{"title":"Artificial Intelligence in Palliative Care: A Scoping Review of Current Applications, Challenges, and Future Directions.","authors":"Maria Nikoloudi, Kyriaki Mystakidou","doi":"10.1177/10499091251358379","DOIUrl":null,"url":null,"abstract":"<p><p>BackgroundArtificial Intelligence (AI) is increasingly integrated into healthcare systems, presenting opportunities to improve clinical outcomes. In the context of palliative care, AI holds potential to enhance quality of life through improved symptom management, effective communication, and greater prognostic accuracy. For this review, AI refers to computational systems capable of learning, reasoning, or predicting outcomes. As integration advances, a critical examination of its applications, practical challenges, and ethical implications in palliative care is warranted.MethodsA scoping review was conducted using 4 major databases: PubMed, Google Scholar, Scopus, and CINAHL. A total of 7 studies were included, each addressing the use of AI technologies in palliative care settings, with a focus on clinical implementation, ethical challenges, and system integration. Both quantitative and qualitative studies were considered.ResultsAI applications in palliative care include predictive analytics, symptom control, and enhanced patient-caregiver communication. These tools demonstrate potential in facilitating early identification of patient needs and supporting timely interventions. However, significant challenges persist, particularly around data privacy, patient autonomy, algorithmic bias, and the \"black box\" nature of many AI models. Additional practical limitations include integration into clinician workflows, clinician trust, and concerns about the depersonalization of care.ConclusionAI offers substantial potential to improve palliative care, but implementation must be grounded in ethical frameworks prioritizing dignity, compassion, and patient-centeredness. Multidisciplinary collaboration is essential to ensure that AI augments rather than replaces the humanistic core of palliative care. Ongoing research and development of transparent, equitable algorithms are critical to responsibly harnessing AI's transformative potential.</p>","PeriodicalId":94222,"journal":{"name":"The American journal of hospice & palliative care","volume":" ","pages":"10499091251358379"},"PeriodicalIF":1.4000,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The American journal of hospice & palliative care","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/10499091251358379","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
BackgroundArtificial Intelligence (AI) is increasingly integrated into healthcare systems, presenting opportunities to improve clinical outcomes. In the context of palliative care, AI holds potential to enhance quality of life through improved symptom management, effective communication, and greater prognostic accuracy. For this review, AI refers to computational systems capable of learning, reasoning, or predicting outcomes. As integration advances, a critical examination of its applications, practical challenges, and ethical implications in palliative care is warranted.MethodsA scoping review was conducted using 4 major databases: PubMed, Google Scholar, Scopus, and CINAHL. A total of 7 studies were included, each addressing the use of AI technologies in palliative care settings, with a focus on clinical implementation, ethical challenges, and system integration. Both quantitative and qualitative studies were considered.ResultsAI applications in palliative care include predictive analytics, symptom control, and enhanced patient-caregiver communication. These tools demonstrate potential in facilitating early identification of patient needs and supporting timely interventions. However, significant challenges persist, particularly around data privacy, patient autonomy, algorithmic bias, and the "black box" nature of many AI models. Additional practical limitations include integration into clinician workflows, clinician trust, and concerns about the depersonalization of care.ConclusionAI offers substantial potential to improve palliative care, but implementation must be grounded in ethical frameworks prioritizing dignity, compassion, and patient-centeredness. Multidisciplinary collaboration is essential to ensure that AI augments rather than replaces the humanistic core of palliative care. Ongoing research and development of transparent, equitable algorithms are critical to responsibly harnessing AI's transformative potential.