 It's difficult for an oncologist to keep up with the latest research therapies and clinical trials. Watson scales vital knowledge and helps oncologists. For the past few years, IBM has been working with leading oncologists to train Watson in the field of oncology. This demonstration of IBM Watson for Oncology, trained by Memorial Sloan Kettering, will showcase Watson's unique capability to analyze a patient's medical record to help identify for the clinician evidence-based and personalized treatment options. In this scenario, you can imagine an oncologist has logged into Watson for Oncology and is looking at the list of patients she will be seeing that day. Her next appointment is with a 62-year-old female with stage 2B breast cancer. She selects her from the list. Watson analyzes relevant portions of her electronic medical record, including her family history, notes from prior office visits, and test results. Watson will not only analyze this information, but also will summarize and highlight aspects of her records and notes that are potentially significant to her cancer, based on the expertise of leading oncologists. Watson highlights required information, information extracted from unstructured notes within the record requiring verification, and additional optional information the oncologist may choose to provide. She can also find out where this information is being pulled from by clicking on the derived buttons. Watson has the ability to understand context in a file and can make inferences using natural language processing regarding certain attributes, utilizing information in the notes and comments in the file. This is possible even if there is no specific mention of those attributes in the file. After filling out the necessary attributes, Watson will prompt the doctor to verify the information to make sure it is accurate. If a doctor is interested in finding out why these comorbidity values are relevant, click on the Watson globe to get an explanation. Here our oncologist is being prompted by Watson to add some additional information. This feature was added so a user can enter labs that they feel are relevant and skip the rest. So we can say that logically, when a user is clicking that button, it is telling Watson to ignore the labs for those not entered. In the back end, that is essentially what is happening. We assume the lab is good if it was not specified. Now the oncologist can ask Watson. In seconds, Watson analyzes the case information, identifies a prioritized list of treatment options based on Memorial Sloan Kettering expertise and training, and provides links to supporting evidence to assist Dr. Stone. Watson draws from an impressive corpus of information, including curated literature and rationales from leading oncologists, as well as over 300 medical journals, over 200 textbooks, and almost 15 million pages of text. Dr. Stone now reviews the prioritized treatment plan options for her patient. One treatment plan that Dr. Stone can choose for this patient is a multimodal approach starting with chemotherapy. If you click on the chemotherapy bar, it explains the duration of treatment, which in this case is four to six months. This timeline is the first step in fostering collaboration between the different modalities. The doctor will now look at more details about this treatment plan. The first thing she will see is information used to support the treatment option. Watson is also able to extract relevant statistics from curated literature with the appropriate source information. Here, you can see highlighted outcomes and toxicities that have been extracted and their sources. Underneath, there is supported Memorial Sloan Kettering curated literature about this treatment option. On the Additional Publications tab, you will find publications Watson has identified from its corpus that may be relevant to both the treatment option and patient case. Where available, you can also see key findings reported from those studies. Notice that to the right, we have a feature that allows the user to provide feedback seamlessly about the publications. On the Administration tab, Dr. Stone can view base dosing information supplied by Memorial Sloan Kettering. This information is for reference purposes only. Finally, on the Drug Information tab, Watson displays contraindications, precautions and adverse reactions and highlights possible matches with known patient attributes. So if you click on a specific drug, such as doxorubicin, you can then see the associated adverse reactions reported incidence percentage. After reviewing all the patient information and going through the treatment plans, the doctor now can easily share any of this information with her patient. IBM Watson for Oncology provides new opportunities for cancer care providers to zero in on the most promising care options, confidently engage with patients on a more personalized basis and make better, more informed care choices together.