Mohand-Said Hacid

The polymer industry faces increasing complexity in material design and property characterization, often requiring advanced data handling skills that domain experts may lack. This work presents Poly-WorkFlowX, an integrated agentic system combining machine learning and low-code automation to bridge the gap between materials science and artificial intelligence. We propose an architecture where a conversational agent, powered by Large Language Models (LLMs), orchestrates data workflows based on natural language instructions. The system integrates a custom Multi-Task Learning model for polymer property prediction directly into the n8n low-code platform. This approach enables non-expert researchers to predict physico-chemical properties from molecular representations (PSMILES) and automatically generate reproducible data processing pipelines. We demonstrate the system's efficiency through a complexity analysis, highlighting the reduction in manual configuration steps required to deploy scientific workflows.

Many studies have demonstrated a correlation between environmental predictors and hospital attendance, particularly air pollution, a significant risk to health. One important factor that affects air pollution concentration is meteorology. Both factors contribute to an increase in the healthcare demand, which can lead to the global problem of Emergency Department Crowding. To address this problem, forecasting models are essential in resources allocation and general management to improve patient outcomes. Machine Learning (ML), especially Deep Learning (DL), techniques offer considerable promise for patient volume forecasting of hospital visits and in-hospital mortality. In this work, we present a systematic review of the use of ML to predict patient volume hospital attendance and in-hospital mortality with the use of environmental predictors. We focus on answering how have ML been applied and what are the major environmental predictors. Using the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA), 21 studies were retained from three databases PubMed, Embase, and IEEE Explore. The search included studies from 2012 to 2022. Data extraction and Risk of Bias assessment were done by using standardized tools Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS), and Prediction model Risk Of Bias ASsessment Tool (PROBAST). The study protocol for this review was registered on PROSPERO, assigned registration code CRD42023390400.