Introduction: Comprehensive and standardized colonoscopy reports are crucial in colorectal cancer prevention, monitoring, and research. This study investigates adherence to national and international guidelines by analyzing reporting practices among 21 endoscopists in 7 German centers, with a focus on polyp reporting. Methods: We identified and assessed German, European, American, and World Health Organization-provided statements to identify key elements in colonoscopy reporting. Board-certified gastroenterologists rated the relevance of each element and estimated their reporting frequency. Adherence to the identified report elements was evaluated for 874 polyps from 351 colonoscopy reports ranging from March 2021 to March 2022. Results: We identified numerous recommendations for colonoscopy reporting. We categorized the reasoning behind those recommendations into clinical relevance, justification, and quality control and research. Although all elements were considered relevant by the surveyed gastroenterologists, discrepancies were observed in the evaluated reports. Particularly diminutive polyps or attributes which are rarely abnormal (e.g., surface integrity) respectively rarely performed (e.g., injection) were sparsely documented. Furthermore, the white light morphology of polyps was inconsistently documented using either the Paris classification or free text. In summary, the analysis of 874 reported polyps revealed heterogeneous adherence to the recommendations, with reporting frequencies ranging from 3% to 89%. Conclusion: The inhomogeneous report practices may result from implicit reporting practices and recommendations with varying clinical relevance. Future recommendations should clearly differentiate between clinical relevance and research and quality control or explanatory purposes. Additionally, the role of computer-assisted documentation should be further evaluated to increase report frequencies of non-pathological findings and diminutive polyps.

Colorectal cancer (CRC) screening, primarily conducted via colonoscopy, plays a vital role in early detection and requires precise subsequent care [1, 2]. National and international guidelines stipulate specific intra- and post-procedural regimens, which are determined by factors like polyp size, morphology, histopathology, and removal method [2‒15]. Given the limited evidence remaining after the examination’s completion – usually only selected images and the written report – comprehensive reporting becomes indispensable [6]. Such thorough documentation aids in soliciting second opinions, re-evaluating findings, ensuring quality control, and promoting research. Although there is consensus on many aspects of colonoscopy reports, recommendations on some aspects remain varied. Particularly risk stratification methods like chromoendoscopic polyp classifications keep evolving continuously introducing a plethora of classifications with similar features (e.g., NICE, FICE, Kudo, Hiroshima, WASP, BASIC) [16‒19]. The importance of standardizing reporting structures has been acknowledged for decades, but the European Society of Gastroenterology’s recent position statement asserts that further improvements are still needed [6, 14, 20, 21].

In the context of rapid advancements in artificial intelligence (AI) research, particularly in detecting pathologies such as colon polyps or Barrett’s esophagus, uniform reporting is even more crucial [22, 23]. Inconsistent reporting practices impede the development and widespread application of AI systems in clinical settings [24]. The potential of AI to enhance real-time detection and classification of findings offers a chance to refine endoscopic procedures and reporting [25]. Yet, obstacles such as data inconsistency, biases, lack of universal standards, ethical considerations, and data security concerns must be overcome [14, 24].

We hypothesize that current recommendations for colonoscopy reporting, particularly concerning polyp descriptions, are intricate and may not always reflect clinical needs. Therefore, this complexity may result in inconsistent application across clinical practice. Additionally, we suspect that these recommendations are not uniformly implemented in routine practice. To test these hypotheses, our study’s main objective was to analyze reported polyps in multiple centers and assess adherence to existing polyp description guidelines. This focused investigation aims to shed light on current reporting practices and to identify opportunities for standardization, thereby aligning clinical practice with evidence-based guidelines and enhancing the potential integration of AI in colonoscopy procedures.

Colonoscopy Report Items

To identify relevant colonoscopy report elements, we reviewed guidelines and recommendations published by the German Association for Digestive and Metabolic Diseases (DGVS) [4, 5], European Society for Gastrointestinal Endoscopy (ESGE) [2, 6, 7, 14], World Organisation of Digestive Endoscopy (OMED) [3], and American Society for Gastrointestinal Endoscopy (ASGE) [13, 15]. Statements relevant to high-quality screening colonoscopy reports were extracted and compiled into a list of items for further assessment (Table 1; online suppl. Table 1; for all online suppl. material, see https://doi.org/10.1159/000538113).

Table 1.

National (DGVS, ASGE) and international (ESGE, OMED terminology) colonoscopy reporting recommendations were assessed to identify relevant report elements

Examination-relatedPolyp-relatedIntervention-related
Indication Location Instrument 
Sedation medication Size Salvaged 
Bowel preparation Surface intactness Intervention type 
Withdrawal time Morphology (description) Wound management 
 Morphology (Paris)  
 Digital chromoendoscopy  
 Injection  
 Non-lifting sign  
 Predicted histology  
Examination-relatedPolyp-relatedIntervention-related
Indication Location Instrument 
Sedation medication Size Salvaged 
Bowel preparation Surface intactness Intervention type 
Withdrawal time Morphology (description) Wound management 
 Morphology (Paris)  
 Digital chromoendoscopy  
 Injection  
 Non-lifting sign  
 Predicted histology  

Examiner Survey

A total of 11 board-certified gastroenterologists from 5 endoscopic centers completed a survey (August 19, 2022–December 3, 2022) in which they rated the relevance and self-estimated reporting rates of the identified colonoscopy report elements. The answers were provided on a Likert scale ranging from 1 (irrelevant/never reported) to 5 (highly relevant/always reported). The questionnaires are available in the supplements (online suppl. Table 2 [German], online suppl. Table 3 [English]). During evaluation, items were regarded as relevant or frequently reported if the median rating was above 3.

Colonoscopy Report Analysis

For the evaluation of colonoscopy report practices, examination reports of the 11 surveyed and an additional 10 examiners from 7 endoscopic centers were collected from our database (March 1, 2021–March 1, 2022). At least 5 examinations with detected polyps were required per examiner, and examinations without detected polyps were excluded from the study. The colonoscopy reports were manually evaluated to determine whether the identified report elements were documented. The manual evaluation process was conducted in a blinded fashion regarding the originating center and examiner to minimize potential bias.

Examiners’ Estimated Report Element Relevance and Reporting Rate

The participating examiners had a median of 17 years’ experience in screening colonoscopy (min: 6 years, max: 37 years) and performed a median of 400 screening colonoscopies per year (min: 100, max: >1,200). After literature assessment, we selected 4 examination-related, 9 polyp-related, and 4 intervention-related report elements (Table 1). The examiner questionnaire revealed that each individual examination- and intervention-related report item was regarded as relevant and frequently reported by all examiners. Furthermore, this was also the case for all polyp-related items except the polyp’s surface intactness which was rated as relevant (median: 3.5) but not frequently reported (median: 3). Yet, the range of opinions was highly heterogeneous among the assessed items ranging from unanimous ratings of 5 for relevance and report rate (e.g., whether a polyp was removed or not) to ratings between 1 and 5 in both categories (e.g., Paris classification). Online supplementary Figures 1–3 visualize the survey result in detail.

Reporting Frequency

Patients of the analyzed reports were aged between 18 and 93 years (median: 62, IQR: 54–72). Of those, 133 (37.89%) were female and 189 (53.85%) were male. For 29 (8.26%) examinations, the gender and for 32 (9.12%) examinations the age were not further specified.

Examination-Related Report Elements

Indications for the evaluated examinations were “symptomatic” (n: 99, 28.21%), “screening” (n: 97, 27.64%), “unknown” (n: 84, 23.93%), “surveillance” (n: 64, 18.23%), and “other” (n: 7, 1.99%). The medication used for sedation was not specified in 46 (13.11%) reports. Information regarding the sufficiency of the bowel preparation was missing in 96 (27.35%) cases, and a statement about the completeness of the examination was not reported in 213 (60.68%) cases. The withdrawal time was explicitly stated for 116 (33.05%) examinations even though an endoscopic intervention was performed in each examination.

Polyp Detection and Characteristics

A total of 874 polyps were detected in 351 examinations. Polyps were primarily sized <6 mm (335; 38.33%) or 6–9 mm (200; 22.88%), while no size was provided for 191 (21.85%) polyps. Sizes were specified in millimeters for 631 (72.20%) polyps (Fig. 1), and 52 (5.95%) were described exclusively categorically (e.g., large).

Fig. 1.

Distribution of polyp sizes. Sizes of 631 polyps were specified in millimeters. Interestingly, the sizes 5, 10, and 15 mm were more frequent compared to the surrounding values. Polyps sized larger than 21 mm (n = 24) are not visualized.

Fig. 1.

Distribution of polyp sizes. Sizes of 631 polyps were specified in millimeters. Interestingly, the sizes 5, 10, and 15 mm were more frequent compared to the surrounding values. Polyps sized larger than 21 mm (n = 24) are not visualized.

Close modal

Location and Histology Prediction

Most polyps were located in the ascending (165; 18.88%) or sigmoid colon (142; 16.25%), with 143 polyp locations (16.36%) not explicitly stated. Of the unlocated polyps, 73 (51.05%) were sized <10 mm, and 47 (32.87%) were without size specification (Fig. 2a). In the sigmoid colon or rectum, 38 out of 229 (16.59%) polyps had a location in cm specified. Macroscopic histology prediction (e.g., hyperplastic, adenoma, carcinoma) was missing for 750 (85.81%) of the reported polyps.

Fig. 2.

Report frequencies of polyp attributes. Report frequencies of 874 reported polyps’ attributes were assessed by polyp size (<6 mm: 335 polyps; 6–9 mm: 200 polyps; >9 mm: 148 polyps; unknown size: 191 polyps). We observed varying report rates of location (a), polyp morphology (b), whether an intervention was performed and specified (c), and whether an injection was performed and specified (d).

Fig. 2.

Report frequencies of polyp attributes. Report frequencies of 874 reported polyps’ attributes were assessed by polyp size (<6 mm: 335 polyps; 6–9 mm: 200 polyps; >9 mm: 148 polyps; unknown size: 191 polyps). We observed varying report rates of location (a), polyp morphology (b), whether an intervention was performed and specified (c), and whether an injection was performed and specified (d).

Close modal

Surface Integrity and Morphology Classification

The intactness of polyps’ surfaces was noted for 23 (2.63%) polyps. For 22 of those (95.65%), an intact surface was described. Morphology classifications were absent for 528 (60.41%) polyps using descriptive terms, and 688 (78.72%) using the Paris classification (Fig. 2b). For 418 (47.83%) polyps, neither was available. Polyps without specific morphology were often smaller than 5 mm (191, 45.69%) or of unknown size (161, 38.52%). Digital chromoendoscopy classification was provided for 41 of 148 (27.70%) polyps sized ≥10 mm.

Intervention

Whether a polyp was subject to intervention was reported for 696 (79.63%) polyps. Of those, 64 (9.20%) stated no performed intervention. Only in 54 (8.54%) cases, the report specified the intervention type (piecemeal, en bloc, partial, biopsy) (Fig. 2c). Instruments used for the intervention were missing in 73 (11.55%) cases. For 213 (24.37%) polyps, the report stated whether an injection was performed. For 38 (17.84%) of those, an injection was confirmed. Of the confirmed injections, 13 (34.21%) reports referred to the presence (n = 3) or absence (n = 10) of a non-lifting sign (Fig. 2d).

Additional Observations

For 565 (89.40%) polyps, the report specified if the polyp was salvaged or not. For non-resected polyps (64), a reason for non-removal was provided in 10 (15.62%) cases.

The rapid advancements of technologies and techniques in endoscopy promise increasing possibilities for minimally invasive diagnostics and therapy in CRC prevention and treatment. Because of these advancements, the amount of information recommended to report rises. While many report systems were proposed in the past (e.g., EndoALPHA [26], American CRC Roundtable [27], Stanford Colonoscopy Quality Assurance Program [28], Parkland-UT Southwestern Colonoscopy Reporting System [29], European Society of Gastrointestinal Endoscopy [6, 7]), efforts of widespread and standardized clinical dissemination are still ongoing [14]. In this context, studies even assessed the possibility of natural language processing-based solutions to extract structured information from free text reports [30‒34]. Yet, such efforts are always limited by the quality of the written report and cannot account for missing information. In our study, which analyzed 874 reported polyps across 351 examinations, we observed a gap between ideal reporting according to current recommendations and clinical practice.

During in-depth assessment of the evaluated report items, we identified three clusters of reasoning behind report recommendations: (1) future relevance for the patient, (2) justification of the performed treatment/diagnostics/billing, and (3) quality control/research. Though we anticipated higher report rates for patient-relevant categories, we observed varying report frequencies even for basic information such as polyp size and location. Manual analysis of reports with sparse documentation indicated reasons for missing information such as redundant or distributed reporting, assumed clinical insignificance, assumed default values, and human error.

In more detail, redundant reporting implies that information might be documented elsewhere. Considering that cooperating medical professionals might lack access to additional local systems, the information is not available to the reader. While this may be tolerated for report elements concerning quality control or justification of the performed procedure, it is not acceptable for information concerning the future relevance for the patient.

Indicators like the predominant occurrence of small polyps (<10 mm) in our data suggest that sparse documentation may be due to perceived or actual clinical insignificance of the corresponding item. The surface integrity and the morphological classification of removed polyps, for example, can be necessary to understand the reasoning behind the performed procedure but have no further clinical consequence as surveillance intervals are dictated by polyp size and histology [2, 35]. In contrast, the location of removed polyps should always be provided as histopathology may reveal malignancy even for macroscopically benign polyps.

In cases of very low report frequencies, such as surface integrity (23/874 polyps; 2.6%), injection (213/874 polyps; 24.4%) non-lifting sign (13/38 injections; 34.2%), we suspect that examiners assumed a default value corresponding to the least pathological finding (intact surface, no injection, no non-lifting sign). However, we strongly advise against such implicit statements as the reader cannot distinguish whether information is missing on purpose or by accident. Instead, report systems could include such default values or incorporate AI-assisted reporting for most common findings. Earlier studies could already demonstrate promising results for polyp size measurement, image acquisition, and withdrawal time estimation [36, 37].

The limitations of our study include the relatively small sample of endoscopists (reports: n = 21; questionnaire: n = 11) and the restriction to German centers which limits our findings to Germany, although similar problems are likely to exist in other countries. Furthermore, report creation is highly dependent on the used documentation software and the ability to use it correctly. Anyhow, software development and usage are guided by clinical expertise and guidelines. Furthermore, our analysis was confined to written colonoscopy reports, excluding photo-documentation potentially containing additional information. Lastly, as an observational study, no gold standard for the assessed reports existed. Nevertheless, these limitations are considered minor, as the high variability in reporting habits would probably increase with inclusion from more centers from various countries.

In respect to our study’s findings, we can draw two conclusions with utmost importance for further report recommendations and report software development. First, as the amount of information to be reported increases, future recommendations should clearly state whether information is relevant for the patients’ medical treatment or not. These items should be summarized into a lean set of medically necessary report elements. Second, future studies should evaluate the introduction of “default values” or AI-assisted reporting for the most common findings as this could greatly improve the reports’ comprehensiveness.

The study was approved by the local Ethical Committee responsible for each study center (Ethik-Kommission Landesärztekammer Baden-Württemberg [F-2021–047. F-2020-158], Ethik-Kommission Landesärztekammer Hessen [2021–2531], Ethik-Kommission der Landesärztekammer Rheinland-Pfalz [2021–15,955], and Ethik-Kommission University Hospital Würzburg [12/20, 20200114 04]). All procedures were in accordance with the Helsinki Declaration of 1964 and later versions. Study participants from external centers provided written informed consent before collection and analysis of data. Data from the University Hospital Würzburg were collected from anonymized reports already gathered for quality control, and therefore, patient consent was not required in accordance with local and national guidelines.

The author, A.M., declares the following affiliations: consultancy – Ovesco and Olympus; grants and patents – Ovesco; honoraria – Falk Foundation and AbbVie. Despite these affiliations, the authors confirm that there are no conflicts of interest that could have influenced the submitted work. The author has disclosed these affiliations for the sake of transparency, in compliance with academic standards.

This project was supported by the Interdisciplinary Center for Clinical Research (IZKF) at the University of Würzburg (Z-2/CSP-31). The IZKF provides salary to assure protected research time for T.J.L. This project was supported by the Gastroenterology Foundation (Zürich, Switzerland). The Gastroenterology Foundation provides funding for hardware, software, employees, and article processing charges. Sponsors had no influence during preparation of the data or manuscript.

T.J.L. is the principal investigator and author responsible of this project, and he is from the University Hospital Würzburg, Germany. He was responsible for study design, data analysis, interpretation, and write-up of the manuscript. K.H., I.K., P.S., Z.S., A.M., and A.H. are coinvestigators in the University Hospital Würzburg, Germany. K.H. and Z.S. were responsible for data curation, processing, analysis, and interpretation. I.K. and P.S. were responsible for data management, software infrastructure used for data analysis, and coordination of data annotation. A.M. and A.H. were responsible for overseeing the project, acquisition of funding and data as well as interpretation of the results. All authors were involved in the initial manuscript draft, refinement, and final approval of the manuscript.

The data that support the findings of this study are not publicly available due to potential personal data included in each analyzed report. Further inquiries can be directed to the corresponding author.

1.
Ladabaum
U
,
Dominitz
JA
,
Kahi
C
,
Schoen
RE
.
Strategies for colorectal cancer screening
.
Gastroenterology
.
2020
;
158
(
2
):
418
32
.
2.
Hassan
C
,
Antonelli
G
,
Dumonceau
J-M
,
Regula
J
,
Bretthauer
M
,
Chaussade
S
, et al
.
Post-polypectomy colonoscopy surveillance: European society of gastrointestinal endoscopy (ESGE) guideline – update 2020
.
Endoscopy
.
2020
;
52
(
8
):
687
700
.
3.
Aabakken
L
,
Rembacken
B
,
LeMoine
O
,
Kuznetsov
K
,
Rey
JF
,
Rösch
T
, et al
.
Minimal standard terminology for gastrointestinal endoscopy
.
Endoscopy
.
2009
;
41
(
8
):
727
8
.
4.
Meining
A
,
Schmidbaur
W
,
Schumacher
B
,
Toermer
T
,
Keuchel
M
,
Baltes
P
, et al
.
The revised version of standard terminology in gastroenterological endoscopy: result of a consensus project of the German society for gastroenterology, digestive and metabolic diseases
.
Z Gastroenterol
.
2018
;
56
(
1
):
e1
.
5.
Leifeld
L
,
Denzer
U
,
Frieling
T
,
Jakobs
R
,
Koop
H
,
van Leeuwen
P
, et al
.
Quality management in the field of gastroenterology: proposals of the quality commission of the German society of gastroenterology, digestive and metabolic diseases (DGVS) for outpatient and inpatient quality assurance
.
Z Gastroenterol
.
2021
;
59
(
07
):
665
76
.
6.
Bretthauer
M
,
Aabakken
L
,
Dekker
E
,
Kaminski
MF
,
Rösch
T
,
Hultcrantz
R
, et al
.
Requirements and standards facilitating quality improvement for reporting systems in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement
.
Endoscopy
.
2016
;
48
(
3
):
291
4
.
7.
Kaminski
MF
,
Thomas-Gibson
S
,
Bugajski
M
,
Bretthauer
M
,
Rees
CJ
,
Dekker
E
, et al
.
Performance measures for lower gastrointestinal endoscopy: a European Society of Gastrointestinal Endoscopy (ESGE) quality improvement initiative
.
Endoscopy
.
2017
;
49
(
4
):
378
97
.
8.
Aabakken
L
,
Barkun
AN
,
Cotton
PB
,
Fedorov
E
,
Fujino
MA
,
Ivanova
E
, et al
.
Standardized endoscopic reporting
.
J Gastroenterol Hepatol
.
2014
;
29
(
2
):
234
40
.
9.
Borgaonkar
MR
.
Making a quality endoscopy report
.
Can J Gastroenterol
.
2013
;
27
(
5
):
258
.
10.
Rembacken
B
,
Hassan
C
,
Riemann
J
,
Chilton
A
,
Rutter
M
,
Dumonceau
JM
, et al
.
Quality in screening colonoscopy: position statement of the European Society of Gastrointestinal Endoscopy (ESGE)
.
Endoscopy
.
2012
;
44
(
10
):
957
68
.
11.
Denzer
U
,
Beilenhoff
U
,
Eickhoff
A
,
Faiss
S
,
Hüttl
P
,
Smitten
S
, et al
.
S2k guideline: quality requirements for gastrointestinal endoscopy, AWMF registry no. 021-022
.
Z Gastroenterol
.
2016
;
53
(
12
):
E1
227
.
12.
US Preventive Services Task Force
;
Davidson
KW
,
Barry
MJ
,
Mangione
CM
,
Cabana
M
,
Caughey
AB
, et al
.
Screening for colorectal cancer: US preventive services task force recommendation statement
.
JAMA
.
2021
;
325
(
19
):
1965
77
.
13.
Rex
DK
,
Boland
CR
,
Dominitz
JA
,
Giardiello
FM
,
Johnson
DA
,
Kaltenbach
T
, et al
.
Colorectal cancer screening: recommendations for physicians and patients from the U.S. Multi-society task force on colorectal cancer
.
Am J Gastroenterol
.
2017
;
112
(
7
):
1016
30
.
14.
Bisschops
R
,
Rutter
MD
,
Areia
M
,
Cristiano Spada
,
Domagk
D
,
Kaminski
MF
, et al
.
Overcoming the barriers to dissemination and implementation of quality measures for gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) and United European Gastroenterology (UEG) position statement
.
United Eur Gastroenterol J
.
2021
;
9
(
1
):
120
6
.
15.
Kaltenbach
T
,
Anderson
JC
,
Burke
CA
,
Dominitz
JA
,
Gupta
S
,
Lieberman
D
, et al
.
Endoscopic removal of colorectal lesions: recommendations by the US multi-society task force on colorectal cancer
.
Am J Gastroenterol
.
2020
;
115
(
3
):
435
64
.
16.
Hayashi
N
,
Tanaka
S
,
Hewett
DG
,
Kaltenbach
TR
,
Sano
Y
,
Ponchon
T
, et al
.
Endoscopic prediction of deep submucosal invasive carcinoma: validation of the narrow-band imaging international colorectal endoscopic (NICE) classification
.
Gastrointest Endosc
.
2013
;
78
(
4
):
625
32
.
17.
Kudo
S
,
Hirota
S
,
Nakajima
T
,
Hosobe
S
,
Kusaka
H
,
Kobayashi
T
, et al
.
Colorectal tumours and pit pattern
.
J Clin Pathol
.
1994
;
47
(
10
):
880
5
.
18.
Bisschops
R
,
Hassan
C
,
Bhandari
P
,
Coron
E
,
Neumann
H
,
Pech
O
, et al
.
BASIC (BLI Adenoma Serrated International Classification) classification for colorectal polyp characterization with blue light imaging
.
Endoscopy
.
2018
;
50
(
3
):
211
20
.
19.
IJspeert
JEG
,
Bastiaansen
BAJ
,
van Leerdam
ME
,
Meijer
GA
,
van Eeden
S
,
Sanduleanu
S
, et al
.
Development and validation of the WASP classification system for optical diagnosis of adenomas, hyperplastic polyps and sessile serrated adenomas/polyps
.
Gut
.
2016
;
65
(
6
):
963
70
.
20.
Gaus
W
,
Wechsler
JG
,
Janowitz
P
,
Tudyka
J
,
Kratzer
W
,
Swobodnik
W
, et al
.
Structured reporting of medical findings: evaluation of a system in gastroenterology
.
Methods Inf Med
.
1992
;
31
(
4
):
268
74
.
21.
Reiner
BI
.
The challenges, opportunities, and imperative of structured reporting in medical imaging
.
J Digit Imaging
.
2009
;
22
(
6
):
562
8
.
22.
Hassan
C
,
Spadaccini
M
,
Iannone
A
,
Maselli
R
,
Jovani
M
,
Chandrasekar
VT
, et al
.
Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis
.
Gastrointest Endosc
.
2021
;
93
(
1
):
77
85.e6
.
23.
Lux
TJ
,
Banck
M
,
Saßmannshausen
Z
,
Troya
J
,
Krenzer
A
,
Fitting
D
, et al
.
Pilot study of a new freely available computer-aided polyp detection system in clinical practice
.
Int J Colorectal Dis
.
2022
;
37
(
6
):
1349
54
.
24.
Schmitz
R
,
Werner
R
,
Repici
A
,
Bisschops
R
,
Meining
A
,
Zornow
M
, et al
.
Artificial intelligence in GI endoscopy: stumbling blocks, gold standards and the role of endoscopy societies
.
Gut
.
2022
;
71
(
3
):
451
4
.
25.
Rajpurkar
P
,
Chen
E
,
Banerjee
O
,
Topol
EJ
.
AI in health and medicine
.
Nat Med
.
2022
;
28
(
1
):
31
8
.
26.
van Doorn
SC
,
van Vliet
J
,
Fockens
P
,
Dekker
E
.
A novel colonoscopy reporting system enabling quality assurance
.
Endoscopy
.
2014
;
46
(
3
):
181
7
.
27.
Lieberman
D
,
Nadel
M
,
Smith
RA
,
Atkin
W
,
Duggirala
SB
,
Fletcher
R
, et al
.
Standardized colonoscopy reporting and data system: report of the quality assurance task group of the national colorectal cancer roundtable
.
Gastrointest Endosc
.
2007
;
65
(
6
):
757
66
.
28.
Ladabaum
U
,
Shepard
J
,
Mannalithara
A
.
Developing and deploying an automated quality reporting system in your practice: learning from the Stanford colonoscopy quality assurance Program
.
Am J Gastroenterol
.
2021
;
116
(
7
):
1365
70
.
29.
Skinner
CS
,
Gupta
S
,
Halm
EA
,
Wright
S
,
McCallister
K
,
Bishop
W
, et al
.
Development of the parkland-UT southwestern colonoscopy reporting system (CoRS) for evidence-based colon cancer surveillance recommendations
.
J Am Med Inform Assoc
.
2016
;
23
(
2
):
402
6
.
30.
Mehrotra
A
,
Dellon
ES
,
Schoen
RE
,
Saul
M
,
Bishehsari
F
,
Farmer
C
, et al
.
Applying a natural language processing tool to electronic health records to assess performance on colonoscopy quality measures
.
Gastrointest Endosc
.
2012
;
75
(
6
):
1233
9.e14
.
31.
Imler
TD
,
Morea
J
,
Kahi
C
,
Sherer
EA
,
Cardwell
J
,
Johnson
CS
, et al
.
Multi-center colonoscopy quality measurement utilizing natural language processing
.
Am J Gastroenterol
.
2015
;
110
(
4
):
543
52
.
32.
Harkema
H
,
Chapman
WW
,
Saul
M
,
Dellon
ES
,
Schoen
RE
,
Mehrotra
A
.
Developing a natural language processing application for measuring the quality of colonoscopy procedures
.
J Am Med Inform Assoc
.
2011
;
18
(
Suppl 1
):
i150
6
.
33.
Raju
GS
,
Lum
PJ
,
Slack
RS
,
Thirumurthi
S
,
Lynch
PM
,
Miller
E
, et al
.
Natural language processing as an alternative to manual reporting of colonoscopy quality metrics
.
Gastrointest Endosc
.
2015
;
82
(
3
):
512
9
.
34.
Deutsch
JC
.
Colonoscopy quality, quality measures, and a natural language processing tool for electronic health records
.
Gastrointest Endosc
.
2012
;
75
(
6
):
1240
2
.
35.
Abu-Freha
N
,
Katz
LH
,
Kariv
R
,
Vainer
E
,
Laish
I
,
Gluck
N
, et al
.
Post-polypectomy surveillance colonoscopy: comparison of the updated guidelines
.
United Eur Gastroenterol J
.
2021
;
9
(
6
):
681
7
.
36.
Lux
TJ
,
Saßmanshausen
Z
,
Kafetzis
I
,
Sodmann
P
,
Herold
K
, et al
.
Assisted documentation as new focus for artificial intelligence in endoscopy: the precedent of reliable withdrawal time and image reporting
.
Endoscopy
.
2023
;
55
(
12
):
1118
1123
.
37.
Sudarevic
B
,
Sodmann
P
,
Kafetzis
I
,
Troya
J
,
Lux
TJ
,
Saßmannshausen
Z
, et al
.
Artificial intelligence-based polyp size measurement in gastrointestinal endoscopy using the auxiliary waterjet as a reference
.
Endoscopy
.
2023
;
55
(
9
):
871
6
.