Ischemic heart disease, factor predisposing to Barrett’s adenocarcinoma: A case control study

Tsibouris, Panagiotis; Hendrickse, Mark T.; Mavrogianni, Panagiota; Isaacs, Peter Et

doi:10.4292/wjgpt.v5.i3.183

Cited by 2 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Patient Summary, Jane saw that the group is associated with hypertension and diseases of oesophagus. It has been reported that there might be relationship between heart disease (e.g., ischaemic heart disease) and diseases of oesophagus (e.g., Barrett's esophagus) [78]. The group also showed high contribution scores of bilirubin, suspected as a predictive marker of pulmonary arterial hypertension [77].…”

Section: Case Study: Patients With Heart Failurementioning

confidence: 97%

RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

Kwon

Choi

Kim

et al. 2019

IEEE Trans. Visual. Comput. Graphics

233

141

View full text Add to dashboard Cite

We have recently seen many successful applications of recurrent neural networks (RNNs) on electronic medical records (EMRs), which contain histories of patients' diagnoses, medications, and other various events, in order to predict the current and future states of patients. Despite the strong performance of RNNs, it is often challenging for users to understand why the model makes a particular prediction. Such black-box nature of RNNs can impede its wide adoption in clinical practice. Furthermore, we have no established methods to interactively leverage users' domain expertise and prior knowledge as inputs for steering the model. Therefore, our design study aims to provide a visual analytics solution to increase interpretability and interactivity of RNNs via a joint effort of medical experts, artificial intelligence scientists, and visual analytics researchers. Following the iterative design process between the experts, we design, implement, and evaluate a visual analytics tool called RetainVis, which couples a newly improved, interpretable, and interactive RNN-based model called RetainEX and visualizations for users' exploration of EMR data in the context of prediction tasks. Our study shows the effective use of RetainVis for gaining insights into how individual medical codes contribute to making risk predictions, using EMRs of patients with heart failure and cataract symptoms. Our study also demonstrates how we made substantial changes to the state-of-the-art RNN model called RETAIN in order to make use of temporal information and increase interactivity. This study will provide a useful guideline for researchers that aim to design an interpretable and interactive visual analytics tool for RNNs.

show abstract

Section: Case Study: Patients With Heart Failurementioning

confidence: 97%

RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

Kwon

Choi

Kim

et al. 2019

IEEE Trans. Visual. Comput. Graphics

233

141

View full text Add to dashboard Cite

show abstract

“…Today, data concerning BE patients with ischemic heart disease are scarce. We have reported that low-dose aspirin could reduce the risk of EAC in BE patients with ischemic heart disease, but it had no beneficial effect in patients without cardiovascular co-morbidities [53] , possibly due to cofactors common to the etiology of ischemic heart disease and EAC, such as alcohol, tobacco, diet and exercise.…”

Section: Nsaids and Eac Chemopreventionmentioning

confidence: 99%

“…Because reactive oxygen species are overproduced in the ischemic tissue [92] and various angiogenic factors are abundant in patients with cardiovascular diseases [93] , NSAIDs are expected to be more effective in this patient group. Nevertheless, non-aspirin NSAID are not effective in BE patients with ischemic heart disease, while aspirin is especially effective in this patient group [53] . Although low-dose aspirin clearly prevents EAC when prescribed in healthy controls, it suppresses COX insufficiently [34] .…”

Section: Mechanisms Of Nsaid Chemopreventive Effectmentioning

confidence: 99%

“…Because mortality due to cardiovascular disease is high in BE patients, "technical review on the management of Barrett's esophagus today" suggests screening for cardiovascular factors in BE patients and aspirin and statin use as warranted [45] . Because we have shown no benefit for non-aspirin NSAID use in BE patients with ischemic heart disease [53] and substantial cardiovascular side effects are expected [103,104] , use of non-aspirin NSAIDs should be withheld in patients with BE and cardiovascular co-morbidities, at least until more clinical data might justify their use.…”

Section: Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Role of chemoprophylaxis with either NSAIDs or statins in patients with Barrett’s esophagus

Tsibouris

Vlachou

Isaacs

2014

WJGPT

Self Cite

View full text Add to dashboard Cite

The incidence of esophageal adenocarcinoma, a poor prognosis neoplasia, has risen dramatically in recent decades. Barrett's esophagus represents the best-known risk factor for esophageal adenocarcinoma development. Non-steroidal anti-inflammatory drugs through cyclooxygenase-2 inhibition and prostaglandin metabolism regulation could control cell proliferation, increase cell apoptosis and regulate the expression of growth and angiogenic factors. Statins can achieve equivalent effects through prenylation and subsequently control of cellular signaling cascades. At present, epidemiological studies are small and underpowered. Their data could not justify either medication as a chemo-preventive agent. Population based studies have shown a 43% reduction of the odds of developing an esophageal adenocarcinoma, leaving out or stating a 25% reduction in patients consuming non-aspirin nonsteroidal antiinflammatory drugs and a 50% reduction in those patients consuming aspirin. They have also stated a 19% reduction of esophageal cancer incidence when statins have been used. Observational studies have shown that non-steroidal anti-inflammatory drugs could reduce the adenocarcinoma incidence in patients with Barrett's esophagus by 41%, while statins could reduce the risk by 43%. The cancer preventive effect has been enhanced in those patients taking a combination of non-steroidal anti-inflammatory drugs and statins (a 74% decrease). Observational data are equivocal concerning the efficacy of non-steroidal anti-inflammatory drug subclasses. Non-steroidal anti-inflammatory drugs clearly have substantial potential for toxicity, while statins are rather safe drugs. In conclusion, both non-steroidal anti-inflammatory drugs and statins are promising chemopreventive agents and deserve further exploration with interventional studies. In the meanwhile, their use is justified only in patients with cardiovascular disease.© 2014 Baishideng Publishing Group Co., Limited. All rights reserved.Key words: Esophageal adenocarcinoma; Barrett's esophagus; Non-steroidal anti-inflammatory drugs; Aspirin; Statins; Cancer chemoprevention Core tip: Esophageal adenocarcinoma remains a major burden upon health. Experimental studies have suggested that non-steroidal anti-inflammatory drugs and statins may have useful actions against esophageal cancer cells. This review of observational studies shows that non-steroidal anti-inflammatory drugs reduced adenocarcinoma incidence in patients with Barrett' s esophagus by 41%, while statins reduced the risk by 43%. The cancer preventive effect is enhanced in those patients taking a combination of non-steroidal anti-inflammatory drugs and statins (a 74% decrease). Non-steroidal anti-inflammatory drugs clearly have substantial potential for toxicity, while statins are rather safe drugs. Their combination offers promise for chemoprevention and further interventional studies are warranted.Tsibouris P, Vlachou E, Isaacs PET. Role of chemoprophylaxis REVIEWOnline Submissions: http://www.wjgnet.com/esps/

show abstract

Ischemic heart disease, factor predisposing to Barrett’s adenocarcinoma: A case control study

Cited by 2 publications

References 37 publications

RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

Role of chemoprophylaxis with either NSAIDs or statins in patients with Barrett’s esophagus

Contact Info

Product

Resources

About