ABSTRACT
Early detection of oral cancer necessitates a minimally invasive, tissue-specific diagnostic tool that facilitates screening/surveillance. Brush biopsy, though minimally invasive, demands skilled cyto-pathologist expertise. In this study, we explored the clinical utility/efficacy of a tele-cytology system in combination with Artificial Neural Network (ANN) based risk-stratification model for early detection of oral potentially malignant (OPML)/malignant lesion. A portable, automated tablet-based tele-cytology platform capable of digitization of cytology slides was evaluated for its efficacy in the detection of OPML/malignant lesions (n = 82) in comparison with conventional cytology and histology. Then, an image pre-processing algorithm was established to segregate cells, ANN was trained with images (n = 11,981) and a risk-stratification model developed. The specificity, sensitivity and accuracy of platform/ stratification model were computed, and agreement was examined using Kappa statistics. The tele-cytology platform, Cellscope, showed an overall accuracy of 84-86% with no difference between tele-cytology and conventional cytology in detection of oral lesions (kappa, 0.67-0.72). However, OPML could be detected with low sensitivity (18%) in accordance with the limitations of conventional cytology. The integration of image processing and development of an ANN-based risk stratification model improved the detection sensitivity of malignant lesions (93%) and high grade OPML (73%), thereby increasing the overall accuracy by 30%. Tele-cytology integrated with the risk stratification model, a novel strategy established in this study, can be an invaluable Point-of-Care (PoC) tool for early detection/screening in oral cancer. This study hence establishes the applicability of tele-cytology for accurate, remote diagnosis and use of automated ANN-based analysis in improving its efficacy.
Subject(s)
Cytodiagnosis/methods , Early Detection of Cancer , Mouth Neoplasms/diagnosis , Point-of-Care Systems , Telemedicine/methods , Algorithms , Female , Humans , Image Processing, Computer-Assisted , Male , Middle Aged , Neural Networks, Computer , Risk Assessment , Sensitivity and SpecificityABSTRACT
BACKGROUND: India is highly endemic for rabies. Although fatal, rabies is a preventable disease. Several factors interfere with the timely utilization of post exposure prophylaxis (PEP) in the population. There is a need to explore the factors leading to delay in PEP initiation. OBJECTIVE: To study the factors associated with delay in initiation of PEP among animal bite cases attending anti-rabies clinic in the out-patient department (OPD) of a hospital in Delhi. MATERIALS AND METHODS: A cross-sectional hospital based study was conducted among 200 patients attending the anti-rabies clinic. After obtaining informed consent, the patients were interviewed using a pre-tested, semi-structured questionnaire to find out the delay in initiation of PEP and the factors associated with it. RESULTS: Most common biting animal was found to be dog (96%). Out of the studied subjects (n=200), 134 (67%) were males, 123 (61.5%) were from rural areas and 61 (30.5%) were illiterate. Delay in initiation (vaccine initiation in more than or equal to 48 h) of PEP was found among 41% of the studied subjects. The mean time spent during each visit by the study subjects were 3.46 h (SD 1.60). Delay was more likely in people living at a distance of more than 10 km from the vaccination centre (p<0.001) and with a monthly family income less than 5000 INR (p=0.004). Delay showed an increasing trend with age (p=0.041). Most commonly cited reasons by the respondents (n=82) for the inability to come early for vaccination included work related barriers (42.68%), anti-rabies clinic being closed on Sundays/national holidays (36.59%) and unawareness about timely PEP (31.71%). CONCLUSION: Accessibility and lower economic status were the major factors associated with delay in initiation of PEP for rabies prevention.