Publications by authors named "R Saidu"
Article Synopsis
- Cervical cancer screening in low- and middle-income countries (LMICs) faces challenges due to a lack of specialists and costly diagnostic tools, prompting researchers to create low-cost portable devices and automate image analysis for better decision-making.
- A systematic review was conducted to evaluate the range of automated technology systems used for cervical cancer screening, resulting in 17 studies using mobile device images and 56 studies using conventional devices.
- The findings show that computer-aided diagnostics (CAD) outperform manual analysis in accuracy, but the clinical validation of these novel devices is still insufficient in LMICs where they are most needed.
A number of challenges hinder artificial intelligence (AI) models from effective clinical translation. Foremost among these challenges is the lack of generalizability, which is defined as the ability of a model to perform well on datasets that have different characteristics from the training data. We recently investigated the development of an AI pipeline on digital images of the cervix, utilizing a multi-heterogeneous dataset of 9,462 women (17,013 images) and a multi-stage model selection and optimization approach, to generate a diagnostic classifier able to classify images of the cervix into "normal", "indeterminate" and "precancer/cancer" (denoted as "precancer+") categories.
View Article and Find Full Text PDFHuman papillomavirus (HPV)-based screen-and-treat (SAT) is recommended but implementation presents operational challenges. We implemented HPV-SAT at a research site in Khayelitsha, South Africa, screening 3062 women aged 30-65 years (44% women living with HIV [WHIV]). All were screened using point-of-care Xpert HPV and almost all received their HPV results on the same day.
View Article and Find Full Text PDFBackground: Nigeria has the highest number of maternal deaths in the world, which is a major public health problem. One of the major contributory factors is high prevalence of unskilled birth attendance from low facility delivery. However, the reasons for and against facility delivery are complex and not fully understood.
View Article and Find Full Text PDFIntroduction: We assessed the implementation context and image quality in preparation for a clinical study evaluating the effectiveness of automated visual assessment devices within cervical cancer screening of women living without and with HIV.
Methods: We developed a semi-structured questionnaire based on three Consolidated Framework for Implementation Research (CFIR) domains; intervention characteristics, inner setting, and process, in Cape Town, South Africa. Between December 1, 2020, and August 6, 2021, we evaluated two devices: MobileODT handheld colposcope; and a commercially-available cell phone (Samsung A21ST).