Dataset Information

Machine learning and XAI approaches highlight the strong connection between O3 and NO2 pollutants and Alzheimer's disease.

ABSTRACT: Alzheimer's disease (AD) is the most common type of dementia with millions of affected patients worldwide. Currently, there is still no cure and AD is often diagnosed long time after onset because there is no clear diagnosis. Thus, it is essential to study the physiology and pathogenesis of AD, investigating the risk factors that could be strongly connected to the disease onset. Despite AD, like other complex diseases, is the result of the combination of several factors, there is emerging agreement that environmental pollution should play a pivotal role in the causes of disease. In this work, we implemented an Artificial Intelligence model to predict AD mortality, expressed as Standardized Mortality Ratio, at Italian provincial level over 5 years. We employed a set of publicly available variables concerning pollution, health, society and economy to feed a Random Forest algorithm. Using methods based on eXplainable Artificial Intelligence (XAI) we found that air pollution (mainly O3 and NO2 ) contribute the most to AD mortality prediction. These results could help to shed light on the etiology of Alzheimer's disease and to confirm the urgent need to further investigate the relationship between the environment and the disease.

SUBMITTER: Fania A

PROVIDER: S-EPMC11319812 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning and XAI approaches highlight the strong connection between O 3 and N O 2 pollutants and Alzheimer's disease.

Fania Alessandro A Monaco Alfonso A Amoroso Nicola N Bellantuono Loredana L Cazzolla Gatti Roberto R Firza Najada N Lacalamita Antonio A Pantaleo Ester E Tangaro Sabina S Velichevskaya Alena A Bellotti Roberto R

Scientific reports 20240305 1

Alzheimer's disease (AD) is the most common type of dementia with millions of affected patients worldwide. Currently, there is still no cure and AD is often diagnosed long time after onset because there is no clear diagnosis. Thus, it is essential to study the physiology and pathogenesis of AD, investigating the risk factors that could be strongly connected to the disease onset. Despite AD, like other complex diseases, is the result of the combination of several factors, there is emerging agreem ...[more]

PMID: 38443419

Similar Datasets

Project description:IntroductionAir pollution represents a serious threat to health on a global scale, being responsible for a large portion of the global burden of disease from environmental factors. Current evidence about the association between air pollution exposure and Diabetes Mellitus (DM) is still controversial. We aimed to evaluate the association between area-level ambient air pollution and self-reported DM in a large population sample in Italy.Materials and methodsWe extracted information about self-reported and physician diagnosed DM, risk factors and socio-economic status from 12 surveys conducted nationwide between 1999 and 2013. We obtained annual averaged air pollution levels for the years 2003, 2005, 2007 and 2010 from the AMS-MINNI national integrated model, which simulates the dispersion and transformation of pollutants. The original maps, with a resolution of 4 x 4 km2, were normalized and aggregated at the municipality class of each Italian region, in order to match the survey data. We fit logistic regression models with a hierarchical structure to estimate the relationship between PM10, PM2.5, NO2 and O3 four-years mean levels and the risk of being affected by DM.ResultsWe included 376,157 individuals aged more than 45 years. There were 39,969 cases of DM, with an average regional prevalence of 9.8% and a positive geographical North-to-South gradient, opposite to that of pollutants' concentrations. For each 10 μg/m3 increase, the resulting ORs were 1.04 (95% CI 1.01-1.07) for PM10, 1.04 (95% CI 1.02-1.07) for PM2.5, 1.03 (95% CI 1.01-1.05) for NO2 and 1.06 (95% CI 1.01-1.11) for O3, after accounting for relevant individual risk factors. The associations were robust to adjustment for other pollutants in two-pollutant models tested (ozone plus each other pollutant).ConclusionsWe observed a significant positive association between each examined pollutant and prevalent DM. Risk estimates were consistent with current evidence, and robust to sensitivity analysis. Our study adds evidence about the effects of air pollution on diabetes and suggests a possible role of ozone as an independent factor associated with the development of DM. Such relationship is of great interest for public health and deserves further investigation.

Project description:Alzheimer's disease (AD) is a progressive neurodegenerative disorder, accounting for nearly 60% of all dementia cases. The occurrence of the disease has been increasing rapidly in recent years. Presently about 46.8 million individuals suffer from AD worldwide. The current absence of effective treatment to reverse or stop AD progression highlights the importance of disease prevention and early diagnosis. Brain structural Magnetic Resonance Imaging (MRI) has been widely used for AD detection as it can display morphometric differences and cerebral structural changes. In this study, we built three machine learning-based MRI data classifiers to predict AD and infer the brain regions that contribute to disease development and progression. We then systematically compared the three distinct classifiers, which were constructed based on Support Vector Machine (SVM), 3D Very Deep Convolutional Network (VGGNet) and 3D Deep Residual Network (ResNet), respectively. To improve the performance of the deep learning classifiers, we applied a transfer learning strategy. The weights of a pre-trained model were transferred and adopted as the initial weights of our models. Transferring the learned features significantly reduced training time and increased network efficiency. The classification accuracy for AD subjects from elderly control subjects was 90%, 95%, and 95% for the SVM, VGGNet and ResNet classifiers, respectively. Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to show discriminative regions that contributed most to the AD classification by utilizing the learned spatial information of the 3D-VGGNet and 3D-ResNet models. The resulted maps consistently highlighted several disease-associated brain regions, particularly the cerebellum which is a relatively neglected brain region in the present AD study. Overall, our comparisons suggested that the ResNet model provided the best classification performance as well as more accurate localization of disease-associated regions in the brain compared to the other two approaches.

Project description:This paper investigates the correlation between the high level of coronavirus SARS-CoV-2 infection accelerated transmission and lethality, and surface air pollution in Milan metropolitan area, Lombardy region in Italy. For January-April 2020 period, time series of daily average inhalable gaseous pollutants ozone (O3) and nitrogen dioxide (NO2), together climate variables (air temperature, relative humidity, wind speed, precipitation rate, atmospheric pressure field and Planetary Boundary Layer) were analyzed. In spite of being considered primarily transmitted by indoor bioaerosols droplets and infected surfaces or direct human-to-human personal contacts, it seems that high levels of urban air pollution, and climate conditions have a significant impact on SARS-CoV-2 diffusion. Exhibited positive correlations of ambient ozone levels and negative correlations of NO2 with the increased rates of COVID-19 infections (Total number, Daily New positive and Total Deaths cases), can be attributed to airborne bioaerosols distribution. The results show positive correlation of daily averaged O3 with air temperature and inversely correlations with relative humidity and precipitation rates. Viral genome contains distinctive features, including a unique N-terminal fragment within the spike protein, which allows coronavirus attachment on ambient air pollutants. At this moment it is not clear if through airborne diffusion, in the presence of outdoor and indoor aerosols, this protein "spike" of the new COVID-19 is involved in the infectious agent transmission from a reservoir to a susceptible host during the highest nosocomial outbreak in some agglomerated industrialized urban areas like Milan is. Also, in spite of collected data for cold season (winter-early spring) period, when usually ozone levels have lower values than in summer, the findings of this study support possibility as O3 can acts as a COVID-19 virus incubator. Being a novel pandemic coronavirus version, it might be ongoing during summer conditions associated with higher air temperatures, low relative humidity and precipitation levels.

Project description:MotivationMetabolomics generates complex data necessitating advanced computational methods for generating biological insight. While machine learning (ML) is promising, the challenges of selecting the best algorithms and tuning hyperparameters, particularly for non-experts, remain. Automated machine learning (AutoML) can streamline this process; however, the issue of interpretability could persist. This research introduces a unified pipeline that combines AutoML with explainable AI (XAI) techniques to optimize metabolomics analysis.ResultsWe tested our approach on two datasets: renal cell carcinoma (RCC) urine metabolomics and ovarian cancer (OC) serum metabolomics. AutoML, using auto-sklearn, surpassed standalone ML algorithms such as SVM and random forest in differentiating between RCC and healthy controls, as well as OC patients and those with other gynecological cancers (Non-OC). Auto-sklearn employed a mix of algorithms and ensemble techniques, yielding a superior performance (AUC of 0.97 for RCC and 0.85 for OC). Shapley Additive Explanations (SHAP) provided a global ranking of feature importance, identifying dibutylamine and ganglioside GM(d34:1) as the top discriminative metabolites for RCC and OC, respectively. Waterfall plots offered local explanations by illustrating the influence of each metabolite on individual predictions. Dependence plots spotlighted metabolite interactions, such as the connection between hippuric acid and one of its derivatives in RCC, and between GM3(d34:1) and GM3(18:1_16:0) in OC, hinting at potential mechanistic relationships. Through decision plots, a detailed error analysis was conducted, contrasting feature importance for correctly versus incorrectly classified samples. In essence, our pipeline emphasizes the importance of harmonizing AutoML and XAI, facilitating both simplified ML application and improved interpretability in metabolomics data science.Availabilityhttps://github.com/obifarin/automl-xai-metabolomics.

Dataset Information

Machine learning and XAI approaches highlight the strong connection between O3 and NO2 pollutants and Alzheimer's disease.

Publications

Machine learning and XAI approaches highlight the strong connection between O 3 and N O 2 pollutants and Alzheimer's disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets