholipid Asymmetry.

BACKGROUND: Apoptosis in atherosclerotic lesions contributes to plaque vulnerability by lipid core enlargement and fibrous cap attenuation. Apoptosis is associated with exteriorization of phosphatidylserine (PS) and phosphatidylethanolamine (PE) on the cell membrane. Although PS-avid radiolabeled annexin-V has been employed for molecular imaging of high-risk plaques, PE-targeted imaging in atherosclerosis has not been studied. OBJECTIVES: This study sought to evaluate the feasibility of molecular imaging with PE-avid radiolabeled duramycin in experimental atherosclerotic lesions in a rabbit model and compare duramycin targeting with radiolabeled annexin-V. METHODS: Of the 27 rabbits, 21 were fed high-cholesterol, high-fat diet for 16 weeks. Nine of the 21 rabbits received 99mTc-duramycin (test group), 6 received 99mTc-linear duramycin (duramycin without PE-binding capability, negative radiotracer control group), and 6 received 99mTc-annexin-V for radionuclide imaging. The remaining normal chow-fed 6 animals (disease control group) received 99mTc-duramycin. In vivo microSPECT/microCT imaging was performed, and the aortas were explanted for ex vivo imaging and for histological characterization of atherosclerosis. RESULTS: A significantly higher duramycin uptake was observed in the test group compared with that of disease control and negative radiotracer control animals; duramycin uptake was also significantly higher than the annexin-V uptake. Quantitative duramycin uptake, represented as the square root of percent injected dose per cm (√ID/cm) of abdominal aorta was >2-fold higher in atherosclerotic lesions in test group (0.08 ± 0.01%) than in comparable regions of disease control animals (0.039 ± 0.0061%, p = 3.70·10-8). Mean annexin uptake (0.060 ± 0.010%) was significantly lower than duramycin (p = 0.001). Duramycin uptake corresponded to the lesion severity and macrophage burden. The radiation burden to the kidneys was substantially lower with duramycin (0.49% ID/g) than annexin (5.48% ID/g; p = 4.00·10-4). CONCLUSIONS: Radiolabeled duramycin localizes in lipid-rich areas with high concentration of apoptotic macrophages in the experimental atherosclerosis model. Duramycin uptake in atherosclerotic lesions was significantly greater than annexin-V uptake and produced significantly lower radiation burden to nontarget organs.

Clinical features and prognosis of patients with spontaneous coronary artery dissection.

There have been inconsistent reports regarding the clinical features and characteristics of patients diagnosed with spontaneous coronary artery dissection (SCAD). In addition, predictors of mortality in SCAD patients are unknown. We evaluated the prevalence, clinical characteristics, medical management, and predictors of in-hospital mortality of SCAD-related hospitalizations using data from a single health care system from January 1, 2008, to December 31, 2018. Among 30,425 patients who presented with an acute coronary syndrome, 375 (1.2%) patients were diagnosed with SCAD. Of these, the mean age was 52.2 ± 12.8 years, 64.3% were women, and 44% were white. SCAD was significantly associated with emotional stress, fibromuscular dysplasia (FMD), chronic kidney disease (CKD), chronic obstructive pulmonary disease (COPD), peripheral artery disease (PAD), and carotid artery disease compared with non-SCAD acute coronary syndrome (all p-values < 0.05). Multivariable analysis showed that atrial fibrillation (OR 2.56; 95% CI 1.01-6.23; p = 0.04), steroid use (OR 7.11; 95% CI 1.31-31.2; p = 0.01), ventricular arrhythmias (OR 4.53; 95% CI 1.58-12.3; p = 0.003), and cardiac arrest (OR 16.82; 95% CI 5.14-56.5; p < 0.001) were independent predictors of in-hospital mortality in SCAD patients. In conclusion, SCAD is an uncommon diagnosis that should be considered across all ages and both sexes and in patients with FMD, carotid artery disease, or PAD. Cardiac arrest, ventricular arrhythmia, steroid use, and atrial fibrillation were independently associated with in-hospital mortality in patients with SCAD.

Prevalence, Presentation, and Associated Conditions of Patients With Fibromuscular Dysplasia.

Fibromuscular dysplasia (FMD) is defined by focal narrowing of small and medium-sized arteries due to an idiopathic, noninflammatory, nonatherosclerotic vascular disease. The population-based prevalence of FMD remains unknown. Using the National Inpatient Sample database, we evaluated the prevalence, clinical presentation, mortality, and associated conditions of FMD from January 1, 2004, to September 30, 2015. Among 2,420 patients who presented with FMD, 2,086 (86.20%) of patients were female. The mean age was 55.18 ± 18.99 years in men and 63.37 ± 17.10 years in women. FMD patients most commonly presented with hypertension (67.3%), transient ischemic attack (3.7%), headache (2.1%), dizziness (1.1%), abdominal pain (0.6%), or hematuria (0.3%). In-hospital mortality of FMD patients was 0.74%. In conclusion, FMD is a rare condition with low in-hospital mortality that may be considered among female patients presenting with hypertension.

Conditions and Factors Associated With Spontaneous Coronary Artery Dissection (from a National Population-Based Cohort Study).

The pathophysiology of spontaneous coronary artery dissection (SCAD) is heterogeneous, associated with systemic arteriopathies and inflammatory diseases, and often compounded by environmental precipitants, genetics, or stressors. However, the frequency of these associated conditions with SCAD on a population level remains unknown. Therefore, the objective of this analysis was to evaluate heterogeneous phenotypes of SCAD in the United States using data from the Nationwide Inpatient Sample collected from January 1, 2004, to September 31, 2015. Among 66,360 patients diagnosed with SCAD, the mean age was 63.1 ± 13.2 years and 44.2% were women. A total of 3,415 (5.14%) had depression, 670 (1.0%) had rheumatoid arthritis, 640 (0.96%) had anxiety, 545 (0.82%) had a migraine disorder, 440 (0.66%) used steroids, 385 (0.58%) had malignant hypertension, 280 (0.42%) had systemic lupus erythematosus, 250 (0.38%) had cocaine abuse, 215 (0.32%) had hypertensive heart or renal disease, 130 (0.19%) had coronary spasm, 105 (0.16%) had fibromuscular dysplasia, 85 (0.13%) had Crohn's disease, 75 (0.11%) had celiac disease, 60 (0.09%) had adult autosomal dominant polycystic kidney disease, 60 (0.09%) had hormone replacement therapy, 55 (0.08%) had sarcoidosis, 55 (0.08%) had amphetamine abuse, 15 (0.02%) had granulomatosis polyangiitis, 10 (0.02%) had α1-antitrypsin deficiency, 10 (0.02%) had Marfan syndrome, 10 (0.02%) had Ehlers-Danlos syndrome, 10 (0.02%) had Kawasaki disease, 10 (0.02%) had polyarteritis nodosa, and 5 (0.01%) had multiparity. In conclusion, most cases of SCAD had no apparent concomitant arteriopathy, inflammatory disorder, or evident risk factor.

Systematic analyses of drugs and disease indications in RepurposeDB reveal pharmacological, biological and epidemiological factors influencing drug repositioning.

Increase in global population and growing disease burden due to the emergence of infectious diseases (Zika virus), multidrug-resistant pathogens, drug-resistant cancers (cisplatin-resistant ovarian cancer) and chronic diseases (arterial hypertension) necessitate effective therapies to improve health outcomes. However, the rapid increase in drug development cost demands innovative and sustainable drug discovery approaches. Drug repositioning, the discovery of new or improved therapies by reevaluation of approved or investigational compounds, solves a significant gap in the public health setting and improves the productivity of drug development. As the number of drug repurposing investigations increases, a new opportunity has emerged to understand factors driving drug repositioning through systematic analyses of drugs, drug targets and associated disease indications. However, such analyses have so far been hampered by the lack of a centralized knowledgebase, benchmarking data sets and reporting standards. To address these knowledge and clinical needs, here, we present RepurposeDB, a collection of repurposed drugs, drug targets and diseases, which was assembled, indexed and annotated from public data. RepurposeDB combines information on 253 drugs [small molecules (74.30%) and protein drugs (25.29%)] and 1125 diseases. Using RepurposeDB data, we identified pharmacological (chemical descriptors, physicochemical features and absorption, distribution, metabolism, excretion and toxicity properties), biological (protein domains, functional process, molecular mechanisms and pathway cross talks) and epidemiological (shared genetic architectures, disease comorbidities and clinical phenotype similarities) factors mediating drug repositioning. Collectively, RepurposeDB is developed as the reference database for drug repositioning investigations. The pharmacological, biological and epidemiological principles of drug repositioning identified from the meta-analyses could augment therapeutic development.

Enabling Precision Cardiology Through Multiscale Biology and Systems Medicine.

The traditional paradigm of cardiovascular disease research derives insight from large-scale, broadly inclusive clinical studies of well-characterized pathologies. These insights are then put into practice according to standardized clinical guidelines. However, stagnation in the development of new cardiovascular therapies and variability in therapeutic response implies that this paradigm is insufficient for reducing the cardiovascular disease burden. In this state-of-the-art review, we examine 3 interconnected ideas we put forth as key concepts for enabling a transition to precision cardiology: 1) precision characterization of cardiovascular disease with machine learning methods; 2) the application of network models of disease to embrace disease complexity; and 3) using insights from the previous 2 ideas to enable pharmacology and polypharmacology systems for more precise drug-to-patient matching and patient-disease stratification. We conclude by exploring the challenges of applying a precision approach to cardiology, which arise from a deficit of the required resources and infrastructure, and emerging evidence for the clinical effectiveness of this nascent approach.