Comparative Analysis of Air Quality Index Using Large Language Models and Machine Learning

Air Quality Index prediction using an effective hybrid deep learning model

A significant challenge in air quality index (AQI) prediction is to accurately evaluate the potential outcomes after conducting interventions in pollutant factors such as industrial emissions for each enterprise. Existed methods often suffer from spurious correlations caused by unmeasured confounders and are lack of interpretability of the model, leading to sub-optimal prediction performance. This motivates us to propose a causal AQI prediction framework (CAP) that employs a structural causal model (SCM) to characterize the causal structural variability of various AQI factors for robust AQI prediction. Specifically, we employ the front-door adjustment to explicitly eliminate unmeasured confounders by intervening in industrial emissions from the target enterprise. Meanwhile, we take industrial emissions of neighboring enterprises into account when intervening in the target enterprise and simulate the dispersion of industrial emissions through a Gaussian plume model based on meteorological factors. Experiments on two real-world datasets validate the superior performance of our model on AQI prediction compared to the state-of-the-art baselines.

SummarySustained engagement in HIV care and adherence to antiretroviral therapy (ART) are essential for achieving the UNAIDS “95-95-95” targets. Despite increased ART access, disengagement from care remains a significant issue, particularly in sub-Saharan Africa. Traditional machine learning (ML) models have shown moderate success in predicting care disengagement, which would enable early intervention. We develop an enhanced large language model (LLM) fine-tuned with electronic medical records (EMRs) to predict people at risk of disengaging from HIV care in Tanzania and to provide interpretative insights into modifiable risk factors.MethodsWe developed a novel AI model by enhancing a pre-trained LLM (LLaMA 3.1, an open-source pre-trained LLM released by Meta) using routinely collected EMRs from Tanzania’s National HIV Care and Treatment Program from January 1, 2018, to June 30, 2023 (4,809,765 records for 261,192 people) to identify people at risk of disengaging from HIV care or developing adverse outcomes. Outcomes included risk of ART non-adherence, non-suppressed viral load, and loss to follow-up. Models were evaluated internally (Kagera region) and externally (Geita region), with performance compared against state-of-art ML models and zero-shot LLMs. Additionally, a team of HIV physicians in Tanzania assessed the LLM’s predictions along with LLM provided justifications for a subset of patient records to evaluate their clinical relevance and reasoning.FindingsThe enhanced LLMs consistently outperformed the supervised ML model and zero-shot LLMs across all outcomes in both internal and external validation datasets. When focusing on the 25% of PLHIV predicted as most likely to lost-to-follow-up (LTFU), the model correctly identified 78% (2,515 of 3,224) of people living with HIV (PLHIV) genuinely at risk in internal validation and 73% (7,105 of 9,733) in external validation. Attention score analysis indicated that the enhanced LLM focused on keywords such as gaps in follow-up care and ART adherence. The human expert evaluation showed alignment between clinician assessments and the LLM’s predictions in 65% of cases, with experts finding the model’s justifications reasonable and clinically relevant in 92.3% of aligned cases.InterpretationIf implemented in HIV clinics, this LLM-based AI model could help allocate resources efficiently and deliver targeted interventions, improving retention in care and advancing the UNAIDS “95-95-95” targets. By functioning like a clinician–analyzing patient summaries, predicting risks, and offering reasoning–the enhanced LLM could be integrated into clinical workflows to complement human expertise, facilitating timely interventions and informed decision-making. If implemented widely, this human-AI collaboration has the potential to improve health outcomes for people living with HIV and reduce onward transmission.FundingThe study was supported by a grant from the US National Institutes of Health (NIH): NIH NIMH 1R01MH125746.

Air pollution remains a major global concern due to its significant impact on public health and environmental sustainability. This study aims to develop a reliable global Air Quality Index (AQI) prediction model by evaluating five regression-based machine learning algorithms, including Linear Regression, Support Vector Regression, Random Forest, XGBoost, and LightGBM. The dataset contains over twenty thousand pollutant concentration records from multiple countries. Since the dataset consists of independent pollutant observations without timestamps or temporal sequences, this research employs supervised regression techniques rather than time-series forecasting methods to ensure methodological consistency with the non-temporal structure of the data. The methodology includes data preprocessing, validation of geocoded country information for missing values, transformations to address skewed pollutant distributions, and feature selection based on established environmental standards. Sample weights were applied to account for uneven regional representation, and systematic hyperparameter tuning with cross-validation was conducted to optimize model parameters and reduce potential overfitting. Evaluation metrics are supported by correlation analysis to quantify relationships between pollutants and AQI. The results show that XGBoost delivers the highest and most stable performance, with a MAE of 0.0216, MSE of 0.0010, RMSE of 0.0318, R² of 0.9971, and MAPE of 0.5664. Feature importance analysis highlights PM2.5 as the most influential pollutant, followed by ozone, nitrogen dioxide, and carbon monoxide. The predicted AQI values closely align with observed measurements, demonstrating strong generalizability across regions. An interactive dashboard was developed to visualize AQI predictions and pollutant contributions across countries, improving practical usability for environmental monitoring. Overall, this study provides a comprehensive framework for global AQI prediction and demonstrates the potential of machine learning to support decision-making in environmental management and public health planning.

Air pollution is one of the most critical environmental challenges affecting public health and economic sustainability. Continuous monitoring and accurate air quality prediction are essential for effective environmental management. This paper presents SmartAQI, an intelligent air quality monitoring and prediction system that integrates environmental data analytics with machine learning techniques. The proposed system utilizes historical air pollution datasets, India district-level geographic information, and real-time meteorological data obtained through the OpenWeather API to analyze air quality conditions across different regions of India. Major pollutants, including PM2.5, PM10, NO₂, SO₂, CO, and O₃, are processed to compute the Air Quality Index (AQI) according to the guidelines established by the Central Pollution Control Board. To improve prediction capability, multiple machine learning models such as Linear Regression, Random Forest, and Time Series forecasting are implemented and evaluated. The system further provides an interactive visualization dashboard that displays live AQI values, pollutant concentration levels, predicted AQI values, and geographic air quality distribution through charts and maps. Results demonstrate that integrating environmental data with machine learning models enables reliable AQI prediction and effective spatial analysis of pollution trends. The SmartAQI framework offers a practical solution for environmental monitoring and can support researchers, policymakers, and the public in understanding and managing air quality conditions more effectively, which is reliable

Day by day the air pollution becomes serious concern in India as well as in overall world. Proper or accurate prediction or forecast of Air Quality or the concentration level of other Ambient air pollutants such as Sulfur Dioxide, Nitrogen Dioxide, Carbon Monoxide, Particulate Matter having diameter less than 10µ, Particulate Matter having diameter less than 2.5µ, Ozone, etc. is very important because impact of these factors on human health becomes severe. This literature review focuses on the various techniques used for prediction or modelling of Air Quality Index (AQI) and forecasting of future concentration levels of pollutants that may cause the air pollution so that governing bodies can take the actions to reduce the pollution.

The adverse effect of air pollution has always been a problem for human health. The presence of a high level of air pollutants can cause severe illnesses such as emphysema, chronic obstructive pulmonary disease (COPD), or asthma. Air quality prediction helps us to undertake practical action plans for controlling air pollution. The Air Quality Index (AQI) reflects the degree of concentration of pollutants in a locality. The average AQI was calculated for the various cities in China to understand the annual trends. Furthermore, the air quality index has been predicted for ten major cities across China using five different deep learning techniques, namely, Recurrent Neural Network (RNN), Bidirectional Gated Recurrent unit (Bi-GRU), Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network BiLSTM (CNN-BiLSTM), and Convolutional BiLSTM (Conv1D-BiLSTM). The performance of these models has been compared with a machine learning model, eXtreme Gradient Boosting (XGBoost) to discover the most efficient deep learning model. The results suggest that the machine learning model, XGBoost, outperforms the deep learning models. While Conv1D-BiLSTM and CNN-BiLSTM perform well among the deep learning models in the estimation of the air quality index (AQI), RNN and Bi-GRU are the least performing ones. Thus, both XGBoost and neural network models are capable of capturing the non-linearity present in the dataset with reliable accuracy.

The impact of air pollution on health is measured by the Air Quality Index (AQI). Accurate AQI prediction is essential for pollution reduction and public health recommendations. Traditional methods of monitoring air quality are inaccurate and time-consuming. This study uses IoT-based air quality data from Kampung Kalipaten, Tangerang to build an AQI prediction model with machine learning, specifically an ensemble model. Ensemble techniques such as bagging and boosting, which increase the reliability of predictions by reducing model bias and inconsistency, improve AQI prediction. Four ensemble models used in this study, they are Random Forest Regressor, Gradient Boosting Regressor, Adaboosting Regressor, and Bagging Regressor. As the evaluation, RMSE and R2 metrics used. Random Forest Regressor perform the best with RMSE value of 0.6054 and R2 value of 0.6271, although no significant differences of RMSE and R2 value of the rest models.

BACKGROUND Accurately assessing perioperative risk is critical for informed surgical planning and patient safety. However, current prediction models often rely on structured data and overlook the nuanced clinical reasoning embedded in free-text preoperative notes. Recent advances in large language models (LLMs) have opened opportunities for harnessing unstructured clinical data, yet their application in perioperative prediction remains limited by concerns about factual accuracy. Retrieval-augmented generation (RAG) offers a promising solution—enhancing LLM performance by grounding outputs in domain-specific knowledge sources, potentially improving both predictive accuracy and clinical interpretability. OBJECTIVE This study aimed to investigate whether integrating LLMs with RAG can improve the prediction of 30-day postoperative mortality and American Society of Anesthesiologists (ASA) physical status classification using unstructured preoperative clinical notes. METHODS We conducted a retrospective cohort study using 24,491 medical records from a tertiary medical center, including preoperative anesthesia assessments, discharge summaries, and surgical information. To extract clinical insights from free-text data, we used the LLaMA 3.1-8B language model with RAG, using MedEmbed for text embedding and Miller’s Anesthesia as the primary retrieval source. We evaluated model performance under various configurations, including embedding models, chunk sizes, and few-shot prompting. Machine learning (ML) models, including random forest, support vector machines (SVM), Extreme Gradient Boosting (XGBoost), and logistic regression, were trained on structured features as baselines. RESULTS A total of 520 (2.1%) patients experienced in-hospital 30-day postoperative mortality. The ASA physical status distribution was as follows: class I: 535 (2.2%); class II: 15,272 (62.4%); class III: 8024 (32.8%); class IV: 606 (2.5%); and class V: 54 (0.22%). For 30-day postoperative mortality prediction, the LLaMA‑RAG model achieved an <i>F</i><sub>1</sub>-score of 0.4663 (95% CI 0.4654-0.4672), versus 0.2369 (95% CI 0.2341-0.2397) without few‑shot prompting, 0.0879 (95% CI 0.0717-0.1041) without RAG, and 0.0436 (95% CI 0.0292-0.0580) without either few‑shot prompting or RAG. Among ML models, XGBoost scored 0.4459 (95% CI 0.4176-0.4742); random forest, 0.3953 (95% CI 0.3791-0.4115); logistic regression, 0.2720 (95% CI 0.2647-0.2793); and SVM, 0.2474 (95% CI 0.2275-0.2673). For ASA classification, LLaMA‑RAG achieved a micro <i>F</i><sub>1</sub>-score of 0.8409 (95% CI 0.8238-0.8551) versus 0.6546 (95% CI 0.6430-0.6796) without few-shot prompting, 0.6340 (95% CI 0.6157-0.6535) without RAG, and 0.4238 (95% CI 0.3952-0.4490) without either few‑shot prompting or RAG. In comparison, XGBoost achieved 0.8273 (95% CI 0.8209-0.8498); logistic regression, 0.7940 (95% CI 0.7671-0.7950); random forest, 0.7847 (95% CI 0.7637-0.7868); and SVM, 0.7697 (95% CI 0.7637-0.7697). Notably, the model demonstrated exceptional sensitivity in identifying rare but high-risk cases, such as ASA Class 5 patients and postoperative deaths. CONCLUSIONS The LLaMA-RAG model significantly improved the prediction of postoperative mortality and ASA classification, especially for rare high-risk cases. By grounding outputs in domain knowledge, retrieval-augmented generation enhanced both accuracy and prompt‑driven interpretability over ML and ablation models—highlighting its promise for real-world clinical decision support. CLINICALTRIAL

Prediction of air quality index for certain locations in Nigeria has been carried out. The data used for this research was gotten from purple air data web site. The locations selected are; University of Ibadan, Edo Broadcasting station, Kogi, Nimet, Benin, Lekki phase1 in Lagos and Space center, Kebbi. Air quality Index was calculated based on PM2.5 data obtained from the purple air website. The other variables obtained are PM10, PM1, Temperature and Humidity. The machine learning algorithms used for modelling are linear regression, support vector machines (SVM), K-Nearest Neighbors (KNN), and regression trees. These algorithms were obtained using R programming language. The results show that for University of Ibadan station. AQI increased towards the end of 2021 up till the end of February 2022. There was a steady decrease in AQI towards the end of May 2022. For Edo Broadcasting station, AQI increased towards the end of 2021 up till the end of February 2022. There was a steady decrease in AQI towards the end of May 2022. There was an increase after May 2022. For Kogi station, AQI increased towards the end of October 2021 up till the end of February 2022. There was a steady decrease in AQI in April 2022. For Lekki phase 1, Lagos station, AQI increased from April 2021 towards the end of December 2021. There was a steady decrease in AQI towards the end of April 2022. For Nimet, Benin station, AQI increased steadily from October 2021 up till the end of February 2022. There was a steady decrease in AQI towards the end of April 2022 and a slight increase in May 2022. For Space center, Kebbi station, AQI decreased steadily from August 2021 up till the end of February 2022. There was a steady increase of AQI in March 2022 and a slight decrease in May 2022. AQI shows that the quality of air in Ibadan was classified as good, Edo broadcasting and Nimet, Benin were unhealthy for sensitive groups while Kogi, Space center Kebbi and Lagos were classified as moderate. Modelling result shows that of all the machine learning model selected for this research work, K-nearest neighbors was found to be the best model for the prediction of AQI across Nigeria. This is because it had the smallest value for the errors. Hence for the prediction of AQI in Nigeria, KNN is recommended.

Air-quality monitoring and forecasting are crucial for atmosphere pollution control and management. We propose an innovative data-driven framework for air quality index (AQI) prediction by integrating GNSS radio occultation (GNSS-RO) observation and weather modeling. Empowered by the state-of-the-art machine learning approach, our method can effectively predict regional AQI with a comparable accuracy much more quickly than the traditional numerical modeling and simulation approach. In a real case study using a representative region of China, our data-driven approach achieves a 2000 times speedup; meanwhile, the prediction error measured by rRMSE is only 2.4%. We investigate further the effects of different models, hyperparameters, and meteorological factors on the performance of our AQI prediction framework, and reveal that wind field and atmospheric boundary-layer height are important influencing factors of AQI. This paper showcases a direct application of GNSS-RO observation in assisting in forecasting regional AQI. From a machine learning point of view, it provides a new way to leverage the unique merits of GNSS atmospheric remote sensing technology with the help of the more traditional weather forecasting modeling approach.

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

Comparative diagnostic accuracy of ChatGPT-4 and machine learning in differentiating spinal tuberculosis and spinal tumors.

Optimizing asphalt mix design through predicting effective asphalt content and absorbed asphalt content using machine learning

Integrated STEM projects and experiments promote interdisciplinary learning, enhance critical thinking, and prepare students for real-world problem-solving by bridging science, technology, engineering, and mathematics. While numerous research studies have explored the STEM education domain, few have focused on supporting educators in identifying and designing effective integrated STEM projects and experiments. This research addresses this gap by introducing a novel system that leverages machine learning (ML) and large language models (LLMs) to assist educators in classifying and creating integrated STEM projects.We created and labeled a dataset of 1,071 project descriptions in this research work, mapped to one or more STEM areas (Science, Technology, Engineering, Mathematics). The dataset was developed using manually curated records, harvesting online sources, and synthetic data generation. Natural Language Processing (NLP) techniques were applied to prepare project descriptions for analysis. Various ML models, including Random Forest, Support Vector Machines (SVM), Logistic Regression, and Naive Bayes, were used for multi-label classification. The Random Forest model achieved the best performance, with a Precision of 91.99%, Recall of 94.59%, F1 Score of 93.27%, and Hamming Loss of 6.74%.The system operates in two phases: In Phase 1, the instructor proposes a project title with a description, and in response, the ML model identifies one or more STEM areas as the most relevant. In Phase 2, ChatGPT, specifically GPT-4o, assists educators by defining experiment objectives, generating ideas, designing procedures, and suggesting tools and resources. This human-in-the-loop system enhances collaboration between educators, ML models, and LLMs, streamlining the design of effective integrated STEM projects.This work's implications extend to improving the accessibility and effectiveness of integrated STEM education by reducing the barriers educators face in designing interdisciplinary projects. It provides a scalable framework for integrating advanced AI techniques into educational practices and fostering classroom innovation.