Quantum Boltzmann Machines Using Parallel Annealing for Medical Image Classification
Daniëlle Schumann, Mark V. Seebode, Tobias Rohe, Maximilian Balthasar Mansky, Michael Schroedl-Baumann, Jonas Stein, Claudia Linnhoff-Popien, Florian Krellner
Abstract
Exploiting the fact that samples drawn from a quantum annealer inherently follow a boltzmann-like distribution, annealing-based Quantum Boltzmann Machines (QBMs) have gained increasing popularity in the quantum research community. While they harbor great promises for quantum speed-up, their usage currently stays a costly endeavor, as large amounts of QPU time are required to train them. This limits their applicability in the NISQ era. Following the idea of Noè et al. [1], who tried to alleviate this cost by incorporating parallel quantum annealing into their unsupervised training of QBMs, this paper presents an improved version of parallel quantum annealing that we employ to train QBMs in a supervised setting. Saving qubits to encode the inputs, the latter setting allows us to test our approach on medical images from the MedMNIST data set [2], thereby moving closer to real-world applicability of the technology. Our experiments show that QBMs using our approach already achieve reasonable results, comparable to those of similarly-sized Convolutional Neural Networks (CNNs), with a markedly smaller numbers of epochs than these classical models. Our using parallel annealing grants it a speed-up of almost 70% compared to regular annealing-based BM execution.
IEEE Xplore. 2025.
The Role of Domain-Specific Models for Synthetic Data Generation with Iterative Prompt Optimization
Nina Freise et al.
Abstract
Synthetic data generation is essential for addressing data scarcity and privacy constraints in medical AI. Large language models (LLMs) can be used to generate medical texts, but their output quality depends on the prompting approach. This study investigates the effectiveness of integrating specialized medical terminology-focused LLMs with IPROPS - an iterative prompt refinement framework - for the task of generating cardiology discharge letters. We fine-tune Llama on German medical texts and compare its performance to an untuned baseline. Our findings indicate that utilizing the fine-tuned model enhances coherence and domain specificity while iterative prompt refinement significantly reduces the performance gap and can be considered as a viable alternative to fine-tuning. A Turing test with physicians confirms that, while synthetic discharge letters achieve high realism, they remain distinguishable from real samples.
IEEE Xplore. 2025.
IPROPS – Iterative Prompt Refinement for Optimizing Privacy-Preserving Synthetic Data Generation
Nina Freise et al.
Abstract
The integration of AI in healthcare is heavily impacted by limitations associated with medical data. Data scarcity, strict privacy regulations, and inherent biases affect the development and deployment of AI solutions in medical settings. One common strategy to combat data limitations is by generating synthetic data and utilizing it for training AI models. We introduce IPROPS—a novel framework for synthetic data generation designed specifically to address the inherent limitations of medical data. IPROPS employs advanced prompt optimization techniques that enable automatic refinement of input prompts in prompt-based models and is designed to operate without requiring direct or explicit access to real patient data. Our framework operates as an integrated pipeline with components that function in an iterative manner to generate high-quality, privacy-compliant synthetic data. To validate IPROPS and demonstrate its practical utility, we implemented and evaluated a prototype. Specifically, we applied our framework to generate synthetic German cardiology discharge letters—a complex medical text generation task requiring both clinical accuracy and strict privacy preservation. Results demonstrate the effectiveness of the actor-critic feedback loop and guided mutation strategies in iterating prompts, ultimately producing synthetic data that closely resembles real data. While opportunities for enhancement remain, the IPROPS framework offers substantial benefits, especially in domains where regulatory constraints and data access restrictions present significant barriers to AI advancement.
IEEE Xplore. 2025.
Automatic Prompt Optimization Techniques: Exploring the Potential for Synthetic Data Generation
Nina Freise et al.
Abstract
Artificial Intelligence (AI) advancement is heavily dependent on access to large-scale, high-quality training data. However, in specialized domains such as healthcare, data acquisition faces significant constraints due to privacy regulations, ethical considerations, and limited availability. While synthetic data generation offers a promising solution, conventional approaches typically require substantial real data for training generative models. The emergence of large-scale prompt-based models presents new opportunities for synthetic data generation without direct access to protected data. However, crafting effective prompts for domain-specific data generation remains challenging, and manual prompt engineering proves insufficient for achieving output with sufficient precision and authenticity. We review recent developments in automatic prompt optimization, following PRISMA guidelines. We analyze six peer-reviewed studies published between 2020 and 2024 that focus on automatic data-free prompt optimization methods. Our analysis reveals three approaches: feedback-driven, error-based, and control-theoretic. Although all approaches demonstrate promising capabilities in prompt refinement and adaptation, our findings suggest the need for an integrated framework that combines complementary optimization techniques to enhance synthetic data generation while minimizing manual intervention. We propose future research directions toward developing robust, iterative prompt optimization frameworks capable of improving the quality of synthetic data. This advancement can be particularly crucial for sensitive fields and in specialized domains where data access is restricted, potentially transforming how we approach synthetic data generation for AI development.
Springer Nature. 2025.