Harrison, Andrew

Abstract RATIONALE: Airway remodeling, a key characteristic of severe asthma, leads to progressive loss of lung function and incomplete reversibility of airflow obstruction. We examined the effect of benralizumab on lung function in patients from the pooled SIROCCO (Bleecker ER, et al. Lancet 2016; PMID: 27609408) and CALIMA (FitzGerald JM, et al. Lancet 2016; PMID: 27609406) studies, utilizing a new analysis of spirometry to highlight important changes in forced expiratory volume in 1 second (FEV1) and forced vital capacity (FVC) throughout the studies. METHODS: This retrospective analysis pooled data from the randomized, placebo-controlled, double-blind Phase 3 SIROCCO and CALIMA studies. SIROCCO enrolled patients with severe asthma, while CALIMA enrolled patients with moderate-to-severe asthma, both with a planned 2:1 randomization for baseline blood eosinophils ≥300 cells/μL versus <300 cells/μL. All patients (aged 12-75 years) had ≥2 exacerbations in the previous year, despite use of medium- to high-dose inhaled corticosteroids plus additional controllers. Patients in this analysis received subcutaneous benralizumab 30 mg every 8 weeks (Q8W; first three doses given every 4 weeks) for 48 weeks in SIROCCO and 56 weeks in CALIMA. The changes in FEV1 and FVC following bronchodilator (BD) were measured at baseline and study end. Effects on FEV1 and FVC were further stratified by baseline eosinophil count (≥300 cells/μL or <300 cells/μL). Results are reported as mean (standard deviation). RESULTS: Overall, 839 patients received benralizumab Q8W; 557 had a baseline eosinophil count of ≥300 cells/μL and 282 had <300 cells/μL. At baseline, pre- and post-BD FEV1 were 1722 mL (615; n=837) and 2128 mL (755; n=813). At study end, pre- and post-BD FEV1 were 2029 mL (756; n=735) and 2225 mL (800; n=738). At baseline, pre- and post-BD FVC were 2865 mL (905; n=837) and 3285 mL (971; n=813). At study end, pre- and post-BD FVC were 3214 mL (1010; n=735) and 3379 mL (1021; n=738). Pre-BD FEV1 and FVC improved by 307 mL and 349 mL and post-BD FEV1 and FVC improved by 97 mL and 94 mL between baseline and study end, respectively. Stratified by baseline eosinophil count, findings were similar in both groups (Figure). CONCLUSIONS: Benralizumab treatment resulted in both improved FEV1 and FVC while maintaining BD response in patients with uncontrolled, moderate-to-severe asthma. Improvements were seen in patients with baseline eosinophil counts of both ≥300 cells/μL and <300 cells/μL. These results may reflect reduced hyperinflation, potentially due to improved airway inflammation and mucus plugging.

Abstract Objective Access to palliative care (PC) is important for many patients with uncontrolled symptom burden from serious or complex illness. However, many patients who could benefit from PC do not receive it early enough or at all. We sought to address this problem by building a predictive model into a comprehensive clinical framework with the aims to (i) identify in-hospital patients likely to benefit from a PC consult, and (ii) intervene on such patients by contacting their care team. Materials and Methods Electronic health record data for 68 349 inpatient encounters in 2017 at a large hospital were used to train a model to predict the need for PC consult. This model was published as a web service, connected to institutional data pipelines, and consumed by a downstream display application monitored by the PC team. For those patients that the PC team deems appropriate, a team member then contacts the patient’s corresponding care team. Results Training performance AUC based on a 20% holdout validation set was 0.90. The most influential variables were previous palliative care, hospital unit, Albumin, Troponin, and metastatic cancer. The model has been successfully integrated into the clinical workflow making real-time predictions on hundreds of patients per day. The model had an “in-production” AUC of 0.91. A clinical trial is currently underway to assess the effect on clinical outcomes. Conclusions A machine learning model can effectively predict the need for an inpatient PC consult and has been successfully integrated into practice to refer new patients to PC.