Predictive Modeling for Diabetes Using GraphLIME
Costi, F.; Onchis, D.; Hogea, E.; Istin, C.
Show abstract
The purpose of this paper is to present a detailed investigation of the advantages of employing GraphLIME (Local Interpretable Model Explanations for Graph Neural Networks) for the trustworthy prediction of diabetes mellitus. Our pursuit involves identifying the strengths of GraphLIME combined with the attention-mechanism over the standard coupling of deep learning neural networks with the original LIME method. The system build this way, provided us a proficient method for extracting the most relevant features and applying the attention mechanism exclusively to those features. We have closely monitored the performance metrics of the two approaches and conducted a comparative analysis. Leveraging attention mechanisms, we have achieved an accuracy of 92.6% for the addressed problem. The models performance is meticulously demonstrated throughout the study, and the results are furthermore evaluated using the Receiver Operating Characteristic (ROC) curve. By implementing this technique on a dataset of 768 patients diagnosed with or without diabetes mellitus, we have successfully boosted the models performance by over 18%.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A Deep Attention-Based Encoder for the Prediction of Type 2 Diabetes Longitudinal Outcomes from Routinely Collected Health Care Data 93%
- Deep Neural Networks for Human’s Fall-risk Prediction using Force-Plate Time Series Signal 93%
- Two distributed semi-supervised algorithms for mining of complex networks using Giraph 93%
Similar papers in this journal
- Harnessing multi-output machine learning approach and dynamical observables from network structure to optimize COVID-19 intervention strategies 93%
- Linking Patient Records at Scale with a Hybrid Approach Combining Contrastive Learning and Deterministic Rules 92%
- Navigating the Multiverse: A Hitchhiker’s Guide to Selecting Harmonisation Methods for Multimodal Biomedical Data 92%
Similar papers in this journal
- Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images 94%
- From theoretical models to practical deployment: A perspective and case study of opportunities and challenges in AI-driven healthcare research for low-income settings 94%
- Identification of predictive patient characteristics for assessing the probability of COVID-19 in-hospital mortality 93%
Similar papers in this journal
- Characterizing subgroup performance of probabilistic phenotype algorithms within older adults: A case study for dementia, mild cognitive impairment, and Alzheimer’s and Parkinson’s diseases 93%
- Modeling physician variability to prioritize relevant medical record information 93%
- Trajectories: a framework for detecting temporal clinical event sequences from health data standardized to the OMOP Common Data Model 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.