Airborne pollen can trigger allergic rhinitis and other respiratory diseases in the synthesised population, which makes it one of the most relevant biological contaminants. Therefore, implementing accurate forecast systems is a priority for public health. The current forecast models are generally useful, but they falter when long time series of data are managed. The emergence of new computational techniques such as the LSTM algorithms could constitute a significant improvement for the pollen risk assessment. In this study, several LSTM variants were applied to forecast monthly pollen integrals in Málaga (southern Spain) using meteorological variables as predictors. Olea and Urticaceae pollen types were modelled as proxies of different annual pollen curves, using data from the period 1992-2022. The aims of this study were to determine the LSTM variants with the highest accuracy when forecasting monthly pollen integrals as well as to compare their performance with the traditional pollen forecast methods. The results showed that the CNN-LSTM were the most accurate when forecasting the monthly pollen integrals for both pollen types. Moreover, the traditional forecast methods were outperformed by all the LSTM variants. These findings highlight the importance of implementing LSTM models in pollen forecasting for public health and research applications.

In the last decade, clinical trial management systems have become an essential support tool for data management and analysis in clinical research. However, these clinical tools have design limitations, since they are currently not able to cover the needs of adaptation to the continuous changes in the practice of the trials due to the heterogeneous and dynamic nature of the clinical research data. These systems are usually proprietary solutions provided by vendors for specific tasks. In this work, we propose FIMED, a software solution for the flexible management of clinical data from multiple trials, moving towards personalized medicine, which can contribute positively by improving clinical researchers quality and ease in clinical trials. This tool allows a dynamic and incremental design of patients' profiles in the context of clinical trials, providing a flexible user interface that hides the complexity of using databases. Clinical researchers will be able to define personalized data schemas according to their needs and clinical study specifications. Thus, FIMED allows the incorporation of separate clinical data analysis from multiple trials. The efficiency of the software has been demonstrated by a real-world use case for a clinical assay in Melanoma disease, which has been indeed anonymized to provide a user demonstration. FIMED currently provides three data analysis and visualization components, guaranteeing a clinical exploration for gene expression data: heatmap visualization, clusterheatmap visualization, as well as gene regulatory network inference and visualization. An instance of this tool is freely available on the web at https://khaos.uma.es/fimed. It can be accessed with a demo user account, "researcher", using the password "demo". This paper shows FIMED as a flexible and user-friendly way of managing multidimensional clinical research data. Hence, without loss of generality, FIMED is flexible enough to be used in the context of any other disease where clinical data and assays are involved.

Accurate crop yield forecasting requires identifying informative predictors from high-dimensional meteorological time series with multiple time lags. Such settings often lead to overfitting, reduced interpretability, and increased computational cost. This paper proposes a two-phase feature-selection framework, termed CS $$_\text {MRMR}$$ MRMR -DWES $$_R$$ R , to address these challenges in agricultural time-series regression. In the first phase, a supervised filter ranks features using correlation statistics with a maximum relevance-minimum redundancy criterion, retaining a compact subset of informative variables. In the second phase, a wrapper-based discrete weighted evolutionary strategy automatically selects the optimal feature subset by directly optimizing the predictive performance of a SARIMAX regression model. The proposed framework is evaluated on 20 years of monthly avocado and mango yield data from the Axarquía region of Málaga in Spain under multiple lag configurations. This feature selection might slightly change over time and depends entirely on the crop type and geographical location. The proposed CS $$_\text {MRMR}$$ MRMR -DWES $$_\text {R}$$ R framework inherently requires high-performance computing (HPC) capabilities due to the scale and complexity of the agricultural time-series datasets under study. Experimental results show that CS $$_\text {MRMR}$$ MRMR -DWES $$_R$$ R improves forecasting accuracy while reducing feature dimensionality and computational cost compared with baseline and existing feature-selection methods. These findings highlight the effectiveness of the proposed approach for high-dimensional agricultural time-series analysis.