Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 3 appraisals
JMIR cancer
Multiturn Large Language Model-Based Conversational Agents for Patients With Cancer and Caregivers: Scoping Review
BACKGROUND: Large language model (LLM)-based conversational agents are increasingly used in health care, yet their capacity to support genuine multiturn dialogue remains underexplored. In oncology, where patients and caregivers experience complex informational and emotional needs throughout the disease trajectory, conversational agents may support information provision, symptom consultation, and emotional assistance. However, research specifically examining multiturn conversational agents designed for patients with cancer and informal caregivers remains limited. OBJECTIVE: This scoping review aimed to map the research landscape of LLM-based multiturn conversational chatbots developed for patients with cancer and informal caregivers, focusing on system design, intervention purposes, evaluation approaches, safety considerations, and transparency of LLM-related components. METHODS: This scoping review followed the Joanna Briggs Institute methodology and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Six databases-PubMed, Embase, Scopus, Web of Science, CINAHL, and PsycINFO-were searched for studies published between January 2022 and January 2026, with supplementary searches conducted in IEEE Xplore Digital Library and ACM Digital Library in May 2026. Studies were included if they described LLM-based chatbots designed for patients with cancer or informal caregivers that supported multiturn conversational interaction. Two reviewers independently conducted the study selection and data extraction. RESULTS: Eight studies met the inclusion criteria. Most studies focused on prototype development, with limited research evaluating clinical outcomes. ChatGPT-based models were the most commonly used LLMs, and retrieval-augmented generation techniques were applied in several studies. Chatbots were primarily designed for emotional support or information provision. Evaluation approaches varied widely, including response quality, psychological outcomes, and user experience. However, no studies evaluated interaction-level characteristics such as conversational continuity or context retention, and only 2 studies reported any conversational memory mechanism. Reporting on safety risks, mitigation strategies, prompt design, model parameters, and adherence to LLM reporting guidelines was often limited or absent. CONCLUSIONS: This scoping review identified only 8 studies on LLM-based multiturn conversational chatbots for patients with cancer and informal caregivers. The field remains at an early stage, characterized by prototype-oriented development, heterogeneous design and evaluation approaches, and inconsistent safety and transparency reporting. Future development should prioritize genuine conversational capability, safety management, and transparent reporting.
22 July 2026
Read appraisal →BMJ open
Association of wearable device-based perioperative physical activity with recovery outcomes in patients undergoing lung cancer surgery: a systematic review and meta-analysis protocol.
INTRODUCTION: Lung cancer surgery is a cornerstone of curative treatment for resectable disease, but postoperative recovery is often prolonged and may be complicated by impaired pulmonary function, reduced physical activity, symptom burden and delayed functional restoration. Wearable devices may support perioperative physical activity through objective monitoring and activity promotion; however, existing evidence remains fragmented and has not been synthesised in a focused review. This protocol describes a systematic review and meta-analysis to evaluate the association of wearable device-based perioperative physical activity with recovery outcomes in patients undergoing lung cancer surgery. METHODS AND ANALYSIS: We will include randomised controlled trials, non-randomised interventional studies and prospective or retrospective cohort studies involving adults undergoing surgery for suspected or confirmed primary lung cancer. Eligible studies must examine wearable device-based perioperative physical activity during the preoperative period, postoperative period or both. The primary outcomes will be postoperative pulmonary complications, length of hospital stay and physical function or exercise capacity. Secondary outcomes will include overall postoperative complications, pulmonary function, symptom burden, health-related quality of life, chest tube duration, readmission and postoperative mortality. We will search PubMed, EMBASE, Web of Science, CINAHL and the Cochrane Library from inception to the final search date, supplemented by reference screening, forward citation tracking, grey literature and trial registry searches. Two reviewers will independently perform study selection, data extraction and risk-of-bias assessment. Where appropriate, meta-analysis will be performed using random-effects models; otherwise, findings will be synthesised narratively. ETHICS AND DISSEMINATION: Ethical approval is not required because this review will use data from published studies and publicly accessible sources only and will not involve individual participants or identifiable personal data. The findings will be disseminated through publication in a peer-reviewed journal and presentation at relevant academic or professional conferences. PROSPERO REGISTRATION NUMBER: CRD420261375254.
11 July 2026
Read appraisal →Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer
The effectiveness of non-pharmacological interventions on sleep quality in lung cancer patients: a systematic review and meta-analysis (2015-2025)
PURPOSE: Sleep disorders are highly prevalent among lung cancer patients and seriously affect their quality of life and mental health. This systematic review and meta-analysis aimed to assess the effects of non-pharmacological interventions on sleep quality, quality of life, and anxiety in lung cancer patients. METHODS: PubMed, Web of Science, Cochrane Library, CINAHL, Embase, CNKI, Wanfang Data, and VIP databases for studies published between 2015 and February 2025. The primary outcome was sleep quality, with quality of life and anxiety levels as secondary outcomes. We assessed the risk of bias using the Cochrane tool and synthesized data using meta-analysis. RESULTS: Twenty-four studies involving 2604 patients were included. Non-pharmacological interventions were compared with usual care, placebo, or standard oncology care. After excluding studies with inappropriate content and methods, 20 studies evaluated sleep quality, and 12 studies evaluated quality of life and anxiety levels, respectively. The quality of the evidence was low to moderate; the promotion results should be interpreted with caution, but they may have a positive effect on the sleep quality, quality of life, and anxiety levels of lung cancer patients. CONCLUSIONS: Diverse non-pharmacological interventions can improve sleep quality, quality of life, and anxiety in lung cancer patients. However, high-quality, rigorously designed randomized controlled trials are still needed to confirm these findings. Future research should focus on personalized interventions tailored to lung cancer patients' characteristics and integrate digital health interventions to better support clinical decision-making.
28 June 2026
Read appraisal →