Evaluation of Synthetic Categorical Data Generation Techniques for Predicting Cardiovascular Diseases and Post-hoc Interpretability of the Risk Factors

García-Vicente, Clara; Chushig-Muzo, David; Jiménez, Inmaculada; Fabelo, Himar; Gram, Inger Torhild; Løchen, Maja‐Lisa; Granja, Conceição; Soguero-Ruíz, Cristina

doi:10.20944/preprints202302.0117.v1

Cited by 4 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, SHAP shows the contribution of each feature to the final prediction and can support the interpretability of data-driven models. The SHAP has shown great ability to provide model interpretability in multiple clinical studies [60][61][62].…”

Section: Post-hoc Interpretability Methodsmentioning

confidence: 99%

A multimodal and interpretable-based approach for improving melanoma detection using dermoscopy images

Gómez-Martínez,

Chushig-Muzo,

Veierød

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Background: The global incidence of skin cancers, particularly melanoma, the deadliest among them, has risen in recent decades. Artificial Intelligence (AI) has yielded remarkable results across diverse domains including healthcare. However, most AI models for skin cancer prediction primarily focus on a single data type or modality, such as images. Emerging research highlights the potential of multimodal approaches to enhance predictive performance and interpretability in clinical tasks. Methods: In this work, the effectiveness of multimodal fusion methods —including early and late fusion— for the detection of melanoma is assessed. Three public skin image datasets (ISIC, PH2, and Derm7pt) were considered, and two types of modalities were used, including dermoscopy images and tabular data comprising metadata, image features, and image embeddings. This study employed AI-based image classification and extended feature extraction to capture the color and texture characteristics of skin lesions, aiming to discover factors related to melanoma. Results: Experimental findings reveal that the proposed multimodal fusion methods outperform single-modality models. Early fusion methods achieve the highest classification results, with an overall AUCROC of 0.873, 0.963, and 0.857 for ISIC, PH2, and Derm7pt, respectively. Compared with models trained with single-modality data, fusion approaches exhibited notable improvements of 6.67% (ISIC), 8.27% (Derm7pt), and 7% (PH2) in AUCROC. Two post-hoc techniques were used for detecting salient regions in dermoscopy images and identifying the most relevant image features for melanoma diagnosis. Conclusions: These results hold promise for early skin lesion detection, contributing valuable support to dermatologists in their daily practice.

show abstract

Section: Post-hoc Interpretability Methodsmentioning

confidence: 99%

A multimodal and interpretable-based approach for improving melanoma detection using dermoscopy images

Gómez-Martínez,

Chushig-Muzo,

Veierød

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, the novel conditional tabular GAN (CTGAN) has shown excellent performance for addressing the main issues in the generation of mixed-type tabular data [26]. In the clinical setting, different authors have used CTGAN variants [27,28] to create synthetic data that conserve underlying distribution from original data by aiming to enhance the results in predictive tasks.…”

Section: Introductionmentioning

confidence: 99%

Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability

Gómez-Martínez,

Chushig-Muzo,

Veierød

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Cutaneous melanoma, the most serious skin cancer, constitutes a considerable health burden in fair-skinned populations. Its increasing incidence highlights the need to develop automated computer-aided approaches that support dermatologists in melanoma detection. Recent advances in artificial intelligence (AI), jointly with the availability of public dermoscopy image datasets, have led to create data-driven models with high predictive performance, thus contributing to dermatology research. Despite these advantages, most image datasets present the class imbalance problem, where a few classes have numerous samples, whereas others are under-represented, impacting the performance of AI-based models. Methods: In this paper, we propose to combine ensemble feature selection (FS) methods and data augmentation with the conditional tabular generative adversarial networks (CTGAN) to enhance melanoma identification in imbalanced datasets. We employed dermoscopy images from two public datasets, PH2 and Derm7pt, which contain melanoma and not-melanoma lesions. To capture intrinsic information from skin lesions, we conduct two feature extraction (FE) approaches, including handcrafted and embedding features. For the former, color, geometric and first-, second-, and higher-order texture features were extracted, while for the latter, embeddings were obtained using ResNet-based models. To alleviate the high-dimensionality in the FE, ensemble FS with filter methods were used and evaluated. For data augmentation, we conducted a progressive analysis of the imbalance ratio (IR), related to the amount of synthetic samples created, and evaluated the impact on the predictive results. To gain interpretability on predictive models, we used SHAP, bootstrap resampling statistical tests and UMAP visualizations. Results: Experimental results showed that the combination of CTGAN and linear models achieved the best predictive results, achieving AUCROC values of 86% (with LASSO and IR=0.8) and 71% (with support vector machine and IR=0.9) for the PH2 and Derm7pt, respectively. We also identified that ‘melanoma’ lesions were mainly characterized by features related to color, while ‘not melanoma’ lesions were characterized by texture features. Conclusions: Our results demonstrated the effectiveness of synthetic data to build generalizable models for melanoma prediction. Our work contributes to skin lesion research, helping in melanoma identification and the interpretation of main characteristics associated with melanoma.

show abstract

Exploring Innovative Approaches to Synthetic Tabular Data Generation

Papadaki,

Vrahatis,

Kotsiantis

2024

Electronics

View full text Add to dashboard Cite

The rapid advancement of data generation techniques has spurred innovation across multiple domains. This comprehensive review delves into the realm of data generation methodologies, with a keen focus on statistical and machine learning-based approaches. Notably, novel strategies like the divide-and-conquer (DC) approach and cutting-edge models such as GANBLR have emerged to tackle a spectrum of challenges, spanning from preserving intricate data relationships to enhancing interpretability. Furthermore, the integration of generative adversarial networks (GANs) has sparked a revolution in data generation across sectors like healthcare, cybersecurity, and retail. This review meticulously examines how these techniques mitigate issues such as class imbalance, data scarcity, and privacy concerns. Through a meticulous analysis of evaluation metrics and diverse applications, it underscores the efficacy and potential of synthetic data in refining predictive models and decision-making software. Concluding with insights into prospective research trajectories and the evolving role of synthetic data in propelling machine learning and data-driven solutions across disciplines, this work provides a holistic understanding of the transformative power of contemporary data generation methodologies.

show abstract

Evaluation of Synthetic Categorical Data Generation Techniques for Predicting Cardiovascular Diseases and Post-hoc Interpretability of the Risk Factors

Cited by 4 publications

References 49 publications

A multimodal and interpretable-based approach for improving melanoma detection using dermoscopy images

A multimodal and interpretable-based approach for improving melanoma detection using dermoscopy images

Ensemble feature selection and tabular data augmentation with generative adversarial networks to enhance cutaneous melanoma identification and interpretability

Exploring Innovative Approaches to Synthetic Tabular Data Generation

Contact Info

Product

Resources

About