Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational study.

OBJECTIVE: Our study compares physician judgement with an automated early warning system (EWS) for predicting clinical deterioration of hospitalised general internal medicine patients. DESIGN: Prospective observational study of clinical predictions made at the end of the daytime work-shift for an academic general internal medicine floor team compared with the risk assessment from an automated EWS collected at the same time. SETTING: Internal medicine teaching wards at a single tertiary care academic medical centre in the USA. PARTICIPANTS: Intern physicians working on the internal medicine wards and an automated EWS (Rothman Index by PeraHealth). OUTCOME: Clinical deterioration within 24 hours including cardiac or pulmonary arrest, rapid response team activation or unscheduled intensive care unit transfer. RESULTS: We collected predictions for 1874 patient days and saw 35 clinical deteriorations (1.9%). The area under the receiver operating curve (AUROC) for the EWS was 0.73 vs 0.70 for physicians (p=0.571). A linear regression model combining physician and EWS predictions had an AUROC of 0.75, outperforming physicians (p=0.016) and the EWS (p=0.05). CONCLUSIONS: There is no significant difference in the performance of the EWS and physicians in predicting clinical deterioration at 24 hours on an inpatient general medicine ward. A combined model outperformed either alone. The EWS and physicians identify partially overlapping sets of at-risk patients suggesting they rely on different cues or decision rules for their predictions. TRIAL REGISTRATION NUMBER: NCT02648828.

The Effects of Obesity in Asthma.

PURPOSE OF REVIEW: Rising costs and increasing morbidity makes the identification and treatment of high-risk asthma phenotypes important. In this review, we outline the complex relationship between obesity and asthma. RECENT FINDINGS: Studies have confirmed a bi-directional relationship between obesity and asthma. Pathophysiological factors implicated include genetic risk, the effect of diet and microbiome, and obesity-related cytokines. There have been robust, albeit derived, efforts to phenotype this group with distinct clinical presentations based on age of onset of asthma. Unfortunately, the poor performance of biomarkers and traditional lung function testing has impeded diagnosis, phenotyping, and management of the obese asthma patient. There is also a lack of targeted interventions with weight loss showing some benefits. Obesity increases the prevalence of asthma and is associated with worse outcomes. There are unique research and clinical challenges while managing this group of patients.

Obesity and adult asthma: diagnostic and management challenges.

PURPOSE OF REVIEW: Despite advances in our understanding of the obese asthma phenotype, heterogeneity and large gaps in knowledge have hindered significant advances in directed interventions. RECENT FINDINGS: Obesity is associated with poorer asthma-related outcomes and increased risk of progression to severe asthma. Obese asthma is associated with variability in the expression of inflammatory markers, lung function impairments, and response to conventional and biologic therapies. In addition, traditional asthma biomarkers are not as reliable in obese patients. Several mechanistic pathways that uniquely impact asthma in obesity have been identified. Pathways involving innate lymphoid cells (ILC) type 2 (ILC-2) cells, surfactant protein-A, cell division control protein (CDC)42, interleukin (IL)-6, IL-17, and IL-33 are likely causal inflammatory pathways. Obesity also confounds lung function parameters making accurate diagnosis more challenging. As such, personalized asthma therapies directed towards obese asthma endotypes remain elusive. SUMMARY: Obesity confounds traditional asthma biomarkers and lung function measurements, thus defining obese asthma endotypes remains challenging. Novel pathways are being identified and hold promise for future targeted therapies. However, we are in dire need of updated guidelines regarding asthma diagnosis in obese patients and the development of biomarkers that more accurately identify specific endotypes.

Mediastinal and Subcutaneous Chest Fat Are Differentially Associated with Emphysema Progression and Clinical Outcomes in Smokers.

BACKGROUND: Studies have demonstrated both positive and negative effects of obesity on clinical outcomes in chronic obstructive pulmonary disease (COPD). In other chronic diseases, fat location is differentially associated with disease outcomes; however, this relationship has not been well studied in COPD. OBJECTIVE: To determine if fat location explains the differential association of body mass index (BMI) with clinical outcome measures in smokers. METHODS: Baseline and 6-year chest computed tomography scans from 68 current and former smokers were used to quantify mediastinal and subcutaneous fat. The relationships of BMI, mediastinal fat, and subcutaneous fat with cross-sectional and 6-year changes in pulmonary function, incremental shuttle walk distance (ISWD), quantitative emphysema, and circulating interleukin-6 (IL-6) and C-reactive protein (CRP) levels were assessed using generalized linear models adjusted for clinically relevant covariates. RESULTS: Baseline subcutaneous fat was negatively associated with emphysema progression over 6 years (p < 0.01). BMI and mediastinal fat volume were inversely associated with baseline ISWD (p < 0.01 and p = 0.043, respectively) as well as 6-year change in ISWD (p = 0.020 and p = 0.028, respectively). IL-6 was directly associated with BMI and mediastinal fat (p < 0.01) and CRP was directly associated with BMI only (p = 0.033). CONCLUSIONS: Increased subcutaneous chest fat is associated with less emphysema progression over time in smokers, while increased mediastinal fat volume is associated with decreased walk distance and increased IL-6 levels. These findings suggest a complex interaction between fat, inflammation, and emphysema that should be considered when phenotyping patients with COPD and provide new evidence of an inverse association between emphysema progression and chest subcutaneous fat.