A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS)

Abstract

Involvement of many variables, uncertainty in treatment response, and inter-patient heterogeneity challenge objective decision-making in dynamic treatment regime (DTR) in oncology. Advanced machine learning analytics in conjunction with information-rich dense multi-omics data have the ability to overcome such challenges. We have developed a comprehensive artificial intelligence (AI)-based optimal decision-making framework for assisting oncologists in DTR. In this work, we demonstrate the proposed framework to Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications by developing an interactive software tool entitled Adaptive Radiotherapy Clinical Decision Support (ARCliDS). ARCliDS is composed of two main components: Artifcial RT Environment (ARTE) and Optimal Decision Maker (ODM). ARTE is designed as a Markov decision process and modeled via supervised learning. Given a patient’s pre- and during-treatment information, ARTE can estimate treatment outcomes for a selected daily dosage value (radiation fraction size). ODM is formulated using reinforcement learning and is trained on ARTE. ODM can recommend optimal daily dosage adjustments to maximize the tumor local control probability and minimize the side effects. Graph Neural Networks (GNN) are applied to exploit the inter-feature relationships for improved modeling performance and a novel double GNN architecture is designed to avoid nonphysical treatment response. Datasets of size 117 and 292 were available from two clinical trials on adaptive RT in non-small cell lung cancer (NSCLC) patients and adaptive stereotactic body RT (SBRT) in hepatocellular carcinoma (HCC) patients, respectively. For training and validation, dense data with 297 features were available for 67 NSCLC patients and 110 features for 71 HCC patients. To increase the sample size for ODM training, we applied Generative Adversarial Networks to generate 10,000 synthetic patients. The ODM was trained on the synthetic patients and validated on the original dataset. We found that, Double GNN architecture was able to correct the nonphysical dose-response trend and improve ARCliDS recommendation. The average root mean squared difference (RMSD) between ARCliDS recommendation and reported clinical decisions using double GNNs were 0.61 [0.03] Gy/frac (mean [sem]) for adaptive RT in NSCLC patients and 2.96 [0.42] Gy/frac for adaptive SBRT HCC compared to the single GNN’s RMSDs of 0.97 [0.12] Gy/frac and 4.75 [0.16] Gy/frac, respectively. Overall, For NSCLC and HCC, ARCliDS with double GNNs was able to reproduce 36% and 50% of the good clinical decisions (local control and no side effects) and improve 74% and 30% of the bad clinical decisions, respectively. In conclusion, ARCliDS is the first web-based software dedicated to assist KBR-ART with multi-omics data. ARCliDS can learn from the reported clinical decisions and facilitate AI-assisted clinical decision-making for improving the outcomes in DTR.

404‐error “Disease not found”: Unleashing the translational potential of ‐omics approaches beyond traditional disease classification in heart failure research

“…Moreover, the notion of dynamic treatment regimens, rooted in the integration of rich molecular information, holds particular promise. 54 Given the dynamic nature of both clinical progression and molecular makeup, tailoring treatment strategies to align with changes in molecular profiles offers significant prospects for enhancing patient prognosis and managing disease evolution.…”

XAI-based Clinical Decision Support System: A Systematic Review

“…A privacy-preserving reinforcement learning framework with iterative secure computation was proposed to provide dynamic treatment decisions without leaking sensitive information to unauthorized users [3]. A reinforcement learning-based conversational software for radiotherapy was also studied, where the framework used graph neural networks and reinforcement learning to improve clinical decisionmaking performance in radiology with many variables, uncertain treatment responses, and interpatient heterogeneity [61].…”

Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration

“…An outcome prediction model can be employed to develop a decision-support system that maximizes local control and minimizes toxicities. 77,80 Niraula et al 33,81 have developed decision-making software for adaptive radiotherapy that can take in patients’ pre- and mid-treatment multiomics data and recommend optimal dose decisions for the rest of the treatment period. The decision-making tool consists of two main AI components: (i) artificial radiotherapy environment (ARTE) and (ii) optimal decision-maker (ODM).…”