![scott schwartz critical content scott schwartz critical content](https://www.brown.edu/academics/medical/anesthesiology/sites/academics-medical-anethesiology/files/styles/full_column/public/people/Kristopher-Davignon.jpg)
normal tissue side effects) in recent decades, medical physics has made significant advances in the technology and techniques of radiation delivery to spare normal tissue ( 7). To improve therapeutic ratio (i.e., the cost–benefit of tumor control vs. Technology Has Improved Normal Tissue Toxicity Advances in the last decades from the fields of radiation physics and radiation biology have focused on finding ways to separate these two effects with varying success, as discussed below.ġ.2. As Becquerel noted, tumor control and normal tissue toxicity have been, and remain, irrevocably linked. This is because dose tolerances are typically set for 5–10% toxicity in clinical trials, so the patients with the most radiosensitive normal tissue ultimately determine the limit for the maximum dosage for all patients ( 5, 6). However, acute toxicity may also constrain dose escalation, which directly limits tumor control, since a therapeutically efficacious dose may not be achievable due to toxicity. The importance of this goal has increased as cancers that were previously fatal became curable and patients have had to live with long-lasting late effects and secondary malignancies ( 3, 4).įor several tumors, an argument can be made that survival is so poor that one should not be as concerned for late effects. Ever since, the goal of therapeutic radiation has been to deliver a maximal effective dose while minimizing toxicity to normal tissues. Over 50 years before the discovery of the DNA double helix, radiation therapy and normal tissue radiobiology became irrevocably linked after Antoine Henri Becquerel left a container of radium in his vest pocket, causing a burn-like reaction of erythema followed by ulceration and necrosis ( 1, 2). Normal Tissue Toxicity Directly Limits Tumor Control We end with important lessons for the proper integration of ML into radiogenomics.ġ.1. The application of ML specifically to radiogenomics is next presented. Current ML approaches to genome-wide association studies are examined. We then introduce ML and compare it to statistical hypothesis testing to reflect on shared lessons and to avoid common pitfalls. We begin with a brief history of radiogenomics and its relationship to precision medicine. Hence, the goal of this publication is to provide an overview of ML as it applies to radiogenomics. In the field of genomics, ML methods are being used to extract harder-to-detect knowledge, but these methods have yet to fully penetrate radiogenomics. Despite significant advances in radiogenomics, the magnitude of the genetic contribution to radiation response far exceeds our current understanding of individual risk variants. Second, two patients with nearly identical dose distributions can have substantially different acute and late toxicities, resulting in lengthy treatment breaks and suboptimal control, or chronic morbidities leading to poor quality of life. First, the dose that can be delivered to the target volume may be insufficient for control but is constrained by the surrounding normal tissue, as dose escalation can lead to significant morbidity and rare. Currently, patients undergoing radiotherapy are treated using uniform dose constraints specific to the tumor and surrounding normal tissues. An emerging field in precision radiation oncology that can take advantage of ML approaches is radiogenomics, which is the study of the impact of genomic variations on the sensitivity of normal and tumor tissue to radiation. Radiation oncology is particularly suited for predictive machine learning (ML) models due to the enormous amount of diagnostic data used as input and therapeutic data generated as output. Due to the rapid increase in the availability of patient data, there is significant interest in precision medicine that could facilitate the development of a personalized treatment plan for each patient on an individual basis.