Introduction: The aim of this systematic review was to summarize the current literature on wearable technologies in oncology patients for the purpose of prognostication, treatment monitoring, and rehabilitation planning. Methods: A search was conducted in Medline ALL, Cochrane Central Register of Controlled Trials, Embase, Emcare, CINAHL, Scopus, and Web of Science, up until February 2022. Articles were included if they reported on consumer grade and/or non-commercial wearable devices in the setting of either prognostication, treatment monitoring or rehabilitation. Results: We found 199 studies reporting on 18 513 patients suitable for inclusion. One hundred and eleven studies used wearable device data primarily for the purposes of rehabilitation, 68 for treatment monitoring, and 20 for prognostication. The most commonly-reported brands of wearable devices were ActiGraph (71 studies; 36%), Fitbit (37 studies; 19%), Garmin (13 studies; 7%), and ActivPAL (11 studies; 6%). Daily minutes of physical activity were measured in 121 studies (61%), and daily step counts were measured in 93 studies (47%). Adherence was reported in 86 studies, and ranged from 40% to 100%; of these, 63 (74%) reported adherence in excess of 80%. Conclusion: Wearable devices may provide valuable data for the purposes of treatment monitoring, prognostication, and rehabilitation. Future studies should investigate live-time monitoring of collected data, which may facilitate directed interventions.

Background: Natural language processing systems for data extraction from unstructured clinical text require expert-driven input for labeled annotations and model training. The natural language processing competency of large language models (LLM) can enable automated data extraction of important patient characteristics from electronic health records, which is useful for accelerating cancer clinical research and informing oncology care. Objective: This scoping review aims to map the current landscape, including definitions, frameworks, and future directions of LLMs applied to data extraction from clinical text in oncology. Methods: We queried Ovid MEDLINE for primary, peer-reviewed research studies published since 2000 on June 2, 2024, using oncology- and LLM-related keywords. This scoping review included studies that evaluated the performance of an LLM applied to data extraction from clinical text in oncology contexts. Study attributes and main outcomes were extracted to outline key trends of research in LLM-based data extraction. Results: The literature search yielded 24 studies for inclusion. The majority of studies assessed original and fine-tuned variants of the BERT LLM (n=18, 75%) followed by the Chat-GPT conversational LLM (n=6, 25%). LLMs for data extraction were commonly applied in pan-cancer clinical settings (n=11, 46%), followed by breast (n=4, 17%), and lung (n=4, 17%) cancer contexts, and were evaluated using multi-institution datasets (n=18, 75%). Comparing the studies published in 2022‐2024 versus 2019‐2021, both the total number of studies (18 vs 6) and the proportion of studies using prompt engineering increased (5/18, 28% vs 0/6, 0%), while the proportion using fine-tuning decreased (8/18, 44.4% vs 6/6, 100%). Advantages of LLMs included positive data extraction performance and reduced manual workload. Conclusions: LLMs applied to data extraction in oncology can serve as useful automated tools to reduce the administrative burden of reviewing patient health records and increase time for patient-facing care. Recent advances in prompt-engineering and fine-tuning methods, and multimodal data extraction present promising directions for future research. Further studies are needed to evaluate the performance of LLM-enabled data extraction in clinical domains beyond the training dataset and to assess the scope and integration of LLMs into real-world clinical environments.

Background: The aim of this study is to provide a comprehensive understanding of the current landscape of artificial intelligence (AI) for cancer clinical trial enrollment and its predictive accuracy in identifying eligible patients for inclusion in such trials.Methods: Databases of PubMed, Embase, and Cochrane CENTRAL were searched until June 2022. Articles were included if they reported on AI actively being used in the clinical trial enrollment process. Narrative synthesis was conducted among all extracted data: accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. For studies where the 2x2 contingency table could be calculated or supplied by authors, a meta-analysis to calculate summary statistics was conducted using the hierarchical summary receiver operating characteristics curve model.Results: Ten articles reporting on more than 50 000 patients in 19 datasets were included. Accuracy, sensitivity, and specificity exceeded 80% in all but 1 dataset. Positive predictive value exceeded 80% in 5 of 17 datasets. Negative predictive value exceeded 80% in all datasets. Summary sensitivity was 90.5% (95% confidence interval [CI] = 70.9% to 97.4%); summary specificity was 99.3% (95% CI = 81.8% to 99.9%).Conclusions: AI demonstrated comparable, if not superior, performance to manual screening for patient enrollment into cancer clinical trials. As well, AI is highly efficient, requiring less time and human resources to screen patients. AI should be further investigated and implemented for patient recruitment into cancer clinical trials. Future research should validate the use of AI for clinical trials enrollment in less resource-rich regions and ensure broad inclusion for generalizability to all sexes, ages, and ethnicities.

Artificial intelligence chatbots can draft empathetic responses to cancer questions, but how patients perceive chatbot empathy remains unclear. Here, we found that people with cancer rated chatbot responses as more empathetic than physician responses. However, differences between patient and physician perceptions of empathy highlight the need for further research to tailor clinical messaging to better meet patient needs. Chatbots may be effective in generating empathetic template responses to patient questions under clinician oversight.

Large language models (LLMs) have demonstrated emergent human-like capabilities in natural language processing, leading to enthusiasm about their integration in healthcare environments. In oncology, where synthesising complex, multimodal data is essential, LLMs offer a promising avenue for supporting clinical decision-making, enhancing patient care, and accelerating research. This narrative review aims to highlight the current state of LLMs in medicine; applications of LLMs in oncology for clinicians, patients, and translational research; and future research directions. Clinician-facing LLMs enable clinical decision support and enable automated data extraction from electronic health records and literature to inform decision-making. Patient-facing LLMs offer the potential for disseminating accessible cancer information and psychosocial support. However, LLMs face limitations that must be addressed before clinical adoption, including risks of hallucinations, poor generalisation, ethical concerns, and scope integration. We propose the incorporation of LLMs within compound artificial intelligence systems to facilitate adoption and efficiency in oncology. This narrative review serves as a non-technical primer for clinicians to understand, evaluate, and participate as active users who can inform the design and iterative improvement of LLM technologies deployed in oncology settings. While LLMs are not intended to replace oncologists, they can serve as powerful tools to augment clinical expertise and patient-centred care, reinforcing their role as a valuable adjunct in the evolving landscape of oncology.

Multimodal artificial intelligence (AI) chatbots have been proposed as useful tools to answer patient questions about general medicine.¹ Multimodal AI chatbots, compared with unimodal, text-only AI chatbots, can process complex medical image and text-based information that may further improve their accuracy as a diagnostic and management tool.^2,3 Multimodal chatbots have demonstrated an accuracy of more than 70% when answering questions about general medicine clinical cases based on free-text and image-based input.⁴ Coupled with the adoption of electronic health record systems that can access large amounts of digital patient data, computer-assisted clinical decision support systems enabled by multimodal AI can facilitate and potentially optimize clinician decision-making with clinical knowledge and patient data.⁵ Pilot studies of AI chatbots have shown that the implementation of generative AI tools in clinical settings may relieve clinician burden and burnout.^6,7 By integrating multimodal AI with clinical decision support systems, clinicians may interact with a chatbot interface by asking open-ended questions about the patient presentation and leverage multimodal data, including imaging, unstructured clinical text in the electronic health record, and laboratory results, to iteratively generate a recommendation for clinician interpretation.