An Explainable Multimodal Neural Network Architecture for Predicting Epilepsy Comorbidities Based on Administrative Claims Data.
Ontology highlight
ABSTRACT:
SUBMITTER: Linden T
PROVIDER: S-EPMC8176093 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Introduction: Existing large-scale preclinical cancer drug response databases provide us with a great opportunity to identify and predict potentially effective drugs to combat cancers. Deep learning models built on these databases have been developed and applied to tackle the cancer drug-response prediction task. Their prediction has been demonstrated to significantly outperform traditional machine learning methods. However, due to the “black box” characteristic, biologically faithful explanations are hardly derived from these deep learning models. Interpretable deep learning models that rely on visible neural networks (VNNs) have been proposed to provide biological justification for the predicted outcomes. However, their performance does not meet the expectation to be applied in clinical practice. Methods: In this paper, we develop an XMR model, an eXplainable Multimodal neural network for drug Response prediction. XMR is a new compact multimodal neural network consisting of two sub-networks: a visible neural network for learning genomic features and a graph neural network (GNN) for learning drugs’ structural features. Both sub-networks are integrated into a multimodal fusion layer to model the drug response for the given gene mutations and the drug’s molecular structures. Furthermore, a pruning approach is applied to provide better interpretations of the XMR model. We use five pathway hierarchies (cell cycle, DNA repair, diseases, signal transduction, and metabolism), which are obtained from the Reactome Pathway Database, as the architecture of VNN for our XMR model to predict drug responses of triple negative breast cancer. Results: We find that our model outperforms other state-of-the-art interpretable deep learning models in terms of predictive performance. In addition, our model can provide biological insights into explaining drug responses for triple-negative breast cancer. Discussion: Overall, combining both VNN and GNN in a multimodal fusion layer, XMR captures key genomic and molecular features and offers reasonable interpretability in biology, thereby better predicting drug responses in cancer patients. Our model would also benefit personalized cancer therapy in the future.
| S-EPMC10433751 | biostudies-literature
Project description:Patients with drug-resistant epilepsy (DRE) are at high risk of morbidity and mortality, yet their referral to specialist care is frequently delayed. The ability to identify patients at high risk of DRE at the time of treatment initiation, and to subsequently steer their treatment pathway toward more personalized interventions, has high clinical utility. Here, we aim to demonstrate the feasibility of developing algorithms for predicting DRE using machine learning methods. Longitudinal, intersected data sourced from US pharmacy, medical, and adjudicated hospital claims from 1,376,756 patients from 2006 to 2015 were analyzed; 292,892 met inclusion criteria for epilepsy, and 38,382 were classified as having DRE using a proxy measure for drug resistance. Patients were characterized using 1270 features reflecting demographics, comorbidities, medications, procedures, epilepsy status, and payer status. Data from 175,735 randomly selected patients were used to train three algorithms and from the remainder to assess the trained models' predictive power. A model with only age and sex was used as a benchmark. The best model, random forest, achieved an area under the receiver operating characteristic curve (95% confidence interval [CI]) of 0.764 (0.759, 0.770), compared with 0.657 (0.651, 0.663) for the benchmark model. Moreover, predicted probabilities for DRE were well-calibrated with the observed frequencies in the data. The model predicted drug resistance approximately 2 years before patients in the test dataset had failed two antiepileptic drugs (AEDs). Machine learning models constructed using claims data predicted which patients are likely to fail ≥3 AEDs and are at risk of developing DRE at the time of the first AED prescription. The use of such models can ensure that patients with predicted DRE receive specialist care with potentially more aggressive therapeutic interventions from diagnosis, to help reduce the serious sequelae of DRE.
| S-EPMC6461470 | biostudies-literature
Project description:Predicting potentially dangerous chemical reactions is a critical task for laboratory safety. However, a traditional experimental investigation of reaction conditions for possible hazardous or explosive byproducts entails substantial time and cost, for which machine learning prediction could accelerate the process and help detailed experimental investigations. Several machine learning models have been developed which allow the prediction of major chemical reaction products with reasonable accuracy. However, these methods may not present sufficiently high accuracy for the prediction of hazardous products which particularly requires a low false negative result for laboratory safety in order not to miss any dangerous reactions. In this work, we propose an explainable artificial intelligence model that can predict the formation of hazardous reaction products in a binary classification fashion. The reactant molecules are transformed into substructure-encoded fingerprints and then fed into a convolutional neural network to make the binary decision of the chemical reaction. The proposed model shows a false negative rate of 0.09, which can be compared with 0.47-0.66 using the existing main product prediction models. To provide explanations for what substructures of the given reactant molecules are important to make a decision for target hazardous product formation, we apply an input attribution method, layer-wise relevance propagation, which computes the contributions of individual inputs per input data. The computed attributions indeed match some of the existing chemical intuitions and mechanisms, and also offer a way to analyze possible data-imbalance issues of the current predictions based on relatively small positive datasets. We expect that the proposed hazardous product prediction model will be complementary to existing main product prediction models and experimental investigations.
| S-EPMC8386654 | biostudies-literature
Project description:ObjectivesWe aimed to describe clinical characteristics, treatment patterns and major comorbidities of a US-based adult-onset Still's disease (AOSD) cohort.MethodsAdministrative claims data from Truven MarketScan were collected from 2009 to 2015. An AOSD case was defined as ≥1 M06.1 International Classification of Diseases 10th revision (ICD-10) medical claim code. We extracted data for the AOSD cohort (n = 106) and 1:5 matched controls (n = 530) without AOSD. Outcomes of interest and a novel claims-based set of Yamaguchi criteria were identified by relevant ICD 9th revision (ICD-9) and ICD-10 codes. Bivariate descriptive analyses were conducted on all variables. Comorbidity rates and rate ratios were calculated in AOSD cases and matched controls. Statistical significance of cohort differences was determined to compare AOSD cases and matched controls.ResultsThe AOSD cohort, with a mean age of 43.08 (standard deviation, s.d. 13.9) years and with female predominance (68.9%) was observed over a mean of 750.12 (637.6) days. A total of 35.9% of AOSD patients fulfilled claims-based Yamaguchi criteria compared with 0.4% matched controls (P< 0.05). We identified severe AOSD-related complications, including macrophage activation syndrome (4.7%) and acute respiratory distress syndrome (12.3%). Treatment commonly involved systemic glucocorticoids (62.2%), MTX (51%) and anakinra (24.5%). Compared with matched controls, serious infections were significantly increased (rate ratio 2.58, 95% CI: 1.53, 4.37, P = 0.0004), while hyperlipidaemia (0.54, 95% CI: 0.35, 0.85; P = 0.008) and obesity (0.30, 95% CI: 0.15, 0.62; P = 0.001) were significantly decreased in AOSD patients.ConclusionWe characterized a first US-based AOSD cohort using a large national administrative claims database, and identified key complications, treatments and comorbidities.
| S-EPMC7310096 | biostudies-literature
Project description:MotivationThe identification of cancer genes is a critical yet challenging problem in cancer genomics research. Existing computational methods, including deep graph neural networks, fail to exploit the multilayered gene-gene interactions or provide limited explanations for their predictions. These methods are restricted to a single biological network, which cannot capture the full complexity of tumorigenesis. Models trained on different biological networks often yield different and even opposite cancer gene predictions, hindering their trustworthy adaptation. Here, we introduce an Explainable Multilayer Graph Neural Network (EMGNN) approach to identify cancer genes by leveraging multiple gene-gene interaction networks and pan-cancer multi-omics data. Unlike conventional graph learning on a single biological network, EMGNN uses a multilayered graph neural network to learn from multiple biological networks for accurate cancer gene prediction.ResultsOur method consistently outperforms all existing methods, with an average 7.15% improvement in area under the precision-recall curve over the current state-of-the-art method. Importantly, EMGNN integrated multiple graphs to prioritize newly predicted cancer genes with conflicting predictions from single biological networks. For each prediction, EMGNN provided valuable biological insights via both model-level feature importance explanations and molecular-level gene set enrichment analysis. Overall, EMGNN offers a powerful new paradigm of graph learning through modeling the multilayered topological gene relationships and provides a valuable tool for cancer genomics research.Availability and implementationOur code is publicly available at https://github.com/zhanglab-aim/EMGNN.
| S-EPMC10636280 | biostudies-literature
Project description:Objective: COVID-19 is a sort of infectious disease caused by a new strain of coronavirus. This study aims to develop a more accurate COVID-19 diagnosis system. Methods: First, the n-conv module (nCM) is introduced. Then we built a 12-layer convolutional neural network (12l-CNN) as the backbone network. Afterwards, PatchShuffle was introduced to integrate with 12l-CNN as a regularization term of the loss function. Our model was named PSCNN. Moreover, multiple-way data augmentation and Grad-CAM are employed to avoid overfitting and locating lung lesions. Results: The mean and standard variation values of the seven measures of our model were 95.28 ± 1.03 (sensitivity), 95.78 ± 0.87 (specificity), 95.76 ± 0.86 (precision), 95.53 ± 0.83 (accuracy), 95.52 ± 0.83 (F1 score), 91.7 ± 1.65 (MCC), and 95.52 ± 0.83 (FMI). Conclusion: Our PSCNN is better than 10 state-of-the-art models. Further, we validate the optimal hyperparameters in our model and demonstrate the effectiveness of PatchShuffle.
| S-EPMC8585997 | biostudies-literature
Project description:Early detection of potential side effects (SE) is a critical and challenging task for drug discovery and patient care. In-vitro or in-vivo approach to detect potential SEs is not scalable for many drug candidates during the preclinical stage. Recent advances in explainable machine learning may facilitate detecting potential SEs of new drugs before market release and elucidating the critical mechanism of biological actions. Here, we leverage multi-modal interactions among molecules to develop a biologically informed graph-based SE prediction model, called HHAN-DSI. HHAN-DSI predicted frequent and even uncommon SEs of the unseen drug with higher or comparable accuracy against benchmark methods. When applying HHAN-DSI to the central nervous system, the organs with the largest number of SEs, the model revealed diverse psychiatric medications' previously unknown but probable SEs, together with the potential mechanisms of actions through a network of genes, biological functions, drugs, and SEs.
| S-EPMC10275013 | biostudies-literature
Project description:Human behavior and cognition result from a complex pattern of interactions between brain regions. The flexible reconfiguration of these patterns enables behavioral adaptation, such as the acquisition of a new motor skill. Yet, the degree to which these reconfigurations depend on the brain's baseline sensorimotor integration is far from understood. Here, we asked whether spontaneous fluctuations in sensorimotor networks at baseline were predictive of individual differences in future learning. We analyzed functional MRI data from 19 participants prior to six weeks of training on a new motor skill. We found that visual-motor connectivity was inversely related to learning rate: sensorimotor autonomy at baseline corresponded to faster learning in the future. Using three additional scans, we found that visual-motor connectivity at baseline is a relatively stable individual trait. These results suggest that individual differences in motor skill learning can be predicted from sensorimotor autonomy at baseline prior to task execution.
| S-EPMC5910215 | biostudies-literature
Project description:Predicting drug-target affinity (DTA) is beneficial for accelerating drug discovery. Graph neural networks (GNNs) have been widely used in DTA prediction. However, existing shallow GNNs are insufficient to capture the global structure of compounds. Besides, the interpretability of the graph-based DTA models highly relies on the graph attention mechanism, which can not reveal the global relationship between each atom of a molecule. In this study, we proposed a deep multiscale graph neural network based on chemical intuition for DTA prediction (MGraphDTA). We introduced a dense connection into the GNN and built a super-deep GNN with 27 graph convolutional layers to capture the local and global structure of the compound simultaneously. We also developed a novel visual explanation method, gradient-weighted affinity activation mapping (Grad-AAM), to analyze a deep learning model from the chemical perspective. We evaluated our approach using seven benchmark datasets and compared the proposed method to the state-of-the-art deep learning (DL) models. MGraphDTA outperforms other DL-based approaches significantly on various datasets. Moreover, we show that Grad-AAM creates explanations that are consistent with pharmacologists, which may help us gain chemical insights directly from data beyond human perception. These advantages demonstrate that the proposed method improves the generalization and interpretation capability of DTA prediction modeling.
| S-EPMC8768884 | biostudies-literature
Project description:Colonoscopy outcomes, such as polyp detection or complication rates, may differ by procedure indication.To develop methods to classify colonoscopy indications from administrative data, facilitating study of colonoscopy quality and outcomes.We linked 14,844 colonoscopy reports from the Clinical Outcomes Research Initiative, a national repository of endoscopic reports, to the corresponding Medicare Carrier and Outpatient File claims. Colonoscopy indication was determined from the procedure reports. We developed algorithms using classification and regression trees and linear discriminant analysis (LDA) to classify colonoscopy indication. Predictor variables included ICD-9CM and CPT/HCPCS codes present on the colonoscopy claim or in the 12 months prior, patient demographics, and site of colonoscopy service. Algorithms were developed on a training set of 7515 procedures, then validated using a test set of 7329 procedures.Sensitivity was lowest for identifying average-risk screening colonoscopies, varying between 55% and 86% for the different algorithms, but specificity for this indication was consistently over 95%. Sensitivity for diagnostic colonoscopy varied between 77% and 89%, with specificity between 55% and 87%. Algorithms with classification and regression trees with 7 variables or LDA with 10 variables had similar overall accuracy, and generally lower accuracy than the algorithm using LDA with 30 variables.Algorithms using Medicare claims data have moderate sensitivity and specificity for colonoscopy indication, and will be useful for studying colonoscopy quality in this population. Further validation may be needed before use in alternative populations.
| S-EPMC3387505 | biostudies-literature