Suryakanth R. Gurudu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Suryakanth R. Gurudu has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
- Michael D. Crowell
Division of Gastroenterology and Hepatology
7 shared publications Jonathan A. Leighton
GI, Mayo Clinic, Phoenix, AZ
6 shared publicationsFrancisco C. Ramirez
4 shared publicationsJonathan A Leighton
Dr Franco is a gastroenterology fellow, Dr Leighton is a professor of medicine, and Dr Gurudu is an associate professor of medicine in the Division of Gastroenterology at the Mayo Clinic Arizona in Scottsdale, Arizona
4 shared publications- Derek W. Ebner
Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, Minnesota, USA
2 shared publications - Ivana Dzeletovic
Beth Israel Deaconess Medical Center, Boston, Massachusetts
2 shared publications
Latest Publications
- 3 September 2026
- Published by Wolters Kluwer Health in American Journal of Gastroenterology
Longitudinal Data From a Large, Multitarget Stool DNA Colorectal Cancer Screening Program
INTRODUCTION: Multitarget stool DNA (mt-sDNA) is an established stool-based colorectal cancer screening test, yet long-term performance is not well-described. We evaluated follow-up colonoscopy rates & quality, neoplasia yield, and repeat-testing adherence over 10 years with an integrated screening program. METHODS: We assembled a retrospective cohort of mt-sDNA tests (September 2014–July 2025) within a multisite health system. A validated large-language-model pipeline extracted colonoscopy, pathology, and quality end points from free-text reports. Detection outcomes (adenoma detection rate, advanced neoplasia, modified advanced adenoma [AA], sessile serrated lesion, and negative examinations) were calculated among high-quality examinations; adenocarcinoma, bowel preparation adequacy, and cecal intubation rate used all screening examinations. We assessed colonoscopy completion ≤1 year after positive mt-sDNA, follow-up colonoscopy findings, findings by time-to-colonoscopy, and adherence to repeat mt-sDNA after negative result. RESULTS: Among 148,624 tests in 110,410 individuals, positivity was 13.6%. Of 19,506 positives, 65.1% completed colonoscopy within 12 months (median 82 days). Colonoscopy after a positive mt-sDNA had high yield: AA diagnosis was 30.7%; adenocarcinoma was 1.3%. Of patients who had colonoscopy within 3 years of a negative mt-sDNA test, 45.2% had adenoma/serrated lesion, 9.3% had AA and 0.5% had colon cancer. Adenoma detection rate after positive mt-sDNA (>50%) exceeded specialty society quality benchmarks and increased over time; Longer intervals (>6 months) to colonoscopy after a positive test were associated with higher AA (trend P = 0.001).After an initial negative mt-sDNA, only 35.3% were screened again by mt-sDNA testing within 3 years. DISCUSSION: Over a decade, mt-sDNA screening achieved high colonoscopy quality but revealed critical gaps in the care cascade. One-third of positive tests lacked timely follow-up and nearly two-thirds of negative tests were not repeated on schedule, suggesting opportunities for system-level interventions.
- 3 September 2026
- Published by Wolters Kluwer Health in American Journal of Gastroenterology
Longitudinal Data From a Large, Multitarget Stool DNA Colorectal Cancer Screening Program
INTRODUCTION: Multitarget stool DNA (mt-sDNA) is an established stool-based colorectal cancer screening test, yet long-term performance is not well-described. We evaluated follow-up colonoscopy rates & quality, neoplasia yield, and repeat-testing adherence over 10 years with an integrated screening program. METHODS: We assembled a retrospective cohort of mt-sDNA tests (September 2014–July 2025) within a multisite health system. A validated large-language-model pipeline extracted colonoscopy, pathology, and quality end points from free-text reports. Detection outcomes (adenoma detection rate, advanced neoplasia, modified advanced adenoma [AA], sessile serrated lesion, and negative examinations) were calculated among high-quality examinations; adenocarcinoma, bowel preparation adequacy, and cecal intubation rate used all screening examinations. We assessed colonoscopy completion ≤1 year after positive mt-sDNA, follow-up colonoscopy findings, findings by time-to-colonoscopy, and adherence to repeat mt-sDNA after negative result. RESULTS: Among 148,624 tests in 110,410 individuals, positivity was 13.6%. Of 19,506 positives, 65.1% completed colonoscopy within 12 months (median 82 days). Colonoscopy after a positive mt-sDNA had high yield: AA diagnosis was 30.7%; adenocarcinoma was 1.3%. Of patients who had colonoscopy within 3 years of a negative mt-sDNA test, 45.2% had adenoma/serrated lesion, 9.3% had AA and 0.5% had colon cancer. Adenoma detection rate after positive mt-sDNA (>50%) exceeded specialty society quality benchmarks and increased over time; Longer intervals (>6 months) to colonoscopy after a positive test were associated with higher AA (trend P = 0.001).After an initial negative mt-sDNA, only 35.3% were screened again by mt-sDNA testing within 3 years. DISCUSSION: Over a decade, mt-sDNA screening achieved high colonoscopy quality but revealed critical gaps in the care cascade. One-third of positive tests lacked timely follow-up and nearly two-thirds of negative tests were not repeated on schedule, suggesting opportunities for system-level interventions.
- Open Access
- 17 December 2024
- Published by Wolters Kluwer Health in Clinical and Translational Gastroenterology
- Vol. 17  (2) , e00959
Accurate and Scalable Classification of Colonoscopy Neoplasia Using Machine Learning and Natural Language Processing
INTRODUCTION: Colorectal cancer remains a leading cause of cancer associated death in the United States and colonoscopy the primary screening strategy for prevention. Rates of adenomatous and serrated neoplasia detection are inversely associated with postcolonoscopy colorectal cancer. This crucial quality metric depends on accurate ascertainment of colorectal neoplasia findings from both endoscopy and histopathology records. We aimed to assess the feasibility of a random forest machine learning model to rapidly and accurately categorize colorectal neoplasia from electronic health record data. METHODS: A retrospective cohort study compared neoplasia detection rates among individuals undergoing colonoscopy at a large academic institution to develop a rule-based algorithm to categorize colorectal neoplasia from endoscopy reports and pathology systematized nomenclature of medicine – clinical terms. This cohort provided a large training set to develop a natural language processing system using a random forest approach to automatically classify unstructured pathology findings into adenoma, serrated, or advanced neoplasms. This system was manually validated through an independent holdout set. RESULTS: The training set comprised 35,953 unstructured pathology reports with matched systematized nomenclature of medicine – clinical terms from 95,188 unstructured colonoscopy reports. The final model was assessed on an independent holdout set of 337 manually annotated procedures obtaining an area under the receiver operating characteristic curve of 0.997 (confidence interval [CI] 0.994–1), 0.99 (CI 0.98–1), and 0.99 (CI 0.98–0.99) for prediction of adenoma, serrated, and advanced lesions, respectively. DISCUSSION: The random forest-based hybrid natural language processing system for classification of colonoscopy results was both accurate and explainable. NLP combined with effective machine learning algorithms can provide a scalable strategy for colonoscopy quality monitoring.
- 17 December 2024
- Published by Wolters Kluwer Health in Clinical and Translational Gastroenterology
- Vol. 17  (2) , e00959
Open AccessAccurate and Scalable Classification of Colonoscopy Neoplasia Using Machine Learning and Natural Language Processing
INTRODUCTION: Colorectal cancer remains a leading cause of cancer associated death in the United States and colonoscopy the primary screening strategy for prevention. Rates of adenomatous and serrated neoplasia detection are inversely associated with postcolonoscopy colorectal cancer. This crucial quality metric depends on accurate ascertainment of colorectal neoplasia findings from both endoscopy and histopathology records. We aimed to assess the feasibility of a random forest machine learning model to rapidly and accurately categorize colorectal neoplasia from electronic health record data. METHODS: A retrospective cohort study compared neoplasia detection rates among individuals undergoing colonoscopy at a large academic institution to develop a rule-based algorithm to categorize colorectal neoplasia from endoscopy reports and pathology systematized nomenclature of medicine – clinical terms. This cohort provided a large training set to develop a natural language processing system using a random forest approach to automatically classify unstructured pathology findings into adenoma, serrated, or advanced neoplasms. This system was manually validated through an independent holdout set. RESULTS: The training set comprised 35,953 unstructured pathology reports with matched systematized nomenclature of medicine – clinical terms from 95,188 unstructured colonoscopy reports. The final model was assessed on an independent holdout set of 337 manually annotated procedures obtaining an area under the receiver operating characteristic curve of 0.997 (confidence interval [CI] 0.994–1), 0.99 (CI 0.98–1), and 0.99 (CI 0.98–0.99) for prediction of adenoma, serrated, and advanced lesions, respectively. DISCUSSION: The random forest-based hybrid natural language processing system for classification of colonoscopy results was both accurate and explainable. NLP combined with effective machine learning algorithms can provide a scalable strategy for colonoscopy quality monitoring.
- 1 June 2018
- Published by Elsevier in Gastrointestinal Endoscopy
- Vol. 87  (6) , AB474-AB475
Mo1677 FACTORS AFFECTING OUTCOMES OF LARGE COLON POLYPECTOMIES AT A TERTIARY CARE CENTER
- 1 June 2018
- Published by Elsevier in Gastrointestinal Endoscopy
- Vol. 87  (6) , AB474-AB475
Mo1677 FACTORS AFFECTING OUTCOMES OF LARGE COLON POLYPECTOMIES AT A TERTIARY CARE CENTER
- 1 June 2018
- Published by Elsevier in Gastrointestinal Endoscopy
- Vol. 87  (6) , AB298
Su1253 CLINICAL CHARACTERISTICS, READMISSIONS, AND MORTALITY IN PATIENTS WITH SMALL BOWEL BLEEDING
- 1 June 2018
- Published by Elsevier in Gastrointestinal Endoscopy
- Vol. 87  (6) , AB298
Su1253 CLINICAL CHARACTERISTICS, READMISSIONS, AND MORTALITY IN PATIENTS WITH SMALL BOWEL BLEEDING
- 7 May 2018
- Published by Springer Nature in Digestive Diseases and Sciences
- Vol. 63  (9) , 2413-2418
Comparison of Small Versus Large Volume Split Dose Preparation for Colonoscopy: A Study of Colonoscopy Outcomes
Split dose bowel preparations (SDP) have superior outcomes for colonoscopy as compared to evening before regimens. However, the association of the actual volume of the SDP to colonoscopy outcome measures has not been well studied.
- 7 May 2018
- Published by Springer Nature in Digestive Diseases and Sciences
- Vol. 63  (9) , 2413-2418
Comparison of Small Versus Large Volume Split Dose Preparation for Colonoscopy: A Study of Colonoscopy Outcomes
Split dose bowel preparations (SDP) have superior outcomes for colonoscopy as compared to evening before regimens. However, the association of the actual volume of the SDP to colonoscopy outcome measures has not been well studied.
- 1 August 2017
- Vol. 13  (8) , 476-483
Approach to Incomplete Colonoscopy: New Techniques and Technologies.
Colonoscopy is the most widely used screening modality for the detection and removal of colon polyps and for the prevention of colorectal cancer. To identify all colon lesions and reduce the risk of colorectal cancer, it is important to perform a complete colonoscopy. The success of screening colonoscopy depends upon several parameters, including bowel preparation and adenoma detection rate. Incomplete colonoscopy rates vary from 4% to 25% and are associated with higher rates of interval proximal colon cancer. This article reviews the potential causes of and preventive measures for incomplete colonoscopy, as well as techniques and technologies that may improve the rate of complete colonoscopy.
- 1 August 2017
- Vol. 13  (8) , 476-483
Approach to Incomplete Colonoscopy: New Techniques and Technologies.
Colonoscopy is the most widely used screening modality for the detection and removal of colon polyps and for the prevention of colorectal cancer. To identify all colon lesions and reduce the risk of colorectal cancer, it is important to perform a complete colonoscopy. The success of screening colonoscopy depends upon several parameters, including bowel preparation and adenoma detection rate. Incomplete colonoscopy rates vary from 4% to 25% and are associated with higher rates of interval proximal colon cancer. This article reviews the potential causes of and preventive measures for incomplete colonoscopy, as well as techniques and technologies that may improve the rate of complete colonoscopy.
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2017  (10636919) , 4761-4772
Fine-Tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally
Intense interest in applying convolutional neural networks (CNNs) in biomedical image analysis is wide spread, but its success is impeded by the lack of large annotated datasets in biomedical imaging. Annotating biomedical images is not only tedious and time consuming, but also demanding of costly, specialty - oriented knowledge and skills, which are not easily accessible. To dramatically reduce annotation cost, this paper presents a novel method called AIFT (active, incremental fine-tuning) to naturally integrate active learning and transfer learning into a single framework. AIFT starts directly with a pre-trained CNN to seek "worthy" samples from the unannotated for annotation, and the (fine-tuned) CNN is further fine-tuned continuously by incorporating newly annotated samples in each iteration to enhance the CNNs performance incrementally. We have evaluated our method in three different biomedical imaging applications, demonstrating that the cost of annotation can be cut by at least half. This performance is attributed to the several advantages derived from the advanced active and incremental capability of our AIFT method.
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2017  (10636919) , 4761-4772
Fine-Tuning Convolutional Neural Networks for Biomedical Image Analysis: Actively and Incrementally
Intense interest in applying convolutional neural networks (CNNs) in biomedical image analysis is wide spread, but its success is impeded by the lack of large annotated datasets in biomedical imaging. Annotating biomedical images is not only tedious and time consuming, but also demanding of costly, specialty - oriented knowledge and skills, which are not easily accessible. To dramatically reduce annotation cost, this paper presents a novel method called AIFT (active, incremental fine-tuning) to naturally integrate active learning and transfer learning into a single framework. AIFT starts directly with a pre-trained CNN to seek "worthy" samples from the unannotated for annotation, and the (fine-tuned) CNN is further fine-tuned continuously by incorporating newly annotated samples in each iteration to enhance the CNNs performance incrementally. We have evaluated our method in three different biomedical imaging applications, demonstrating that the cost of annotation can be cut by at least half. This performance is attributed to the several advantages derived from the advanced active and incremental capability of our AIFT method.
- 1 September 2015
- Published by Wolters Kluwer Health in Journal of Healthcare Management
- Vol. 60  (5) , 363-376
Using Hybrid Change Strategies to Improve the Patient Experience in Outpatient Specialty Care
EXECUTIVE SUMMARY The emerging changes in healthcare impose significant burdens on integrated outpatient specialty services with respect to setting patient expectations, handling outside medical records, and coordinating specialty appointments scheduling. Moreover, because of the evolution of the electronic health record and its widespread use, it is critical that patient and physician interaction is maintained and clerical tasks are minimized. In the context of increased government regulation, declining reimbursement, and the rise of new payment models, outpatient practices need to be reimagined so that they are more efficient for the patient and the provider. The redesign of integrated outpatient specialty services can be accomplished only through teamwork, innovation, and efficient use of technology. To address these challenges, the Department of Medicine at Mayo Clinic in Scottsdale, Arizona, implemented an ideal practice design initiative that leveraged a hybrid set of change strategies. The change strategy, which was initiated after examination of current practices and design options, engaged key stakeholders and patients. A number of enablers and barriers to adoption were identified as a result of the implementation experience.
- 1 September 2015
- Published by Wolters Kluwer Health in Journal of Healthcare Management
- Vol. 60  (5) , 363-376
Using Hybrid Change Strategies to Improve the Patient Experience in Outpatient Specialty Care
EXECUTIVE SUMMARY The emerging changes in healthcare impose significant burdens on integrated outpatient specialty services with respect to setting patient expectations, handling outside medical records, and coordinating specialty appointments scheduling. Moreover, because of the evolution of the electronic health record and its widespread use, it is critical that patient and physician interaction is maintained and clerical tasks are minimized. In the context of increased government regulation, declining reimbursement, and the rise of new payment models, outpatient practices need to be reimagined so that they are more efficient for the patient and the provider. The redesign of integrated outpatient specialty services can be accomplished only through teamwork, innovation, and efficient use of technology. To address these challenges, the Department of Medicine at Mayo Clinic in Scottsdale, Arizona, implemented an ideal practice design initiative that leveraged a hybrid set of change strategies. The change strategy, which was initiated after examination of current practices and design options, engaged key stakeholders and patients. A number of enablers and barriers to adoption were identified as a result of the implementation experience.
- 23 June 2015
- Published by Springer Nature
- Vol. 24, 327-338
A Comprehensive Computer-Aided Polyp Detection System for Colonoscopy Videos
Computer-aided detection (CAD) can help colonoscopists reduce their polyp miss-rate, but existing CAD systems are handicapped by using either shape, texture, or temporal information for detecting polyps, achieving limited sensitivity and specificity. To overcome this limitation, our key contribution of this paper is to fuse all possible polyp features by exploiting the strengths of each feature while minimizing its weaknesses. Our new CAD system has two stages, where the first stage builds on the robustness of shape features to reliably generate a set of candidates with a high sensitivity, while the second stage utilizes the high discriminative power of the computationally expensive features to effectively reduce false positives. Specifically, we employ a unique edge classifier and an original voting scheme to capture geometric features of polyps in context and then harness the power of convolutional neural networks in a novel score fusion approach to extract and combine shape, color, texture, and temporal information of the candidates. Our experimental results based on FROC curves and a new analysis of polyp detection latency demonstrate a superiority over the state-of-the-art where our system yields a lower polyp detection latency and achieves a significantly higher sensitivity while generating dramatically fewer false positives. This performance improvement is attributed to our reliable candidate generation and effective false positive reduction methods.
- 23 June 2015
- Published by Springer Nature
- Vol. 24, 327-338
A Comprehensive Computer-Aided Polyp Detection System for Colonoscopy Videos
Computer-aided detection (CAD) can help colonoscopists reduce their polyp miss-rate, but existing CAD systems are handicapped by using either shape, texture, or temporal information for detecting polyps, achieving limited sensitivity and specificity. To overcome this limitation, our key contribution of this paper is to fuse all possible polyp features by exploiting the strengths of each feature while minimizing its weaknesses. Our new CAD system has two stages, where the first stage builds on the robustness of shape features to reliably generate a set of candidates with a high sensitivity, while the second stage utilizes the high discriminative power of the computationally expensive features to effectively reduce false positives. Specifically, we employ a unique edge classifier and an original voting scheme to capture geometric features of polyps in context and then harness the power of convolutional neural networks in a novel score fusion approach to extract and combine shape, color, texture, and temporal information of the candidates. Our experimental results based on FROC curves and a new analysis of polyp detection latency demonstrate a superiority over the state-of-the-art where our system yields a lower polyp detection latency and achieves a significantly higher sensitivity while generating dramatically fewer false positives. This performance improvement is attributed to our reliable candidate generation and effective false positive reduction methods.
- Open Access
- 1 January 2015
- Published by Baishideng Publishing Group Inc. in World Journal of Gastrointestinal Endoscopy
- Vol. 7  (4) , 328-335
Quality monitoring in colonoscopy: Time to act
Quality monitoring in colonoscopy: Time to act
- 1 January 2015
- Published by Baishideng Publishing Group Inc. in World Journal of Gastrointestinal Endoscopy
- Vol. 7  (4) , 328-335
Open AccessQuality monitoring in colonoscopy: Time to act
Quality monitoring in colonoscopy: Time to act