User login
Artificial intelligence (AI) holds the promise of identifying premalignant and advanced malignant lesions during colonoscopy that might otherwise be missed.
Is it living up to that promise?
It seems that depends on where, how, and by whom it’s being implemented.
Clinical Trials vs the Real World
The majority of randomized clinical trials of AI use conducted worldwide “clearly show an increase in the adenoma detection rate (ADR) during colonoscopy,” Prateek Sharma, MD, a gastroenterologist at The University of Kansas Cancer Center, Kansas City, told this news. “But the real-world results have been quite varied; some show improvement, and others don’t.”
Dr. Sharma is coauthor of a recent pooled analysis of nine randomized controlled trials on the impact of AI on colonoscopy surveillance after polyp removal. It found that AI use increased the proportion of patients requiring intensive surveillance by approximately 35% in the United States and 20% in Europe (absolute increases of 2.9% and 1.3%, respectively).
“While this may contribute to improved cancer prevention, it significantly adds patient burden and healthcare costs,” the authors concluded.
A recent retrospective analysis of staggered implementation of a computer-aided detection (CADe) system at a single academic center in Chicago found that for screening and surveillance colonoscopy combined, endoscopists using CADe identified more adenomas and serrated polyps — but only endoscopists who used CADe regularly (“majority” users).
A systematic review and meta-analysis of 21 randomized controlled trials comparing CADe with standard colonoscopy found increased detection of adenomas, but not of advanced adenomas, as well as higher rates of unnecessary removal of non-neoplastic polyps.
Adding to the mix, a multicenter randomized controlled trial of patients with a positive fecal immunochemical test found that AI use was not associated with better detection of advanced neoplasias. Lead author Carolina Mangas Sanjuán, MD, PhD, Hospital General Universitario Dr. Balmis, Alicante, Spain, told this news organization the results were “surprising,” given previous studies showing benefit.
Similarly, a pragmatic implementation trial conducted by Stanford, California, researchers showed no significant effect of CADe on ADR, adenomas per colonoscopy, or any other detection metric. Furthermore, CADe had no effect on procedure times or non-neoplastic detection rates.
The authors cautioned against viewing their study as an “outlier,” however, and pointed to an Israeli study comparing adenoma and polyp detection rates 6 months before and after the introduction of AI-aided colonoscopy. Those authors reported no performance improvement with the AI device and concluded that it was not useful in routine practice.
A ‘Mishmash’ of Methods
“It’s not clear why some studies are positive, and some are negative,” Dr. Sharma acknowledged.
Study design is a factor, particularly in real-world studies, he said. Some researchers use the before/after approach, as in the Israeli study; others compare use in different rooms — that is, one with a CADe device and one without. Like the Chicago analysis, findings from such studies probably depend on whether the colonoscopists with the CADe device in the room actually use it.
Other real-world studies look at detection by time, Dr. Sharma said.
For example, a study of 1780 colonoscopies in China found that AI systems showed higher assistance ability among colonoscopies performed later in the day, when adenoma detection rates typically declined, perhaps owing to fatigue.
These authors suggest that AI may have the potential to maintain high quality and homogeneity of colonoscopies and improve endoscopist performance in large screening programs and centers with high workloads.
“There’s a mishmash of different kinds of real-world studies coming in, and it’s very difficult to figure it all out,” Dr. Sharma said. “We just have to look at these devices as innovations and embrace them and work with them to see how it fits it in our practice.”
Perceptions and Expectations
Emerging evidence suggests that endoscopists’ perceptions and expectations may affect assessments of AI’s potential benefits in practice, Dr. Sharma noted.
“Someone might say, ‘I’m a trained physician. Why do I need a machine to help me?’ That can create a situation in which the endoscopist is constantly challenging the device, trying to overrule it or not give it credit.”
Others might perceive that the AI device will definitely help and therefore not look as carefully themselves for adenomas.
A study at The University of Texas MD Anderson Cancer Center in Houston in which activation of the AI system was at the discretion of the endoscopist found that real-time CADe did not improve adenoma detection among endoscopists with high baseline detection rates.
However, despite its availability, AI-assisted colonoscopy was activated in only half of the cases, and multiple concerns were raised by staff and endoscopists in a postprocedural survey. In particular, endoscopists were concerned that the system would result in too many false-positive signals (82.4%), was too distracting (58.8%), and prolonged procedure time (47.1%).
The authors of the Stanford study that found no benefit with CADe in routine practice noted, “Most concerning would be if, inadvertently, CADe use was accompanied by a simultaneous unconscious degradation in the quality of mucosal exposure, possibly due to a false sense of comfort that CADe would ensure a high-quality examination.”
“We’re trying to evaluate some of these interactions between endoscopists and AI devices both pragmatically in practice as well as in clinical trials,” Dr. Sharma said. “Much depends on the context of how you approach and present the devices. We tell physicians that this is an assist device, not something you’re competing against and not something that’s here to replace you. This is something which may make your lives easier, so try it out.”
Are Less Experienced Endoscopists Helped More?
It seems intuitive that less experienced endoscopists would be helped by AI, and indeed, some recent studies confirm this.
A small randomized controlled trial in Japan, presented during the Presidential Plenary at the American Society for Gastrointestinal Endoscopy (ASGE) annual meeting in May 2023, showed that a CADe system was “particularly useful” for beginning endoscopists, who had lower adenoma miss rates with the device vs a white light control device.
Another randomized controlled trial in Japan found that CADe use was associated with an increased overall ADR among endoscopists in training.
But experienced endoscopists probably can benefit as well, noted Jennifer Christie, MD, Division Director, Gastroenterology and Hepatology at the University of Colorado School of Medicine Anschutz Medical Campus in Aurora.
“We know that these AI devices can be useful in training our fellows to detect certain lesions in the colon,” she said. “However, they’re also helpful for many very seasoned practitioners, as an adjunctive tool to help in terms of diagnosis.”
Some studies reflect that dual benefit.
The AID-2 study, designed specifically to look at whether experience had an effect on AI findings during colonoscopy, was conducted among nonexpert endoscopists (lifetime volume of less than 2000 colonoscopies). The researchers, including Dr. Sharma, found that CADe increased the ADR by 22% compared with the control group.
An earlier study, AID-1 , used a similar design but was conducted among experienced endoscopists. In AID-1, the ADR was also significantly higher in the CADe group (54.8%) compared with the control group (40.4%), and adenomas detected per colonoscopy were significantly higher in the CADe group (mean, 1.07) than in the control group (mean, 0.71).
A multivariate post hoc analysis that pooled results from both AID-1 and AID-2 showed that use of CADe and colonoscopy indication, but not the level of examiner experience, were associated with ADR differences. This led the researchers to conclude, “Experience appears to play a minor role as a determining factor for ADR.”
Similarly, a 2023 study from China looked at the mean number of adenomas detected per colonoscopy according to the endoscopist’s experience. All rates were significantly higher in AI-assisted colonoscopies compared with conventional non-AI colonoscopy: overall ADR, 39.9% vs 32.4%; advanced ADR, 6.6% vs 4.9%; ADR of expert endoscopists, 42.3% vs 32.8%; ADR of nonexpert endoscopists, 37.5% vs 32.1%; and adenomas per colonoscopy, 0.59 vs 0.45, respectively.
The authors concluded that “AI-assisted colonoscopy improved overall ADR, advanced ADR, and ADR of both expert and nonexpert attending endoscopists.”
Improving the Algorithms
Experts agree that current and future research will improve the accuracy and quality of AI colonoscopy for all users, leading to new standards and more consistent outcomes in both clinical trials and real-world applications.
Work underway now to improve the algorithms will be an important step in that direction, according to Dr. Christie.
“We need to have enough information to create AI algorithms that allow us to detect early lesions, at least from an imaging standpoint, and we need to improve and increase the sensitivity and the specificity, as well as the predictive value,” she said.
AI can also play a role in health equity, she noted.
“But it’s a double-edged sword, because it depends again on algorithms and machine learning. Perhaps AI can eliminate some of the bias in our clinical decision-making. However, if we don’t train the machine properly with a good, diverse sample of patients and figure out how to integrate some of the social determinants of health that a computer may not otherwise consider, it can create larger disparities and larger biases. AI devices can only be as good and as inclusive as we make them,” Dr. Christie said.
Looking Ahead
Dr. Sharma predicts that “the next slew of studies are going to be on characterization — not just saying there’s an abnormality but distinguishing it further and saying whether the lesion is noncancerous, precancerous, or cancer.”
Other studies will focus on quality improvement of factors, such as withdrawal time and bowel preparation.
In its clinical practice update on AI, the American Gastroenterological Association states, “Eventually, we predict an AI suite of tools for colonoscopy will seem indispensable, as a powerful adjunct to support safe and efficient clinical practice. AI tools that improve colonoscopy quality may become more accepted, and perhaps demanded, by payors, administrators, and possibly even by well-informed patients who want to ensure the highest-quality examination of their colon.”
Dr. Sharma and Dr. Christie disclose no relevant conflicts of interest.
A version of this article appeared on Medscape.com.
Artificial intelligence (AI) holds the promise of identifying premalignant and advanced malignant lesions during colonoscopy that might otherwise be missed.
Is it living up to that promise?
It seems that depends on where, how, and by whom it’s being implemented.
Clinical Trials vs the Real World
The majority of randomized clinical trials of AI use conducted worldwide “clearly show an increase in the adenoma detection rate (ADR) during colonoscopy,” Prateek Sharma, MD, a gastroenterologist at The University of Kansas Cancer Center, Kansas City, told this news. “But the real-world results have been quite varied; some show improvement, and others don’t.”
Dr. Sharma is coauthor of a recent pooled analysis of nine randomized controlled trials on the impact of AI on colonoscopy surveillance after polyp removal. It found that AI use increased the proportion of patients requiring intensive surveillance by approximately 35% in the United States and 20% in Europe (absolute increases of 2.9% and 1.3%, respectively).
“While this may contribute to improved cancer prevention, it significantly adds patient burden and healthcare costs,” the authors concluded.
A recent retrospective analysis of staggered implementation of a computer-aided detection (CADe) system at a single academic center in Chicago found that for screening and surveillance colonoscopy combined, endoscopists using CADe identified more adenomas and serrated polyps — but only endoscopists who used CADe regularly (“majority” users).
A systematic review and meta-analysis of 21 randomized controlled trials comparing CADe with standard colonoscopy found increased detection of adenomas, but not of advanced adenomas, as well as higher rates of unnecessary removal of non-neoplastic polyps.
Adding to the mix, a multicenter randomized controlled trial of patients with a positive fecal immunochemical test found that AI use was not associated with better detection of advanced neoplasias. Lead author Carolina Mangas Sanjuán, MD, PhD, Hospital General Universitario Dr. Balmis, Alicante, Spain, told this news organization the results were “surprising,” given previous studies showing benefit.
Similarly, a pragmatic implementation trial conducted by Stanford, California, researchers showed no significant effect of CADe on ADR, adenomas per colonoscopy, or any other detection metric. Furthermore, CADe had no effect on procedure times or non-neoplastic detection rates.
The authors cautioned against viewing their study as an “outlier,” however, and pointed to an Israeli study comparing adenoma and polyp detection rates 6 months before and after the introduction of AI-aided colonoscopy. Those authors reported no performance improvement with the AI device and concluded that it was not useful in routine practice.
A ‘Mishmash’ of Methods
“It’s not clear why some studies are positive, and some are negative,” Dr. Sharma acknowledged.
Study design is a factor, particularly in real-world studies, he said. Some researchers use the before/after approach, as in the Israeli study; others compare use in different rooms — that is, one with a CADe device and one without. Like the Chicago analysis, findings from such studies probably depend on whether the colonoscopists with the CADe device in the room actually use it.
Other real-world studies look at detection by time, Dr. Sharma said.
For example, a study of 1780 colonoscopies in China found that AI systems showed higher assistance ability among colonoscopies performed later in the day, when adenoma detection rates typically declined, perhaps owing to fatigue.
These authors suggest that AI may have the potential to maintain high quality and homogeneity of colonoscopies and improve endoscopist performance in large screening programs and centers with high workloads.
“There’s a mishmash of different kinds of real-world studies coming in, and it’s very difficult to figure it all out,” Dr. Sharma said. “We just have to look at these devices as innovations and embrace them and work with them to see how it fits it in our practice.”
Perceptions and Expectations
Emerging evidence suggests that endoscopists’ perceptions and expectations may affect assessments of AI’s potential benefits in practice, Dr. Sharma noted.
“Someone might say, ‘I’m a trained physician. Why do I need a machine to help me?’ That can create a situation in which the endoscopist is constantly challenging the device, trying to overrule it or not give it credit.”
Others might perceive that the AI device will definitely help and therefore not look as carefully themselves for adenomas.
A study at The University of Texas MD Anderson Cancer Center in Houston in which activation of the AI system was at the discretion of the endoscopist found that real-time CADe did not improve adenoma detection among endoscopists with high baseline detection rates.
However, despite its availability, AI-assisted colonoscopy was activated in only half of the cases, and multiple concerns were raised by staff and endoscopists in a postprocedural survey. In particular, endoscopists were concerned that the system would result in too many false-positive signals (82.4%), was too distracting (58.8%), and prolonged procedure time (47.1%).
The authors of the Stanford study that found no benefit with CADe in routine practice noted, “Most concerning would be if, inadvertently, CADe use was accompanied by a simultaneous unconscious degradation in the quality of mucosal exposure, possibly due to a false sense of comfort that CADe would ensure a high-quality examination.”
“We’re trying to evaluate some of these interactions between endoscopists and AI devices both pragmatically in practice as well as in clinical trials,” Dr. Sharma said. “Much depends on the context of how you approach and present the devices. We tell physicians that this is an assist device, not something you’re competing against and not something that’s here to replace you. This is something which may make your lives easier, so try it out.”
Are Less Experienced Endoscopists Helped More?
It seems intuitive that less experienced endoscopists would be helped by AI, and indeed, some recent studies confirm this.
A small randomized controlled trial in Japan, presented during the Presidential Plenary at the American Society for Gastrointestinal Endoscopy (ASGE) annual meeting in May 2023, showed that a CADe system was “particularly useful” for beginning endoscopists, who had lower adenoma miss rates with the device vs a white light control device.
Another randomized controlled trial in Japan found that CADe use was associated with an increased overall ADR among endoscopists in training.
But experienced endoscopists probably can benefit as well, noted Jennifer Christie, MD, Division Director, Gastroenterology and Hepatology at the University of Colorado School of Medicine Anschutz Medical Campus in Aurora.
“We know that these AI devices can be useful in training our fellows to detect certain lesions in the colon,” she said. “However, they’re also helpful for many very seasoned practitioners, as an adjunctive tool to help in terms of diagnosis.”
Some studies reflect that dual benefit.
The AID-2 study, designed specifically to look at whether experience had an effect on AI findings during colonoscopy, was conducted among nonexpert endoscopists (lifetime volume of less than 2000 colonoscopies). The researchers, including Dr. Sharma, found that CADe increased the ADR by 22% compared with the control group.
An earlier study, AID-1 , used a similar design but was conducted among experienced endoscopists. In AID-1, the ADR was also significantly higher in the CADe group (54.8%) compared with the control group (40.4%), and adenomas detected per colonoscopy were significantly higher in the CADe group (mean, 1.07) than in the control group (mean, 0.71).
A multivariate post hoc analysis that pooled results from both AID-1 and AID-2 showed that use of CADe and colonoscopy indication, but not the level of examiner experience, were associated with ADR differences. This led the researchers to conclude, “Experience appears to play a minor role as a determining factor for ADR.”
Similarly, a 2023 study from China looked at the mean number of adenomas detected per colonoscopy according to the endoscopist’s experience. All rates were significantly higher in AI-assisted colonoscopies compared with conventional non-AI colonoscopy: overall ADR, 39.9% vs 32.4%; advanced ADR, 6.6% vs 4.9%; ADR of expert endoscopists, 42.3% vs 32.8%; ADR of nonexpert endoscopists, 37.5% vs 32.1%; and adenomas per colonoscopy, 0.59 vs 0.45, respectively.
The authors concluded that “AI-assisted colonoscopy improved overall ADR, advanced ADR, and ADR of both expert and nonexpert attending endoscopists.”
Improving the Algorithms
Experts agree that current and future research will improve the accuracy and quality of AI colonoscopy for all users, leading to new standards and more consistent outcomes in both clinical trials and real-world applications.
Work underway now to improve the algorithms will be an important step in that direction, according to Dr. Christie.
“We need to have enough information to create AI algorithms that allow us to detect early lesions, at least from an imaging standpoint, and we need to improve and increase the sensitivity and the specificity, as well as the predictive value,” she said.
AI can also play a role in health equity, she noted.
“But it’s a double-edged sword, because it depends again on algorithms and machine learning. Perhaps AI can eliminate some of the bias in our clinical decision-making. However, if we don’t train the machine properly with a good, diverse sample of patients and figure out how to integrate some of the social determinants of health that a computer may not otherwise consider, it can create larger disparities and larger biases. AI devices can only be as good and as inclusive as we make them,” Dr. Christie said.
Looking Ahead
Dr. Sharma predicts that “the next slew of studies are going to be on characterization — not just saying there’s an abnormality but distinguishing it further and saying whether the lesion is noncancerous, precancerous, or cancer.”
Other studies will focus on quality improvement of factors, such as withdrawal time and bowel preparation.
In its clinical practice update on AI, the American Gastroenterological Association states, “Eventually, we predict an AI suite of tools for colonoscopy will seem indispensable, as a powerful adjunct to support safe and efficient clinical practice. AI tools that improve colonoscopy quality may become more accepted, and perhaps demanded, by payors, administrators, and possibly even by well-informed patients who want to ensure the highest-quality examination of their colon.”
Dr. Sharma and Dr. Christie disclose no relevant conflicts of interest.
A version of this article appeared on Medscape.com.
Artificial intelligence (AI) holds the promise of identifying premalignant and advanced malignant lesions during colonoscopy that might otherwise be missed.
Is it living up to that promise?
It seems that depends on where, how, and by whom it’s being implemented.
Clinical Trials vs the Real World
The majority of randomized clinical trials of AI use conducted worldwide “clearly show an increase in the adenoma detection rate (ADR) during colonoscopy,” Prateek Sharma, MD, a gastroenterologist at The University of Kansas Cancer Center, Kansas City, told this news. “But the real-world results have been quite varied; some show improvement, and others don’t.”
Dr. Sharma is coauthor of a recent pooled analysis of nine randomized controlled trials on the impact of AI on colonoscopy surveillance after polyp removal. It found that AI use increased the proportion of patients requiring intensive surveillance by approximately 35% in the United States and 20% in Europe (absolute increases of 2.9% and 1.3%, respectively).
“While this may contribute to improved cancer prevention, it significantly adds patient burden and healthcare costs,” the authors concluded.
A recent retrospective analysis of staggered implementation of a computer-aided detection (CADe) system at a single academic center in Chicago found that for screening and surveillance colonoscopy combined, endoscopists using CADe identified more adenomas and serrated polyps — but only endoscopists who used CADe regularly (“majority” users).
A systematic review and meta-analysis of 21 randomized controlled trials comparing CADe with standard colonoscopy found increased detection of adenomas, but not of advanced adenomas, as well as higher rates of unnecessary removal of non-neoplastic polyps.
Adding to the mix, a multicenter randomized controlled trial of patients with a positive fecal immunochemical test found that AI use was not associated with better detection of advanced neoplasias. Lead author Carolina Mangas Sanjuán, MD, PhD, Hospital General Universitario Dr. Balmis, Alicante, Spain, told this news organization the results were “surprising,” given previous studies showing benefit.
Similarly, a pragmatic implementation trial conducted by Stanford, California, researchers showed no significant effect of CADe on ADR, adenomas per colonoscopy, or any other detection metric. Furthermore, CADe had no effect on procedure times or non-neoplastic detection rates.
The authors cautioned against viewing their study as an “outlier,” however, and pointed to an Israeli study comparing adenoma and polyp detection rates 6 months before and after the introduction of AI-aided colonoscopy. Those authors reported no performance improvement with the AI device and concluded that it was not useful in routine practice.
A ‘Mishmash’ of Methods
“It’s not clear why some studies are positive, and some are negative,” Dr. Sharma acknowledged.
Study design is a factor, particularly in real-world studies, he said. Some researchers use the before/after approach, as in the Israeli study; others compare use in different rooms — that is, one with a CADe device and one without. Like the Chicago analysis, findings from such studies probably depend on whether the colonoscopists with the CADe device in the room actually use it.
Other real-world studies look at detection by time, Dr. Sharma said.
For example, a study of 1780 colonoscopies in China found that AI systems showed higher assistance ability among colonoscopies performed later in the day, when adenoma detection rates typically declined, perhaps owing to fatigue.
These authors suggest that AI may have the potential to maintain high quality and homogeneity of colonoscopies and improve endoscopist performance in large screening programs and centers with high workloads.
“There’s a mishmash of different kinds of real-world studies coming in, and it’s very difficult to figure it all out,” Dr. Sharma said. “We just have to look at these devices as innovations and embrace them and work with them to see how it fits it in our practice.”
Perceptions and Expectations
Emerging evidence suggests that endoscopists’ perceptions and expectations may affect assessments of AI’s potential benefits in practice, Dr. Sharma noted.
“Someone might say, ‘I’m a trained physician. Why do I need a machine to help me?’ That can create a situation in which the endoscopist is constantly challenging the device, trying to overrule it or not give it credit.”
Others might perceive that the AI device will definitely help and therefore not look as carefully themselves for adenomas.
A study at The University of Texas MD Anderson Cancer Center in Houston in which activation of the AI system was at the discretion of the endoscopist found that real-time CADe did not improve adenoma detection among endoscopists with high baseline detection rates.
However, despite its availability, AI-assisted colonoscopy was activated in only half of the cases, and multiple concerns were raised by staff and endoscopists in a postprocedural survey. In particular, endoscopists were concerned that the system would result in too many false-positive signals (82.4%), was too distracting (58.8%), and prolonged procedure time (47.1%).
The authors of the Stanford study that found no benefit with CADe in routine practice noted, “Most concerning would be if, inadvertently, CADe use was accompanied by a simultaneous unconscious degradation in the quality of mucosal exposure, possibly due to a false sense of comfort that CADe would ensure a high-quality examination.”
“We’re trying to evaluate some of these interactions between endoscopists and AI devices both pragmatically in practice as well as in clinical trials,” Dr. Sharma said. “Much depends on the context of how you approach and present the devices. We tell physicians that this is an assist device, not something you’re competing against and not something that’s here to replace you. This is something which may make your lives easier, so try it out.”
Are Less Experienced Endoscopists Helped More?
It seems intuitive that less experienced endoscopists would be helped by AI, and indeed, some recent studies confirm this.
A small randomized controlled trial in Japan, presented during the Presidential Plenary at the American Society for Gastrointestinal Endoscopy (ASGE) annual meeting in May 2023, showed that a CADe system was “particularly useful” for beginning endoscopists, who had lower adenoma miss rates with the device vs a white light control device.
Another randomized controlled trial in Japan found that CADe use was associated with an increased overall ADR among endoscopists in training.
But experienced endoscopists probably can benefit as well, noted Jennifer Christie, MD, Division Director, Gastroenterology and Hepatology at the University of Colorado School of Medicine Anschutz Medical Campus in Aurora.
“We know that these AI devices can be useful in training our fellows to detect certain lesions in the colon,” she said. “However, they’re also helpful for many very seasoned practitioners, as an adjunctive tool to help in terms of diagnosis.”
Some studies reflect that dual benefit.
The AID-2 study, designed specifically to look at whether experience had an effect on AI findings during colonoscopy, was conducted among nonexpert endoscopists (lifetime volume of less than 2000 colonoscopies). The researchers, including Dr. Sharma, found that CADe increased the ADR by 22% compared with the control group.
An earlier study, AID-1 , used a similar design but was conducted among experienced endoscopists. In AID-1, the ADR was also significantly higher in the CADe group (54.8%) compared with the control group (40.4%), and adenomas detected per colonoscopy were significantly higher in the CADe group (mean, 1.07) than in the control group (mean, 0.71).
A multivariate post hoc analysis that pooled results from both AID-1 and AID-2 showed that use of CADe and colonoscopy indication, but not the level of examiner experience, were associated with ADR differences. This led the researchers to conclude, “Experience appears to play a minor role as a determining factor for ADR.”
Similarly, a 2023 study from China looked at the mean number of adenomas detected per colonoscopy according to the endoscopist’s experience. All rates were significantly higher in AI-assisted colonoscopies compared with conventional non-AI colonoscopy: overall ADR, 39.9% vs 32.4%; advanced ADR, 6.6% vs 4.9%; ADR of expert endoscopists, 42.3% vs 32.8%; ADR of nonexpert endoscopists, 37.5% vs 32.1%; and adenomas per colonoscopy, 0.59 vs 0.45, respectively.
The authors concluded that “AI-assisted colonoscopy improved overall ADR, advanced ADR, and ADR of both expert and nonexpert attending endoscopists.”
Improving the Algorithms
Experts agree that current and future research will improve the accuracy and quality of AI colonoscopy for all users, leading to new standards and more consistent outcomes in both clinical trials and real-world applications.
Work underway now to improve the algorithms will be an important step in that direction, according to Dr. Christie.
“We need to have enough information to create AI algorithms that allow us to detect early lesions, at least from an imaging standpoint, and we need to improve and increase the sensitivity and the specificity, as well as the predictive value,” she said.
AI can also play a role in health equity, she noted.
“But it’s a double-edged sword, because it depends again on algorithms and machine learning. Perhaps AI can eliminate some of the bias in our clinical decision-making. However, if we don’t train the machine properly with a good, diverse sample of patients and figure out how to integrate some of the social determinants of health that a computer may not otherwise consider, it can create larger disparities and larger biases. AI devices can only be as good and as inclusive as we make them,” Dr. Christie said.
Looking Ahead
Dr. Sharma predicts that “the next slew of studies are going to be on characterization — not just saying there’s an abnormality but distinguishing it further and saying whether the lesion is noncancerous, precancerous, or cancer.”
Other studies will focus on quality improvement of factors, such as withdrawal time and bowel preparation.
In its clinical practice update on AI, the American Gastroenterological Association states, “Eventually, we predict an AI suite of tools for colonoscopy will seem indispensable, as a powerful adjunct to support safe and efficient clinical practice. AI tools that improve colonoscopy quality may become more accepted, and perhaps demanded, by payors, administrators, and possibly even by well-informed patients who want to ensure the highest-quality examination of their colon.”
Dr. Sharma and Dr. Christie disclose no relevant conflicts of interest.
A version of this article appeared on Medscape.com.