TransConv-DDPM: Enhanced Diffusion Model for Generating Time-Series Data in Healthcare

TL;DR

This paper introduces TransConv-DDPM, a novel diffusion-based generative model that effectively produces realistic physiological time-series data for healthcare, improving data augmentation and model training in medical AI applications.

Contribution

The paper presents TransConv-DDPM, an enhanced diffusion model combining U-Net, multi-scale convolution, and transformer layers for better time-series data generation in healthcare.

Findings

TransConv-DDPM outperforms TimeGAN and Diffusion-TS on multiple datasets.

Synthetic data from TransConv-DDPM improves predictive accuracy by over 13%.

Model effectively captures gradual temporal changes in physiological signals.

Abstract

The lack of real-world data in clinical fields poses a major obstacle in training effective AI models for diagnostic and preventive tools in medicine. Generative AI has shown promise in increasing data volume and enhancing model training, particularly in computer vision and natural language processing (NLP) domains. However, generating physiological time-series data, a common type in medical AI applications, presents unique challenges due to its inherent complexity and variability. This paper introduces TransConv-DDPM, an enhanced generative AI method for biomechanical and physiological time-series data generation. The model employs a denoising diffusion probabilistic model (DDPM) with U-Net, multi-scale convolution modules, and a transformer layer to capture both global and local temporal dependencies. We evaluated TransConv-DDPM on three diverse datasets, generating both long and short-sequence time-series data. Quantitative comparisons against state-of-the-art methods, TimeGAN and Diffusion-TS, using four performance metrics, demonstrated promising results, particularly on the SmartFallMM and EEG datasets, where it effectively captured the more gradual temporal change patterns between data points. Additionally, a utility test on the SmartFallMM dataset revealed that adding synthetic fall data generated by TransConv-DDPM improved predictive model performance, showing a 13.64% improvement in F1-score and a 14.93% increase in overall accuracy compared to the baseline model trained solely on fall data from the SmartFallMM dataset. These findings highlight the potential of TransConv-DDPM to generate high-quality synthetic data for real-world applications.