BACKGROUND: Smartphones recently have been applied in the medical setting. However, the literature evaluating the utility of smartphones in gynecologic oncology is limited. OBJECTIVE: To evaluate the utility of a smartphone in the detection of uterine cervical lesions in patients with abnormal cervical cytology. STUDY DESIGN: Seventy-five women with abnormal cervical cytology were enrolled. Two doctors independently inspected the uterine cervix by using smartphone or colposcopy. Images were captured using acetic acid, and biopsies were taken as standard-of-care procedures. The diagnostic performance of the smartphone for cervical intraepithelial neoplasm 1 or worse and cervical intraepithelial neoplasm 2 or worse were evaluated, and the kappa value was calculated to determine the chance corrected agreement of the histologic diagnoses based on the smartphone and colposcopic findings. RESULTS: There was a substantial agreement between histologic diagnoses based on the smartphone and colposcopic findings, with a kappa value of 0.67 (95% confidence interval, 0.43-0.90). The sensitivity, specificity, positive predictive value, and negative predictive value of the smartphone in the diagnosis of cervical intraepithelial neoplasm 1 or worse were 0.89 (95% confidence interval, 0.79-0.96), 0.33 (95% confidence interval, 0.08-0.70), 0.91 (95% confidence interval, 0.81-0.97), and 0.30 (95% confidence interval, 0.07-0.65), respectively. The sensitivity, specificity, positive predictive value, and negative predictive value in the diagnosis of cervical intraepithelial neoplasm 2 or worse were 0.92 (95% confidence interval, 0.81-0.98), 0.24 (95% confidence interval, 0.09-0.45), 0.71 (95% confidence interval, 0.58-0.81), and 0.60 (95% confidence interval, 0.26-0.88), respectively. CONCLUSION: We found that there was a substantial agreement between the histologic diagnoses based on the smartphone and colposcopic findings. The smartphone seems to be useful and may be an alternative to colposcopy.
BACKGROUND: Smartphones recently have been applied in the medical setting. However, the literature evaluating the utility of smartphones in gynecologic oncology is limited. OBJECTIVE: To evaluate the utility of a smartphone in the detection of uterine cervical lesions in patients with abnormal cervical cytology. STUDY DESIGN: Seventy-five women with abnormal cervical cytology were enrolled. Two doctors independently inspected the uterine cervix by using smartphone or colposcopy. Images were captured using acetic acid, and biopsies were taken as standard-of-care procedures. The diagnostic performance of the smartphone for cervical intraepithelial neoplasm 1 or worse and cervical intraepithelial neoplasm 2 or worse were evaluated, and the kappa value was calculated to determine the chance corrected agreement of the histologic diagnoses based on the smartphone and colposcopic findings. RESULTS: There was a substantial agreement between histologic diagnoses based on the smartphone and colposcopic findings, with a kappa value of 0.67 (95% confidence interval, 0.43-0.90). The sensitivity, specificity, positive predictive value, and negative predictive value of the smartphone in the diagnosis of cervical intraepithelial neoplasm 1 or worse were 0.89 (95% confidence interval, 0.79-0.96), 0.33 (95% confidence interval, 0.08-0.70), 0.91 (95% confidence interval, 0.81-0.97), and 0.30 (95% confidence interval, 0.07-0.65), respectively. The sensitivity, specificity, positive predictive value, and negative predictive value in the diagnosis of cervical intraepithelial neoplasm 2 or worse were 0.92 (95% confidence interval, 0.81-0.98), 0.24 (95% confidence interval, 0.09-0.45), 0.71 (95% confidence interval, 0.58-0.81), and 0.60 (95% confidence interval, 0.26-0.88), respectively. CONCLUSION: We found that there was a substantial agreement between the histologic diagnoses based on the smartphone and colposcopic findings. The smartphone seems to be useful and may be an alternative to colposcopy.