Cluster analysis of weather and pollution features and its role in predicting acute cardiac or cerebrovascular events.

BACKGROUND: Despite mounting evidence, the impact of the interplay between weather and pollution features on the risk of acute cardiac and cerebrovascular events has not been entirely appraised. The aim of this study was to perform a comprehensive cluster analysis of weather and pollution features in a large metropolitan area, and their association with acute cardiac and cerebrovascular events. METHODS: Anonymized data on acute myocardial infarction (AMI) and acute cerebrovascular events were obtained from 3 tertiary care centers from a single large metropolitan area. Weather and pollution data were obtained averaging measurements from several city measurement stations managed by the competent regional agency for enviromental protection, and from the Metereological Center of Italian Military Aviation. Unsupervised machine learning was performed with hierarchical clustering to identify specific days with distinct weather and pollution features. Clusters were then compared for rates of acute cardiac and cerebrovascular events with Poisson models. RESULTS: As expected, significant pairwise correlations were found between weather and pollution features. Building upon these correlations, hierarchical clustering, from a total of 1169 days, generated 4 separate clusters: mostly winter days with low temperatures and high ozone concentrations (cluster 1, N.=60, 5.1%), days with moderately high temperatures and low pollutants concentrations (cluster 2, N.=419, 35.8%), mostly summer and spring days with high temperatures and high ozone concentrations (cluster 3, N.=673, 57.6%), and mostly winter days with low temperatures and low ozone concentrations (cluster 4, N.=17, 1.5%). Overall cluster-wise comparisons showed significant differences in adverse cardiac and cerebrovascular events (P<0.001), as well as in cerebrovascular events (P<0.001) and strokes (P=0.001). Between-cluster comparisons showed that cluster 1 was associated with an increased risk of any event, cerebrovascular events, and strokes in comparison to cluster 2, cluster 3 and cluster 4 (all P<0.05), as well as AMI in comparison to cluster 3 (P=0.047). In addition, cluster 2 was associated with a higher risk of strokes in comparison to cluster 4 (P=0.030). Analysis adjusting for season confirmed the increased risk of any event, cerebrovascular events and strokes for cluster 1 and cluster 2. CONCLUSIONS: Unsupervised machine learning can be leveraged to identify specific days with a unique clustering of adverse weather and pollution features which are associated with an increased risk of acute cardiovascular events, especially cerebrovascular events. These findings may improve collective and individual risk prediction and prevention.

Impact of weather and pollution on the rate of cerebrovascular events in a large metropolitan area.

BACKGROUND: Despite mounting evidence, there is uncertainty on the impact of the interplay between weather and pollution features on the risk of acute cerebrovascular events (CVE). We aimed at appraising role of weather and pollution on the daily risk of CVE. METHODS: Anonymized data from a hub CVE center in a large metropolitan area were collected and analyzed according to weather (temperature, pressure, humidity, and rainfall) and pollution (carbon monoxide [CO], nitrogen dioxide [NO2], nitrogen oxides [NOX], ozone [O3], and particulate matter [PM]) on the same and the preceding days. Poisson regression and time series analyses were used to appraise the association between environmental features and daily CVE, distinguishing also several subtypes of events. RESULTS: We included a total of 2534 days, with 1363 days having ≥1 CVE, from 2012 to 2017. Average daily rate was 1.56 (95% confidence interval: 1.49; 1.63) for CVE, with other event rates ranging between 1.42 for stroke and 0.01 for ruptured intracranial aneurysm. Significant associations were found between CVE and temperature, pressure, CO, NO2, NOX, O3, and PM <10 µm (all P<0.05), whereas less stringent associations were found for humidity, rainfall, and PM <2.5 µm. Time series analysis exploring lag suggested that associations were stronger at same-day analysis (lag 0), but even environmental features predating several days or weeks were significantly associated with events. Multivariable analysis suggested that CO (point estimate 1.362 [1.011; 1.836], P=0.042) and NO2 (1.011 [1.005; 1.016], P<0.001) were the strongest independent predictors of CVE. CONCLUSIONS: Environmental features are significantly associated with CVE, even several days before the actual event. Levels of CO and NO2 can be potentially leveraged for population-level interventions to reduce the burden of CVE.