Barriers to Surgical Outcomes Research in Low- and Middle-Income Countries: A Scoping Review.

INTRODUCTION: Systematic collection and analysis of surgical outcomes data is a cornerstone of surgical quality improvement. Unfortunately, there remains a dearth of surgical outcomes data from low- and middle-income countries (LMICs). To improve surgical outcomes in LMICs, it is essential to have the ability to collect, analyze, and report risk-adjusted postoperative morbidity and mortality data. This study aimed to review the barriers and challenges to developing perioperative registries in LMIC settings. METHODS: We conducted a scoping review of all published literature on barriers to conducting surgical outcomes research in LMICs using PubMed, Embase, Scopus, and GoogleScholar. Keywords included 'surgery', 'outcomes research', 'registries', 'barriers', and synonymous Medical Subject Headings derivatives. Articles found were subsequently reference-mined. All relevant original research and reviews published between 2000 and 2021 were included. The performance of routine information system management framework was used to organize identified barriers into technical, organizational, or behavioral factors. RESULTS: Twelve articles were identified in our search. Ten articles focused specifically on the creation, success, and obstacles faced during the implementation of trauma registries. Technical factors reported by 50% of the articles included limited access to a digital platform for data entry, lack of standardization of forms, and complexity of said forms. 91.7% articles mentioned organizational factors, including the availability of resources, financial constraints, human resources, and lack of consistent electricity. Behavioral factors highlighted by 66.6% of the studies included lack of team commitment, job constraints, and clinical burden, which contributed to poor compliance and dwindling data collection over time. CONCLUSIONS: There is a paucity of published literature on barriers to developing and maintaining perioperative registries in LMICs. There is an immediate need to study and understand barriers and facilitators to the continuous collection of surgical outcomes in LMICs.

Deep learning applications in neuro-oncology.

Deep learning (DL) is a relatively newer subdomain of machine learning (ML) with incredible potential for certain applications in the medical field. Given recent advances in its use in neuro-oncology, its role in diagnosing, prognosticating, and managing the care of cancer patients has been the subject of many research studies. The gamut of studies has shown that the landscape of algorithmic methods is constantly improving with each iteration from its inception. With the increase in the availability of high-quality data, more training sets will allow for higher fidelity models. However, logistical and ethical concerns over a prospective trial comparing prognostic abilities of DL and physicians severely limit the ability of this technology to be widely adopted. One of the medical tenets is judgment, a facet of medical decision making in DL that is often missing because of its inherent nature as a "black box." A natural distrust for newer technology, combined with a lack of autonomy that is normally expected in our current medical practices, is just one of several important limitations in implementation. In our review, we will first define and outline the different types of artificial intelligence (AI) as well as the role of AI in the current advances of clinical medicine. We briefly highlight several of the salient studies using different methods of DL in the realm of neuroradiology and summarize the key findings and challenges faced when using this nascent technology, particularly ethical challenges that could be faced by users of DL.