Chronic disease management often requires use of multiple drug regimens that lead to polypharmacy challenges and suboptimal utilization of healthcare services. While the rising costs and healthcare utilization associated with polypharmacy and drug interactions have been well documented, effective tools to address these challenges remain elusive. Emerging evidence that proactive medication management, combined with pharmacogenomic testing, can lead to improved health outcomes and reduced cost burdens may help to address such gaps. In this report, we describe informatic and bioanalytic methodologies that integrate weak signals in symptoms and chief complaints with pharmacogenomic analysis of ~90 single nucleotide polymorphic variants, CYP2D6 copy number, and clinical pharmacokinetic profiles to monitor drug–gene pairs and drug–drug interactions for medications with significant pharmacogenomic profiles. The utility of the approach was validated in a virtual patient case showing detection of significant drug–gene and drug–drug interactions of clinical significance. This effort is being used to establish proof-of-concept for the creation of a regional database to track clinical outcomes in patients enrolled in a bioanalytically-informed medication management program. Our integrated informatic and bioanalytic platform can provide facile clinical decision support to inform and augment medication management in the primary care setting.

Current best practices in tumor registries provide a glimpse into a limited time frame over the natural history of disease, usually a narrow window around diagnosis and biopsy. This creates challenges meeting public health and healthcare reimbursement policies that increasingly require robust documentation of long-term clinical trajectories, quality of life, and health economics outcomes. These challenges are amplified for underrepresented minority (URM) and other disadvantaged populations, who tend to view the institution of clinical research with skepticism. Participation gaps leave such populations underrepresented in clinical research and, importantly, in policy decisions about treatment choices and reimbursement, thus further augmenting health, social, and economic disparities. Cloud computing, mobile computing, digital ledgers, tokenization, and artificial intelligence technologies are powerful tools that promise to enhance longitudinal patient engagement across the natural history of disease. These tools also promise to enhance engagement by giving participants agency over their data and addressing a major impediment to research participation. This will only occur if these tools are available for use with all patients. Distributed ledger technologies (specifically blockchain) converge these tools and offer a significant element of trust that can be used to engage URM populations more substantively in clinical research. This is a crucial step toward linking composite cohorts for training and optimization of the artificial intelligence tools for enhancing public health in the future. The parameters of an idealized clinical genomic registry are presented.

Randomized controlled trials are considered the ‘gold standard’ to reduce bias by randomizing patients to an experimental intervention, versus placebo or standard of care cohort. There are inherent challenges to enrolling a standard of care or cohorts: costs, site engagement logistics, socioeconomic variability, patient willingness, ethics of placebo interventions, cannibalizing the treatment arm population, and extending study duration. The COVID-19 pandemic has magnified aspects of constraints in trial recruitment and logistics, spurring innovative approaches to reducing trial sizes, accelerating trial accrual while preserving statistical rigor. Using data from medical records and databases allows for construction of external control arms that reduce the costs of an external control arm (ECA) randomized to standard of care. Simultaneously examining covariates of the clinical outcomes in ECAs that are being measured in the interventional arm can be particularly useful in phase 2 trials to better understand social and genetic determinants of clinical outcomes that might inform pivotal trial design. The FDA and EMA have promulgated a number of publicly available guidance documents and qualification reports that inform the use of this regulatory science tool to streamline clinical development, of phase 4 surveillance, and policy aspects of clinical outcomes research. Availability and quality of real-world data (RWD) are a prevalent impediment to the use of ECAs given such data is not collected with the rigor and deliberateness that characterizes prospective interventional control arm data. Conversely, in the case of contemporary control arms, a clinical trial outcome can be compared to a contemporary standard of care in cases where the standard of care is evolving at a fast pace, such as the use of checkpoint inhibitors in cancer care. Innovative statistical methods are an essential aspect of an ECA strategy and regulatory paths for these innovative approaches have been navigated, qualified, and in some cases published.

Most forms of clinical research examine a very minute cross section of the patient journey. Much of the knowledge and evidence base driving current genomic medicine practice entails blind spots arising from underrepresentation and lack of research participation in clinicogenomic databases. The flaws are perpetuated in AI models and clinical practice guidelines that reflect the lack of diversity in data being used. Participation in clinical research and biobanks is impeded in many populations due to a variety of factors that include knowledge, trust, healthcare access, administrative barriers, and technology gaps. A recent symposium brought industry, clinical, and research participants in clinicogenomics to discuss practical challenges and potential for new data sharing models that are patient centric and federated in nature and can address health disparities that might be perpetuated by lack of diversity in clinicogenomic research, biobanks, and datasets. Clinical data governance was recognized as a multiagent problem, and governance practices need to be more patient centric to address most barriers. Digital tools that preserve privacy, document provenance, and enable the management of data as intellectual property have great promise. Policy updates realigning and rationalizing clinical data governance practices are warranted.

Glioblastoma is an aggressive central nervous system tumor characterized by diffuse infiltration. Despite substantial advances in oncology, survival outcomes have shown little improvement over the past three decades. Radiotherapy remains a cornerstone of treatment; however, it faces several challenges, including considerable inter-observer variability in clinical target volume delineation, dose constraints associated with adjacent organs at risk, and the persistently poor prognosis of affected patients. Recent advances in artificial intelligence, particularly deep learning, have shown promise in automating radiation therapy mapping to improve consistency, accuracy, and efficiency. This narrative review explores current auto segmentation frameworks, dose mapping, and biologically informed radiotherapy planning guided by multimodal imaging and mathematical modeling. Studies have demonstrated reproducible tumor segmentations with DSCs exceeding 0.90, reduced planning within minutes, and emerging predictive capabilities for treatment response. Radiogenomic integration has enabled imaging-based classification of critical biomarkers with high accuracy, reinforcing the potential of deep learning models in personalized radiotherapy. Despite these innovations, deployment into clinical practice remains limited, primarily due to insufficient external validation and single-institution training datasets. This review emphasizes the importance of large, annotated imaging datasets, multi-institutional collaboration, and biologically explainable modeling to successfully translate deep learning into glioblastoma radiation planning and longitudinal monitoring.

Cloud and distributed computing, code repositories, and large language models are democratizing the less computationally intensive use cases of artificial intelligence (AI) in medicine. The convergence and democratization of these powerful tools promises to mobilize and utilize humanity’s knowledge and data, at least the knowledge bases and data that are readily available in the public commons. Healthcare represents a challenge due to fragmentation of the data fabric and governance mechanisms intrinsic to that sector of the economy. Privacy laws, stewardship practices, and the fragmented nature of the patient data journey (medical record silos) create cumbersome impediments to health data sharing, particularly longitudinal patient‐level data. Consequently, obtaining the data necessary to train and operationalize AI in many healthcare and clinical genomics use cases limits the promise of these new technologies in addressing complexities in healthcare. We posit that trust, provenance, and fitness of health data and transaction costs represent challenges that blockchain ledgers and smart digital contracts might address. Here, we present frameworks from some of the great economic thinkers that might help address some of the stewardship and agency issues inherent to health data sharing. Our goal is to promote a more equitable and patient‐centric healthcare data fabric to address current challenges of healthcare.