Internal validation of Automated Visual Evaluation (AVE) on smartphone images for cervical cancer screening in a prospective study in Zambia.

OBJECTIVES: Visual inspection with acetic acid (VIA) is a low-cost approach for cervical cancer screening used in most low- and middle-income countries (LMICs) but, similar to other visual tests, is subjective and requires sustained training and quality assurance. We developed, trained, and validated an artificial-intelligence-based "Automated Visual Evaluation" (AVE) tool that can be adapted to run on smartphones to assess smartphone-captured images of the cervix and identify precancerous lesions, helping augment VIA performance. DESIGN: Prospective study. SETTING: Eight public health facilities in Zambia. PARTICIPANTS: A total of 8204 women aged 25-55. INTERVENTIONS: Cervical images captured on commonly used low-cost smartphone models were matched with key clinical information including human immunodeficiency virus (HIV) and human papillomavirus (HPV) status, plus histopathology analysis (where applicable), to develop and train an AVE algorithm and evaluate its performance for use as a primary screen and triage test for women who are HPV positive. MAIN OUTCOME MEASURES: Area under the receiver operating curve (AUC); sensitivity; specificity. RESULTS: As a general population screening tool for cervical precancerous lesions, AVE identified cases of cervical precancerous and cancerous (CIN2+) lesions with high performance (AUC = 0.91, 95% confidence interval [CI] = 0.89-0.93), which translates to a sensitivity of 85% (95% CI = 81%-90%) and specificity of 86% (95% CI = 84%-88%) based on maximizing the Youden's index. This represents a considerable improvement over naked eye VIA, which as per a meta-analysis by the World Health Organization (WHO) has a sensitivity of 66% and specificity of 87%. For women living with HIV, the AUC of AVE was 0.91 (95% CI = 0.88-0.93), and among those testing positive for high-risk HPV types, the AUC was 0.87 (95% CI = 0.83-0.91). CONCLUSIONS: These results demonstrate the feasibility of utilizing AVE on images captured using a commonly available smartphone by nurses in a screening program, and support our ongoing efforts for moving to more broadly evaluate AVE for its clinical sensitivity, specificity, feasibility, and acceptability across a wider range of settings. Limitations of this study include potential inflation of performance estimates due to verification bias (as biopsies were only obtained from participants with visible aceto-white cervical lesions) and due to this being an internal validation (the test data, while independent from that used to develop the algorithm was drawn from the same study).

Internal Validation of Automated Visual Evaluation (AVE) on Smartphone Images for Cervical Cancer Screening in a Prospective Study in Zambia.

Objectives: Visual inspection with acetic acid (VIA) is a low-cost approach for cervical cancer screening used in most low- and middle-income countries (LMICs) but, similar to other visual tests like histopathology, is subjective and requires sustained training and quality assurance. We developed, trained, and validated an artificial-intelligence-based "Automated Visual Evaluation" (AVE) tool that can be adapted to run on smartphones to assess smartphone-captured images of the cervix and identify precancerous lesions, helping augment performance of VIA. Design: Prospective study. Setting: Eight public health facilities in Zambia. Participants: 8,204 women aged 25-55. Interventions: Cervical images captured on commonly used low-cost smartphone models were matched with key clinical information including human immunodeficiency virus (HIV) and human papillomavirus (HPV) status, plus histopathology analysis (where applicable), to develop and train an AVE algorithm and evaluate its performance for use as a primary screen and triage test for women who are HPV positive. Main outcome measures: Area under the receiver operating curve (AUC); sensitivity; specificity. Results: As a general population screening for cervical precancerous lesions, AVE identified cases of cervical precancerous and cancerous (CIN2+) lesions with high performance (AUC = 0.91, 95% confidence interval [CI] = 0.89 to 0.93), which translates to a sensitivity of 85% (95% CI = 81% to 90%) and specificity of 86% (95% CI = 84% to 88%) based on maximizing the Youden's index. This represents a considerable improvement over VIA, which a meta-analysis by the World Health Organization (WHO) estimates to have sensitivity of 66% and specificity of 87%. For women living with HIV, the AUC of AVE was 0.91 (95% CI = 0.88 to 0.93), and among those testing positive for high-risk HPV types, the AUC was 0.87 (95% CI = 0.83 to 0.91). Conclusions: These results demonstrate the feasibility of utilizing AVE on images captured using a commonly available smartphone by screening nurses and support our transition to clinical evaluation of AVE's sensitivity, specificity, feasibility, and acceptability across a broader range of settings. The performance of the algorithm as reported may be inflated, as biopsies were obtained only from study participants with visible aceto-white cervical lesions, which can lead to verification bias; and the images and data sets used for testing of the model, although "unseen" by the algorithm during training, were acquired from the same set of patients and devices, limiting the study to that of an internal validation of the AVE algorithm.

An artificial intelligence algorithm is highly accurate for detecting endoscopic features of eosinophilic esophagitis.

The endoscopic features associated with eosinophilic esophagitis (EoE) may be missed during routine endoscopy. We aimed to develop and evaluate an Artificial Intelligence (AI) algorithm for detecting and quantifying the endoscopic features of EoE in white light images, supplemented by the EoE Endoscopic Reference Score (EREFS). An AI algorithm (AI-EoE) was constructed and trained to differentiate between EoE and normal esophagus using endoscopic white light images extracted from the database of the University Hospital Augsburg. In addition to binary classification, a second algorithm was trained with specific auxiliary branches for each EREFS feature (AI-EoE-EREFS). The AI algorithms were evaluated on an external data set from the University of North Carolina, Chapel Hill (UNC), and compared with the performance of human endoscopists with varying levels of experience. The overall sensitivity, specificity, and accuracy of AI-EoE were 0.93 for all measures, while the AUC was 0.986. With additional auxiliary branches for the EREFS categories, the AI algorithm (AI-EoE-EREFS) performance improved to 0.96, 0.94, 0.95, and 0.992 for sensitivity, specificity, accuracy, and AUC, respectively. AI-EoE and AI-EoE-EREFS performed significantly better than endoscopy beginners and senior fellows on the same set of images. An AI algorithm can be trained to detect and quantify endoscopic features of EoE with excellent performance scores. The addition of the EREFS criteria improved the performance of the AI algorithm, which performed significantly better than endoscopists with a lower or medium experience level.

Laryngopharyngeal Reflux and Atypical Gastroesophageal Reflux Disease.

Laryngopharyngeal reflux and atypical manifestations of gastroesophageal reflux disease have a high economic and social burden in the United States. There is increasing research supporting the reflex theory and hypersensitivity syndrome underlying this disease pathophysiology. Novel diagnostic biomarkers have gained more traction in the search for a more reliable diagnostic tool, but further research is needed. Current standard-of-care treatment relies on proton pump inhibitor therapy. Antireflux surgery is usually not recommended. Neuromodulators and treatments targeting specific neuronal receptors are discussed. A diagnostic algorithm is proposed for the evaluation of laryngeal symptoms suspected to be related to extraesophageal reflux disease.

Mucosal Impedance: a New Approach to Diagnosing Gastroesophageal Reflux Disease and Eosinophilic Esophagitis.

PURPOSE OF REVIEW: In this review, we discuss current diagnostic testing modalities for both gastroesophageal reflux disease (GERD) and eosinophilic esophagitis (EoE) and then introduce mucosal impedance (MI), a novel technology that measures epithelial integrity in real time during endoscopy. We describe the advantages and disadvantages of MI as compared with traditional diagnostic testing. RECENT FINDINGS: We review studies that demonstrate that GERD and EoE have distinct MI patterns, and that physicians can accurately diagnose and distinguish the two during endoscopy with minimal time added to the procedure. We also review studies showing that MI has the capability to assess treatment response in both GERD and EoE and that it can be used to diagnose GERD in patients with extraesophageal reflux symptoms. Mucosal impedance testing is a major advancement in the diagnosis of GERD and EoE. Future studies are planned to assess whether MI can be used as a treatment endpoint in EoE and whether it can be used to predict response to anti-reflux surgery.

Membranous glomerulonephritis with crescents.

PURPOSE: The coexistence of membranous glomerulonephritis (MGN) and necrotizing and crescentic glomerulonephritis (NCGN) is an unusual finding in a renal biopsy except in lupus nephritis. Little is known about whether these lesions are causally related in any clinical setting. METHODS: We reviewed the pathology, presentation, and clinical course of 13 non-lupus patients with combined MGN and NCGN in native kidney biopsies (nine females, four males; median age 69 years), with particular attention to evidence of secondary MGN. Additional IgG subclass and phospholipase A2 receptor (PLA2R) immunofluorescence studies were conducted in seven cases. RESULTS: Eight biopsies were pauci-immune other than the capillary wall deposits of MGN; one patient had a non-lupus immune complex disease, and four had mesangial deposits, including one with rare subendothelial deposits. None had anti-glomerular basement membrane disease. IgG4 was dominant or codominant in the capillary wall deposits in three cases and virtually absent in four; PLA2R was positive in two cases, and negative in five. Seven patients were judged to have secondary MGN, including five of eight ANCA+ patients. Twelve patients were treated with combinations of steroids, cyclophosphamide, rituximab, followed by durable response in seven and relentless progression to end stage renal disease in four. CONCLUSIONS: Secondary MGN occurs with higher frequency in ANCA-positive NCGN than in the general MGN population. A causal relationship between MGN and NCGN was not established in any patient, but circumstances suggest a common cause in several, including immune complex disease, drug reaction and paraneoplastic syndrome.