1. Point‐of‐care oral cytology tool for the screening and assessment of potentially malignant oral lesions
- Author
-
Sayli S. Modak, Steven J. Dietl, Glennon W. Simmons, Nadarajah Vigneswaran, Craig Murdoch, Nicolaos Christodoulides, Martin H. Thornhill, Denise A. Trochesset, John T. McDevitt, Roger Markham, Spencer W. Redding, Michael P. McRae, Stella K. Kang, and A. Ross Kerr
- Subjects
squamous cell carcinoma ,Adult ,Male ,Mild Dysplasia ,Oncology ,single‐cell analysis ,Cancer Research ,Epithelial dysplasia ,medicine.medical_specialty ,Cytodiagnosis ,Point-of-Care Systems ,Point-of-care testing ,030209 endocrinology & metabolism ,Logistic regression ,Malignancy ,Machine Learning ,03 medical and health sciences ,0302 clinical medicine ,oral epithelial dysplasia ,Internal medicine ,Biomarkers, Tumor ,medicine ,Humans ,Mass Screening ,Prospective Studies ,Medical diagnosis ,Early Detection of Cancer ,Point of care ,business.industry ,biomarkers ,Original Articles ,Middle Aged ,Models, Theoretical ,artificial intelligence ,medicine.disease ,3. Good health ,ROC Curve ,Cytopathology ,030220 oncology & carcinogenesis ,cytology ,Carcinoma, Squamous Cell ,Original Article ,Female ,Mouth Neoplasms ,business ,Algorithms ,Software ,point‐of‐care testing - Abstract
Background The effective detection and monitoring of potentially malignant oral lesions (PMOL) are critical to identifying early‐stage cancer and improving outcomes. In the current study, the authors described cytopathology tools, including machine learning algorithms, clinical algorithms, and test reports developed to assist pathologists and clinicians with PMOL evaluation. Methods Data were acquired from a multisite clinical validation study of 999 subjects with PMOLs and oral squamous cell carcinoma (OSCC) using a cytology‐on‐a‐chip approach. A machine learning model was trained to recognize and quantify the distributions of 4 cell phenotypes. A least absolute shrinkage and selection operator (lasso) logistic regression model was trained to distinguish PMOLs and cancer across a spectrum of histopathologic diagnoses ranging from benign, to increasing grades of oral epithelial dysplasia (OED), to OSCC using demographics, lesion characteristics, and cell phenotypes. Cytopathology software was developed to assist pathologists in reviewing brush cytology test results, including high‐content cell analyses, data visualization tools, and results reporting. Results Cell phenotypes were determined accurately through an automated cytological assay and machine learning approach (99.3% accuracy). Significant differences in cell phenotype distributions across diagnostic categories were found in 3 phenotypes (type 1 [“mature squamous”], type 2 [“small round”], and type 3 [“leukocytes”]). The clinical algorithms resulted in acceptable performance characteristics (area under the curve of 0.81 for benign vs mild dysplasia and 0.95 for benign vs malignancy). Conclusions These new cytopathology tools represent a practical solution for rapid PMOL assessment, with the potential to facilitate screening and longitudinal monitoring in primary, secondary, and tertiary clinical care settings., A point‐of‐care oral cytology tool has been developed for the noninvasive detection and monitoring of potentially malignant oral lesions. The distribution of cell phenotypes identified by machine learning and a cytology‐on‐a‐chip approach provides useful information as part of the assessment of oral lesions, with improved interpretability, calibration, and generalizability compared with conventional methods.
- Published
- 2020
- Full Text
- View/download PDF