As AI technologies continue to evolve, they may be able to make a significant impact on patient care by reducing the amount of time physicians spend sorting through paperwork and documentation. A new analysis published by the Journal of the American College of Radiology examined this potential at length, focusing on how it applies to radiation oncology.

“The burden of clinical documentation on physicians has substantially increased in recent years due to multiple factors including the introduction of the electronic health record (EHR), the elimination of in-house transcriptionists, and value-based payment programs requiring the reporting of quality metrics,” wrote Join Y. Luh, MD, department of radiation oncology for Providence St. Joseph Health in Eureka, Calif., and colleagues. “Physicians spend an estimated 34% to 78% of their work day creating notes and reviewing medical records in the EHR, costing an estimated $90 to $140 billion in physician time per year.”

So how can AI help? According to Luh and colleagues, these solutions can help automate much of the documentation physicians face, “freeing physician time from clerical tasks, reducing burnout, preserving privacy, and organizing medical data into searchable and useable element.” EHRs, for instance, could seek out every last bit of needed context from a wide variety of places and piece them together into one helpful story that can be read in an instant. Continue reading “How AI can improve patient care in radiation oncology”

With the emergence of individualized medicine and the increasing amount and complexity of available medical data, a growing need exists for the development of clinical decision-support systems based on prediction models of treatment outcome. In radiation oncology, these models combine both predictive and prognostic data factors from clinical, imaging, molecular and other sources to achieve the highest accuracy to predict tumour response and follow-up event rates. In this Review, we provide an overview of the factors that are correlated with outcome-including survival, recurrence patterns and toxicity-in radiation oncology and discuss the methodology behind the development of prediction models, which is a multistage process. Even after initial development and clinical introduction, a truly useful predictive model will be continuously re-evaluated on different patient datasets from different regions to ensure its population-specific strength. In the future, validated decision-support systems will be fully integrated in the clinic, with data and knowledge being shared in a standardized, instant and global manner.

Continue reading “Predicting outcomes in radiation oncology – multifactorial decision support systems”

In the field of Radiation Oncology, clinical decision support has at least three main applications:

1. The pre-planning prediction of dosimetric tradeoffs to assist physicians, patients and payers alike to make better informed decisions about treatment modality and dose prescription.
2. The integration of dosimetric information with orthogonal data (e.g. genomics, imaging, EMR) to build accurate outcomes models of Tumor Control Probability (TCP) and Normal Tissue Complication Probability (NTCP).
3. Radiomics, which is a branch of medical imaging analytics that relies upon primary extraction of quantitative imaging features (e.g. texture) to predict various clinical phenomena.

Continue reading “Artificial Intelligence in Radiation Oncology: A Specialty-wide Disruptive Transformation?”