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.     

Echophonocardiography in patients undergoing percutaneous mitral balloon valvotomy (PMV): the learning curve of PMV

Percutaneous mitral balloon valvotomy (PMV) was performed in 10 female patients with mitral stenosis; their mean age was 31 +/- 1 years. All patients underwent echophonocardiography (Echophono) before and less than 24 hours after PMV1. Cardiac catheterization and Echophono were repeated 10 and 22 months after PMV1. Eight patients with suboptimal results (defined as a post-PMV mitral valve area [MVA]/less than 1.0 cm2 and mean gradient greater than/10 mm Hg) underwent repeat PMV (PMV2) 10 months after PMV1. The Echophono data are correlated with clinical and hemodynamic changes produced by PMV1 and PMV2. MVA increased from 0.6 +/- 0.1 to 1.1 +/- 0.01 cm2 (p = 0.0009) when PMV1 was performed with a mean effective balloon dilating area (EBDA) of 5 +/- 0.19 cm2. MVA increased from 1.0 +/- 0.1 to 1.7 +/- 0.2 cm2 (p = 0.0002) when PMV2 was performed with larger EBDA (6.4 +/- 0.34 cm2). Two factors related to the learning curve account for the superior result of PMV2: (1) use of larger EBDA and (2) optimal position of the balloons parallel to the long axis of the left ventricle. PMV1 resulted in Echophono changes consistent with decreased severity of mitral stenosis: shortening of Q-S1 from 93 +/- 4 to 82 +/- 4 msec (p less than 0.05) and (Q-S1)-(S2-OS) from 1.8 +/- 0.8 to -0.9 +/- 0.6 (p less than 0.01); prolongation of S2-OS from 75 +/- 5 to 91 +/- 5 msec (p less than 0.05) and increase of EF slope from 7 +/- 1 to 17 +/- 4 mm/sec (p less than 0.05). Compared with PMV1, post PMV2 Echophono showed a further decrease in the severity of mitral stenosis: Q-S1 decreased to 78 +/- 3 msec and (Q-S1)-(S2-OS) decreased to -0.5 +/- 0.3 msec. S2-OS increased to 86 +/- 5 msec and EF slope increased to 22 +/- 4 mm/sec. The hemodynamic and Echophono changes produced by PMV1 and PMV2 persisted at the corresponding follow-up studies. There was no evidence of restenosis. Thus Echophono is a simple, low cost method helpful in the evaluation and follow-up of patients undergoing PMV.     

Effects on the buoyant density of rabbit platelets of ADP and agents that increase the concentration of cyclic AMP

Rabbit platelets were aggregated by adenosine diphosphate (ADP), allowed to deaggregate and then separated into density subpopulations by centrifugation through discontinuous Stractan density gradients. Although ADP causes little or no release of the contents of the amine storage granules of rabbit platelets, ADP caused a decrease in platelet density as compared with control platelets subjected to the same procedures except for exposure to ADP. The density change persisted for at least four hours. The apparent size of platelets stimulated with ADP increased initially, but returned to control values during a one-hour period. A similar decrease in platelet density was observed with an albumin density gradient. Under conditions in which aggregation did not occur in response to ADP with ethylenediaminetetraacetic acid (EDTA) in the medium, little or no decrease in platelet density was observed. Agglutination with polylysine did not change platelet density. Thus, not only agents such as thrombin and plasmin that cause the release of the contents of the platelet granules decrease platelet density, but ADP also has this effect. Platelets would be exposed to all of these stimuli during thromboembolic processes, and their effect on platelets may account for the decrease in platelet density observed previously in experiments with rabbits with indwelling aortic catheters. Agents that increase the concentration of cyclic AMP (cAMP) in platelets (PGE1, adenosine, dibutyryl cAMP, forskolin, and papaverine) also decreased platelet density. This effect persisted when the platelets were washed and resuspended in fresh medium and was also demonstrable in plasma. Platelet size was gradually increased by prostaglandin E1 (PGE1) which maintains platelets in a disc shape and does not cause the release of granule contents, indicating that the decrease in platelet density caused by PGE1 may be attributable to platelet swelling.     

Dementia in Down’s syndrome: an MRI comparison with Alzheimer’s disease in the general population

Background

Down’s syndrome (DS) is the most common genetic cause of intellectual disability. People with DS are at an increased risk of Alzheimer’s disease (AD) compared to the general population. Neuroimaging studies of AD have focused on medial temporal structures; however, to our knowledge, no in vivo case–control study exists comparing the anatomy of dementia in DS to people with AD in the general population. We therefore compared the in vivo brain anatomy of people with DS and dementia (DS+) to those with AD in the general population.

Method

Using MRI in 192 adults, we compared the volume of whole brain matter, lateral ventricles, temporal lobes and hippocampus in DS subjects with and without dementia (DS+, DS-), to each other and to three non-DS groups. These included one group of individuals with AD and two groups of controls (each age-matched for their respective DS and general population AD cohorts).

Results

AD and DS+ subjects showed significant reductions in the volume of the whole brain, hippocampus and temporal lobes and a significant elevation in the volume of the lateral ventricle, compared to their non-demented counterparts. People with DS+ had a smaller reduction in temporal lobe volume compared to individuals with AD.

Conclusions

DS+ and AD subjects have a significant reduction in volume of the same brain regions. We found preliminary evidence that DS individuals may be more sensitive to tissue loss than others and have less ‘cognitive reserve’.     

Nodding syndrome in Mundri county,South Sudan: environmental,nutritional and infectious factors

Background

Nodding Syndrome is a seizure disorder of children in Mundri County, Western Equatoria, South Sudan. The disorder is reported to be spreading in South Sudan and northern Uganda.

Objective

To describe environmental, nutritional, infectious, and other factors that existed before and during the de novo 1991 appearance and subsequent increase in cases through 2001.

Methods

Household surveys, informant interviews, and case-control studies conducted in Lui town and Amadi village in 2001–2002 were supplemented in 2012 by informant interviews in Lui and Juba, South Sudan.

Results

Nodding Syndrome was associated with Onchocerca volvulus and Mansonella perstans infections, with food use of a variety of sorghum (serena) introduced as part of an emergency relief program, and was inversely associated with a history of measles infection. There was no evidence to suggest exposure to a manmade neurotoxic pollutant or chemical agent, other than chemically dressed seed intended for planting but used for food. Food use of cyanogenic plants was documented, and exposure to fungal contaminants could not be excluded.

Conclusion

Nodding Syndrome in South Sudan has an unknown etiology. Further research is recommended on the association of Nodding Syndrome with onchocerciasis/mansonelliasis and neurotoxins in plant materials used for food.