Evaluation of ChatGPT's responses to information needs and information seeking of dementia patients.

Many people in the advanced stages of dementia require full-time caregivers, most of whom are family members who provide informal (non-specialized) care. It is important to provide these caregivers with high-quality information to help them understand and manage the symptoms and behaviors of dementia patients. This study aims to evaluate ChatGPT, a chatbot built using the Generative Pre-trained Transformer (GPT) large language model, in responding to information needs and information seeking of such informal caregivers. We identified the information needs of dementia patients based on the relevant literature (22 articles were selected from 2442 retrieved articles). From this analysis, we created a list of 31 items that describe these information needs, and used them to formulate 118 relevant questions. We then asked these questions to ChatGPT and investigated its responses. In the next phase, we asked 15 informal and 15 formal dementia-patient caregivers to analyze and evaluate these ChatGPT responses, using both quantitative (questionnaire) and qualitative (interview) approaches. In the interviews conducted, informal caregivers were more positive towards the use of ChatGPT to obtain non-specialized information about dementia compared to formal caregivers. However, ChatGPT struggled to provide satisfactory responses to more specialized (clinical) inquiries. In the questionnaire study, informal caregivers gave higher ratings to ChatGPT's responsiveness on the 31 items describing information needs, giving an overall mean score of 3.77 (SD 0.98) out of 5; the mean score among formal caregivers was 3.13 (SD 0.65), indicating that formal caregivers showed less trust in ChatGPT's responses compared to informal caregivers. ChatGPT's responses to non-clinical information needs related to dementia patients were generally satisfactory at this stage. As this tool is still under heavy development, it holds promise for providing even higher-quality information in response to information needs, particularly when developed in collaboration with healthcare professionals. Thus, large language models such as ChatGPT can serve as valuable sources of information for informal caregivers, although they may not fully meet the needs of formal caregivers who seek specialized (clinical) answers. Nevertheless, even in its current state, ChatGPT was able to provide responses to some of the clinical questions related to dementia that were asked.

ChatGPT in medical libraries, possibilities and future directions: An integrative review.

BACKGROUND: The emergence of the artificial intelligence chatbot ChatGPT in November 2022 has garnered substantial attention across diverse disciplines. Despite widespread adoption in various sectors, the exploration of its application in libraries, especially within the medical domain, remains limited. AIMS/OBJECTIVES: Many areas of interest remain unexplored like ChatGPT in medical libraries and this review aims to synthesise what is currently known about it to identify gaps and stimulate further research. METHODS: Employing Cooper's integrative review method, this study involves a comprehensive analysis of existing literature on ChatGPT and its potential implementations within library contexts. RESULTS: A systematic literature search across various databases yielded 166 papers, with 30 excluded for irrelevance. After abstract reviews and methodological assessments, 136 articles were selected. Critical Appraisal Skills Programme qualitative checklist further narrowed down to 29 papers, forming the basis for the present study. The literature analysis reveals diverse applications of ChatGPT in medical libraries, including aiding users in finding relevant medical information, answering queries, providing recommendations and facilitating access to resources. Potential challenges and ethical considerations associated with ChatGPT in this context are also highlighted. CONCLUSION: Positioned as a review, our study elucidates the applications of ChatGPT in medical libraries and discusses relevant considerations. The integration of ChatGPT into medical library services holds promise for enhancing information retrieval and user experience, benefiting library users and the broader medical community.

Design, development, implementation, and evaluation of a severe drug-drug interaction alert system in the ICU: An analysis of acceptance and override rates.

BACKGROUND AND OBJECTIVE: The override rate of Drug-Drug Interaction Alerts (DDIA) in Intensive Care Units (ICUs) is very high. Therefore, this study aimed to design, develop, implement, and evaluate a severe Drug-Drug Alert System (DDIAS) in a system of ICUs and measure the override rate of this system. METHODS: This is a cross-sectional study that details the design, development, implementation, and evaluation of a DDIAS for severe interactions into a Computerized Provider Order Entry (CPOE) system in the ICUs of Nemazee general teaching hospitals in 2021. The patients exposed to the volume of DDIAS, acceptance and overridden of DDIAS, and usability of DDIAS have been collected. The study was approved by the local Institutional Review Board (IRB) and; the ethics committee of Shiraz University of Medical Science on date: 2019-11-23 (Approval ID: IR.SUMS.REC.1398.1046). RESULTS: The knowledge base of the DDIAS contains 9,809 severe potential drug-drug interactions (pDDIs). A total of 2672 medications were prescribed in the population study. The volume and acceptance rate for the DDIAS were 81 % and 97.5 %, respectively. The override rate was 2.5 %. The mean System Usability Scale (SUS) score of the DDIAS was 75. CONCLUSION: This study demonstrates that implementing high-risk DDIAS at the point of prescribing in ICUs improves adherence to alerts. In addition, the usability of the DDIAS was reasonable. Further studies are needed to investigate the establishment of severe DDIAS and measure the prescribers' response to DDIAS on a larger scale.

Is academic research and publishing still leaving developing countries behind?

In this short commentary, the author reflects on his experience working with researchers from developing nations and argues that it is the professional responsibility of those researchers privileged by conducting research in a developed, English-speaking nation to pursue collaboration with researchers in more disadvantageous positions. As noted in a recent article from Matthews et al., researchers from developing countries experience tremendous barriers to identifying collaborators and publishing in top research journals. This commentary notes that researchers from developed countries have both humanitarian and symbiotic rationales for seeking international collaborations with researchers from developing countries. These relationships support the growth of research fields and help deconstruct a western hemispheric hegemony present in much of existing research approaches and thought and publishing practices.