Fiona Tummon

Developed using the GRADE methodology, these EAACI guidelines provide evidence‐based recommendations on the effectiveness of pollen reduction/avoidance strategies for allergic rhinitis (AR) and asthma, the utility of biomarkers for monitoring pollen‐induced asthma and the efficiency of mitigation measures and of public health strategies. Systematic and narrative reviews and health economic analysis support the recommendations. According to GRADE, the certainty of evidence was moderate to very low, therefore conditional recommendations are provided to guide healthcare professionals, patients, and policymakers in developing personalized, preventive, and scalable interventions. Reducing/avoiding exposure to pollen should be recommended to reduce the risk of severe asthma exacerbations. Lung function decrease and exhaled nitric oxide increase may be predictive for pollen‐induced asthma exacerbations. Real‐time pollen monitoring and pollen concentration‐based forecast may be recommended for managing pollen‐induced AR and/or asthma. Pollutant information should be included in pollen information systems. Combined forecast (weather, pollen, pollutants) and warning systems might reduce the impact of thunderstorm asthma (TA). Emergency department/asthma‐related services should be strengthened during pollen season and in TA. Personalized frameworks covering the types and allergenic potential of pollen, the coaggressors and the vulnerability of each patient are needed in daily practice. The fundamental role of prevention should be further prioritized.

Advances in automatic bioaerosol monitoring require updated approaches to evaluate particle classification algorithms. We present a training and evaluation framework based on three metrics: (1) Kendall's Tau correlation between predicted and manual concentrations, (2) scaling factor, to assess identification efficiency, and (3) off-season noise ratio, quantifying off-season false predictions. Metrics are computed per class across confidence thresholds and five stations, and visualised in graphs revealing overfitting, station-specific biases, and sensitivity–specificity trade-offs. We provide optimal ranges for each metric respectively calculated from correlations on co-located manual measurements, worst-case scenario off-season noise ratio, and physical sampling limits constraining acceptable scaling factor. The evaluation framework was applied to seven deep-learning classifiers trained on holography and fluorescence data from SwisensPoleno devices, and compared with the 2022 holography-only classifier. Classifier performances are compared through visualisation methods, helping identifying over-training, misclassification between morphologically similar taxa or between pollen and non-pollen particles. This methodology allows a transparent and reproducible comparison of classification algorithms, independent of classifier architecture and device. Its adoption could help standardise performance reporting across the research community, even more so when evaluation datasets are standardised across different regions.

Advances in automatic bioaerosol monitoring require updated approaches to evaluate particle classification algorithms. We present a training and evaluation framework based on three metrics: (1) Kendall’s Tau correlation between predicted and manual concentrations, (2) scaling factor, to assess identification efficiency, and (3) off-season noise ratio, quantifying off-season false predictions. Metrics are computed per class across confidence thresholds and five stations stations, and visualised in graphs revealing overfitting, station-specific biases, and sensitivity–specificity trade-offs. We provide optimal ranges for each metric respectively calculated from correlations on co-located manual measurements, worst-case scenario off-season noise ratio, and physical sampling limits constraining acceptable scaling factor. The evaluation framework was applied to seven deep-learning classifiers trained on holography and fluorescence data from SwisensPoleno devices, and compared with the 2022 holography-only classifier. Classifier performances are compared through visualisation methods, helping identifying over-training, misclassification between morphologically similar taxa or between pollen and non-pollen particles. This methodology allows a transparent and reproducible comparison of classification algorithms, independent of classifier architecture and device. Its adoption could help standardise performance reporting across the research community, even more so when evaluation datasets are standardised across different regions.

Advances in automatic bioaerosol monitoring require updated approaches to evaluate particle classification algorithms. We present a training and evaluation framework based on three metrics: (1) Kendall’s Tau correlation between predicted and manual concentrations, (2) scaling factor, to assess identification efficiency, and (3) off-season noise ratio, quantifying off-season false predictions. Metrics are computed per class across confidence thresholds and five stations stations, and visualised in graphs revealing overfitting, station-specific biases, and sensitivity–specificity trade-offs. We provide optimal ranges for each metric respectively calculated from correlations on co-located manual measurements, worst-case scenario off-season noise ratio, and physical sampling limits constraining acceptable scaling factor. The evaluation framework was applied to seven deep-learning classifiers trained on holography and fluorescence data from SwisensPoleno devices, and compared with the 2022 holography-only classifier. Classifier performances are compared through visualisation methods, helping identifying over-training, misclassification between morphologically similar taxa or between pollen and non-pollen particles. This methodology allows a transparent and reproducible comparison of classification algorithms, independent of classifier architecture and device. Its adoption could help standardise performance reporting across the research community, even more so when evaluation datasets are standardised across different regions.

Advances in automatic bioaerosol monitoring require updated approaches to evaluate particle classification algorithms. We present a training and evaluation framework based on three metrics: (1) Kendall’s Tau correlation between predicted and manual concentrations, (2) scaling factor, to assess identification efficiency, and (3) off-season noise ratio, quantifying off-season false predictions. Metrics are computed per class across confidence thresholds and five stations stations, and visualised in graphs revealing overfitting, station-specific biases, and sensitivity–specificity trade-offs. We provide optimal ranges for each metric respectively calculated from correlations on co-located manual measurements, worst-case scenario off-season noise ratio, and physical sampling limits constraining acceptable scaling factor. The evaluation framework was applied to seven deep-learning classifiers trained on holography and fluorescence data from SwisensPoleno devices, and compared with the 2022 holography-only classifier. Classifier performances are compared through visualisation methods, helping identifying over-training, misclassification between morphologically similar taxa or between pollen and non-pollen particles. This methodology allows a transparent and reproducible comparison of classification algorithms, independent of classifier architecture and device. Its adoption could help standardise performance reporting across the research community, even more so when evaluation datasets are standardised across different regions.

Advances in automatic bioaerosol monitoring require updated approaches to evaluate particle classification algorithms. We present a training and evaluation framework based on three metrics: (1) Kendall’s Tau correlation between predicted and manual concentrations, (2) scaling factor, to assess identification efficiency, and (3) off-season noise ratio, quantifying off-season false predictions. Metrics are computed per class across confidence thresholds and five stations stations, and visualised in graphs revealing overfitting, station-specific biases, and sensitivity–specificity trade-offs. We provide optimal ranges for each metric respectively calculated from correlations on co-located manual measurements, worst-case scenario off-season noise ratio, and physical sampling limits constraining acceptable scaling factor. The evaluation framework was applied to seven deep-learning classifiers trained on holography and fluorescence data from SwisensPoleno devices, and compared with the 2022 holography-only classifier. Classifier performances are compared through visualisation methods, helping identifying over-training, misclassification between morphologically similar taxa or between pollen and non-pollen particles. This methodology allows a transparent and reproducible comparison of classification algorithms, independent of classifier architecture and device. Its adoption could help standardise performance reporting across the research community, even more so when evaluation datasets are standardised across different regions.

Advances in automatic bioaerosol monitoring require updated approaches to evaluate particle classification algorithms. We present a training and evaluation framework based on three metrics: (1) Kendall’s Tau correlation between predicted and manual concentrations, (2) scaling factor, to assess identification efficiency, and (3) off-season noise ratio, quantifying off-season false predictions. Metrics are computed per class across confidence thresholds and five stations stations, and visualised in graphs revealing overfitting, station-specific biases, and sensitivity–specificity trade-offs. We provide optimal ranges for each metric respectively calculated from correlations on co-located manual measurements, worst-case scenario off-season noise ratio, and physical sampling limits constraining acceptable scaling factor. The evaluation framework was applied to seven deep-learning classifiers trained on holography and fluorescence data from SwisensPoleno devices, and compared with the 2022 holography-only classifier. Classifier performances are compared through visualisation methods, helping identifying over-training, misclassification between morphologically similar taxa or between pollen and non-pollen particles. This methodology allows a transparent and reproducible comparison of classification algorithms, independent of classifier architecture and device. Its adoption could help standardise performance reporting across the research community, even more so when evaluation datasets are standardised across different regions.

Advances in automatic bioaerosol monitoring require updated approaches to evaluate particle classification algorithms. We present a training and evaluation framework based on three metrics: (1) Kendall’s Tau correlation between predicted and manual concentrations, (2) scaling factor, to assess identification efficiency, and (3) off-season noise ratio, quantifying off-season false predictions. Metrics are computed per class across confidence thresholds and five stations stations, and visualised in graphs revealing overfitting, station-specific biases, and sensitivity–specificity trade-offs. We provide optimal ranges for each metric respectively calculated from correlations on co-located manual measurements, worst-case scenario off-season noise ratio, and physical sampling limits constraining acceptable scaling factor. The evaluation framework was applied to seven deep-learning classifiers trained on holography and fluorescence data from SwisensPoleno devices, and compared with the 2022 holography-only classifier. Classifier performances are compared through visualisation methods, helping identifying over-training, misclassification between morphologically similar taxa or between pollen and non-pollen particles. This methodology allows a transparent and reproducible comparison of classification algorithms, independent of classifier architecture and device. Its adoption could help standardise performance reporting across the research community, even more so when evaluation datasets are standardised across different regions.

Advances in automatic bioaerosol monitoring require updated approaches to evaluate particle classification algorithms. We present a training and evaluation framework based on three metrics: (1) Kendall’s Tau correlation between predicted and manual concentrations, (2) scaling factor, to assess identification efficiency, and (3) off-season noise ratio, quantifying off-season false predictions. Metrics are computed per class across confidence thresholds and five stations stations, and visualised in graphs revealing overfitting, station-specific biases, and sensitivity–specificity trade-offs. We provide optimal ranges for each metric respectively calculated from correlations on co-located manual measurements, worst-case scenario off-season noise ratio, and physical sampling limits constraining acceptable scaling factor. The evaluation framework was applied to seven deep-learning classifiers trained on holography and fluorescence data from SwisensPoleno devices, and compared with the 2022 holography-only classifier. Classifier performances are compared through visualisation methods, helping identifying over-training, misclassification between morphologically similar taxa or between pollen and non-pollen particles. This methodology allows a transparent and reproducible comparison of classification algorithms, independent of classifier architecture and device. Its adoption could help standardise performance reporting across the research community, even more so when evaluation datasets are standardised across different regions.

Advances in automatic bioaerosol monitoring require updated approaches to evaluate particle classification algorithms. We present a training and evaluation framework based on three metrics: (1) Kendall’s Tau correlation between predicted and manual concentrations, (2) scaling factor, to assess identification efficiency, and (3) off-season noise ratio, quantifying off-season false predictions. Metrics are computed per class across confidence thresholds and five stations stations, and visualised in graphs revealing overfitting, station-specific biases, and sensitivity–specificity trade-offs. We provide optimal ranges for each metric respectively calculated from correlations on co-located manual measurements, worst-case scenario off-season noise ratio, and physical sampling limits constraining acceptable scaling factor. The evaluation framework was applied to seven deep-learning classifiers trained on holography and fluorescence data from SwisensPoleno devices, and compared with the 2022 holography-only classifier. Classifier performances are compared through visualisation methods, helping identifying over-training, misclassification between morphologically similar taxa or between pollen and non-pollen particles. This methodology allows a transparent and reproducible comparison of classification algorithms, independent of classifier architecture and device. Its adoption could help standardise performance reporting across the research community, even more so when evaluation datasets are standardised across different regions.