St Sauver, Jennifer

Systematic reviews of randomized controlled trials (RCTs) support evidence-based clinical advancement. Clinical trial reporting guidelines, including CONSORT, establish common data elements that support systematic synthesis of published trial outcomes. However, the rapid rise of digital health technologies presents new challenges for reporting guidelines, and substantial real-world reporting heterogeneity has been observed. Therefore, machine-assisted evaluation of reporting adherence offers a pathway for more agile information management to accommodate the diverse and disruptive nature of digital health technology-enabled RCTs. Here, we propose an accelerated retrieval-to-abstraction literature synthesis framework to conduct article screening, text and table data preprocessing, and full-text review using an unmodified pretrained large language model. We apply this methodology in two digital health technology-enabled RCT case studies evaluating adherence to technology and digital health equity guideline reporting items. Large language model performance was on par with inter-annotator agreement F1 scores (≥0.9) in both screening and information-extraction tasks. These findings support the scalability and rigor of accelerated evidence synthesis and demonstrate the importance of common reporting elements across digital health technology-enabled RCTs.

Background Alzheimer's disease (AD) and related dementias are leading causes of death worldwide. While socioeconomic status (SES) is a critical determinant, its impact on mortality after diagnosis remains understudied. Objective To investigate the roles of neighborhood-level and individual-level SES in predicting mortality risk among older adults with incident dementia. Methods We analyzed data from 924 participants with incident dementia from the Mayo Clinic Study of Aging (N = 6909), a cohort with clinical follow-up visits every 15 months. We assessed mortality risk using Cox's time-varying survival regression, adjusting for time-fixed and time-varying covariates. Primary predictors were neighborhood-level SES (Area Deprivation Index [ADI]) and individual-level SES (housing-based SES index [HOUSES], education, and occupation). We also applied a random survival forest model to assess the predictive contribution of SES indicators and identify influential predictors. Results 857 participants (92.7%) died, with a median time from dementia diagnosis to death of 29 months (IQR: 12–54). Lower SES measured by HOUSES was associated with increased mortality risk (HR 1.28, 95% CI 1.07–1.52). Conversely, ADI, education, and occupation were not associated with mortality. Male sex, older age, congestive heart failure and diabetes were associated with higher mortality risk. In predictive analysis, HOUSES ranked among the top 10 contributors to mortality risk. Conclusions Among older adults with dementia, lower HOUSES was associated with higher mortality risk beyond neighborhood-level deprivation, education, and occupation. Integrating this housing-based individual-level SES measure into dementia care planning may help identify patients with greater socioeconomic vulnerability and inform mortality risk stratification.

Abstract Background Integrating advanced artificial intelligence (AI) into clinical decision-support often requires the sharing of sensitive patient data with external services, raising privacy concerns. Homomorphic encryption (HE) allows computing directly on encrypted data, without revealing the underlying patient information. Objectives To develop a large language model (LLM)-assisted diagnosis framework while preserving patient privacy in the clinical text analysis, by leveraging HE and using rare disease (RD) diagnosis as a representative application. To demonstrate HE does not hinder the system performance. Materials and Methods Texts from patient histories and a RD knowledge base were embedded by LLMs into vectors, then encrypted using HE to obscure private information while retaining the semantic nuances. Diagnostic recommendations were generated by computing and ranking the similarities between the patient history and RD vectors in the encrypted space. The system was evaluated using 50 synthetic case reports (5 RDs, each with 10 reports). Results Applying HE did protect private information from reverse-embedding attacks. HE imposed little disruption to the diagnostic accuracy, with normalized discounted cumulative gains (nDCG) of 0.6108 ± 0.3412 (encrypted) versus 0.6083 ± 0.3415 (unencrypted). The accuracy and computational performance were tunable and consistent, as demonstrated across five different LLMs. Discussion Our privacy-preserving framework opens tremendous opportunities toward hosting and serving powerful AI solutions across institution boundaries, which would remove the need for local deidentification and incentivize users to access secure external decision-support services. Conclusions Integrating HE with LLM retrieval can promote the dissemination of nonredundant, high-capacity AI services by preserving both privacy and accuracy.

Abstract With global aging, assessing functional status is vital for precision medicine. Electronic Health Records (EHRs), particularly unstructured data, hold abundant information on patient mobility. This study explores using Large Language Models (LLMs) to extract and standardize mobility status from unstructured EHR data (i.e., clinical notes). We annotated 600 clinical notes from three health care institutions located in southeastern Minnesota and west-central Wisconsin, focusing on expressions of mobility and associated impairment. Leveraging the open-source Llama 3 model, we tested various prompting strategies—including zero-shot, few-shot, and task decomposition—and evaluated their performance. Error analysis showed that while the model sometimes inferred impairments without explicit evidence, most errors were clinically reasonable, often reflecting borderline or ambiguous cases. While considering reasonable inference as correct, at the patient-level, Mobility Extraction achieves a micro-average accuracy of 0.952 with an F1-score of 0.962, and Impairment Classification produces a micro-average accuracy of 0.912 and an F1-score of 0.948. A local, deterministic setup improved trustworthiness by ensuring consistent outputs, safeguarding privacy, and demonstrating cross-institution generalizability. These findings highlight the feasibility of LLM-based solutions for extracting mobility functional status from unstructured EHR data, supporting both clinical applications and research.

Background More than 1 in 5 US adults live with mental illness. Novel therapies as complements to standard therapies are needed to improve patient well-being. Reiki is a biofield therapy that may improve well-being in mental health. Objective The primary aim of this study was to evaluate the feasibility of providing Reiki at a behavioral health clinic serving a low-income population. The secondary aim was to evaluate outcomes in terms of patients’ symptoms, emotions, and feelings before and after Reiki. Methods This was a mixed-methods, feasibility pilot study with a pre-post experimental design. Reiki was offered to adult outpatients at a community behavioral health center in Rochester, Minnesota. Patients with a stable mental health diagnosis seen between July 22, 2021, and May 18, 2023, completed surveys before and after the Reiki intervention and provided qualitative feedback. Patients were asked to report their ratings of pain, anxiety, fatigue, and feelings (eg, happy, calm) on 0- to 10-point numeric rating scales. Data were analyzed with Wilcoxon signed rank tests. Results Among 91 patients who completed a Reiki session during the study period, 74 (81%) were women. Major depressive disorder (71%), posttraumatic stress disorder (47%), and generalized anxiety disorder (43%) were the most common diagnoses. The study was feasible in terms of recruitment, retention, data quality, acceptability, and fidelity of the intervention. Patient ratings of pain, fatigue, anxiety, stress, sadness, and agitation were significantly lower, and ratings of happiness, energy levels, relaxation, and calmness were significantly higher after a single Reiki session. Conclusion The results of this study suggest that Reiki is feasible and could be fit into the flow of clinical care in an outpatient behavioral health clinic. It improved positive emotions and feelings and decreased negative measures. Implementing Reiki in clinical practice should be further explored to improve mental health and well-being.

Abstract Obesity accelerates the onset and progression of age-related conditions. In preclinical models, obesity drives cellular senescence, a cell fate that compromises tissue health and function, in part through a robust and diverse secretome. In humans, components of the secretome have been used as senescence biomarkers that are predictive of age-related disease, disability, and mortality. Here, using biospecimens and clinical data from two large and independent cohorts of older adults, we tested the hypothesis that the circulating concentrations of senescence biomarkers are influenced by body mass index. After adjusting for age, sex, and race, we observed significant increases in activin A, Fas, MDC, PAI1, PARC, TNFR1, and VEGFA, and a significant decrease in RAGE, from normal weight, to overweight, to obesity body mass index categories by linear regression in both cohorts (all p < .05). These results highlight the influence of body mass index on circulating concentrations of senescence biomarkers.

Objectives Primary human papillomavirus (HPV) testing by clinician-collection is endorsed by U.S. guideline organizations for cervical cancer screening, but uptake remains low and insights into patients’ understanding are limited. This study aims to primarily address patient awareness of primary HPV screening by clinician-collection and acceptance of primary HPV screening by clinician- and self-collection, and secondarily assess factors associated with awareness and acceptance. Setting Primary care practices affiliated with an academic medical center. Methods A cross-sectional survey study of screening-eligible women aged 30–65 years was conducted to assess awareness and acceptability of primary HPV screening. We analyzed bivariate associations of respondent characteristics with awareness of primary HPV screening by clinician-collection, willingness to have clinician- or self-collected primary HPV testing, and reasons for self-collection preference. Results Respondents (n = 351; response rate = 23.4%) reported cervical cancer screening adherence of 82.8% but awareness of clinician-collected primary HPV as an option was low (18.9%) and only associated with HPV testing with recent screening ( p = 0.003). After reviewing a description of primary HPV screening, willingness for clinician-collected (81.8%) or home self-collected (76.1%) HPV testing was high, if recommended by a provider. Acceptability of clinician-collected HPV testing was associated with higher income ( p = 0.009) and for self-collection was associated with higher income ( p = 0.002) and higher education ( p = 0.02). Higher education was associated with reporting self-collection as easier than clinic-collection ( p = 0.02). Women expected self-collection to be more convenient (94%), less embarrassing (85%), easier (85%), and less painful (81%) than clinician-collection. Conclusions Educational interventions are needed to address low awareness about the current clinician-collected primary HPV screening option and to prepare for anticipated federal licensure of self-collection kits. Informing women about self-collection allows them to recognize benefits which could address screening barriers.

Abstract Background Error analysis plays a crucial role in clinical concept extraction, a fundamental subtask within clinical natural language processing (NLP). The process typically involves a manual review of error types, such as contextual and linguistic factors contributing to their occurrence, and the identification of underlying causes to refine the NLP model and improve its performance. Conducting error analysis can be complex, requiring a combination of NLP expertise and domain-specific knowledge. Due to the high heterogeneity of electronic health record (EHR) settings across different institutions, challenges may arise when attempting to standardize and reproduce the error analysis process. Objectives This study aims to facilitate a collaborative effort to establish common definitions and taxonomies for capturing diverse error types, fostering community consensus on error analysis for clinical concept extraction tasks. Materials and Methods We iteratively developed and evaluated an error taxonomy based on existing literature, standards, real-world data, multisite case evaluations, and community feedback. The finalized taxonomy was released in both .dtd and .owl formats at the Open Health Natural Language Processing Consortium. The taxonomy is compatible with several different open-source annotation tools, including MAE, Brat, and MedTator. Results The resulting error taxonomy comprises 43 distinct error classes, organized into 6 error dimensions and 4 properties, including model type (symbolic and statistical machine learning), evaluation subject (model and human), evaluation level (patient, document, sentence, and concept), and annotation examples. Internal and external evaluations revealed strong variations in error types across methodological approaches, tasks, and EHR settings. Key points emerged from community feedback, including the need to enhancing clarity, generalizability, and usability of the taxonomy, along with dissemination strategies. Conclusion The proposed taxonomy can facilitate the acceleration and standardization of the error analysis process in multi-site settings, thus improving the provenance, interpretability, and portability of NLP models. Future researchers could explore the potential direction of developing automated or semi-automated methods to assist in the classification and standardization of error analysis.