Challenges and opportunities in the application of artificial intelligence in gastroenterology and hepatology

Christou, Chrysanthos D.; Tsoulfas, Georgios

doi:10.3748/wjg.v27.i37.6191

Cited by 23 publications

(18 citation statements)

References 180 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…60 In the future, highly sophisticated accounting systems could be embedded in the clinical setting and, combined with other innovative tools such as machine learning models, could be used to create a framework for cost-effective, evidence-based healthcare. 98 The push for reduction of OR costs should not compromise the quality of care. It is crucial to understand that changes in physicians' practices will affect only the direct costs.…”

Section: Discussionmentioning

confidence: 99%

“…Among them are the reform in payment mechanisms, the care delivery in less restrictive settings, the growth of telemedicine, the adaptation of new technologies, patient privacy concerns, and the growing efforts to implement guidelines 60 . In the future, highly sophisticated accounting systems could be embedded in the clinical setting and, combined with other innovative tools such as machine learning models, could be used to create a framework for cost‐effective, evidence‐based healthcare 98 …”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The process of estimating the cost of surgery: Providing a practical framework for surgeons

Christou

Athanasiadou

Tooulias

et al. 2022

Health Planning & Management

Self Cite

View full text Add to dashboard Cite

Over the last decades, health care costs have been increasing at an alarming, exponential rate which is considered unsustainable. Surgical care utilizes one-third of health care costs. Estimating, evaluating, and understanding the cost of surgery is a vital step towards cost management and reduction. Current cost estimation studies and costeffectiveness studies have vast disparities in their methodology, with published costs of Operating Room varying from as low as $7 and as high as $113 per minute. Costs in surgery are distinguished as direct and indirect. Allocation of direct costs involves identification, measurement, and valuation processes. Allocation of indirect costs involves the allocation of capital and overhead costs and of indirect department costs. Annualised capital costs and overhead hospital costs are then allocated to surgery by either the costcentre allocation or the activity-based allocation frameworks. Indirect department costs are allocated to a specific surgery by weighted service allocation or hourly rate allocation or inpatient day allocation, or marginal markup allocation. The growing societal, financial and political pressure for cost reduction has brought cost analysis to the forefront of healthcare discussions. Thus, we believe that almost every single surgeon will eventually enter the field of healthcare economics by necessity. This review aims to provide surgeons with a practical framework for engaging in cost estimation studies.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

The process of estimating the cost of surgery: Providing a practical framework for surgeons

Christou

Athanasiadou

Tooulias

et al. 2022

Health Planning & Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…Medicine has already benefited from the use of Artificial Intelligence (AI) and machine learning. Two recent reviews analyzed the applications of AI and machine learning in gastroenterology [ 12 , 13 ]. AI was used in polyp detection during colonoscopy [ 14 ], celiac disease diagnosis [ 15 ], predicting mortality in variceal bleeding [ 16 ], or prediction of liver fibrosis in hepatitis C virus infection [ 17 ].…”

Section: Discussionmentioning

confidence: 99%

“…The second objective was to identify if the catheter was positioned correctly, allowing swallow interpretation. The innovation of our approach is supported by both the few references quoted and two recent reviews [ 12 , 13 ] on applications of AI to gastroenterology failing to consider its potential to improve diagnosis of EMD.…”

Section: Discussionmentioning

confidence: 99%

Integrated Relaxation Pressure Classification and Probe Positioning Failure Detection in High-Resolution Esophageal Manometry Using Machine Learning

Czako

Surdea-Blaga

Sebestyen

et al. 2021

Sensors

View full text Add to dashboard Cite

High-resolution esophageal manometry is used for the study of esophageal motility disorders, with the help of catheters with up to 36 sensors. Color pressure topography plots are generated and analyzed and using the Chicago algorithm a final diagnosis is established. One of the main parameters in this algorithm is integrated relaxation pressure (IRP). The procedure is time consuming. Our aim was to firstly develop a machine learning based solution to detect probe positioning failure and to create a classifier to automatically determine whether the IRP is in the normal range or higher than the cut-off, based solely on the raw images. The first step was the preprocessing of the images, by finding the region of interest—the exact moment of swallowing. Afterwards, the images were resized and rescaled, so they could be used as input for deep learning models. We used the InceptionV3 deep learning model to classify the images as correct or failure in catheter positioning and to determine the exact class of the IRP. The accuracy of the trained convolutional neural networks was above 90% for both problems. This work is just the first step in fully automating the Chicago Classification, reducing human intervention.

show abstract

“…However, as others have opined, several challenges in the technology involved in deploying these various ML/AI applications remain to be overcome. [ 1,2 ]…”

mentioning

confidence: 99%

Digitizing DILI: Who can? RUCAM? RECAM?

Lewis

2022

Hepatology

View full text Add to dashboard Cite

The age of machine learning (ML) and artificial intelligence (AI) is poised to dramatically alter the practice of medicine in many disciplines, including the field of liver disease. How the radiologist diagnoses hepatic tumors and how the pathologist interprets liver histology are among the areas in which the digital revolution is being incorporated in gastroenterology and hepatology. However, as others have opined, several challenges in the technology involved in deploying these various ML/AI applications remain to be overcome. [1,2] Attempts to computerize the diagnosis of druginduced liver injury (DILI) have been on the minds of hepatologists for years but have thus far remained elusive. In this issue of Hepatology, Hayashi and colleagues, [3] all of whom have long-standing expertise in the causality assessment of DILI, present their evidencebased, computerized modification of the Roussel Uclaf Causality Assessment Methodology (RUCAM), which they have renamed Revised Electronic Causality Assessment Method (RECAM), for diagnosing DILI. Their attempt to bring causality assessment into the digital age is a welcome addition to our diagnostic armamentarium. But although their offering has several advantages over the current version of RUCAM, as the authors themselves recognize, as with other attempts to enter the computerized age of medicine, it remains a work in progress.Given the hundreds of drugs, herbal products, and chemicals that can cause liver injury and mimic every possible form of acute, chronic, benign, and malignant liver disease, the ability to make a firm diagnosis of DILI has remained clinically challenging in the absence of a definitive diagnostic biomarker. Many health care professionals, especially nonhepatologists, rely heavily on consultation with an individual with expertise in the field of drug hepatotoxicity. But despite more than three decades of research searching for a validated and specific biomarker, DILI remains a diagnosis of exclusion. [4] Efforts to devise semiobjective algorithmic approaches to analyze the important elements needed to suspect possible DILI-i.e., a compatible time to onset (latency), time to recovery after the drug has been stopped (positive dechallenge), and the ability to adequately exclude alternative causes-have given rise to a number of causality assessment methodologies over the last

show abstract

Challenges and opportunities in the application of artificial intelligence in gastroenterology and hepatology

Cited by 23 publications

References 180 publications

The process of estimating the cost of surgery: Providing a practical framework for surgeons

The process of estimating the cost of surgery: Providing a practical framework for surgeons

Integrated Relaxation Pressure Classification and Probe Positioning Failure Detection in High-Resolution Esophageal Manometry Using Machine Learning

Digitizing DILI: Who can? RUCAM? RECAM?

Contact Info

Product

Resources

About