Developing a short-term prediction model for asthma exacerbations from Swedish primary care patients' data using machine learning - Based on the ARCTIC study.

OBJECTIVE: The ability to predict impending asthma exacerbations may allow better utilization of healthcare resources, prevention of hospitalization and improve patient outcomes. We aimed to develop models using machine learning to predict risk of exacerbations. METHODS: Data from 29,396 asthma patients was collected from electronic medical records and national registers covering clinical and epidemiological factors (e.g. comorbidities, health care contacts), between 2000 and 2013. Machine-learning classifiers were used to create models to predict exacerbations within the next 15 days. Model selection was done using the mean cross validation score of area under precision-recall curve (AUPRC). RESULTS: The most important predictors of exacerbation were comorbidity burden and previous exacerbations. Model validation on test data yielded an AUPRC = 0.007 (95% CI: ± 0.0002), indicating that historic clinical information alone may not be sufficient to predict a near future risk of asthma exacerbation. CONCLUSIONS: Supplementation with additional data on environmental triggers, (e.g. weather, pollen count, air quality) and from wearables, might be necessary to improve performance of the short-term predictive model to develop a more clinically useful tool.

Predicting Hospitalization Due to COPD Exacerbations in Swedish Primary Care Patients Using Machine Learning - Based on the ARCTIC Study.

PURPOSE: Chronic obstructive pulmonary disease (COPD) exacerbations can negatively impact disease severity, progression, mortality and lead to hospitalizations. We aimed to develop a model that predicts a patient's risk of hospitalization due to severe exacerbations (defined as COPD-related hospitalizations) of COPD, using Swedish patient level data. PATIENTS AND METHODS: Patient level data for 7823 Swedish patients with COPD was collected from electronic medical records (EMRs) and national registries covering healthcare contacts, diagnoses, prescriptions, lab tests, hospitalizations and socioeconomic factors between 2000 and 2013. Models were created using machine-learning methods to predict risk of imminent exacerbation causing patient hospitalization due to COPD within the next 10 days. Exacerbations occurring within this period were considered as one event. Model performance was assessed using the Area under the Precision-Recall Curve (AUPRC). To compare performance with previous similar studies, the Area Under Receiver Operating Curve (AUROC) was also reported. The model with the highest mean cross validation AUPRC was selected as the final model and was in a final step trained on the entire training dataset. RESULTS: The most important factors for predicting severe exacerbations were exacerbations in the previous six months and in whole history, number of COPD-related healthcare contacts and comorbidity burden. Validation on test data yielded an AUROC of 0.86 and AUPRC of 0.08, which was high in comparison to previously published attempts to predict COPD exacerbation. CONCLUSION: Our work suggests that clinically available information on patient history collected via automated retrieval from EMRs and national registries or directly during patient consultation can form the basis for future clinical tools to predict risk of severe COPD exacerbations.

Fevipiprant, a prostaglandin D2 receptor 2 antagonist, in patients with persistent eosinophilic asthma: a single-centre, randomised, double-blind, parallel-group, placebo-controlled trial.

BACKGROUND: Eosinophilic airway inflammation is often present in asthma, and reduction of such inflammation results in improved clinical outcomes. We hypothesised that fevipiprant (QAW039), an antagonist of prostaglandin D2 receptor 2, might reduce eosinophilic airway inflammation in patients with moderate-to-severe eosinophilic asthma. METHODS: We performed a single-centre, randomised, double-blind, parallel-group, placebo-controlled trial at Glenfield Hospital (Leicester, UK). We recruited patients with persistent, moderate-to-severe asthma and an elevated sputum eosinophil count (≥2%). After a 2-week single-blind placebo run-in period, patients were randomly assigned (1:1) by the trial pharmacist, using previously generated treatment allocation cards, to receive fevipiprant (225 mg twice per day orally) or placebo, stratified by the use of oral corticosteroid treatment and bronchoscopy. The 12-week treatment period was followed by a 6-week single-blind placebo washout period. The primary outcome was the change in sputum eosinophil percentage from baseline to 12 weeks after treatment, analysed in the intention-to-treat population. All patients who received at least one dose of study drug were included in the safety analyses. This trial is registered with ClinicalTrials.gov, number NCT01545726, and with EudraCT, number 2011-004966-13. FINDINGS: Between Feb 10, 2012, and Jan 30, 2013, 61 patients were randomly assigned to receive fevipiprant (n=30) or placebo (n=31). Three patients in the fevipiprant group and four patients in the placebo group withdrew because of asthma exacerbations. Two patients in the fevipiprant group were incorrectly given placebo (one at the mid-treatment visit and one throughout the course of the study). They were both included in the fevipiprant group for the primary analysis, but the patient who was incorrectly given placebo throughout was included in the placebo group for the safety analyses. Between baseline and 12 weeks after treatment, sputum eosinophil percentage decreased from a geometric mean of 5·4% (95% CI 3·1-9·6) to 1·1% (0·7-1·9) in the fevipiprant group and from 4·6% (2·5-8·7) to 3·9% (CI 2·3-6·7) in the placebo group. Compared with baseline, mean sputum eosinophil percentage was reduced by 4·5 times in the fevipiprant group and by 1·3 times in the placebo group (difference between groups 3·5 times, 95% CI 1·7-7·0; p=0·0014). Fevipiprant had a favourable safety profile, with no deaths or serious adverse events reported. No patient withdrawals were judged by the investigator to be related to the study drug. INTERPRETATION: Fevipiprant reduces eosinophilic airway inflammation and is well tolerated in patients with persistent moderate-to-severe asthma and raised sputum eosinophil counts despite inhaled corticosteroid treatment. FUNDING: Novartis Pharmaceuticals, AirPROM project, and the UK National Institute for Health Research.

Inhaled vasoactive intestinal peptide exerts immunoregulatory effects in sarcoidosis.

RATIONALE: Previous studies suggest an important immunoregulatory role of vasoactive intestinal peptide (VIP) in experimental models of chronic noninfectious inflammation. Sarcoidosis is characterized by noncaseating epitheloid cell granulomas, where excessive tumor necrosis factor-alpha production by pulmonary macrophages plays a critical role in granuloma formation and disease progression, which may lead to fatal organ dysfunction. OBJECTIVES: To test whether inhaled VIP has an immunoregulatory role. Sarcoid alveolitis was used as a prototype of immune-mediated chronic lung inflammation. METHODS: In an open clinical phase II study, we treated 20 patients with histologically proved sarcoidosis and active disease with nebulized VIP for 4 weeks. MEASUREMENTS AND MAIN RESULTS: VIP inhalation was safe, well-tolerated, and significantly reduced the production of tumor necrosis factor-alpha by cells isolated from bronchoalveolar lavage fluids of these patients. VIP treatment significantly increased the numbers of bronchoalveolar lavage CD4(+)CD127(-)CD25(+) T cells, which showed regulatory activities on conventional effector T cells. In vitro experiments demonstrated the capacity of VIP to convert naive CD4(+)CD25(-) T cells into CD4(+)CD25(+)FoxP3(+) regulatory T cells, suggesting the generation of peripheral regulatory T cells by VIP treatment. CONCLUSIONS: This study is the first to show the immunoregulatory effect of VIP in humans, and supports the notion of inhaled VIP as an attractive future therapy to dampen exaggerated immune responses in lung disorders. Thus, the inhalation of neuropeptides may be developed into a new therapeutic principle for chronic inflammatory lung disorders in humans.

Indibulin, a novel microtubule inhibitor, discriminates between mature neuronal and nonneuronal tubulin.

Microtubule inhibitors interfere with microtubule dynamics, causing cell cycle arrest and apoptosis. These effects are responsible for the chemotherapeutic activities of members of the taxane and Vinca alkaloid families in oncology. Unfortunately, a major side effect of the taxanes and Vinca alkaloids is the development of peripheral neuropathies. Indibulin (N-[pyridin-4-yl]-[1-(4-chlorbenzyl)-indol-3-yl]-glyoxyl-amid; D-24851; ZIO-301), a novel synthetic small molecule microtubule inhibitor, destabilizes microtubules and has antitumor activity but does not exhibit neurotoxicity in preclinical animal studies. In the present study, it has been found that indibulin is able to discriminate between highly posttranslationally modified tubulin present in mature neuronal microtubules, and less-modified tubulin present in immature neuronal or nonneuronal microtubules. Vincristine and colchicine act on either tubulin equally well. The binding site of indibulin on mature neuronal microtubules seems to be inaccessible due to the posttranslational modifications, a theory that is supported by the observation that indibulin did not disrupt the integrity of highly modified microtubules present in neurites of pheochromocytoma (PC12) cells. The specificity of indibulin for unmodified microtubules seems to be dependent on the pyridyl moiety of indibulin because derivatives that have the pyridyl moiety replaced are not able to discriminate between highly and less-modified tubulins. The observed broad antitumor activity of indibulin and the lack of central and peripheral nervous system toxicity in preclinical studies make it a promising candidate for development as a cancer treatment. Indibulin is currently in phase I clinical trials.

Protein kinase G from pathogenic mycobacteria promotes survival within macrophages.

Pathogenic mycobacteria resist lysosomal delivery after uptake into macrophages, allowing them to survive intracellularly. We found that the eukaryotic-like serine/threonine protein kinase G from pathogenic mycobacteria was secreted within macrophage phagosomes, inhibiting phagosome-lysosome fusion and mediating intracellular survival of mycobacteria. Inactivation of protein kinase G by gene disruption or chemical inhibition resulted in lysosomal localization and mycobacterial cell death in infected macrophages. Besides identifying a target for the control of mycobacterial infections, these findings suggest that pathogenic mycobacteria have evolved eukaryotic-like signal transduction mechanisms capable of modulating host cell trafficking pathways.