Document text
Principal Investigator: Sharmila Anandasabapathy
Organization: BAYLOR COLLEGE OF MEDICINE
Fiscal Year: 2024
Award: $557,624
Funding agency: National Cancer Institute
Abstract: Esophageal cancer is the 6th most common cause of cancer-related mortality worldwide. While
esophageal squamous cell neoplasia (ESCN) carries a significant global burden, those in certain underserved
geographic regions (South America, eastern Africa, eastern Iran, northern China) have particularly high
incidence and mortality rates due to lack of endoscopic screening capacity. While endoscopy with Lugol’s
chromoendoscopy or “digital” chromoendoscopy has shown high sensitivity (>95%) for screening, specificity is
poor (<60%) and false-positive results abound due to confounding inflammatory areas. As a result, standard of
care endoscopy produces many unnecessary biopsies, increasing risk and cost of endoscopic screening and
surveillance.
In our ongoing R01 project, we developed and validated a mobile, high-resolution microendoscope (mHRME)
for screening and surveillance of ESCN. Despite ≥2 years of COVID delays, which especially impacted the
Chinese sites, we completed: (1) a randomized, controlled clinical trial (USA and China; n=918) of mHRME with
visual interpretation in patients undergoing screening or surveillance for esophageal squamous cell neoplasia,
(2) deep-learning software algorithms for automated detection of neoplastic images, and (3) a pilot trial (n=41)
of the software-assisted mHRME in Brazil. The trial revealed higher specificity for qualitative (visual)
interpretation by experts but not novices, in surveillance arm (100% vs. 19%, p<0.05). In the screening arm,
diagnostic yield (neoplastic biopsies/total biopsies) increased 3.6 times (8 to 29%); 16% of patients were
correctly spared any biopsy; and 18% had a change in clinical plan. In a single-arm pilot study, we also evaluated
an artificial intelligence-based mobile HRME (AI-mHRME) in 41 Brazilian subjects. This study (January 2022)
confirmed that quantitative interpretation (AI-mHRME) doubled diagnostic yield, improved endoscopists’
confidence, and had significant clinical impact (change of clinical plan in 64%). Our initial deep-learning algorithm
had a sensitivity/specificity of 100%/85%. Participating clinicians uniformly said they favored an AI-guided
approach but expressed concerns about its implementation.
In this competing renewal, we will build on this valuable global data to optimize an AI-mHRME and evaluate
its clinical impact and implementation potential in ethnically and socioeconomically diverse populations in the
USA and Brazil. A stakeholder-engaged approach will be used to evaluate barriers, acceptability,
appropriateness, and feasibility of using AI-mHRME in ESCN management and to determine contextual factors
influencing adoption. Data obtained will facilitate implementation and dissemination of innovative, AI-assisted
cancer screening strategies in diverse populations and other cancers.
Terms: <AI system><Adoption><Algorithmic Software><Algorithmic Tools><Algorithms><Anal><Anus><Application Context><Area><Artificial Intelligence><Biopsy><Brazil><COVID-19><CV-19><Cancer Cause><Cancer Etiology><Cancer Hospital><Cancers><Carcinoma><Cell Nucleus><China><Chinese><Classification><Clinical><Clinical Research><Clinical Study><Colon><Computer Assisted><Computer Reasoning><Computer software><Computers><Coronavirus Infectious Disease 2019><Data><Data Set><Death Rate><Detection><Devices><Diagnosis><Diagnostic><Dissemination and Implementation><Early Diagnosis><Eastern Africa><Effectiveness><Endoscopy><Environment><Epithelial cancer><Epithelium><Esophageal Cancer><Esophagus><Esophagus Cancer><Ethnic Origin><Ethnicity><Evaluation><Geographic Area><Geographic Locations><Geographic Region><Geographical Location><Goals><Health Status><Hospitals><Image><Incidence><Inflammatory><International><Iran><Language><Level of Health><Machine Intelligence><Mainland China><Malignant Epithelial Neoplasms><Malignant Epithelial Tumors><Malignant Esophageal Neoplasm><Malignant Esophageal Tumor><Malignant Neoplasms><Malignant Tumor><Malignant Tumor of the Esophagus><Malignant neoplasm of esophagus><Microscopic><Modeling><Neoplasms><Nuclear><Nucleus><Optical Biopsy><Oral><Participant><Patients><Performance><Pilot Projects><Population Heterogeneity><Preventative strategy><Prevention strategy><Preventive strategy><Randomized Controlled Clinical Trials><Randomized, Controlled Trials><Resolution><Risk><Screening for cancer><Sensitivity and Specificity><Site><Skin><Software><Software Algorithm><South America><Specificity><Speed><Stomach><Systematics><Technology><Testing><Texas><Time><Training><Validation><Veterans Hospitals><Visual><Work><arm><automated algorithm><automatic algorithm><cancer prevention><chromoendoscopy><chromoscopy><clinical relevance><clinically relevant><computer aided><contextual factors><coronavirus disease 2019><coronavirus disease-19><coronavirus infectious disease-19><cost><deep learning><deep learning algorithm><deep learning method><deep learning strategy><digital><diverse populations><early cancer detection><early detection><endomicroscopy><endomicrosope><endoscopic imaging><epithelial carcinoma><esophageal squamous cell neoplasia><experience><gastric><geographic site><handheld mobile device><health level><health literacy><heterogeneous population><high risk><imaging><implementation facilitation><improved><innovate><innovation><innovative><malignancy><microendoscope><microendoscopy><microscope imaging><microscopic imaging><microscopy imaging><mobile device><mortality><mortality rate><mortality ratio><neoplasia><neoplasm/cancer><neoplastic><neoplastic growth><oesophageal cancer><patient population><pilot study><pilot trial><population diversity><portability><randomized control clinical trial><randomized control trial><resolutions><screening><screening cancer patients><screenings><simulation><socio-economic><socio-economically><socioeconomically><socioeconomics><standard of care><validations>