RESUMEN

The brain-computer interface (BCI) systems based on motor imagery typically rely on a large number of electrode channels to acquire information. The rational selection of electroencephalography (EEG) channel combinations is crucial for optimizing computational efficiency and enhancing practical applicability. However, evaluating all potential channel combinations individually is impractical. This study aims to explore a strategy for quickly achieving a balance between maximizing channel reduction and minimizing precision loss. To this end, we developed a spatio-temporal attention perception network named STAPNet. Based on the channel contributions adaptively generated by its subnetwork, we propose an extended step bi-directional search strategy that includes variable ratio channel selection (VRCS) and strided greedy channel selection (SGCS), designed to enhance global search capabilities and accelerate the optimization process. Experimental results show that on the High Gamma and BCI Competition IV 2a public datasets, the framework respectively achieved average maximum accuracies of 91.47% and 84.17%. Under conditions of zero precision loss, the average number of channels was reduced by a maximum of 87.5%. Additionally, to investigate the impact of neural information loss due to channel reduction on the interpretation of complex brain functions, we employed a heatmap visualization algorithm to verify the universal importance and complete symmetry of the selected optimal channel combination across multiple datasets. This is consistent with the brain's cooperative mechanism when processing tasks involving both the left and right hands.

RESUMEN

The design of masonry structures requires accurate estimation of compressive strength (CS) of hollow concrete masonry prisms. Generally, the CS of masonry prisms is determined by destructive laboratory testing which results in time and resource wastage. Thus, this study aims to provide machine learning-based predictive models for CS of hollow concrete masonry blocks using different algorithms including Multi Expression Programming (MEP), Random Forest Regression (RFR), and Extreme Gradient Boosting (XGB) etc. A dataset of 159 experimental results was collected from published literature for this purpose. The collected dataset consisted of four input parameters including strength of masonry units ( f b ), height-to-thickness ratio (h/t), strength of mortar ( f m ), and ratio of f m / f b and only one output parameter i.e., CS. Out of all the algorithms employed in current study, only MEP and GEP expressed their output in the form of an empirical equation. The accuracy of developed models was assessed using root mean squared error (RMSE), objective function (OF), and R 2 etc. Among all algorithms assessed, XGB turned out to be the most accurate having R 2  = 0.99 and least OF value of 0.0063 followed by AdaBoost, RFR, and other algorithms. The developed XGB model was also used to conduct different explainable artificial intelligence (XAI) analysis including sensitivity and shapley analysis and the results showed that strength of masonry unit ( f b ) is the most significant variable in predicting CS. Thus, the ML-based predictive models presented in this study can be utilized practically for determining CS of hollow concrete masonry prisms without requiring expensive and time-consuming laboratory testing.

RESUMEN

Objective: This study aimed to investigate the predictive capabilities of historical patient records to predict patient adverse outcomes such as mortality, readmission, and prolonged length of stay (PLOS). Methods: Leveraging a de-identified dataset from a tertiary care university hospital, we developed an eXplainable Artificial Intelligence (XAI) framework combining tree-based and traditional machine learning (ML) models with interpretations and statistical analysis of predictors of mortality, readmission, and PLOS. Results: Our framework demonstrated exceptional predictive performance with a notable area under the receiver operating characteristic (AUROC) of 0.9625 and an area under the precision-recall curve (AUPRC) of 0.8575 for 30-day mortality at discharge and an AUROC of 0.9545 and AUPRC of 0.8419 at admission. For the readmission and PLOS risk, the highest AUROC achieved were 0.8198 and 0.9797, respectively. The tree-based models consistently outperformed the traditional ML models in all 4 prediction tasks. The key predictors were age, derived temporal features, routine laboratory tests, and diagnostic and procedural codes. Conclusion: The study underscores the potential of leveraging medical history for enhanced hospital predictive analytics. We present an accurate and intuitive framework for early warning models that can be easily implemented in the current and developing digital health platforms to predict adverse outcomes accurately.

RESUMEN

Early detection of Alzheimer's disease (AD) is vital for effective treatment, as interventions are most successful in the disease's early stages. Combining Magnetic Resonance Imaging (MRI) with artificial intelligence (AI) offers significant potential for enhancing AD diagnosis. However, traditional AI models often lack transparency in their decision-making processes. Explainable Artificial Intelligence (XAI) is an evolving field that aims to make AI decisions understandable to humans, providing transparency and insight into AI systems. This research introduces the Squeeze-and-Excitation Convolutional Neural Network with Random Forest (SECNN-RF) framework for early AD detection using MRI scans. The SECNN-RF integrates Squeeze-and-Excitation (SE) blocks into a Convolutional Neural Network (CNN) to focus on crucial features and uses Dropout layers to prevent overfitting. It then employs a Random Forest classifier to accurately categorize the extracted features. The SECNN-RF demonstrates high accuracy (99.89%) and offers an explainable analysis, enhancing the model's interpretability. Further exploration of the SECNN framework involved substituting the Random Forest classifier with other machine learning algorithms like Decision Tree, XGBoost, Support Vector Machine, and Gradient Boosting. While all these classifiers improved model performance, Random Forest achieved the highest accuracy, followed closely by XGBoost, Gradient Boosting, Support Vector Machine, and Decision Tree which achieved lower accuracy.

RESUMEN

Background: Sepsis is characterized by an atypical immune response to infection and is a dangerous health problem leading to significant mortality. Current diagnostic methods exhibit insufficient sensitivity and specificity and require the discovery of precise biomarkers for the early diagnosis and treatment of sepsis. Platelets, known for their hemostatic abilities, also play an important role in immunological responses. This study aims to develop a model integrating machine learning and explainable artificial intelligence (XAI) to identify novel platelet metabolomics markers of sepsis. Methods: A total of 39 participants, 25 diagnosed with sepsis and 14 control subjects, were included in the study. The profiles of platelet metabolites were analyzed using quantitative 1H-nuclear magnetic resonance (NMR) technology. Data were processed using the synthetic minority oversampling method (SMOTE)-Tomek to address the issue of class imbalance. In addition, missing data were filled using a technique based on random forests. Three machine learning models, namely extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and kernel tree boosting (KTBoost), were used for sepsis prediction. The models were validated using cross-validation. Clinical annotations of the optimal sepsis prediction model were analyzed using SHapley Additive exPlanations (SHAP), an XAI technique. Results: The results showed that the KTBoost model (0.900 accuracy and 0.943 AUC) achieved better performance than the other models in sepsis diagnosis. SHAP results revealed that metabolites such as carnitine, glutamate, and myo-inositol are important biomarkers in sepsis prediction and intuitively explained the prediction decisions of the model. Conclusion: Platelet metabolites identified by the KTBoost model and XAI have significant potential for the early diagnosis and monitoring of sepsis and improving patient outcomes.

RESUMEN

Background/Objectives: The purpose of this study was to analyze relevant areas in acute-stage fluorescein angiography (FA) images, predicting the long-term visual prognosis of branch retinal vein occlusion (BRVO) based on gradient-weighted class activation mapping (Grad-CAM). Methods: This retrospective observational study included 136 eyes with BRVO that were followed up for more than a year post-FA. Cropped grayscale images centered on the fovea (200 × 200 pixels) were manually pre-processed from early-phase FA at the acute phase. Pairs of the cropped FA images and the best-corrected visual acuity (BCVA) in remission at least one year post-FA were used to train a 38-layer ResNet with five-fold cross-validation. Correlations between the ResNet-predicted and true (actually measured) logMAR BCVAs in remission, and between the foveal avascular zone (FAZ) area measured by ImageJ (version 1.52r) from FA images and true logMAR BCVA in remission were evaluated. The heat maps generated by Grad-CAM were evaluated to determine which areas were consumed as computational resources for BCVA prediction. Results: The correlation coefficient between the predicted and true logMAR BCVAs in remission was 0.47, and that between the acute-stage FAZ area and true logMAR BCVA in remission was 0.42 (p < 0.0001 for both). The Grad-CAM-generated heat maps showed that retinal vessels adjacent to the FAZ and the FAZ per se had high selectivity (95.7% and 62.2%, respectively). Conclusions: The Grad-CAM-based analysis demonstrated FAZ-neighboring vessels as the most relevant predictor for the long-term visual prognosis of BRVO.

RESUMEN

Oral squamous cell carcinoma recognition presents a challenge due to late diagnosis and costly data acquisition. A cost-efficient, computerized screening system is crucial for early disease detection, minimizing the need for expert intervention and expensive analysis. Besides, transparency is essential to align these systems with critical sector applications. Explainable Artificial Intelligence (XAI) provides techniques for understanding models. However, current XAI is mostly data-driven and focused on addressing developers' requirements of improving models rather than clinical users' demands for expressing relevant insights. Among different XAI strategies, we propose a solution composed of Case-Based Reasoning paradigm to provide visual output explanations and Informed Deep Learning (IDL) to integrate medical knowledge within the system. A key aspect of our solution lies in its capability to handle data imperfections, including labeling inaccuracies and artifacts, thanks to an ensemble architecture on top of the deep learning (DL) workflow. We conducted several experimental benchmarks on a dataset collected in collaboration with medical centers. Our findings reveal that employing the IDL approach yields an accuracy of 85%, surpassing the 77% accuracy achieved by DL alone. Furthermore, we measured the human-centered explainability of the two approaches and IDL generates explanations more congruent with the clinical user demands.

RESUMEN

Prostate Imaging Reporting and Data System (PI-RADS) score, a reporting system of prostate MRI cases, has become a standard prostate cancer (PCa) screening method due to exceptional diagnosis performance. However, PI-RADS 3 lesions are an unmet medical need because PI-RADS provides diagnosis accuracy of only 30-40% at most, accompanied by a high false-positive rate. Here, we propose an explainable artificial intelligence (XAI) based PCa screening system integrating a highly sensitive dual-gate field-effect transistor (DGFET) based multi-marker biosensor for ambiguous lesions identification. This system produces interpretable results by analyzing sensing patterns of three urinary exosomal biomarkers, providing a possibility of an evidence-based prediction from clinicians. In our results, XAI-based PCa screening system showed a high accuracy with an AUC of 0.93 using 102 blinded samples with the non-invasive method. Remarkably, the PCa diagnosis accuracy of patients with PI-RADS 3 was more than twice that of conventional PI-RADS scoring. Our system also provided a reasonable explanation of its decision that TMEM256 biomarker is the leading factor for screening those with PI-RADS 3. Our study implies that XAI can facilitate informed decisions, guided by insights into the significance of visualized multi-biomarkers and clinical factors. The XAI-based sensor system can assist healthcare professionals in providing practical and evidence-based PCa diagnoses.

RESUMEN

Pregnancy termination remains a complex and sensitive issue with approximately 45% of abortions worldwide being unsafe, and 97% of abortions occurring in developing countries. Unsafe pregnancy terminations have implications for women's reproductive health. This research aims to compare black box models in their prediction of pregnancy termination among reproductive-aged women and identify factors associated with pregnancy termination using explainable artificial intelligence (XAI) methods. We used comprehensive secondary data on reproductive-aged women's demographic and socioeconomic data from the Demographic Health Survey (DHS) from six countries in East Africa in the analysis. This study implemented five black box ML models, Bagging classifier, Random Forest, Extreme Gradient Boosting (XGB) Classifier, CatBoost Classifier, and Extra Trees Classifier on a dataset with 338,904 instances and 18 features. Additionally, SHAP, Eli5, and LIME XAI techniques were used to determine features associated with pregnancy termination and Statistical analysis were employed to understand the distribution of pregnancy termination. The results demonstrated that machine learning algorithms were able to predict pregnancy termination on DHS data with an overall accuracy ranging from 79.4 to 85.6%. The ML classifier random forest achieved the highest result, with an accuracy of 85.6%. Based on the results of the XAI tool, the most contributing factors for pregnancy termination are wealth index, current working experience, and source of drinking water, sex of household, education level, and marital status. The outcomes of this study using random forest is expected to significantly contribute to the field of reproductive healthcare in East Africa and can assist healthcare providers in identifying individuals' countries at greater risk of pregnancy termination, allowing for targeted interventions and support.

Asunto(s)

RESUMEN

PURPOSE: Metabolic bariatric surgery (MBS) became integral to managing severe obesity. Understanding surgical risks associated with MBS is crucial. Different scores, such as the Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program (MBSAQIP), aid in patient selection and outcome prediction. This study aims to evaluate machine learning (ML) models performance in predicting 30-day post-operative complications and compare them with the MBSAQIP risk score. MATERIALS AND METHODS: We retrospectively evaluated 424 consecutive patients (2006-2020) who underwent MBS, analyzing 30-day surgical complications according to Clavien-Dindo Classification. ML models, including logistic regression, support vector machine, random forest, k-nearest neighbors, multi-layer perceptron, and extreme gradient boosting, were analyzed and compared to MBSAQIP risk score. Performance was measured by area under receiver operating characteristic curve (AUROC) analysis. RESULTS: Random forest showed the highest AUROC in the training (AUROC = 0.94) and the validation set (AUROC = 0.88). ML algorithms, particularly random forest, outperformed MBSAQIP in predicting negative 30-day outcomes in both the training and validation sets (AUROC = 0.64, DeLong's Test p < 0.001). The five features that were more relevant for the prediction of the random forest model were serum alkaline phosphatase, platelet count, triglycerides, glycated hemoglobin, and albumin. CONCLUSION: We developed several ML model that identifies patients at risk for 30-day complications after MBS. Among these, random forest is the most performing one and outperforms the already established MBSAQIP score. This model could increase the identification of high-risk patients before MBS.

RESUMEN

In the high-stakes realm of critical care, where daily decisions are crucial and clear communication is paramount, comprehending the rationale behind Artificial Intelligence (AI)-driven decisions appears essential. While AI has the potential to improve decision-making, its complexity can hinder comprehension and adherence to its recommendations. "Explainable AI" (XAI) aims to bridge this gap, enhancing confidence among patients and doctors. It also helps to meet regulatory transparency requirements, offers actionable insights, and promotes fairness and safety. Yet, defining explainability and standardising assessments are ongoing challenges and balancing performance and explainability can be needed, even if XAI is a growing field.

Asunto(s)

RESUMEN

Childhood stunting is a serious public health concern in Rwanda. Although stunting causes have been documented, we still lack a more in-depth understanding of their local factors at a more detailed geographic level. We cross-sectionally examined 615 height-for-age prevalence observations in the Northern Province of Rwanda, linked with their related covariates, to explore the spatial heterogeneity in the low height-for-age prevalence by fitting linear and non-linear spatial regression models and explainable machine learning. Specifically, complemented with generalized additive models, we fitted the ordinary least squares (OLS), a standard geographically weighted regression (GWR), and multiscale geographically weighted regression (MGWR) models to characterize the imbalanced distribution of stunting risk factors and uncover the nonlinear effect of significant predictors, explaining the height-for-age variations. The results reveal that 27% of the children measured were stunted, and that likelihood was found to be higher in the districts of Musanze, Gakenke, and Gicumbi. The local MGWR model outperformed the ordinary GWR and OLS, with coefficients of determination of 0.89, 0.84, and 0.25, respectively. At specific ranges, the study shows that height-for-age decreases with an increase in the number of days a child was left alone, elevation, and rainfall. In contrast, land surface temperature is positively associated with height-for-age. However, variables like the normalized difference vegetation index, slope, soil fertility, and urbanicity exhibited bell-shaped and U-shaped non-linear associations with the height-for-age prevalence. Identifying areas with the highest rates of stunting will help determine the most effective measures for reducing the burden of undernutrition.

RESUMEN

Recent advancements in artificial intelligence (AI) have prompted researchers to expand into the field of oculomics; the association between the retina and systemic health. Unlike conventional AI models trained on well-recognized retinal features, the retinal phenotypes that most oculomics models use are more subtle. Consequently, applying conventional tools, such as saliency maps, to understand how oculomics models arrive at their inference is problematic and open to bias. We hypothesized that neuron activation patterns (NAPs) could be an alternative way to interpret oculomics models, but currently, most existing implementations focus on failure diagnosis. In this study, we designed a novel NAP framework to interpret an oculomics model. We then applied our framework to an AI model predicting systolic blood pressure from fundus images in the United Kingdom Biobank dataset. We found that the NAP generated from our framework was correlated to the clinically relevant endpoint of cardiovascular risk. Our NAP was also able to discern two biologically distinct groups among participants who were assigned the same predicted systolic blood pressure. These results demonstrate the feasibility of our proposed NAP framework for gaining deeper insights into the functioning of oculomics models. Further work is required to validate these results on external datasets.

Asunto(s)

RESUMEN

OBJECTIVE: Clinical visual intraoperative electrocorticography (ioECoG) reading intends to localize epileptic tissue and improve epilepsy surgery outcome. We aimed to understand whether machine learning (ML) could complement ioECoG reading, how subgroups affected performance, and which ioECoG features were most important. METHODS: We included 91 ioECoG-guided epilepsy surgery patients with Engel 1A outcome. We allocated 71 training and 20 test set patients. We trained an extra trees classifier (ETC) with 14 spectral features to classify ioECoG channels as covering resected or non-resected tissue. We compared the ETC's performance with clinical ioECoG reading and assessed whether patient subgroups affected performance. Explainable artificial intelligence (xAI) unveiled the most important ioECoG features learnt by the ETC. RESULTS: The ETC outperformed clinical reading in five test set patients, was inferior in six, and both were inconclusive in nine. The ETC performed best in the tumor subgroup (area under ROC curve: 0.84 [95%CI 0.79-0.89]). xAI revealed predictors of resected (relative theta, alpha, and fast ripple power) and non-resected tissue (relative beta and gamma power). CONCLUSIONS: Combinations of subtle spectral ioECoG changes, imperceptible by the human eye, can aid healthy and pathological tissue discrimination. SIGNIFICANCE: ML with spectral ioECoG features can support, rather than replace, clinical ioECoG reading, particularly in tumors.

RESUMEN

Antibiotics are misused and discharged into environmental water, posing a constant potential threat to the ecosystem. Utilising plasma's physical and chemical effects to remove antibiotics has emerged as a promising wastewater treatment technology. However, the complexity and high cost of reactor configurations represent significant limitations to the practical application of this technology. Furthermore, evaluating the degradation efficiency of antibiotics necessitates using costly and sophisticated testing instruments, coupled with time-consuming and labour-intensive experiments. The present study developed a generalised model using machine learning algorithms to predict the removal efficiency of antibiotics by a plasma system. Of the eight machine learning algorithms constructed, the ensemble model XGBoost exhibited the highest prediction accuracy, as indicated by a Pearson correlation coefficient of 0.943. This correlation indicates a strong relationship between the predicted removal rates and the experimental values. Moreover, the accuracy of the prediction was enhanced through the utilisation of a multi-model stacking approach. A further quantitative assessment of the key factors affecting the efficiency of the plasma process, and their synergistic effects, is provided by the interpretable analysis of the model's behaviour. It is anticipated that the results will facilitate the design of efficient plasma systems, reduce the need for extensive experimental screening, and improve practical applications in the removal of antibiotic contamination. This provides an informative view of the applications of plasma technology, opening the way for new environmental research questions.

RESUMEN

BACKGROUND: Recurrent pericarditis (RP) is a complex condition associated with significant morbidity. Prior studies have evaluated which variables are associated with clinical remission. However, there is currently no established risk-stratification model for predicting outcomes in these patients. OBJECTIVES: We developed a risk stratification model that can predict long-term outcomes in patients with RP and enable identification of patients with characteristics that portend poor outcomes. METHODS: We retrospectively studied a total of 365 consecutive patients with RP from 2012 to 2019. The primary outcome was clinical remission (CR), defined as cessation of all anti-inflammatory therapy with complete resolution of symptoms. Five machine learning survival models were used to calculate the likelihood of CR within 5 years and stratify patients into high-risk, intermediate-risk, and low-risk groups. RESULTS: Among the cohort, the mean age was 46 ± 15 years, and 205 (56%) were women. CR was achieved in 118 (32%) patients. The final model included steroid dependency, total number of recurrences, pericardial late gadolinium enhancement, age, etiology, sex, ejection fraction, and heart rate as the most important parameters. The model predicted the outcome with a C-index of 0.800 on the test set and exhibited a significant ability in stratification of patients into low-risk, intermediate-risk, and high-risk groups (log-rank test; P < 0.0001). CONCLUSIONS: We developed a novel risk-stratification model for predicting CR in RP. Our model can also aid in stratifying patients, with high discriminative ability. The use of an explainable machine learning model can aid physicians in making individualized treatment decision in RP patients.

RESUMEN

This research aims to use the power of geospatial artificial intelligence (GeoAI), employing the categorical boosting (CatBoost) machine learning model in conjunction with two metaheuristic algorithms, the firefly algorithm (CatBoost-FA) and the fruit fly optimization algorithm (CatBoost-FOA), to spatially assess and map noise pollution prone areas in Tehran city, Iran. To spatially model areas susceptible to noise pollution, we established a comprehensive spatial database encompassing data for the annual average Leq (equivalent continuous sound level) from 2019 to 2022. This database was enriched with critical spatial criteria influencing noise pollution, including urban land use, traffic volume, population density, and normalized difference vegetation index (NDVI). Our study evaluated the predictive accuracy of these models using key performance metrics, including root mean square error (RMSE), mean absolute error (MAE), and receiver operating characteristic (ROC) indices. The results demonstrated the superior performance of the CatBoost-FA algorithm, with RMSE and MAE values of 0.159 and 0.114 for the training data and 0.437 and 0.371 for the test data, outperforming both the CatBoost-FOA and CatBoost models. ROC analysis further confirmed the efficacy of the models, achieving an accuracy of 0.897, CatBoost-FOA with an accuracy of 0.871, and CatBoost with an accuracy of 0.846, highlighting their robust modeling capabilities. Additionally, we employed an explainable artificial intelligence (XAI) approach, utilizing the SHAP (Shapley Additive Explanations) method to interpret the underlying mechanisms of our models. The SHAP results revealed the significant influence of various factors on noise-pollution-prone areas, with airport, commercial, and administrative zones emerging as pivotal contributors.

RESUMEN

Deep learning models have achieved state-of-the-art performance for text classification in the last two decades. However, this has come at the expense of models becoming less understandable, limiting their application scope in high-stakes domains. The increased interest in explainability has resulted in many proposed forms of explanation. Nevertheless, recent studies have shown that rationales, or language explanations, are more intuitive and human-understandable, especially for non-technical stakeholders. This survey provides an overview of the progress the community has achieved thus far in rationalization approaches for text classification. We first describe and compare techniques for producing extractive and abstractive rationales. Next, we present various rationale-annotated data sets that facilitate the training and evaluation of rationalization models. Then, we detail proxy-based and human-grounded metrics to evaluate machine-generated rationales. Finally, we outline current challenges and encourage directions for future work.

RESUMEN

In this study, attention deficit hyperactivity disorder (ADHD), a childhood neurodevelopmental disorder, is being studied alongside its comorbidity, conduct disorder (CD), a behavioral disorder. Because ADHD and CD share commonalities, distinguishing them is difficult, thus increasing the risk of misdiagnosis. It is crucial that these two conditions are not mistakenly identified as the same because the treatment plan varies depending on whether the patient has CD or ADHD. Hence, this study proposes an electroencephalogram (EEG)-based deep learning system known as ADHD/CD-NET that is capable of objectively distinguishing ADHD, ADHD + CD, and CD. The 12-channel EEG signals were first segmented and converted into channel-wise continuous wavelet transform (CWT) correlation matrices. The resulting matrices were then used to train the convolutional neural network (CNN) model, and the model's performance was evaluated using 10-fold cross-validation. Gradient-weighted class activation mapping (Grad-CAM) was also used to provide explanations for the prediction result made by the 'black box' CNN model. Internal private dataset (45 ADHD, 62 ADHD + CD and 16 CD) and external public dataset (61 ADHD and 60 healthy controls) were used to evaluate ADHD/CD-NET. As a result, ADHD/CD-NET achieved classification accuracy, sensitivity, specificity, and precision of 93.70%, 90.83%, 95.35% and 91.85% for the internal evaluation, and 98.19%, 98.36%, 98.03% and 98.06% for the external evaluation. Grad-CAM also identified significant channels that contributed to the diagnosis outcome. Therefore, ADHD/CD-NET can perform temporal localization and choose significant EEG channels for diagnosis, thus providing objective analysis for mental health professionals and clinicians to consider when making a diagnosis. Supplementary Information: The online version contains supplementary material available at 10.1007/s11571-023-10028-2.