Improving bowel preparation for colonoscopy with a smartphone application driven by artificial intelligence

Zhu, Yan; Zhang, Danfeng; Wu, Huili; Fu, Pei-Yao; Li, Feng; Zhuang, Kun; Geng, Zi-Han; Li, Kunkun; Zhang, Xiaohong; Zhu, Boqun; Qin, Wen‐Zheng; Lin, Shengli; Zhang, Zhen; Chen, Tian‐Yin; Huang, Yuan; Xu, Xiaoyue; Liu, Jing-Zheng; Wang, Shuo; Zhang, Wei; Li, Quan‐Lin; Zhou, Ping‐Hong

doi:10.1038/s41746-023-00786-y

Cited by 14 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…44 Recently, two studies proposed smartphone apps to assist patients in judging BP status through the appearance of feces; however, there was still a gap in widespread clinical application. 45,46 The current research had several advantages. First, this was an extensive review of the factors affecting IBP to date, and it was the first meta-analysis of factors related to colonoscopy indications and preparation processes.…”

Section: Discussionmentioning

confidence: 99%

Risk factors for inadequate bowel preparation before colonoscopy: A meta‐analysis

Feng,

Guan,

Dong

et al. 2024

J Evidence Based Medicine

View full text Add to dashboard Cite

ObjectiveThis meta‐analysis aimed to comprehensively explore the risk factors for inadequate bowel preparation (IBP).MethodsWe searched the Embase, PubMed, Web of Science, and The Cochrane Library databases up to August 24, 2023, to identify observational studies and randomized controlled trials (RCTs) that examined risk factors for IBP. A random effects model was used to pool the adjusted odds ratios and 95% confidence intervals.ResultsA total of 125 studies (91 observational studies, 34 RCTs) were included. Meta‐analyses of observational studies revealed that three preparation‐related factors, namely, characteristics of last stool (solid or brown liquid), incomplete preparation intake, and incorrect diet restriction, were strong predictors of IBP. The other factors were moderately correlated with IBP incidence, including demographic variables (age, body mass index, male sex, Medicaid insurance, and current smoking), comorbidities (diabetes, liver cirrhosis, psychiatric disease, Parkinson's disease, previous IBP, poor mobility, inpatient, and Bristol stool form 1/2), medications (tricyclic antidepressants, opioids, antidepressants, narcotics, antipsychotics, and calcium channel blockers), and preparation‐related factors (preparation‐to‐colonoscopy interval not within 3 to 5/6 h, nonsplit preparation, and preparation instructions not followed). No colonoscopy indications were found to be related to IBP. Meta‐analyses of RCTs showed that education, constipation, stroke/dementia, and discomfort during preparation were also moderately associated with IBP. Most of the other findings were consistent with the pooled results of observational studies. However, primarily due to imprecision and inconsistency, the certainty of evidence for most factors was very low to moderate.ConclusionsWe summarized five categories of risk factors for IBP. Compared to demographic variables, comorbidities, medications, and colonoscopy indications, preparation‐related elements were more strongly associated with IBP. These findings may help clinicians identify high‐risk individuals and provide guidance for IBP prevention.

show abstract

Section: Discussionmentioning

confidence: 99%

Risk factors for inadequate bowel preparation before colonoscopy: A meta‐analysis

Feng,

Guan,

Dong

et al. 2024

J Evidence Based Medicine

View full text Add to dashboard Cite

show abstract

“…Additional applications have developed rapidly to include detection and diagnosis of other pathology in upper and lower GI endoscopy, capsule endoscopy and biliary endoscopy. There has also been initial exploratory use of LLMs to aid decision-making on management of early CRCs and patient-facing applications to determine adequacy of bowel preparation prior to colonoscopy[ 15 - 19 ].…”

Section: Introductionmentioning

confidence: 99%

Human-artificial intelligence interaction in gastrointestinal endoscopy

Campion,

O'Connor,

Lahiff

2024

World J Gastrointest Endosc

View full text Add to dashboard Cite

The number and variety of applications of artificial intelligence (AI) in gastrointestinal (GI) endoscopy is growing rapidly. New technologies based on machine learning (ML) and convolutional neural networks (CNNs) are at various stages of development and deployment to assist patients and endoscopists in preparing for endoscopic procedures, in detection, diagnosis and classification of pathology during endoscopy and in confirmation of key performance indicators. Platforms based on ML and CNNs require regulatory approval as medical devices. Interactions between humans and the technologies we use are complex and are influenced by design, behavioural and psychological elements. Due to the substantial differences between AI and prior technologies, important differences may be expected in how we interact with advice from AI technologies. Human–AI interaction (HAII) may be optimised by developing AI algorithms to minimise false positives and designing platform interfaces to maximise usability. Human factors influencing HAII may include automation bias, alarm fatigue, algorithm aversion, learning effect and deskilling. Each of these areas merits further study in the specific setting of AI applications in GI endoscopy and professional societies should engage to ensure that sufficient emphasis is placed on human-centred design in development of new AI technologies.

show abstract

“…Colorectal cancer (CRC) is the third leading cause of cancer and the second leading cause of cancer-related deaths in the world [ 1 ]. In 2020, there were approximately 1.9 million new cases of CRC, which accounted for 935,000 deaths [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Design and evaluation of a colon cancer mobile application

Sadeghi,

Salar,

Moghadam

et al. 2024

BMC Gastroenterol

View full text Add to dashboard Cite

Background Colorectal cancer (CRC) is the third leading cause of cancer and the second cause of cancer-related deaths in the world. Despite the infrastructure and the availability of organized screening programs, participation in their screening programs is less than the set goals. Considering the importance of informing the society about the prevention and early detection of colorectal cancer symptoms and the positive impact of mobile health technologies, the present research was conducted with the aim of designing and evaluating a colon cancer mobile application. Methods The present research was conducted in two phases: software design and evaluation. In the first phase, the software was prepared using the cascade method. First, all the educational content related to colorectal cancer was collected through an expert panel with the participation of 10 specialists. Then the software was evaluated with alpha and beta testing, and the initial version was approved by users in terms of simplicity and usability. In the second phase, a parallel clinical randomized trial study was conducted with the aim of investigating the effect of a colon cancer mobile application on the early detection of colorectal cancer. In this stage, 204 volunteers participated; inclusion criteria were age 18–85 years, owning a smartphone and the ability to read and write. Participants were randomized into control and intervention groups. The intervention group was educated with the colon cancer application for education about colorectal cancer, and the control group was educated with a pamphlet. After education, both groups were screened for colorectal cancer symptoms, and the results were compared. Results In the software evaluation phase, the application was used by 204 users. In this stage, 84 (41.2%) women and 120 (58.8%) men, with an average (Standard Deviation) age of 47.53 (13.68) participated. Participants were randomized in two groups, 103 people with an average (Standard Deviation) age of 47.62 (14.65) in intervention group and 101 people with an average (Standard Deviation) age of 47.44 (12.70) in control group. There were no significant differences between the demographic characteristics of age, gender, marriage, occupation, instruction level, digestive disease history, cancer history, cancer risk factors, and family history of cancer between the two groups (P > 0.05). The Mann-Whitney U test indicated that there is a significant difference between the two groups of participants in self-assessment, willingness to do the screening, and the results of the assessment of colorectal cancer (P < 0.05). Conclusion The results of the research indicated the positive impact of the Colon Cancer Application on the abilities of the users of self-assessment of colon cancer. Therefore, based on the findings, it can be concluded that the use of the colon cancer mobile application is effective for colon cancer prevention and self-care. Trial registration This study was registered in the Iranian Registry of Clinical Trials (https://irct.behdasht.gov.ir) on 13/2/2024, with the IRCT ID: IRCT20210131050189N9.

show abstract

Improving bowel preparation for colonoscopy with a smartphone application driven by artificial intelligence

Cited by 14 publications

References 27 publications

Risk factors for inadequate bowel preparation before colonoscopy: A meta‐analysis

Risk factors for inadequate bowel preparation before colonoscopy: A meta‐analysis

Human-artificial intelligence interaction in gastrointestinal endoscopy

Design and evaluation of a colon cancer mobile application

Contact Info

Product

Resources

About