Personalized treatment recommendation requires translating heterogeneous causal evidence into an interpretable policy while balancing expected benefit, individual regret, and consistency across clinically similar patients. In this position paper, we argue that quantum optimization is justified in this setting only if the downstream policy-optimization problem is hard for strong classical methods, small and structured enough for quantum hardware, and consequential for patient outcomes. We build on an established causal policy-learning pipeline in which classical causal machine learning methods first provide patient-specific doubly robust treatment rewards, and we focus on the optimization layer that follows. A small proof of concept using five clinical covariates and ten patients shows that progressively richer policy decisions, including rule selection, treatment assignment, candidate-structure selection, and hard local-consistency constraints, can be encoded as Quadratic Unconstrained Binary Optimization (QUBO) problems whose evaluation reproduces the corresponding classical optimum. These checks establish formulation feasibility over the evaluated configurations, a precondition for any quantum experiment. Because exact search over fixed-depth policy trees runs in polynomial time, we locate the open question in constraints that couple patients across tree leaves and set out four research questions, each with a stop rule.
Personalized treatment recommendation requires translating heterogeneous causal evidence into an interpretable policy while balancing expected benefit, individual regret, and consistency across clinically similar patients. In this position paper, we argue that quantum optimization is justified in this setting only if the downstream policy-optimization problem is hard for strong classical methods, small and structured enough for quantum hardware, and consequential for patient outcomes. We build on an established causal policy-learning pipeline in which classical causal machine learning methods first provide patient-specific doubly robust treatment rewards, and we focus on the optimization layer that follows. A small proof of concept using five clinical covariates and ten patients shows that progressively richer policy decisions, including rule selection, treatment assignment, candidate-structure selection, and hard local-consistency constraints, can be encoded as Quadratic Unconstrained Binary Optimization (QUBO) problems whose evaluation reproduces the corresponding classical optimum. These checks establish formulation feasibility over the evaluated configurations, a precondition for any quantum experiment. Because exact search over fixed-depth policy trees runs in polynomial time, we locate the open question in constraints that couple patients across tree leaves and set out four research questions, each with a stop rule.
Personalized adaptive systems frequently learn from biased logs generated by historical policies, where spurious correlations and environment shift degrade both generalization and cohort safety. This paper introduces a unified pipeline that couples causal representation learning with quantum encodings to produce stable embeddings for offline-trained decision policies. Across environment-split evaluations, the proposed quantum causal representation reduced the invariance gap from 0.118 (baseline classical) and 0.067 (causal classical) to 0.041, while improving reward prediction AUROC from 0.791 and 0.816 to 0.842. Under drifted splits, representation shift-drop decreased from 7.6% to 2.5%, indicating stronger transfer under distributional change. Policies trained on these embeddings achieved higher normalized off-policy value, improving from 0.456 (baseline) and 0.472 (causal classical) to 0.489, while reducing shift gap from 6.9% to 2.6% and increasing worst-cohort uplift to 0.028. Drift stress tests showed sustained value retention at severe drift (level 3), with values 0.401 (baseline), 0.433 (causal classical), and 0.459 (quantum causal), accompanied by lower calibration error (0.084, 0.068, and 0.056, respectively). Ablations demonstrated a capacity sweet spot at 6 qubits and 4 layers, delivering strong value (0.489) at deployable latency (6.7 ms), whereas higher capacity yielded marginal value gains (0.491) at increased latency (9.4 ms). These results indicate that integrating causal invariance with carefully budgeted quantum feature maps improves personalization effectiveness, robustness, and reliability in adaptive decision-making from logs.
One of the significant ways to treat cancer is Radio Therapy. But traditionally the Radio Therapy treatment planning process is founded on a population-based protocol, which does not account individual variations among patients. Human genetics and physiology are usually small variations that can have much impact on the radiotherapy treatment. New solutions to this problem have been offered by recent developments in artificial intelligence and Quantum computing. A novel Quantum Reinforcement Learning based Clinical Decision Support System (CDSS) is introduced to plan adaptive radiotherapy treatment with Proximal Policy Optimization and Variational Quantum Circuits. In addition to this, a new concept of Personalized Patient Dashboard has been introduced to enable healthcare professionals to understand patient treatment procedures in a better manner. In that sense, the recent developments in quantum reinforcement learning have given experimental data that these artificial intelligence based systems have the capacity to enhance the accuracy of clinical decisions and patient outcomes.
The central claim of this thesis is simple but underappreciated: the primary bottleneck in near-term quantum computing is not a shortage of algorithms; it is a lack of systematic decision-making. Which problem instances should we test? Which circuit architectures are worth training? Which hyperparameters actually drive performance, and which are distractions? Today’s quantum hardware sits in an uncomfortable middle ground. It is expressive enough to explore nontrivial quantum dynamics, yet it is too noisy and shallow for the theoretical speedups that motivate the field. This thesis argues that applying machine learning to classical control decisions in hybrid quantum classical methods is one of the most tractable ways to make these methods genuinely useful in this regime. This argument is developed through four research questions, each addressing a distinct decision-making layer and illustrating the thesis. The first asks whether the decisions inside a hybrid heuristic can be learned rather than hand-coded. Chapter 4 analyzes Recursive QAOA (RQAOA), a promising yet brittle approach to combinatorial optimization, and identifies regimes in which its fixed-elimination strategy fails. It then replaces that strategy with a reinforcement learning policy, RL-RQAOA, that adapts to instance structure. The resulting method performs better on the constructed failure cases while remaining competitive elsewhere. The broader point is that learned classical control policies can materially improve hybrid quantum heuristics without increasing quantum depth, which is a significant practical advantage on constrained hardware. The second question evaluates whether the quantum optimization algorithm benchmarking instances we use are principled. Chapter 5 observes that much benchmarking in this space is driven by convenience. Researchers test on whatever graphs are readily available and then report aggregate performance. Instead, the chapter proposes a generative pipeline that couples a permutation-invariant graph autoencoder with evolutionary optimization to deliberately construct Max-Cut instances that strongly discriminate between a quantum-inspired solver, RQAOA, and a strong classical baseline, Goemans-Williamson, in both directions. By connecting solver behavior to structural graph features, the chapter turns benchmarking from a static choice into an interpretable experimental tool. The generated instances also expose failure modes that random graphs often fail to reveal. The third question asks what changes when realistic noise constraints are taken seriously during circuit design, not only during execution. Chapter 6 develops RLQAS, a reinforcement learning framework for quantum architecture search that incorporates noise assumptions informed by real IBM device characteristics throughout training, rather than treating noise as a post hoc correction. Paired with an efficient Pauli transfer matrix simulation, the framework makes large-scale noisy circuit search computationally feasible. The circuits it discovers are compact, trainable, and achieve competitive accuracy on ground-state energy tasks. This suggests that hardware-aware circuit design is tractable and can yield materially different choices than noise-agnostic search. The fourth question asks: even when the circuit architecture is fixed, how much of what we attribute to quantum model design is actually due to hyperparameter sensitivity? Chapter 7 extends functional ANOVA to quantum neural networks to quantify which hyperparameter choices drive performance variance. The finding is clear. Learning rate, circuit depth, and data encoding/reuploading dominate, while many architectural micro-choices contribute far less than the literature often implies. Rather than stopping at diagnosis, the chapter turns these importance rankings into data-driven priors that accelerate hyperparameter optimization. It converts a critique into a practical improvement. Taken together, these contributions form a coherent toolkit for developing and evaluating hybrid quantum–classical methods in the NISQ regime. While the work does not eliminate the fundamental constraints of shallow, noisy hardware, it clarifies what can be improved immediately and how to do so in a reproducible manner. The broader goal is to help shift near-term quantum research from isolated demonstrations toward an engineering discipline, in which algorithms, benchmarks, and model-selection practices can be compared fairly, stress-tested rigorously, and iterated systematically as hardware matures.
Near-term quantum approaches to combinatorial optimization are limited by qubit counts, circuit fidelity, sampling cost, and the difficulty of encoding constraints, while machine learning is increasingly used to configure and control quantum optimization workflows. We call such workflows adaptive: decisions conventionally fixed in advance, from formulation and penalties to shot budgets, backends, and whether to invoke a quantum processor at all, are made by learned policies that respond to the instance, the progress of the solve, or the hardware. This review examines three paradigms, AI for quantum optimization, quantum for AI-driven optimization, and AI-quantum co-optimization, and organizes the literature by the decision being learned rather than by application. A structured search identified a 119-paper corpus, of which 67 papers form an evidence core coded in detail. The evidence is considerably stronger for AI-assisted quantum optimization than for the reverse direction: learning already reduces quantum evaluations, improves initialization, supports decomposition and penalty control, and mitigates noise, whereas evidence that quantum computation improves learned optimizers remains largely confined to small-scale simulation. Experimental controls are thin: of 52 studies in the three paradigms, 22 include no classical baseline, the quantum contribution is fully isolated in 10 of 24 where an ablation applies, and the median largest experiment uses 16 qubits. We introduce an M0-M5 evidence hierarchy, from simulation to practical quantum advantage, and find no broadly convincing result at the highest level. We argue that scaling is increasingly a systems problem: the question is not only whether a problem fits on a quantum processor, but how classical and quantum resources should be allocated across the optimization process.
The rapid advancements in artificial intelligence (AI) and quantum computing have catalyzed an unprecedented shift in the methodologies utilized for healthcare diagnostics and treatment optimization. This research paper explores the integration of quantum neural networks (QNNs) with classical machine learning (ML) algorithms to enhance diagnostic accuracy, facilitate personalized treatment plans, and predict patient outcomes with a higher degree of precision. Quantum neural networks, leveraging the principles of quantum mechanics such as superposition, entanglement, and quantum parallelism, have demonstrated the potential to perform complex computations more efficiently than classical counterparts. When coupled with established machine learning algorithms, QNNs can overcome traditional limitations in data processing, enabling more sophisticated models capable of uncovering intricate patterns in large and high-dimensional datasets. Machine learning, with its vast applications in the medical field, has long been instrumental in improving diagnostics and tailoring treatment regimens to patient-specific characteristics. However, despite significant advancements, classical ML approaches face substantial challenges, particularly in terms of computational complexity and the ability to process large-scale, multi-modal healthcare data effectively. Quantum neural networks address these challenges by introducing quantum computational paradigms that facilitate exponentially faster processing, allowing for real-time analysis of vast and complex datasets. The synergy between QNNs and ML algorithms introduces novel approaches that are poised to revolutionize predictive analytics in healthcare, optimizing patient outcomes and enabling highly personalized treatment plans. A key aspect of integrating quantum neural networks into machine learning frameworks is the potential for improved precision in diagnostic systems. Traditional diagnostic procedures often rely on predefined models that may overlook nuanced correlations within patient data. Quantum neural networks, with their ability to represent and process data in a quantum space, provide a more robust framework that can adaptively learn from intricate relationships in patient information. For instance, QNNs can significantly enhance the efficacy of disease detection algorithms, such as those used for identifying early-stage cancers or predicting the onset of chronic conditions like diabetes and heart disease, by offering superior pattern recognition capabilities. Furthermore, QNNs combined with classical machine learning architectures facilitate the creation of hybrid models that harness the strengths of both approaches, leading to diagnostic tools that are not only more precise but also more adaptive to varied data sources. The integration of QNNs with machine learning extends beyond diagnostics to personalized treatment optimization. Traditional treatment planning methodologies, including rule-based and data-driven ML models, often face difficulties in accounting for the multifaceted nature of patient data and individual variability. Quantum neural networks enhance this process by leveraging quantum algorithms that provide an efficient search space for complex treatment optimization problems, allowing for a more detailed understanding of patient responses and potential treatment outcomes. The ability of QNNs to perform parallel processing enables the assessment of a wide range of treatment scenarios simultaneously, leading to more accurate predictions regarding patient reactions to specific drugs, therapies, or medical interventions. This facilitates an adaptive approach that can recommend personalized treatment regimens based on comprehensive patient profiles, ultimately enhancing patient outcomes and reducing the likelihood of adverse drug reactions. In addition to enhancing diagnostics and treatment recommendations, quantum neural networks show promise in forecasting patient outcomes by offering a more robust analysis of longitudinal patient data. Forecasting models that leverage the combined power of quantum and classical algorithms can process historical data more rapidly, allowing healthcare providers to anticipate potential health issues and intervene earlier. For example, predictive models utilizing QNNs can anticipate patient deterioration in critical care settings, facilitating timely interventions that mitigate risks and improve survival rates. Such predictive models can be instrumental in managing chronic diseases, monitoring recovery trajectories, and optimizing resource allocation within healthcare systems, thus contributing to overall efficiency and better resource management. Despite the promising capabilities of integrating QNNs with ML algorithms, there are notable challenges that need to be addressed to fully realize their potential. The practical implementation of quantum algorithms in a healthcare context faces hurdles related to hardware limitations, the need for high fidelity in quantum states, and the scalability of quantum systems to handle real-world clinical data. Additionally, the hybrid nature of combining classical and quantum approaches requires sophisticated algorithms that can bridge the gap between quantum computation and classical data processing pipelines. Solutions to these challenges may include advancements in quantum hardware, such as the development of more stable qubits and noise reduction techniques, as well as the optimization of hybrid algorithms that leverage both classical machine learning and quantum computing capabilities effectively. The exploration of quantum neural networks for healthcare applications also necessitates rigorous ethical considerations, particularly in ensuring data privacy and security. The incorporation of quantum computing must comply with healthcare data protection regulations, and quantum algorithms must be designed to maintain patient confidentiality while processing sensitive health data. Moreover, the interpretability of quantum models poses challenges that could hinder their acceptance in clinical practice. Advances in explainable AI and quantum algorithm transparency are crucial to foster trust among healthcare professionals and patients alike. Integration of quantum neural networks with classical machine learning models represents a transformative approach that could significantly advance healthcare diagnostics, personalized treatment strategies, and patient outcome prediction. By harnessing the computational advantages offered by quantum systems and the flexibility of machine learning algorithms, healthcare applications can achieve a new level of precision and adaptability. Despite current challenges, continued research into quantum algorithms, quantum hardware development, and hybrid computational models promises substantial strides in overcoming these limitations. The synergy between QNNs and ML algorithms could ultimately lead to more effective, personalized, and efficient healthcare solutions, ushering in a new era of data-driven medical care characterized by increased diagnostic accuracy and improved treatment outcomes. As the field evolves, interdisciplinary collaboration between quantum physicists, computer scientists, and healthcare professionals will be vital to unlock the full potential of these innovative computational techniques and bring them to mainstream clinical use.
Quantum Optimization (QO) is emerging as a promising approach to tackle hard combinatorial optimization problems by leveraging the unique computational properties of quantum hardware. In recent years, QO has gained traction in Machine Learning (ML), where problems such as clustering and vector quantization can be naturally expressed as Quadratic Unconstrained Binary Optimization (QUBO) problems. These ML applications often involve complex, high-dimensional data, which directly influences both the structure and scale of the resulting QUBO formulations. However, current quantum devices fall under the category of Noisy Intermediate-Scale Quantum (NISQ) hardware, which imposes significant limitations on qubit counts and small error rates. This dissertation investigates the impact of data complexity and data scale—as encountered in ML settings—on the effectiveness and feasibility of QO on NISQ devices. We propose novel, hardware-aware methods to overcome these challenges. The first part of this thesis focuses on the effect of data complexity for QO. We analyze how problem structure—particularly when QUBO formulations are derived from ML tasks—affects quantum solvability. We identify the spectral gap as a key factor in the success of adiabatic quantum algorithms and provide a theoretical and empirical analysis linking data-induced complexity to optimization performance.To address noise sensitivity and limited precision, we introduce a preprocessing framework based on a principled Branch-and-Bound algorithm that reduces dynamic range while preserving global optima. This improves robustness on both quantum annealers and classical solvers. In the second part, the thesis addresses challenges introduced by data scale. First, we propose a recursive Divide-and-Conquer strategy that breaks down large QUBO problems into tractable subproblems, demonstrated through an application to Bundle Adjustment in 3D scene reconstruction. Second, we introduce a variable and constraint generation method inspired by column generation for Integer Linear Programming, enabling dynamic QUBO size growth. This technique is successfully applied to Multi-Agent Pathfinding, where it scales well on NISQ devices while maintaining compatibility with classical solvers. Finally, we explore QUBO reformulations that reduce problem size through compact encodings and cyclic expansion, enabling the use of quantum hardware for tasks such as FPGA placement in chip design. Across all contributions, the developed algorithms are evaluated both theoretically and empirically, with experiments conducted on real quantum and quantum-inspired hardware. These methods significantly improve solution quality, scalability, and hardware compatibility, paving the way for more effective use of QO in practical settings. While tailored for NISQ era constraints, the results remain relevant for fault-tolerant quantum computing, offering insights into the long-term viability of QO across hardware generations.