IMPORTANCE Cervical cancer is highly preventable but remains a common and deadly cancer in areas without screening programs. The creation of a diagnostic system to digitize Papanicolaou test samples and analyze them using a cloud-based deep learning system (DLS) may provide needed cervical cancer screening to resource-limited areas. OBJECTIVE To determine whether artificial intelligence-supported digital microscopy diagnostics can be implemented in a resource-limited setting and used for analysis of Papanicolaou tests. DESIGN, SETTING, AND PARTICIPANTS In this diagnostic study, cervical smears from 740 HIV-positive women aged between 18 and 64 years were collected between September 1, 2018, and September 30, 2019. The smears were digitized with a portable slide scanner, uploaded to a cloud server using mobile networks, and used to train and validate a DLS for the detection of atypical cervical cells. This single-center study was conducted at a local health care center in rural Kenya. EXPOSURES Detection of squamous cell atypia in the digital samples by analysis with the DLS. MAIN OUTCOMES AND MEASURES The accuracy of the DLS in the detection of low-and highgrade squamous intraepithelial lesions in Papanicolaou test whole-slide images. RESULTS Papanicolaou test results from 740 HIV-positive women (mean [SD] age, 41.8 [10.3] years) were collected. The DLS was trained using 350 whole-slide images and validated on 361 whole-slide images (average size, 100 387 × 47 560 pixels). For detection of cervical cellular atypia, sensitivities were 95.7% (95% CI, 85.5%-99.5%) and 100% (95% CI, 82.4%-100%), and specificities were 84.7% (95% CI, 80.2%-88.5%) and 78.4% (95% CI, 73.6%-82.4%), compared with the pathologist assessment of digital and physical slides, respectively. Areas under the receiver operating characteristic curve were 0.94 and 0.96, respectively. Negative predictive values were high (99%-100%), and accuracy was high, particularly for the detection of high-grade lesions. Interrater agreement was substantial compared with the pathologist assessment of digital slides (κ = 0.72) and fair compared with the assessment of glass slides (κ = 0.36). No samples that were classified as high grade by manual sample analysis had false-negative assessments by the DLS. CONCLUSIONS AND RELEVANCE In this study, digital microscopy with artificial intelligence was implemented at a rural clinic and used to detect atypical cervical smears with a high sensitivity compared with visual sample analysis.

Cervical cancer is highly preventable but remains a common and deadly cancer in areas without screening programmes. Pap smear analysis is the most commonly used screening method but is labour-intensive, subjective and requires access to medical experts. We developed a diagnostic system in which microscopy samples are digitized at the point-of-care (POC) and analysed by a cloud-based deep-learning system (DLS) and evaluated the system for the detection of cervical cell atypia in Pap smears at a peripheral clinic in Kenya. A total of 740 conventional Pap smears were collected, digitized with a portable slide scanner and uploaded over mobile networks to a cloud server for training and validation of the system. In total, 16,133 manually-annotated image regions where used for training of the DLS. The DLS achieved a high average sensitivity (97.85%; 95% confidence interval (CI) 83.95-99.75%) and area under the curve (AUCs) (0.95) for the detection of cervical-cellular atypia, compared to the pathologist assessment of digital and physical slides. Specificity was higher for high-grade atypia (95.9%; 95% CI 94.9-97.6%) than for low-grade atypia (84.2%; 95% CI 79.9-87.9%). Negative predictive values were high (99.3-100%), and no samples classified as high grade by manual sample analysis had false-negative assessments by the DLS. The study shows that advanced digital microscopy diagnostics supported by machine learning algorithms is implementable in rural, resource-constrained areas, and can achieve a diagnostic accuracy close to the level of highly trained experts.