We present our ongoing work on upgrading the Amsterdam Public Library's book database search capabilities. So far, users have had to input the exact book title and/or author name without any typos or misspellings in order to retrieve any results. This is in sharp contrast with the manner in which users typically use the interface: they frequently search for books on a particular topic, input the names of the characters, or even ask fully-fledged questions. The aim of this project is therefore to enable smart search in natural language based on book content. The initial focus is on the Dutch language, with the possibility of including English and other languages later. In the first phase of the project, we built a proof-of-concept knowledge graph from a sample of the existing tabular database and enriched the data with named entities extracted from book summaries. Based on this first step, a user query like "Heeft u boeken over de Tweede Wereldoorlog in Amsterdam?" would yield all books that mention both WW2 and Amsterdam. We are currently working on augmenting the knowledge graph with embeddings, which will enable us to retrieve semantically similar results. The final step of the research involves integrating our knowledge graph with a pre-trained large language model.
DOCUMENT
“Most people have known someone in their life who helped them, at just the right moment, to realize their goals or have given them the confidence, which they lacked, to get to the next step in their life.” (Joost van Rossum, 2012)
DOCUMENT
Background: To prevent deterioration after admission to the intensive care unit (ICU), and to improve rehabilitation, the ICU team should use digital technologies to provide comprehensive and practical information alongside personalised support for survivors and their family members. However, a knowledge gap exists on the users’ preferences for such an e-health platform in ICU follow-up services. Objectives: This study aims to explore the opinions and priorities for an e-health platform, including choices in digital elements, according to survivors of critical illness and their family members. Methods: A cross-sectional survey was used among members and other interested individuals of the Dutch volunteer organisation ‘Foundation Family- and Patient-Centred Intensive Care’. An investigator-developed questionnaire was disseminated through the newsletter and social media channels of the Foundation Family- and Patient-Centred Intensive Care. The results of this member consultation were analysed and reported as descriptive statistics on demographic variables and outcome measures in opinions and priorities of the participants. Results: Most of the 227 participants were female (76%), aged 46–55 years (33%), and completed higher education (70%). The participants reported high confidence in advice delivered through an e-health platform (72%). They prioritised the provision of a guide including relevant professionals who may support them during their recovery when using an e-health platform. Conclusions: ICU survivors prioritised the provision of relevant professionals who may support them during their recovery when using an e-health platform; however, selection bias means the population studied is likely to be more digitally connected than the general ICU population. Digital solutions could cater to their information and support needs. For family members, the highest priority reported was receiving help in managing their emotional distress. The development of an e-health platform considering the opinions and priorities of this target group could contribute to a personalised recovery trajectory promoting self-management while including digital elements addressing relevant ICU follow-up services.
MULTIFILE
