Development and validation of a scoring system to predict esophagogastroduodenoscopy necessity

Abstract

Objective: This study aimed to develop and validate a scoring system for predicting the need for esophagogastroduodenoscopy (EGD) in clinical practice to enhance accuracy and reduce misapplications.

Methods: From February 2021 to April 2022, outpatients scheduled for EGD at the Department of Gastroenterology in our hospital were recruited. Patients completed the system evaluation by providing clinical symptoms, relevant medical history, and endoscopic findings. Patients were randomly divided into the training and validation cohorts (at 2:1 ratio). The optimal algorithm was selected from five alternatives including a parallel test. Six physicians participated in a human-computer comparative validation. Sensitivity and negative likelihood ratio (−LR) were used as the primary indicators.

Results: Altogether 865 patients were enrolled, with 578 in the training cohort and 287 in the validation cohort. The scoring system comprised 21 variables, including age, 13 typical clinical symptoms, and seven medical history variables. The parallel test was selected as the final algorithm. Positive EGD findings were reported in 54.5% of the training cohort and 62.7% of the validation cohort. The scoring system demonstrated a sensitivity of 79.0% in the training cohort and 83.9% in the validation cohort, with −LR being 0.627 and 0.615, respectively. Compared to physicians, the scoring system exhibited higher sensitivity (84.0% vs 68.7%,P = 0.02) and a lower −LR (1.11 vs 2.41,P = 0.439).

Conclusions: We developed a scoring system to predict the necessity of EGD using a parallel test algorithm, which was user-friendly and effective, as evidenced by single-center validation.

Keywords

esophagogastroduodenoscopy / necessity / parallel test / prediction / scoring system

References

[1] Zhang XL,Lu ZS,Tang P,Kong JY,Yang YS. Current application situation of gastrointestinal endoscopy in China. World J Gastroenterol. 2013;19(19):2950-2955.

[2] O’sullivan JW,Albasri A,Nicholson BD, et al. Overtesting and undertesting in primary care: a systematic review and meta-analysis. BMJ Open. 2018;8(2):e018557.

[3] Rubenstein JH,Pohl H,Adams MA, et al. Overuse of repeat upper endoscopy in the Veterans Health Administration: a retrospective analysis. Am J Gastroenterol. 2017;112(11):1678-1685.

[4] Aljebreen AM,Alswat K,Almadi MA. Appropriateness and diagnostic yield of upper gastrointestinal endoscopy in an open-access endoscopy system. Saudi J Gastroenterol. 2013;19(5):219-222.

[5] Shaheen NJ,Fennerty MB,Bergman JJ. Less is more: a minimalist approach to endoscopy. Gastroenterology. 2018;154(7):1993-2003.

[6] Early DS,Ben-Menachem T,Decker GA, et al; ASGE Standards of Practice Committee. Appropriate use of GI endoscopy. Gastrointest Endosc. 2012;75(6):1127-1131.

[7] Leal C,Almeida N,Silva M,Santos A,Vasconcelos H,Figueiredo P. Appropriateness of endoscopic procedures: a prospective, multicenter study. GE Port J Gastroenterol. 2022;29(1):5-12.

[8] Hassan C,Bersani G,Buri L, et al. Appropriateness of upper-GI endoscopy: an Italian survey on behalf of the Italian Society of Digestive Endoscopy. Gastrointest Endosc. 2007;65(6):767-774.

[9] Buri L,Hassan C,Bersani G, et al; SIED Appropriateness Working Group. Appropriateness guidelines and predictive rules to select patients for upper endoscopy: a nationwide multicenter study. Am J Gastroenterol. 2010;105(6):1327-1337.

[10] Gupta K,Groudan K,Jobbins K,Hans B,Singhania R. Single-center review of appropriateness and utilization of upper endoscopy in dyspepsia in the United States. Gastroenterology Res. 2021;14(2):81-86.

[11] Chan YM,Goh KL. Appropriateness and diagnostic yield of EGD: a prospective study in a large Asian hospital. Gastrointest Endosc. 2004;59(4):517-524.

[12] Kuo CY,Chiu HM. Application of artificial intelligence in gastroenterology: potential role in clinical practice. J Gastroenterol Hepatol. 2021;36(2):267-272.

[13] Tammaro L,Buda A,Di Paolo MC, et al; T-Score Validation Study Group. A simplified clinical risk score predicts the need for early endoscopy in non-variceal upper gastrointestinal bleeding. Dig Liver Dis. 2014;46(9):783-787.

[14] Hoffmann V,Neubauer H,Heinzler J, et al. A novel easy-to-use prediction scheme for upper gastrointestinal bleeding: Cologne-WATCH (C-WATCH) risk score. Medicine (Baltimore). 2015;94(38):e1614.

[15] Shung DL,Au B,Taylor RA, et al. Validation of a machine learning model that outperforms clinical risk scoring systems for upper gastrointestinal bleeding. Gastroenterology. 2020;158(1):160-167.

[16] Hong SN,Byeon JS,Lee BI, et al. Prediction model and risk score for perforation in patients undergoing colorectal endoscopic submucosal dissection. Gastrointest Endosc. 2016;84(1):98-108.

[17] Gemma M,Pennoni F,Tritto R,Agostoni M. Risk of adverse events in gastrointestinal endoscopy: zero-inflated Poisson regression mixture model for count data and multinomial logit model for the type of event. PLoS One. 2021;16(6):e0253515.

[18] Hunt M,Miguez S,Dukas B,Onwude O,White S. Efficacy of Zemedy, a mobile digital therapeutic for the self-management of irritable bowel syndrome: crossover randomized controlled trial. JMIR Mhealth Uhealth. 2021;9(5):e26152.

[19] Zia J,Schroeder J,Munson S, et al. Feasibility and usability pilot study of a novel irritable bowel syndrome food and gastrointestinal symptom journal smartphone app. Clin Transl Gastroenterol. 2016;7(3):e147.

[20] Weerts ZZRM,Heinen KGE,Masclee AAM, et al. Smart data collection for the assessment of treatment effects in irritable bowel syndrome: observational study. JMIR Mhealth Uhealth. 2020;8(11):e19696.

[21] Bedogni G,Bellentani S,Miglioli L, et al. The Fatty Liver Index: a simple and accurate predictor of hepatic steatosis in the general population. BMC Gastroenterol. 2006;6:33.

[22] Martin GP,Sperrin M,Snell KIE,Buchan I,Riley RD. Clinical prediction models to predict the risk of multiple binary outcomes: a comparison of approaches. Stat Med. 2021;40(2):498-517.

[23] de Jong JJ,Lantinga MA,Tan ACITL, et al. Web-based educational intervention for patients with uninvestigated dyspepsia referred for upper gastrointestinal tract endoscopy: a randomized clinical trial. JAMA Intern Med. 2021;181(6):825-833.

[24] Liu ZJ,Zhang YL,Song GB,Duan Y. Using of combined diagnostic tests and applying Bayes formula to explain results. Chin J Clin Lab Mgt (Electronic Edn). 2015;3(1):6-8. [in Chinese].

[25] Caraguel CGB,Ellard K,Moody NJG, et al. Diagnostic test accuracy when screening for Haliotid herpesvirus 1 (AbHV) in apparently healthy populations of Australian abalone Haliotis spp. Dis Aquat Organ. 2019;136(2):199-207.

[26] Patterson SJ,Clarke C,Clutton-Brock TH, et al. Combining analytical approaches and multiple sources of information to improve interpretation of diagnostic test results for tuberculosis in wild meerkats. Animals (Basel). 2021;11(12):3453.

[27] Serra MAAO,Medeiros AT,Torres MD,Dias ICCM,Santos CAAS,Araújo MFM. Correlation between the symptoms of upper gastrointestinal disease and endoscopy findings: implications for clinical practice. J Taibah Univ Med Sci. 2021;16(3):395-401.

[28] Lin R,Wang WJ,Hou XH. The self-evaluation of upper-gastrointestinal symptoms in Chinese patients with digestive disease: a multicenter questionnaire survey. J Gastroenterol Hepatol. 2016;31(1):87-92.

[29] Lee J. Is artificial intelligence better than human clinicians in predicting patient outcomes? J Med Internet Res. 2020;22(8):e19918.

RIGHTS & PERMISSIONS

2023 The Authors. Journal of Digestive Diseases published by Chinese Medical Association Shanghai Branch, Chinese Society of Gastroenterology, Renji Hospital Affiliated to Shanghai Jiaotong University School of Medicine and John Wiley & Sons Australia, Ltd.