Objective Frailty is a prevalent risk factor for adverse outcomes among patients with chronic lung disease. However, identifying frail patients who may benefit from interventions is challenging using standard data sources. We therefore sought to identify phrases in clinical notes in the electronic health record (EHR) that describe actionable frailty syndromes. Materials and Methods We used an active learning strategy to select notes from the EHR and annotated each sentence for 4 actionable aspects of frailty: respiratory impairment, musculoskeletal problems, fall risk, and nutritional deficiencies. We compared the performance of regression, tree-based, and neural network models to predict the labels for each sentence. We evaluated performance with the scaled Brier score (SBS), where 1 is perfect and 0 is uninformative, and the positive predictive value (PPV). Results We manually annotated 155 952 sentences from 326 patients. Elastic net regression had the best performance across all 4 frailty aspects (SBS 0.52, 95% confidence interval [CI] 0.49–0.54) followed by random forests (SBS 0.49, 95% CI 0.47–0.51), and multi-task neural networks (SBS 0.39, 95% CI 0.37–0.42). For the elastic net model, the PPV for identifying the presence of respiratory impairment was 54.8% (95% CI 53.3%–56.6%) at a sensitivity of 80%. Discussion Classification models using EHR notes can effectively identify actionable aspects of frailty among patients living with chronic lung disease. Regression performed better than random forest and neural network models. Conclusions NLP-based models offer promising support to population health management programs that seek to identify and refer community-dwelling patients with frailty for evidence-based interventions.

No abstract

Unresolved questions in aged muscle involve whether the loss of muscle stem cells, satellite cells, contributes to sarcopenia and impedes hypertrophy of aged muscle. To directly address these questions, we developed the Pax7‐DTA mouse that conditionally and specifically ablates Pax7+ satellite cells following tamoxifen administration (TM). Four month old mice were treated with TM or vehicle and at 5 (young) or 24 (old) months of age were subjected to a synergist ablation (SA; two weeks of overload) or sham surgery. With age, vehicle treated muscles demonstrated a 52% reduction in Pax7+ satellite cells. TM treated muscles showed >;90% ablation after 1 month and no recovery after 20 months, such that the aged mice lived the majority of their lives with a significantly reduced satellite cell pool. Despite Pax7 depletion with TM, muscle mass, fiber cross‐sectional area and function were all reduced with age independent of Pax7 number. After SA, TM mice increased muscle mass and fiber cross‐sectional area to the same extent as vehicle, with old mice demonstrating an attenuated hypertrophy compared to young. Large myofiber distribution decreased with age and increased with SA, independent of Pax7 number. However, the total number of small fibers (<600 um2), relatively more abundant in aged muscle, were reduced with TM. These data provide convincing evidence the satellite cell niche does not play a role in maintenance of skeletal muscle mass across the lifespan or in hypertrophy of young or old muscle.Funding: NIH R01AR060701, R21AG34453. Ellison Foundation/American Federation of Aging Research EPD12102.

No abstract

No abstract