Citations

566 Background: Video telemedicine visits (VTVs) have the potential to overcome disparities in access to cancer care for many socially, geographically, and economically disadvantaged populations. Internet connectivity, digital literacy, and socioeconomic factors are traditionally cited as influencing VTV utilization. However, digital diffusion has occurred rapidly across several sectors, including healthcare, since the onset of the COVID-19 pandemic, and less is known about how these factors have evolved to influence VTV utilization behavior over this time. Through a qualitative approach, we aimed to: (1) explore the lived experiences of cancer patients who transitioned to VTV use as compared to those who persistently did not, and (2) identify similarities and differences between these two groups that could inform targeted interventions to support access and patient acceptance of VTVs in the setting of cancer care. Methods: During June 2024, we conducted semi-structured interviews with 24 patients (Mean age 71.3 years, range 42-88; female 50%) receiving ongoing, longitudinal cancer care at our academic medical center since July 2021 who had not used VTVs through at least October 2022. Using purposeful sampling, patients were equally divided according to VTV utilization behaviors defined as “transitioned users” (TU; i.e. those who transitioned to VTV utilization after October 2022) and “persistent non-users” (PNU). Transcripts were analyzed using a combined deductive–inductive thematic approach and categorized into themes of barriers and facilitators across three domains consistent with the COM-B model: capabilities (C), opportunities (O), and motivations (M). Results: TU patients frequently cited a reduction in travel and logistical considerations as a primary reason for uptake of VTVs. PNU patients frequently reported digital literacy barriers, particularly among older patients, as primary reasons for lack of VTV utilization. TU patients reported more experience and comfort in technical skills as compared to PNU participants. PNU patients also reported less frequent offering of VTV as an option by their care teams over time, implying they may have transitioned to VTV utilization if it had been offered with more regularity. Both study groups desired improved internet access and technical support to enhance (or, in the case of PNU patients, enable) VTV utilization. Conclusions: These findings suggest that multi-modal care delivery may best serve current patient populations, not requiring, yet offering VTV services as an adjunct to in-person care. Longer term, individual barriers to VTV use will also need to be addressed to further optimize access for patients who desire to incorporate this care modality.

Abstract Error analysis is a critical step in evaluating and improving clinical concept extraction models, the most common clinical natural language processing (NLP) task. Unlike corpus annotation, which follows standardized protocols for creating gold-standard datasets, error analysis requires nuanced judgment grounded in both clinical expertise and NLP knowledge. This is especially important given the heterogeneity of clinical text, where variations in documentation style, note structure, and terminology can substantially influence model behavior. Despite its importance, there is currently no standardized, user-level framework to support systematic error analysis in clinical concept extraction task. In this study, we developed and validated MedError, a machine-assisted, human-in-the-loop framework designed to standardize and enhance error analysis for clinical concept extraction tasks. We collected and manually curated a corpus of 1,187 unique errors from a total of 4,237 notes across three different distinct hospitals. The error categories were defined using our previously validated error taxonomy and included 480 false negatives and 707 false positives across 25 error types and 48 clinical concept categories. We evaluated the performance of three proprietary and three open-source large language models (LLMs) in automatically classifying these errors into 26 and 15 predefined categories. We further developed a machine-assisted framework, MedError, which integrates best practices in error analysis, LLM-assisted classification and reasoning, and a user-friendly interface to enable more efficient, reproducible, and context-aware error analysis. The framework supports both single-site and federated multisite error analysis, facilitating the effective translation of clinical NLP systems into real-world settings.

Abstract Objectives The surge in patient portal messages (PPMs) with increasing needs and workloads for efficient PPM triage in healthcare settings has spurred the exploration of AI-driven solutions to streamline the healthcare workflow processes, ensuring timely responses to patients to satisfy their healthcare needs. However, there has been less focus on isolating and understanding patient primary concerns in PPMs—a practice which holds the potential to yield more nuanced insights and enhances the quality of healthcare delivery and patient-centered care. Materials and Methods We propose a fusion framework to leverage pretrained language models (LMs) with different language advantages via a Convolution Neural Network for precise identification of patient primary concerns via multi-class classification. We examined 3 traditional machine learning models, 9 BERT-based language models, 6 fusion models, and 2 ensemble models. Results The outcomes of our experimentation underscore the superior performance achieved by BERT-based models in comparison to traditional machine learning models. Remarkably, our fusion model emerges as the top-performing solution, delivering a notably improved accuracy score of 77.67 ± 2.74% and an F1 score of 74.37 ± 3.70% in macro-average. Discussion This study highlights the feasibility and effectiveness of multi-class classification for patient primary concern detection and the proposed fusion framework for enhancing primary concern detection. Conclusions The use of multi-class classification enhanced by a fusion of multiple pretrained LMs not only improves the accuracy and efficiency of patient primary concern identification in PPMs but also aids in managing the rising volume of PPMs in healthcare, ensuring critical patient communications are addressed promptly and accurately.

Background: Due to lacking evidence on surveillance for gastric cancer (GC), this study aimed to determine the optimal postsurgical surveillance strategy for pathological stage (pStage) II/III GC patients and compare its cost-effectiveness with traditional surveillance strategies. Methods: Prospectively collected data from stage II/III GC patients (n=1661) who underwent upfront surgery at a large-volume tertiary cancer center in China (FJMUUH cohort) between January 2010 and October 2015. For external validation, two independent cohorts were included, which were composed of 380 stage II/III GC patients at an tertiary cancer center in U.S.A (Mayo cohort) between July 1991 and July 2012 and 270 stage II/III GC patients at another tertiary cancer center in China (QUAH cohort) between May 2010 and October 2014. Random forest models were used to predict dynamic recurrence hazards and to construct individual surveillance strategies for stage II/III GC. Cost-effectiveness was assessed by the Markov model. Results: The median follow-up period of the FJMUUH, the Mayo, and QUAH cohorts were 55, 158, and 70 months, respectively. In the FJMUUH cohort, the 5-year recurrence risk was higher in pStage III compared with pStage II GC patients (P<0.001). Our novel individual surveillance strategy achieved optimal cost-effectiveness for pStage II GC patients (ICER =$490/QALY). The most intensive NCCN surveillance guideline was more cost-effective (ICER =$983/QALY) for pStage III GC patients. The external validations confirmed our results. Conclusion: For patients with pStage II GC, individualized risk-based surveillance outperformed the JGCTG and NCCN surveillance guidelines. However, the NCCN surveillance guideline may be more suitable for patients with pStage III GC. Even though our results are limited by the retrospective study design, the authors believe that our findings should be considered when recommending postoperative surveillance for stage II/III GC with upfront surgery in the absence of a randomized clinical trial.

PURPOSE In response to the COVID-19 pandemic, many cancer practices rapidly adopted telehealth services. However, there is a paucity of data regarding ongoing telehealth visit utilization beyond this initial response. The purpose of this study was to assess changes in variables associated with telehealth visit utilization over time. METHODS This is a cross-sectional, year-over-year, retrospective analysis of telehealth visits conducted across a multisite, multiregional cancer practice in the United States. Multivariable models examined the association of patient- and provider-level variables with telehealth utilization across outpatient visits conducted over three 8-week periods from July to August in 2019 (n = 32,537), 2020 (n = 33,399), and 2021 (n = 35,820). RESULTS The rate of telehealth utilization increased from <0.01% (2019) to 11% (2020) to 14% (2021). The most significant patient-level factors associated with increased telehealth utilization included nonrural residence and age ≤65 years. Among patients residing in rural settings, video visit utilization rates were significantly lower and phone visit utilization rates were significantly higher compared with patients from nonrural residences. Regarding provider-level factors, widening differences in telehealth utilization were observed at tertiary versus community-based practice settings. Increased telehealth utilization was not associated with duplicative care as per-patient and per-physician visit volumes in 2021 remained consistent with prepandemic levels. CONCLUSION We observed continuous expansion in telehealth visit utilization from 2020 to 2021. Our experiences suggest that telehealth can be integrated into cancer practices without evidence of duplicative care. Future work should examine sustainable reimbursement structures and policies to ensure accessibility of telehealth as a means to facilitate equitable, patient-centered cancer care.

AbstractBackgroundThe accuracy of the eighth AJCC ypTNM staging system on the prognosis of gastric cancer (GC) patients after neoadjuvant therapy (NAT) is controversial. This study aimed to develop and validate a novel staging system using the log odds of positive lymph nodes scheme (LODDS).MethodsA retrospective analysis of 606 GC patients who underwent radical gastrectomy after neoadjuvant therapy was conducted as the development cohort. (Fujian Medical University Affiliated Union Hospital (n = 183), Qinghai University Affiliated Hospital (n = 169), Mayo Clinic (n = 236), Lanzhou University First Hospital (n = 18)). The validation cohort came from the SEER database (n = 1701). A novel ypTLoddsS (ypTLM) staging system was established using the 3‐year overall survival. The predictive performance of two systems was compared. ResultsTwo‐step multivariate Cox regression analysis in both cohorts showed that ypTLM was an independent predictor of overall survival of GC patients after neoadjuvant therapy (HR: 1.57, 95% CI: 1.30–1.88, p < 0.001). In the development cohort, ypTLM had better discrimination ability than ypTNM (C‐index: 0.663 vs 0.633, p < 0.001), better prediction homogeneity (LR: 97.7 vs. 70.9), and better prediction accuracy (BIC: 3067.01 vs 3093.82; NRI: 0.36). In the validation cohort, ypTLM had a better prognostic predictive ability (C‐index: 0.614 vs 0.588, p < 0.001; LR: 11,909.05 vs. 11,975.75; BIC: 13,263.71 vs 13,328.24; NRI: 0.22). The time‐dependent ROC curve shows that the predictive performance of ypTLM is better than ypTNM, and the analysis of the decision curve shows that ypTLM achieved better net benefits. ConclusionA LODDS‐based ypTLM staging system based on multicenter data was established and validated. The predictive performance was superior to the eighth AJCC ypTNM staging system.