COVID-19 analytics: Towards the effect of vaccine brands through analyzing public sentiment of tweets

A systematic review and future research agenda on detection of polycystic ovary syndrome (PCOS) with computer-aided techniques

Polycystic Ovary Syndrome (PCOS) is among the most prevalent endocrinological abnormalities seen in reproductive female bodies posing serious health hazards. The correctness of interpreting this condition depends heavily on the wide spectrum of associated symptoms and the doctor's expertise, making real-time clinical detection quite challenging. Thus, investigations on computer-aided PCOS detection systems have recently been explored by several researchers worldwide as a potential replacement for manual assessment. This review study's objective is to analyze the relevant research works on computer-assisted methods for automatically identifying PCOS through a systematic literature review (SLR) methodology as well as investigate the research limitations and explore potential future research scopes in this domain. 28 articles have been selected using the PRISMA approach based on a set of inclusion-exclusion criteria for conducting the review. The data synthesis of the selected articles has been conducted using six data exploration themes. As outcomes, the SLR explored the topical association between the studies; their research profiles; objectives; data size, type, and sources; methodologies applied for the detection of PCOS; and lastly the research outcomes along with their evaluation measures and performances. The study also highlights areas for future research directions examining the study gaps to enhance the current efforts for autonomous PCOS identification; such as integrating advanced techniques with the current methods; developing interactive software systems; exploring deep learning and unsupervised machine learning techniques; enhancing datasets and country context; and investigating more unknown factors behind PCOS. Thus, this SLR provides a state-of-the-art paradigm of autonomous PCOS detection which will support significantly efficient clinical assessment, diagnosis and treatment of PCOS.