Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool Output

Background and Aims: Inadequate bowel preparation which occurs in 25% of colonoscopies is a major barrier to the effectiveness of screening for colorectal cancer. We aim to develop an artificial intelligence (machine learning) algorithm to assess photos of stool output after bowel preparation to pre...

Full description

Saved in:
Bibliographic Details
Main Authors: Chethan Ramprasad, Divya Saini, Henry Del Carmen, Lev Krasnovsky, Rajat Chandra, Ryan Mcgregor, Russell T. Shinohara, Eric Eaton, Meghna Gummadi, Shivan Mehta, James D. Lewis
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Gastro Hep Advances
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S277257232400150X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850192592819453952
author Chethan Ramprasad
Divya Saini
Henry Del Carmen
Lev Krasnovsky
Rajat Chandra
Ryan Mcgregor
Russell T. Shinohara
Eric Eaton
Meghna Gummadi
Shivan Mehta
James D. Lewis
author_facet Chethan Ramprasad
Divya Saini
Henry Del Carmen
Lev Krasnovsky
Rajat Chandra
Ryan Mcgregor
Russell T. Shinohara
Eric Eaton
Meghna Gummadi
Shivan Mehta
James D. Lewis
author_sort Chethan Ramprasad
collection DOAJ
description Background and Aims: Inadequate bowel preparation which occurs in 25% of colonoscopies is a major barrier to the effectiveness of screening for colorectal cancer. We aim to develop an artificial intelligence (machine learning) algorithm to assess photos of stool output after bowel preparation to predict inadequate bowel preparation before colonoscopy. Methods: Patients were asked to text a photo of their stool in the commode when they believed that they neared completion of their colonoscopy bowel preparation. Boston Bowel Preparation Scores of 7 and below were labeled as inadequate or fair. Boston Bowel Preparation Scores of 8 and 9 were considered good. A binary classification image-based machine learning algorithm was designed. Results: In a test set of 61 images, the binary classification machine learning algorithm was able to distinguish inadequate/fair preparation from good preparation with a positive predictive value of 78.6% and a negative predictive value of 60.8%. In a test set of 56 images, the algorithm was able to distinguish normal colonoscopy duration (<25 minutes) from long colonoscopy duration (>25 minutes) with a positive predictive value of 78.6% and a negative predictive value of 65.5%. Conclusion: Patients are willing to submit photos of their stool output during bowel preparation through text messages before colonoscopy. This machine learning algorithm demonstrates the ability to predict inadequate/fair preparation from good preparation based on image classification of stool output. It was less accurate to predict long duration of colonoscopy.
format Article
id doaj-art-6ef3176a49ce4f36b63b2a33d2f71e3f
institution OA Journals
issn 2772-5723
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Gastro Hep Advances
spelling doaj-art-6ef3176a49ce4f36b63b2a33d2f71e3f2025-08-20T02:14:30ZengElsevierGastro Hep Advances2772-57232025-01-014210055610.1016/j.gastha.2024.09.011Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool OutputChethan Ramprasad0Divya Saini1Henry Del Carmen2Lev Krasnovsky3Rajat Chandra4Ryan Mcgregor5Russell T. Shinohara6Eric Eaton7Meghna Gummadi8Shivan Mehta9James D. Lewis10Division of Gastroenterology, University of Pennsylvania, Philadelphia, Pennsylvania; Correspondence: Address correspondence to: Chethan Ramprasad, MD, Division of Gastroenterology, University of Pennsylvania, 3400 Civic Center Blvd, Philadelphia, PA 19104.Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PennsylvaniaPerelman School of Medicine at the University of Pennsylvania, Philadelphia, PennsylvaniaPerelman School of Medicine at the University of Pennsylvania, Philadelphia, PennsylvaniaPerelman School of Medicine at the University of Pennsylvania, Philadelphia, PennsylvaniaPerelman School of Medicine at the University of Pennsylvania, Philadelphia, PennsylvaniaPerelman School of Medicine at the University of Pennsylvania, Center for Clinical Epidemiology and Biostatistics, Philadelphia, PennsylvaniaDepartment of Computer and Information Science, University of Pennsylvania, Philadelphia, PennsylvaniaDepartment of Computer and Information Science, University of Pennsylvania, Philadelphia, PennsylvaniaDivision of Gastroenterology, University of Pennsylvania, Philadelphia, PennsylvaniaDivision of Gastroenterology, University of Pennsylvania, Philadelphia, PennsylvaniaBackground and Aims: Inadequate bowel preparation which occurs in 25% of colonoscopies is a major barrier to the effectiveness of screening for colorectal cancer. We aim to develop an artificial intelligence (machine learning) algorithm to assess photos of stool output after bowel preparation to predict inadequate bowel preparation before colonoscopy. Methods: Patients were asked to text a photo of their stool in the commode when they believed that they neared completion of their colonoscopy bowel preparation. Boston Bowel Preparation Scores of 7 and below were labeled as inadequate or fair. Boston Bowel Preparation Scores of 8 and 9 were considered good. A binary classification image-based machine learning algorithm was designed. Results: In a test set of 61 images, the binary classification machine learning algorithm was able to distinguish inadequate/fair preparation from good preparation with a positive predictive value of 78.6% and a negative predictive value of 60.8%. In a test set of 56 images, the algorithm was able to distinguish normal colonoscopy duration (<25 minutes) from long colonoscopy duration (>25 minutes) with a positive predictive value of 78.6% and a negative predictive value of 65.5%. Conclusion: Patients are willing to submit photos of their stool output during bowel preparation through text messages before colonoscopy. This machine learning algorithm demonstrates the ability to predict inadequate/fair preparation from good preparation based on image classification of stool output. It was less accurate to predict long duration of colonoscopy.http://www.sciencedirect.com/science/article/pii/S277257232400150XArtificial IntelligenceColonoscopyBowel PreparationTechnology Positive
spellingShingle Chethan Ramprasad
Divya Saini
Henry Del Carmen
Lev Krasnovsky
Rajat Chandra
Ryan Mcgregor
Russell T. Shinohara
Eric Eaton
Meghna Gummadi
Shivan Mehta
James D. Lewis
Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool Output
Gastro Hep Advances
Artificial Intelligence
Colonoscopy
Bowel Preparation
Technology Positive
title Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool Output
title_full Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool Output
title_fullStr Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool Output
title_full_unstemmed Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool Output
title_short Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool Output
title_sort text message system for the prediction of colonoscopy bowel preparation adequacy before colonoscopy an artificial intelligence image classification algorithm based on images of stool output
topic Artificial Intelligence
Colonoscopy
Bowel Preparation
Technology Positive
url http://www.sciencedirect.com/science/article/pii/S277257232400150X
work_keys_str_mv AT chethanramprasad textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT divyasaini textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT henrydelcarmen textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT levkrasnovsky textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT rajatchandra textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT ryanmcgregor textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT russelltshinohara textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT ericeaton textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT meghnagummadi textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT shivanmehta textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput
AT jamesdlewis textmessagesystemforthepredictionofcolonoscopybowelpreparationadequacybeforecolonoscopyanartificialintelligenceimageclassificationalgorithmbasedonimagesofstooloutput