Chatbot Artificial Intelligence for Genetic Cancer Risk Assessment and Counseling: A Systematic Review and Meta-Analysis.

PURPOSE: Most individuals with a hereditary cancer syndrome are unaware of their genetic status to underutilization of hereditary cancer risk assessment. Chatbots, or programs that use artificial intelligence to simulate conversation, have emerged as a promising tool in health care and, more recently, as a potential tool for genetic cancer risk assessment and counseling. Here, we evaluated the existing literature on the use of chatbots in genetic cancer risk assessment and counseling. METHODS: A systematic review was conducted using key electronic databases to identify studies which use chatbots for genetic cancer risk assessment and counseling. Eligible studies were further subjected to meta-analysis. RESULTS: Seven studies met inclusion criteria, evaluating five distinct chatbots. Three studies evaluated a chatbot that could perform genetic cancer risk assessment, one study evaluated a chatbot that offered patient counseling, and three studies included both functions. The pooled estimated completion rate for the genetic cancer risk assessment was 36.7% (95% CI, 14.8 to 65.9). Two studies included comprehensive patient characteristics, and none involved a comparison group. Chatbots varied as to the involvement of a health care provider in the process of risk assessment and counseling. CONCLUSION: Chatbots have been used to streamline genetic cancer risk assessment and counseling and hold promise for reducing barriers to genetic services. Data regarding user and nonuser characteristics are lacking, as are data regarding comparative effectiveness to usual care. Future research may consider the impact of chatbots on equitable access to genetic services.

A decade of systematic reviews: an assessment of Weill Cornell Medicine's systematic review service.

Background: The Weill Cornell Medicine, Samuel J. Wood Library's Systematic Review (SR) service began in 2011, with 2021 marking a decade of service. This paper will describe how the service policies have grown and will break down our service quantitatively over the past 11 years to examine SR timelines and trends. Case Presentation: We evaluated 11 years (2011-2021) of SR request data from our in-house documentation. In the years assessed, there have been 319 SR requests from 20 clinical departments, leading to 101 publications with at least one librarian collaborator listed as co-author. The average review took 642 days to publication, with the longest at 1408 days, and the shortest at 94 days. On average, librarians spent 14.7 hours in total on each review. SR projects were most likely to be abandoned at the title/abstract screening phase. Several policies have been put into place over the years in order to accommodate workflows and demand for our service. Discussion: The SR service has seen several changes since its inception in 2011. Based on the findings and emerging trends discussed here, our service will inevitably evolve further to adapt to these changes, such as machine learning-assisted technology.

The accuracy of race & ethnicity data in US based healthcare databases: A systematic review.

BACKGROUND: The availability and accuracy of data on a patient's race/ethnicity varies across databases. Discrepancies in data quality can negatively impact attempts to study health disparities. METHODS: We conducted a systematic review to organize information on the accuracy of race/ethnicity data stratified by database type and by specific race/ethnicity categories. RESULTS: The review included 43 studies. Disease registries showed consistently high levels of data completeness and accuracy. EHRs frequently showed incomplete and/or inaccurate data on the race/ethnicity of patients. Databases had high levels of accurate data for White and Black patients but relatively high levels of misclassification and incomplete data for Hispanic/Latinx patients. Asians, Pacific Islanders, and AI/ANs are the most misclassified. Systems-based interventions to increase self-reported data showed improvement in data quality. CONCLUSION: Data on race/ethnicity that is collected with the purpose of research and quality improvement appears most reliable. Data accuracy can vary by race/ethnicity status and better collection standards are needed.