Interpretive Modeling Research Articles

Interpretable model for rockburst intensity prediction based on Shapley values-based Optuna-random forest

To address the limitation of traditional machine learning models in explaining the rockburst intensity prediction process, this study proposes an interpretable rockburst intensity prediction model. The model was developed using 350 sets of actual rockburst sample data to explore the impact of input metrics on the final rockburst intensity level. The collected data underwent pre-processing using the isolation forest algorithm and synthetic minority oversampling technique. The random forest model was optimized through 5-fold cross-validation and the Optuna framework, resulting in the establishment of an Optuna-random forest (Op-RF) model that generates decision rules through its internal decision tree, utilizing the properties of the random forest model. The model was further interpreted using the Shapley additive explanations algorithm, both locally and globally. The results demonstrate that the proposed model achieved an area under curve score of 0.984. In comparison to eight other machine learning models, the proposed Op-RF model demonstrated superior accuracy, precision, recall, and F1 score. The model provides a transparent explanation of the prediction process, linking impact characteristics to the final output. Additionally, a cloud deployment method for the rockburst intensity prediction model is provided and its effectiveness is demonstrated through engineering verification. The proposed model offers a new approach to the application of machine learning in rockburst intensity prediction.

A Sequential Stein's Method for Faster Training of Additive Index Models.

The additive index models (AIMs) can be viewed as a kind of artificial neural networks based on nonparametric activation or so-called ridge functions. Recently, they are shown to achieve enhanced explainability after incorporating various interpretability constraints. However, the training of AIMs by either the backfitting algorithm or the joint stochastic optimization is known to be very slow for especially high dimensional inputs. In this article, we propose a novel sequential approach based on the celebrated Stein's lemma. The proposed SeqStein method can successfully decouple the training of AIMs into two separable steps, namely, the following: 1) Stein's estimation of the projection indices and 2) nonparametric estimation of ridge functions using the smoothing splines. We show through numerical experiments that the SeqStein algorithm is not only more efficient for training AIMs, but also inclined to produce more interpretable models that have smooth ridge functions with sparse and nearly orthogonal projection indices.

Carbon emission prediction in a region of Hainan Province based on improved STIRPAT model.

In 2020, China pledged carbon reduction targets at the United Nations: peaking emissions by 2030 and achieving carbon neutrality by 2060. Research and prediction of regional carbon emissions are crucial for achieving these dual carbon targets across China. This study aims to construct an indicator system for regional carbon emissions and utilize it for forecasting. Analyzing carbon emission data from a specific area in Hainan Province from 2010 to 2020, we established an indicator system. Using the interpretable SHAP model, we assessed indicator importance and trends. Employing an improved STIRPAT model with partial least squares regression to address multicollinearity among influencing factors, we developed a carbon emission prediction model. Based on this, we forecasted carbon emissions from 2021 to 2060 in the specified area under three scenarios: natural, baseline, and ambitious. The results show that the growth of resident population and per capita GDP has the most significant promoting effect on carbon emissions in the region while optimizing industrial structure, energy consumption structure, and reducing energy intensity will inhibit carbon emissions. The prediction results indicate that in the natural scenario, regional carbon emissions will peak in 2035, and achieving carbon neutrality by 2060 is not feasible, while the baseline scenario and ambitious scenario can achieve the dual carbon targets on time or even earlier. The research results of this article provide a reference method for predicting carbon emissions in other regions and a guide for future regional emission reduction.

Improving Clinical Decisions in IR: Interpretable Machine Learning Models for Predicting Ascites Improvement after Transjugular Intrahepatic Portosystemic Shunt Procedures

PurposeTo evaluate the potential of interpretable machine learning (ML) models to predict ascites improvement in patients undergoing transjugular intrahepatic portosystemic shunt (TIPS) placement for refractory ascites. Materials and MethodsIn this retrospective study, 218 patients with refractory ascites who underwent TIPS placement were analyzed. Data on 29 demographic, clinical, and procedural features were collected. Ascites improvement was defined as reduction in the need of paracentesis by 50% or more at the 1-month follow-up. Univariate statistical analysis was performed. Data were split into train and test sets. Feature selection was performed using a wrapper-based sequential feature selection algorithm. Two ML models were built using support vector machine (SVM) and CatBoost algorithms. Shapley additive explanations values were calculated to assess interpretability of ML models. Performance metrics were calculated using the test set. ResultsRefractory ascites improved in 168 (77%) patients. Higher sodium (Na; 136 mEq/L vs 134 mEq/L; P = .001) and albumin (2.91 g/dL vs 2.68 g/dL; P = .03) levels, lower creatinine levels (1.01 mg/dL vs 1.17 mg/dL; P = .04), and lower Model for End-stage Liver Disease (MELD) (13 vs 15; P = .01) and MELD-Na (15 vs 17.5, P = .002) scores were associated with significant improvement, whereas main portal vein puncture was associated with a lower improvement rate (P = .02). SVM and CatBoost models had accuracy ratios of 83% and 87%, with area under the curve values of 0.83 and 0.87, respectively. No statistically significant difference was found between performances of the models in DeLong test (P = .3). ConclusionsAccording to this study, ML models may have potential in patient selection for TIPS placement by predicting the improvement in refractory ascites.

Massive experimental quantification of amyloid nucleation allows interpretable deep learning of protein aggregation.

Protein aggregation is a pathological hallmark of more than fifty human diseases and a major problem for biotechnology. Methods have been proposed to predict aggregation from sequence, but these have been trained and evaluated on small and biased experimental datasets. Here we directly address this data shortage by experimentally quantifying the amyloid nucleation of >100,000 protein sequences. This unprecedented dataset reveals the limited performance of existing computational methods and allows us to train CANYA, a convolution-attention hybrid neural network that accurately predicts amyloid nucleation from sequence. We adapt genomic neural network interpretability analyses to reveal CANYA's decision-making process and learned grammar. Our results illustrate the power of massive experimental analysis of random sequence-spaces and provide an interpretable and robust neural network model to predict amyloid nucleation.

Interpretable machine learning models for predicting probabilistic axial buckling strength of steel circular hollow section members considering discreteness of geometries and material

Steel circular hollow section (CHS) members are widely utilized as axial force-resisting structural members in civil engineering structures. The buckling strength under axial loads is one of the critical parameters to determine the performance of the steel CHS members, which is significantly affected by the discreteness introduced by geometries, material, and initial imperfections. However, the reduction factor employed in the modern design codes (i.e. Chinese codes and EC3) only accounts for the reduction caused by all kinds of discreteness and does not reflect the impacts of every single discreteness and imperfection. To fill the gap, this paper proposed an interpretable machine-learning method to provide the probabilistic axial buckling strength of steel CHS members prediction result in a distribution form with the consideration of detailed discreteness. The model to predict the nominal axial buckling strength of steel CHS members was first developed utilizing ten machine learning algorithms after sufficient numerical simulations, where the numerical model was verified using test results. The artificial neural network (ANN) was selected for developing the prediction model due to its highly reliable performance in testing. The developed ANN models were further interpreted utilizing Shapley Additive exPlanations (SHAP) to determine the interrelationship of different parameters. Then, the probabilistic axial bucking strength prediction model was established based on the developed ANN models, where the Latin hypercube sampling method was applied to address the discreteness of geometries, material, and initial imperfections. The generated probabilistic axial bucking strength prediction model’s effectiveness was verified by the evidence that the machine learning prediction results can highly match the numerical results' probability density function and the result from codes while significantly reducing the computation time. Finally, the design parameters’ impact on the axial buckling strength’s discreteness was evaluated using the global sensitivity analysis (GSA) method. The result shows that the discreteness of design parameters substantially influences the distribution of the axial buckling strength of the steel CHS members and the proposed prediction model can provide an accurate probabilistic distribution prediction.

Combining categorical boosting and Shapley additive explanations for building an interpretable ensemble classifier for identifying mineralization-related geochemical anomalies

The vast majority of shallow and deep learning techniques used to identify mineralization-related geochemical anomalies are black-box algorithms that lack the ability to elucidate the individual contributions of each element towards the model predictions. In addition, most of the anomaly identification models established by both shallow and deep learning algorithms lack robustness. Establishing interpretable and robust machine learning models is a challenge in applying machine learning techniques to geochemical anomaly identification. To this end, the categorical boosting (CatBoost) algorithm was employed to build a robust ensemble classifier to identify mineralization-related anomalies from the 1:50,000 geochemical reconnaissance data (stream sediment survey) in the Yeniugou area of Xinjiang (China). The receiver operating characteristic curve (ROC) and precision-recall (P-R) curve of the ensemble model were plotted, and the area under the ROC curve (AUC) as well as the area under the P-R curve (AUPRC) of the ensemble model were calculated to measure the performance of the ensemble model. The ROC curve of the ensemble model approximates that of the perfect classification model. The P-R curve of the ensemble model is close to the upper right corner of the P-R space. The AUC and AUPRC values of the ensemble model reaches 0.9981 and 0.7816, respectively. The identified polymetallic mineralization-related geochemical anomalies account for 3% of the whole exploration area, correctly identifying all known polymetallic deposits. To enhance the interpretability of the CatBoost model, the Shapley additive explanations (SHAP) tool was adopted to graphically interpret the predictions of the ensemble model. The graphic interpretation shows that the importance order of the 14 elements is Ni-Au-Ag-Sn-As-Cr-Zn-Cu-Pb-Sb-W-Bi-Mo-Co. Cu and Ni are most likely metallogenic elements of the study area. Cu interacts with Ni, Ag, As, Sn, Cr, Zn, Pb, Sb, W, Bi, and Co; and Ni interacts with Au, Sn, As, Zn, Cu, W, Bi, and Co. Two polymetallic prospective areas were delineated in the study area. One is Cu-Ni-polymetallic mineralization prospective area, and the other is Ni-polymetallic mineralization prospective area. It can be concluded that the combination of CatBoost and SHAP is an effective way to construct an interpretable ensemble model with high-performance and robustness in identifying mineralization-related geochemical anomalies.

Urban greenery distribution and its link to social vulnerability

Urban greenery plays a pivotal role in urban environments, impacting the environmental well-being and people’s comfort. Several studies have demonstrated a strong link between urban greenery and socioeconomic status but still lack an analysis of greenery on uneven distribution in social vulnerability. This study assesses how multi-level greenery rates distribute and associate the social vulnerability of people in 429 census tracts in the Seattle metropolitan area. It integrates multi-source urban informatics data, including remote sensing data and street view imagery, to identify various vegetation types. Then, it uses the interpretable machine learning model to explore the relationship between street-level green space distribution and community vulnerability. The results show a serious problem of uneven distribution of green spaces in urban centers since urban areas are built up and fragmented the landscape. Areas with low urban greening in the Seattle area have higher rates of poverty, unemployment, racial segregation, and housing overcrowding. Besides, greening features like street green views, which are more related to human perception, have a great association with social vulnerability. These findings contribute to the urban green spaces to better promote community equity and vulnerability.

Graft Failure and Contralateral ACL Injuries After Primary ACL Reconstruction: An Analysis of Risk Factors Using Interpretable Machine Learning.

Anterior cruciate ligament (ACL) reconstruction (ACLR) can be successful in restoring knee stability. However, secondary ACL injury, either through graft failure or contralateral injury, is a known complication and can significantly impact the ability of a patient to return successfully to previous activities. To develop and internally validate an interpretable machine learning model to quantify the risk of graft failure and contralateral ACL injury in a longitudinal cohort treated with ACLR. Case-control study; Level of evidence, 3. An established geographic database of >600,000 patients was used to identify patients with a diagnosis of ACL rupture between 1990 and 2016 with a minimum 2-year follow-up. Medical records were reviewed for relevant patient information and 4 candidate machine learning algorithms were evaluated for prediction of graft failure and contralateral ACL injury in patients after ACLR as identified either on magnetic resonance imaging or via arthroscopy. Performance of the algorithms was assessed through discrimination, calibration, and decision curve analysis. Model interpretability was enhanced utilizing global variable importance plots and partial dependence curves. A total of 1497 patients met inclusion criteria. Among them, 140 (9.4%) had graft failure and 128 (8.6%) had a contralateral ACL injury after index surgery at a median follow-up of 140.7 months (interquartile range, 77.2-219.2 months). The best performing models achieved an area under the receiver operating characteristics curve of 0.70 for prediction of graft failure and 0.67 for prediction of contralateral ACL injury, outperforming a logistic regression fitted on the identical feature set. Notable predictors for increased risk of graft failure included younger age at injury, body mass index (BMI) <30, return to sports <13 months, initial time to surgery >75 days, utilization of allograft, femoral/tibial fixation with suspension/expansion devices, concomitant collateral ligament injury, and active or former smoking history. Predictors of contralateral ACL injury included greater preoperative pain, younger age at initial injury, BMI <30, active smoking history, initial time to surgery >75 days, history of contralateral knee arthroscopies, and involvement in contact sports. Less than 18% of all patients who undergo ACLR should be expected to sustain either a graft failure or contralateral ACL injury. Machine learning models outperformed logistic regression and identified greater preoperative pain, younger age, BMI <30, earlier return to higher activity, and time to surgical intervention >75 days as common risk factors for both graft failure as well as contralateral ACL injury after ACLR. Surgeon-modifiable risk factors for graft failure included allograft and femoral/tibial fixation with a suspension/expansion combination.

An interpretable surrogate model for H2S solubility forecasting in ionic liquids based on machine learning

Here we investigated four different ML-based models, i.e., gaussian process regression (GPR), extreme gradient boosting (i.e., XGBoost), random forest (RF), and support vector machine (SVM), for predicting the solubility of H2S in various ionic liquids (ILs). The dataset was divided into training and testing sets in an 80:20 ratio while the model performance for all models were evaluated using the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE). Overall, all models effectively predicted H2S solubility, albeit with varying degrees of performance. The GPR provides the best performance, with R2 of 0.9918, MAE of 0.0090, and RMSE of 0.0147. Following this is the XGBoost model with an R2 value of 0.9827, MAE of 0.0155, and RMSE of 0.0213. The RF model displayed slightly lower performance, with an R2 value of 0.9395, MAE of 0.0261, and RMSE of 0.0398 while the lowest performance was demonstrated by the SVM model, which gave an R2 value of 0.9036, MAE of 0.0402, and RMSE of 0.0508. We used SHAP analysis and identified the pressure, temperature, Estate_VSA3, Estate_VSA5, and MinEStateIndex as the top five dominant input features in our model interpretation. In a nutshell, this work presents new insights into the molecular characteristics that affect the solubility of H2S in ILs, paving future research path in this field.

Automated model discovery for textile structures: The unique mechanical signature of warp knitted fabrics

Textile fabrics have unique mechanical properties, which make them ideal candidates for many engineering and medical applications: They are initially flexible, nonlinearly stiffening, and ultra-anisotropic. Various studies have characterized the response of textile structures to mechanical loading; yet, our understanding of their exceptional properties and functions remains incomplete. Here we integrate biaxial testing and constitutive neural networks to automatically discover the best model and parameters to characterize warp knitted polypropylene fabrics. We use experiments from different mounting orientations, and discover interpretable anisotropic models that perform well during both training and testing. Our study shows that constitutive models for warp knitted fabrics are highly sensitive to an accurate representation of the textile microstructure, and that models with three microstructural directions outperform classical orthotropic models with only two in-plane directions. Strikingly, out of 214=16,384 possible combinations of terms, we consistently discover models with two exponential linear fourth invariant terms that inherently capture the initial flexibility of the virgin mesh and the pronounced nonlinear stiffening as the loops of the mesh tighten. We anticipate that the tools we have developed and prototyped here will generalize naturally to other textile fabrics–woven or knitted, weft knit or warp knit, polymeric or metallic–and, ultimately, will enable the robust discovery of anisotropic constitutive models for a wide variety of textile structures. Beyond discovering constitutive models, we envision to exploit automated model discovery for the generative material design of wearable devices, stretchable electronics, and smart fabrics, as programmable textile metamaterials with tunable properties and functions. Our source code, data, and examples are available at https://github.com/LivingMatterLab/CANN. Statement of significanceTextile structures are rapidly gaining popularity in many biomedical applications including tissue engineering, wound healing, and surgical repair. A precise understanding of their unique mechanical properties is critical to tailor them to their specific functions. Here we integrate mechanical testing and machine learning to automatically discover the best models for knitted polypropylene fabrics. We show that warp knitted fabrics possess a complex symmetry with three distinct microstructural directions. Along these, the behavior is dominated by an exponential linear term that characterize the initial flexibility of the virgin mesh and the nonlinear stiffening as the loops of the fabric tighten. We expect that our technology will generalize naturally to other fabrics and enable the robust discovery of complex anisotropic models for a wide variety of textile structures.

Probabilistic framework for strain-based fatigue life prediction and uncertainty quantification using interpretable machine learning

Establishing a unified fatigue life prediction model and quantifying the uncertainty in the mechanical behavior of materials are critical to ensure the structural integrity and equipment performance. For the commonly-used strain-based fatigue methods, existing estimation methods exhibit inevitable deviations, while data-driven methods have shown poor extrapolation ability and interpretability. Therefore, this paper aims to develop a probabilistic framework for strain-based fatigue life prediction and uncertainty quantification (UQ) to provide an indication for fatigue design/assessment using interpretable machine learning (ML) techniques. Based on Shapley additive explanations (SHAP) and symbolic regression (SR), interpretable prediction models with concise expressions and outstanding prediction performance are established and optimized according to the priori physical knowledge. Moreover, accounting for the material variability, the probabilistic assessment with UQ excellently validates the prediction model, and quantifies the variability of ε-N curves. The proposed framework provides valuable reference and shows promising prospects in fatigue design for engineering components.

Comparison and integration of physical and interpretable AI-driven models for rainfall-runoff simulation

Precise streamflow forecasting in river systems is crucial for water resources management and flood risk assessment. The Tagus Headwaters River Basin (THRB) in Spain is a key hydrological hub, providing regulated flow for agricultural, urban, and energy sectors, and facilitating water transfer to the Segura River Basin, a key semi-arid region. Given the basin's near-total allocation of water resources, accurate streamflow simulations are essential to optimize the socio-economic distribution and ensure sustainable management across both interconnected basins. This study conducts a comprehensive evaluation of the Soil and Water Assessment Tool (SWAT+), support vector regression (SVR), feed forward neural network (FFNN), and long short-term memory (LSTM) models in simulating the rainfall-runoff process at four gauging stations within the THRB. An ensemble machine learning technique is then applied to assess improvements in streamflow estimation. Results revealed that AI-based models significantly surpassed the SWAT+ model in performance. Furthermore, the application of an ensemble technique enhanced the precision of rainfall-runoff modeling by 18 to 26% during the calibration period and 4.1 to 9.2% during the validation period, compared to individual AI-based models. Additionally, the SWAT+ model's precision improved by 44 to 74% and 40 to 55% for the respective periods. The use of Shapley Additive Explanations (SHAP) methodology allowed the results of the ensemble with machine learning to be more interpretable by explaining how each model contributes to the prediction. This research offers significant contributions to hydrological modeling, highlighting the importance of ensemble techniques in elevating predictive accuracy for various river basins.

Interpretable general thermal comfort model based on physiological data from wearable bio sensors: Light Gradient Boosting Machine (LightGBM) and SHapley Additive exPlanations (SHAP)

This study aims to develop a general thermal comfort model using physiological signals obtained from wristband-type wearable biosensors. Accordingly, we constructed and evaluated supervised machine learning models by leveraging a diverse array of features extracted from physiological signals, including electrodermal activity (EDA), photoplethysmogram (PPG), and skin temperature (SKT). The model’s performance was evaluated using data collected from 18 subjects across controlled experimental settings. Further, this study employed leave one subject out cross validation (LOSOCV) instead of the traditional k-fold CV to assess the model’s generalizability to new subjects. Furthermore, SHapley Addictive exPlanation (SHAP) was incorporated to augment the interpretability and transparency of the model. The LightGBM model demonstrated a commendable test accuracy of 79.7% in distinguishing thermal preferences, namely, “want warmer,” “comfort,” and “want cooler.” These findings underscore the feasibility of employing wearable biosensors to evaluate occupants’ thermal comfort in real-world environments. This study makes a significant contribution to the literature by laying the groundwork for a broadly applicable method of continuous, objective, and noninvasive thermal comfort monitoring among building occupants. Considering previous challenges associated with personalized thermal comfort models due to individual variability, our study represents a pivotal step toward the development of a generalized thermal comfort model.

Fuzzy based Decision-Making Algorithm for Solving Big Data Issues in Smart Cities

To better provide urban services and build an increasingly sustainable architecture, big data can be used to make more efficient use of current assets while enhancing the caliber of services offered to local inhabitants. However, there are several challenges to incorporating big data into existing infrastructure. Therefore, this research aims to determine the problems associated with Big Data’s effectiveness in developing intelligent towns and to investigate the connections between those difficulties. The 14 issues with Big Data were found through a literature study, and the precision was checked by feedback from professionals. Next, we employ a combined approach based on fuzzy interpretation, Structured simulation, and the Fuzzy Making Decisions Trial and Assessment Laboratories to decipher the connections between our identified problems incorporating Big Data into the development of smart cities is hampered, as shown by the analysis of links between challenges, primarily by the heterogeneous inhabitants in developed cities and the lack of connectivity. The findings of this study will provide creative city practitioners and policy planners with the information they need to successfully tackle these obstacles, clearing the way for the widespread adoption of smart city technologies. This research is a first step towards creating an interpretive structural model of the difficulties brought on by Big Data in cutting-edge urban planning. The study attempts, in part, to use this paradigm to better understand the relationship among the highlighted issues.

Lung nodule classification using radiomics model trained on degraded SDCT images

Background and ObjectiveLow-dose computed tomography (LDCT) screening has shown promise in reducing lung cancer mortality; however, it suffers from high false positive rates and a scarcity of available annotated datasets. To overcome these challenges, we propose a novel approach using synthetic LDCT images generated from standard-dose CT (SDCT) scans from the LIDC-IDRI dataset. Our objective is to develop and validate an interpretable radiomics-based model for distinguishing likely benign from likely malignant pulmonary nodules. MethodsFrom a total of 1010 CT images (695 SDCTs and 315 LDCTs), we degraded SDCTs in the sinogram domain and obtained 1950 nodules as the training set. The 675 nodules from the LDCTs were stratified into 50%-50% partitions for validation and testing. Radiomic features were extracted from nodules, and three feature sets were assessed using: a) only shape and size (SS) features, b) all features but SS features, and c) all features. A systematic pipeline was developed to optimize the feature set and evaluate multiple machine learning models. Models were trained using degraded SDCT, validated and tested on the LDCT nodules. ResultsTraining a logistic regression model using three SS features yielded the most promising results, achieving on the test set mean balanced accuracy, sensitivity, specificity, and AUC-ROC scores of 0.81, 0.76, 0.85, and 0.87, respectively. ConclusionsOur study demonstrates the feasibility and effectiveness of using synthetic LDCT images for developing a relatively accurate radiomics-based model in lung nodule classification. This approach addresses challenges associated with LDCT screening, offering potential implications for improving lung cancer detection and reducing false positives.

BrainQCNet: A Deep Learning attention-based model for the automated detection of artifacts in brain structural MRI scans

Abstract Analyses of structural MRI (sMRI) data depend on robust upstream data quality control (QC). It is also crucial that researchers seek to retain maximal amounts of data to ensure reproducible, generalizable models and to avoid wasted effort, including that of participants. The time-consuming and difficult task of manual QC evaluation has prompted the development of tools for the automatic assessment of brain sMRI scans. Existing tools have proved particularly valuable in this age of Big Data; as datasets continue to grow, reducing execution time for QC evaluation will be of considerable benefit. The development of Deep Learning (DL) models for artifact detection in structural MRI scans offers a promising avenue toward fast, accurate QC evaluation. In this study, we trained an interpretable Deep Learning model, ProtoPNet, to classify minimally preprocessed 2D slices of scans that had been manually annotated with a refined quality assessment (ABIDE 1; n = 980 scans). To evaluate the best model, we applied it to 2141 ABCD T1-weighted MRI scans for which gold-standard manual QC annotations were available. We obtained excellent accuracy: 82.4% for good quality scans (Pass), 91.4% for medium to low quality scans (Fail). Further validation using 799 T1w MRI scans from ABIDE 2 and 750 T1w MRI scans from ADHD-200 confirmed the reliability of our model. Accuracy was comparable to or exceeded that of existing ML models, with fast processing and prediction time (1 minute per scan, GPU machine, CUDA-compatible). Our attention model also performs better than traditional DL (i.e., convolutional neural network models) in detecting poor quality scans. To facilitate faster and more accurate QC prediction for the neuroimaging community, we have shared the model that returned the most reliable global quality scores as a BIDS-app (https://github.com/garciaml/BrainQCNet).

S2MRI-ADNet: an interpretable deep learning framework integrating Euclidean-graph representations of Alzheimer's disease solely from structural MRI.

To establish a multi-dimensional representation solely on structural MRI (sMRI) for early diagnosis of AD. A total of 3377 participants' sMRI from four independent databases were retrospectively identified to construct an interpretable deep learning model that integrated multi-dimensional representations of AD solely on sMRI (called s2MRI-ADNet) by a dual-channel learning strategy of gray matter volume (GMV) from Euclidean space and the regional radiomics similarity network (R2SN) from graph space. Specifically, the GMV feature map learning channel (called GMV-Channel) was to take into consideration spatial information of both long-range spatial relations and detailed localization information, while the node feature and connectivity strength learning channel (called NFCS-Channel) was to characterize the graph-structured R2SN network by a separable learning strategy. The s2MRI-ADNet achieved a superior classification accuracy of 92.1% and 91.4% under intra-database and inter-database cross-validation. The GMV-Channel and NFCS-Channel captured complementary group-discriminative brain regions, revealing a complementary interpretation of the multi-dimensional representation of brain structure in Euclidean and graph spaces respectively. Besides, the generalizable and reproducible interpretation of the multi-dimensional representation in capturing complementary group-discriminative brain regions revealed a significant correlation between the four independent databases (p < 0.05). Significant associations (p < 0.05) between attention scores and brain abnormality, between classification scores and clinical measure of cognitive ability, CSF biomarker, metabolism, and genetic risk score also provided solid neurobiological interpretation. The s2MRI-ADNet solely on sMRI could leverage the complementary multi-dimensional representations of AD in Euclidean and graph spaces, and achieved superior performance in the early diagnosis of AD, facilitating its potential in both clinical translation and popularization.

An interpretable tinnitus prediction framework using gap-prepulse inhibition in auditory late response and electroencephalogram.

Tinnitus is a neuropathological condition that results in mild buzzing or ringing of the ears without an external sound source. Current tinnitus diagnostic methods often rely on subjective assessment and require intricate medical examinations. This study aimed to propose an interpretable tinnitus diagnostic framework using auditory late response (ALR) and electroencephalogram (EEG), inspired by the gap-prepulse inhibition (GPI) paradigm. We collected spontaneous EEG and ALR data from 44 patients with tinnitus and 47 hearing loss-matched controls using specialized hardware to capture responses to sound stimuli with embedded gaps. In this cohort study of tinnitus and control groups, we examined EEG spectral and ALR features of N-P complexes, comparing the responses to gap durations of 50 and 20 ms alongside no-gap conditions. To this end, we developed an interpretable tinnitus diagnostic model using ALR and EEG metrics, boosting machine learning architecture, and explainable feature attribution approaches. Our proposed model achieved 90 % accuracy in identifying tinnitus, with an area under the performance curve of 0.89. The explainable artificial intelligence approaches have revealed gap-embedded ALR features such as the GPI ratio of N1-P2 and EEG spectral ratio, which can serve as diagnostic metrics for tinnitus. Our method successfully provides personalized prediction explanations for tinnitus diagnosis using gap-embedded auditory and neurological features. Deficits in GPI alongside activity in the EEG alpha-beta ratio offer a promising screening tool for assessing tinnitus risk, aligning with current clinical insights from hearing research.

Analyzing factors influencing competitiveness of Indian tech start-ups: modified total interpretive structural model (m-TISM) approach

Analyzing factors influencing competitiveness of Indian tech start-ups: modified total interpretive structural model (m-TISM) approach