Faust, Louis

Abstract Rationale Despite its effectiveness at improving outcomes in patients with COPD, pulmonary rehabilitation (PR) attrition rates are high, often exceeding 50%. Fully remote programs, like home-based PR (HBPR), face additional challenges engaging patients in real-world settings. With the growing adoption of wearables, sensor-derived behavioral measures, like sleep patterns, may identify patients most likely to benefit from remote PR. This study evaluated whether incorporating baseline sleep measures from a wrist-worn activity monitor in machine learning (ML) models improved the prediction of 12-week engagement with HBPR in patients with COPD. Methods Among participants (n = 124), the following sleep measures were collected for 1 week before HBPR: sleep duration (min), standard deviation of sleep duration, wake-after-sleep-onset (WASO) (min), standard deviation of WASO, number of awakenings, length of awakenings (min), activity counts, movement index, movement fragmentation index, and sleep fragmentation index. Sleep measures were processed (1) using a previously validated Tudor-Locke algorithm and (2) applying partial least squares-discriminant analysis (PLS-DA) to generate a single latent variable (Composite Sleep Health Score) for inclusion in models. Engagement was defined as completion of one or more recommended activities per week for the full program duration (12 weeks). To determine if the inclusion of objective sleep measures improved the prediction of HBPR engagement, nested model comparisons for parametric (logistic regression and SVM) and non-parametric (decision tree and naïve bayes) ML models were performed. A sensitivity analysis (SA) replaced the Composite Sleep Health Score with sleep regularity (duration and WASO) measures only. Results In models adjusted for age, sex, Charlson Comorbidity Index, current smoker status, modified Medical Research Council (mMRC), and forced expiratory volume in 1 second (FEV1), the inclusion of the Composite Sleep Health Score significantly improved the prediction of 12-week engagement only in SVM models (AUC 0.755; p = 0.007). Specificity (18.2%) and accuracy (68.5%) also improved by 27.3% and 7.3%, respectively. The Composite Sleep Health Score and mMRC scores ranked most frequently as the variables of highest importance. Identical trends were observed in the SA. Conclusion Although preliminary, these findings support additional investigation into the use of wearable-derived sleep measures to improve screening for HBPR eligibility, identifying patients who will clinically benefit from fully remote PR. Building on these primary findings, future researchers should carefully select variables for model inclusion and initiate new hypotheses elucidating the link between objective sleep measures and HBPR outcomes in COPD patients. This abstract is funded by: NIH R56 HL173214, NIH R01 HL140486, and the Robert D. and Patricia E. Kern Center for the Science of Health Delivery

Introduction Despite its demonstrated effectiveness at improving outcomes, pulmonary rehabilitation (PR) for chronic obstructive pulmonary disease (COPD) is underutilized. Sensor-generated data from wearable devices have the potential to mitigate this challenge by generating digital endpoints that provide insights into patient behaviors at home; however, there is no consensus on how to measure home-based PR (HBPR) outcomes with these tools. This review aims to describe (1) the most frequent digital endpoints used in HBPR studies and (2) the devices used to capture these endpoints, summarizing gaps in their applications to HBPR for COPD patients. Methods We completed a scoping review using the PRISMA checklist across databases (Web of Science, Scopus, and OVID) from January 1, 2005 to June 1, 2025. We included peer-reviewed articles on HBPR for COPD, excluding reviews, commentaries/editorials, poster abstracts, and conference proceedings. Eligible articles included cohort studies and clinical trials of adult patients (age ≥ 18 years) with COPD participating in HBPR that include one or more digital endpoints. Results Among eligible articles ( n = 218), 13 (6.0%) met inclusion criteria, the majority of which were published after 2020 (61.5%). Most studies enrolled fewer than 100 COPD patients (76.9%) for an average monitoring period of 12.5 weeks. Activity trackers were the most commonly used device (46.2%) to capture data. The most frequently used digital endpoints were step count (84.6%), time spent active (38.5%), and time spent sedentary (30.8%). Two study designs were used: randomized controlled trial (76.9%) and observational cohort. Study designs were heterogenous with more than one-third (38.5%) presenting a lack of statistically significant results. Discussion Although we identified analogous digital endpoints in some studies, dissimilar methods and study designs remain barriers to synthesizing results generated from HBPR programs for COPD. Wearable devices have the potential to build novel PR models, but more work is needed to translate real-world data into clinically meaningful measures. Future research should elucidate which participants would benefit most from and complete HBPR to build an evidence base for the validation of HBPR-relevant digital endpoints, particularly those derived from less common sources like cardiovascular and sleep measures.

Background Patients with anti-leucine-rich glioma-inactivated 1 (anti-LGI1) autoimmune encephalitis (AIE) frequently present with faciobrachial dystonic seizures (FBDS), which are often under-detected due to their subtle motor features and lack of consistent EEG correlates. Conventional in-hospital monitoring and patient-reported seizure diaries are limited, particularly during nocturnal periods. In this pilot feasibility study, we evaluated the use of a wearable device (Empatica E4) to objectively monitor FBDS-related motor and autonomic activity in seven patients with anti-LGI1 AIE and four control subjects. Methods Wearable recordings included accelerometry (ACC), electrodermal activity (EDA), photoplethysmography (PPG) and skin temperature. A support vector machine-based algorithm was developed to identify disorder-related events using ACC and EDA features. Analyses were restricted to sleep periods to minimise confounding from voluntary movements. Results Pretreatment recordings from two patients (P1 and P2) showed significantly elevated motor event frequency, ACC magnitude and EDA activity compared to controls. Post-treatment recordings demonstrated marked reductions in these metrics, consistent with patient-reported clinical improvement. Other patients showed variable results depending on treatment timing and signal quality. Conclusion Our pilot study demonstrates the feasibility of using wearable technology for objective, real-world monitoring and assessment of patient status in anti-LGI1 AIE. Nocturnal monitoring offers a low-noise baseline for detecting seizure-related activity and may support earlier diagnosis, more accurate evaluation of treatment response and reduced reliance on resource-intensive inpatient evaluations. Future studies should expand monitoring to daytime periods and validate findings against conventional modalities such as video-EEG and electromyography polygraphy.

Abstract Description Cellular immune responses are critical for protection from environmental and genetic insults, including pathogens and cancer. However, immunity can also drive pathogenic responses that damage organs and drive pathogenesis. Immune response quality is influenced by several factors including genetics, age, sex and the environment. Environmental influences including everyday activities and lifestyle have been shown to modulate the immune system but are often difficult to monitor. We have developed a system of serial monitoring of peripheral blood mononuclear cells that coincided with wearable device activity monitoring to further understand how biometric data correlates with the composition of blood derived immune cells. Using a 31-marker CyTOF phenotyping panel we monitored blood derived immune cell composition over a 14-week period in an individual volunteer while biometric data was collected via wearable technology. To determine whether interventions can be introduced that change peripheral blood immune cell phenotypes our volunteer introduced lifestyle changes at specific intervals in this period of monitoring. These included intermittent fasting and the introduction of regular exercise. In addition, the individual was immunized against COVID-19 during this time to provide an immune challenge that would perturb immune homeostasis. In this study, we find that lifestyle changes can promote alterations in immune cell phenotypes identified using high parameter mass cytometry. Topic Categories Translational and Interventional Immunology (TI)

Objective: To evaluate the feasibility and effectiveness of wrist-worn wearable devices combined with machine learning (ML) approaches for detecting a diverse array of seizure types beyond generalized tonic–clonic (GTC), including focal, generalized, and subclinical seizures. Materials and Methods: Twenty-eight patients undergoing inpatient video-EEG monitoring at Mayo Clinic were concurrently monitored using Empatica E4 wrist-worn devices. These devices captured accelerometry, blood volume pulse, electrodermal activity, skin temperature, and heart rate. Seizures were annotated by neurologists. The data were preprocessed to experiment with various segment lengths (10 s and 60 s) and multiple feature sets. Three ML strategies, XGBoost, deep learning models (LSTM, CNN, Transformer), and ROCKET, were evaluated using leave-one-patient-out cross-validation. Performance was assessed using area under the receiver operating characteristic curve (AUROC), seizure-wise recall (SW-Recall), and false alarms per hour (FA/h). Results: Detection performance varied by seizure type and model. GTC seizures were detected most reliably (AUROC = 0.86, SW-Recall = 0.81, FA/h = 3.03). Hyperkinetic and tonic seizures showed high SW-Recall but also high FA/h. Subclinical and aware-dyscognitive seizures exhibited the lowest SW-Recall and highest FA/h. MultiROCKET and XGBoost performed best overall, though no single model was optimal for all seizure types. Longer segments (60 s) generally reduced FA/h. Feature set effectiveness varied, with multi-biosignal sets improving performance across seizure types. Conclusions: Wrist-worn wearables combined with ML can extend seizure detection beyond GTC seizures, though performance remains limited for non-motor types. Optimizing model selection, feature sets, and segment lengths, and minimizing false alarms, are key to clinical utility and real-world adoption.

Background: Physical function (PF) is an important outcome that can inform cancer treatment tolerability from a clinical and regulatory perspective. PF can be assessed through different modalities: patient-reported (PRO), clinician-reported (ClinRo), performance tests (PerfO), and digital sensors (wearables). No standard approach for PF measurement has been defined, and each modality bears unique implementation challenges. The Integrating 4 Measures to Assess Physical Function study (In4M, NCT05214144) characterized the performance of these PF modalities in patients receiving cytotoxic chemotherapy, with a goal of guiding an assessment strategy in future cancer trials. Here we present feasibility results of the In4M study in patients with lymphoma. Methods: In4M is a prospective observational study with longitudinal PF assessment of PROs, ClinRo, PerfO, and wearable sensor data for over 9 months in patients initiating chemotherapy for lymphoma or breast cancer at Mayo Clinic and Yale University. Patient-reported PF was assessed using several validated ePRO instruments, ClinRo utilized clinician-reported Eastern Cooperative Oncology Group (ECOG) performance status, PerfO was measured via 6-minute walk test (6MWT), and digital sensor data was obtained from a wearable (Fitbit) provided to all participants. We evaluated the feasibility of implementing these PF modalities through compliance outcomes and a study-specific exit survey. Descriptive statistics included medians and interquartile ranges (IQR) for continuous variables and frequencies for categorical variables. We used a mixed model to estimate mean number of Fitbit compliant days per week. Results: Among 66 patients with lymphoma in the study (median age was 57 years; 52% were male), 90% self-reported as White, 4.9% as Black, 1.6% as Asian, 1.6% as American Indian or Alaska Native, and 1.6% as multiple races. Ethnicity was reported as non-Hispanic/Latino by 93% of patients. Education status was reported as more than high school by 92% of patients, and 49% reported full-time employment at time of enrollment. The overall ePROs completion rate was 80.7% for the entire study period. Baseline ePRO completion rate was 93.9%. Completion rate while undergoing chemotherapy was 91.3% and 75.4% in the post-treatment follow-up. The median time to complete ePROs was 4.1 minutes (IQR 2.8-5.9), ranging from 3.1 minutes for surveys with 37 questions to 5.6 minutes for surveys with 55 questions (survey length varied by timepoint). The baseline 6MWT was completed by 91% of patients. The most common reasons for not completing the baseline 6MWT were: patient refusal (50%, 3/6), patient not physically present (33%, 2/6), and unable to complete due to fatigue (17%, 1/6). The 3-month 6MWT was completed by 66% (40/61) of patients, with the most common reasons for missingness being: patient not physically present (38%, 8/21) and unable to complete due to fatigue (14%, 3/21). When considering the days when Fitbit was used, the median wear time was 21.3 hours (IQR 18.9-22.5) per day. The proportion of compliant days (>10 hours of wear time during waking hours) was 53% (IQR 20-84). The median of participants' average compliant days per week was 5.4 (IQR 4.3-6.1) days/week after enrollment, with a slight downward trend over time (-0.017 compliant days per week [95% CI: -0.021, -0.012, p <0.001] over each consecutive week in the study). The exit survey was completed by 39 (59%) patients. Most participants (85%) indicated they did not find the ePRO surveys burdensome to complete. Using the Fitbit (charging and syncing) was found to be manageable by most patients (87% and 84%, respectively). 60.8% of patients did not find the wearable bothersome to use, while the main themes reported by the remaining patients were related to the operation of the wearable itself (functions, small text size, forgetting login information) or discomfort (band material, wearing at night). Conclusion: Multi-modal assessment of PF with PRO, ClinRo, PerfO and wearable sensor data in patients with lymphoma undergoing treatment is feasible. Designing lymphoma therapeutic trials that incorporate at least one PF assessment modality, or assessment with a parsimonious combination of modalities, is achievable and may yield valuable insights into treatment tolerability for clinical and regulatory purposes.

1564 Background: Physical function (PF) is a core outcome in cancer trials that can inform treatment tolerability. PF can be assessed across modalities including by patient (pt) report, clinician (clin) report, performance tests and digital sensors. The optimal approach for PF measurement has not been defined. Methods: In4M is a prospective observational study evaluating PF in pts initiating chemotherapy for breast cancer or lymphoma followed over 9 months. We used an electronic platform (Hugo) to aggregate serially assessed pt-reported PF, clin- and pt-reported ECOG performance status (PS), 6-minute walk test (6MWT) and wearable (Fitbit) data. We evaluated feasibility in all pts; associations among PF measures and the ability of PF measures to detect change were evaluated in pts with both baseline (BL) and 3-month (3M) data. We used Pearson correlations to assess the relationship of average daily steps with measures of PF. To assess change, we compared each PF measure from BL to 3M using a 2-sided α=.05 paired t-test. Results: Of the208 pts enrolled, 193 (93%) and 159 (76%) completed surveys, and 121 (58%) and 124 (60%) provided wearable data (evaluable: ≥1 day data) at BL and 3M, respectively. When requiring a stringent BL with 4+ days of data with ≥1 weekend day to be evaluable, 88 (42%) and 120 (58%) provided wearable data at BL and 3M. At both BL and 3M, pt-reported PF was generally more highly correlated with wearable-derived daily steps than clin-reported PF and 6MWT were (Table). Significant declines in PF were observed for pt- and clin-reported PF (all p<0.05), but not other modalities. Conclusions: Longitudinalassessment of multi-modal PF data including pragmatic wearable data collection was feasible in pts receiving chemotherapy. Pt-reported PF was the only modality that was both correlated with step count and able to detect change. Additional wearable metrics, correlations among PF measurements and outcomes, and clinically meaningful change scores will be reported. Optimal PF measurement may improve future reporting of treatment tolerability. Clinical trial information: NCT05214144 . [Table: see text]