Search

Objective: To summarize the available literature on using machine learning (ML) for palliative care practice as well as research and to assess the adherence of the published studies to the most important ML best practices. Methods: The MEDLINE database was searched for the use of ML in palliative care practice or research, and the records were screened according to PRISMA guidelines. Results: In total, 22 publications using machine learning for mortality prediction (n = 15), data annotation (n = 5), predicting morbidity under palliative therapy (n = 1), and predicting response to palliative therapy (n = 1) were included. Publications used a variety of supervised or unsupervised models, but mostly tree-based classifiers and neural networks. Two publications had code uploaded to a public repository, and one publication uploaded the dataset. Conclusions: Machine learning in palliative care is mainly used to predict mortality. Similarly to other applications of ML, external test sets and prospective validations are the exception.

Background Caring for dying patients is an integral aspect of care, however medical and nursing students lack training and exposure to conversations with dying patients and their families. Thus, many health professionals lack the skills to communicate about imminent death causing a long-lasting impact to all involved. As a basis to develop an educational module, this study aimed at identifying aspects that are essential to conversations about imminent death from the perspective of key stakeholders. Methods Five focus groups were conducted with medical specialists, nurses, medical students, patient representatives, and bereaved relatives (n=30). Based on a semi-structured guide, relevant verbal and nonverbal aspects of conversations about imminent death, associated emotions, and appropriate frameworks for communication were elicited. All conversations were recorded and thematically analyzed. Findings Based on participants’ experiences four main themes were identified as essential to conversations about imminent death: (1) embracing care within medical expertise, (2) preparing the conversation while remaining open to the unexpected, (3) recognizing and reflecting on own emotions and reactions, and (4) establishing a meaningful connection with others. Discussion The Findings: indicate that communicating about imminent death with dying patients and their family members is a complex and challenging task for health professionals at a professional as well as personal level. Hence, comprehensive training is needed in order to impart clinical and interpersonal skills that support health professionals to recognize when and how to engage in these conversations. Furthermore, self-reflection processes and self-care practices are to be taught and encouraged to promote positive coping strategies in the long term. Guidance and supervision are also essential to support debriefing practices in order to revisit confronting experiences, as well as to consolidate and optimize what has been learned.

Hintergrund: Die Kommunikation mit sterbenden Patient:innen ist eine ausserordentlich anspruchsvolle Aufgabe für Gesundheitsfachpersonen [ref:1]. Entsprechend hoch ist der Bedarf an qualitativ hochwertigen Lernangeboten. Basierend auf einem für den deutschsprachigen Raum entwickelten [zum vollständigen Text gelangen Sie über die oben angegebene URL]

Häufig haben Menschen am Lebensende den Wunsch, möglichst lange zuhause zu bleiben. Um dies vermehrt zu ermöglichen, benötigt es neben Gesundheitsfachpersonen, die Betroffene und ihre Angehörigen begleiten, auch Bildungsangebote zur Stärkung der Ressourcen im Umgang mit dem Lebensende. Im Rahmen des Projektes «Compassionate City Lab der Berner Bevölkerung» wurden Erfahrungen im Umgang mit dem Lebensende gesammelt und veröffentlicht sowie ein Kursangebot zur gesundheitlichen Vorausplanung für Menschen im dritten Lebensalter und betreuende Angehörige entwickelt. Das Projekt ist finanziert von Gesundheitsförderung Schweiz und getragen von einer Partnerschaft zwischen Berner Hochschulen und spezialisierten Institutionen der Palliative Care, der Grundversorgung, des Gemeinwesens sowie Ehrenamtlichen in der Stadt Bern und im Berner Oberland., People at the end of life often wish to remain at home for as long as possible. To make this possible to a greater extent, not only health professionals who accompany those affected and their relatives are needed, but also educational programmes to strengthen health literacy at the end of life. Within the framework of the project “Compassionate City Lab of the Bernese People”, experiences in dealing with the end of life were collected and published, and a course on advance care planning for elderly people was developed. The project is funded by Health Promotion Switzerland and supported by a partnership between Bernese institutions of higher education, specialised palliative care and primary care, the community, and volunteers in the city of Bern and the Bernese Oberland., Les personnes en fin de vie souhaitent souvent rester chez elles le plus longtemps possible. Pour que cela soit possible dans une plus large mesure, il faut non seulement des professionnels de la santé qui accompagnent les personnes concernées et leurs proches, mais aussi des programmes éducatifs visant à renforcer la littératie en santé. Dans le cadre du projet «Compassionate City Lab des habitants de Berne», les expériences de gestion de la fin de vie ont été collectées et publiées, et un cours sur la planification des soins anticipés pour les personnes du troisième âge a été élaboré. Le projet est financé par Promotion Santé Suisse et soutenu par un partenariat entre les universités bernoises et les institutions spécialisées en soins palliatifs et les soins primaires, la communauté et les bénévoles de la ville de Berne et de l'Oberland bernois.

Additional file 5. Original version (English) of the “Needs Assessment Tool: Progressive Disease-Heart Failure (NAT: PD-HF)”.

Additional file 6. Changes made for the cultural adaptation.

Additional file 8. Table 2. Frequency of answers from the first application of the tool.

Additional file 7. Table 1. Matrix of the weights used to assess inter-rater reliability and test-retest reliability.

Additional file 9. Table 3. Sensitivity analysis to assess the inter-rater reliability for each one of second evaluators.