Background: Many chemical releases are first noticed by community members, but reporting these concerns often involves considerable hurdles. Artificial Intelligence (AI)-enabled technologies, especially large language models (LLMs), can potentially reduce these barriers.
Objective: We hypothesized that AI-powered chatbots can facilitate reporting of pollution incidents through text messaging.
Methods: We created an AI-powered chatbot, "MyEcoReporter," that enables communities to report environmental incidents to government authorities. Eschewing traditional web-based forms, users text concerns via SMS to the LLM-powered application, engaging in a natural conversation through which required information is collected. The application was built using Python, AWS Lambda, DynamoDB, and Twilio, and deployed via Serverless.
Results: This architecture allowed rapid customization for various use cases, which successfully facilitated conversations and stored structured data for formal submission.
Impact Statement: MyEcoReporter showcases the potential of Artificial Intelligence/Large Language Models to create user-friendly tools that translate community environmental concerns into actionable information for reporting to government authorities.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1038/s41370-025-00747-5 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The Italian version of the Surgical Fear Questionnaire: validation of its measurement properties.
Minerva Anestesiol
December 2024
Pain Management Center, Neurocenter of Southern Switzerland, EOC, Lugano, Switzerland -
Background: Surgical fear is present in many patients awaiting surgery. However, a validated Italian version of the Surgical Fear Questionnaire (SFQ) was not available yet. Therefore, the aim of this study was to translate the SFQ into Italian and to test its reliability and validity.
View Article and Find Full Text PDFImpact of Multimodal Prompt Elements on Diagnostic Performance of GPT-4V in Challenging Brain MRI Cases.
Radiology
January 2025
From the Institute of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Ismaninger Strasse 22, Munich 81675, Germany.
Background Studies have explored the application of multimodal large language models (LLMs) in radiologic differential diagnosis. Yet, how different multimodal input combinations affect diagnostic performance is not well understood. Purpose To evaluate the impact of varying multimodal input elements on the accuracy of OpenAI's GPT-4 with vision (GPT-4V)-based brain MRI differential diagnosis.
View Article and Find Full Text PDFTripartite organization of brain state dynamics underlying spoken narrative comprehension.
Elife
January 2025
State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University & IDG/McGovern Institute for Brain Research, Beijing, China.
Speech comprehension involves the dynamic interplay of multiple cognitive processes, from basic sound perception, to linguistic encoding, and finally to complex semantic-conceptual interpretations. How the brain handles the diverse streams of information processing remains poorly understood. Applying Hidden Markov Modeling to fMRI data obtained during spoken narrative comprehension, we reveal that the whole brain networks predominantly oscillate within a tripartite latent state space.
View Article and Find Full Text PDFComparative Analysis of Recurrent Neural Networks with Conjoint Fingerprints for Skin Corrosion Prediction.
J Chem Inf Model
January 2025
Division of Pharmaceutical Chemistry, Faculty of Pharmaceutical Sciences, Khon Kaen University, Khon Kaen 40002, Thailand.
Skin corrosion assessment is an essential toxicity end point that addresses safety concerns for topical dosage forms and cosmetic products. Previously, skin corrosion assessments required animal testing; however, differences in skin architecture and ethical concerns regarding animal models have fostered the advancement of alternative methods such as and models. This study aimed to develop deep learning (DL) models based on recurrent neural networks (RNNs) for classifying skin corrosion of chemical compounds based on chemical language notation, molecular substructure, physicochemical properties, and a combination of these three properties called conjoint fingerprints.
View Article and Find Full Text PDFSociodemographic and regional differences in neonatal and infant mortality in Switzerland in 2011-2018: the Swiss National Cohort.
Swiss Med Wkly
November 2024
Institute of Social and Preventive Medicine, University of Bern, Bern, Switzerland.
Background And Aims: Despite a well-funded healthcare system with universal insurance coverage, Switzerland has one of the highest neonatal and infant mortality rates among high-income countries. Identifying avoidable risk factors targeted by evidence-based policies is a public health priority. We describe neonatal and infant mortality in Switzerland from 2011 to 2018 and explore associations with neonatal- and pregnancy-related variables, parental sociodemographic information, regional factors and socioeconomic position (SEP) using data from a long-term nationwide cohort study.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!