Beyond Jeopardy!: Harnessing IBM's Watson to improve oncology decision making.

Abstract

6508 Background: Electronic decision support is increasingly prevalent in clinical practice. Traditional tools map guidelines into an interactive platform. An alternative method builds on experience-based learning. Methods: Memorial Sloan-Kettering (MSK), IBM and WellPoint teamed to develop IBM Watson – a cognitive computing system leveraging natural language processing (NLP), machine learning (ML) and massive parallel processing – to help inform clinical decision making. We made a prototype for lung cancers using manufactured and anonymized patient cases. We configured this tool to read medical language and extract specific attributes from each case to identify appropriate treatment options benchmarked against MSK expertise, anonymized patient cases and published evidence. Treatment options reflect consensus guidelines and MSK best practices where guidelines are not granular enough to match treatments to unique patients. Analysis and building accuracy is ongoing and iterative. Results: 420 manufactured and 525 anonymized patient cases trained the initial models. Early results show accuracy improvement in NLP and ML in identifying treatment options (Table). All treatment plans were guideline adherent. A proportion of cases showed the need to incorporate tailored treatment plans reflecting MSK’s practice beyond guidelines – e.g. 11% of cases required addressing a site of critical metastasis before initiating guideline supported treatment. Conclusions: IBM Watson is extracting information from free text medical records that supports building ML models to assist in selecting treatments for persons with lung cancers. This tool can select treatment options from consensus guidelines, and, through ML, it will identify personalized treatment plans. Training is ongoing to improve individualized decision making and optimize the web-based tool that connects with IBM Watson. [Table: see text]

The first steps in the evaluation of a "black-box" decision support tool: a protocol and feasibility study for the evaluation of Watson for Oncology

“…One of these tools is IBM Watson for Oncology (abbreviated as Watson) [2][3][4]. Watson uses natural language processing to extract data from free text in medical records and select treatments from consensus guidelines [5]. Its selection of treatments is refined using machine learning, trained by specialists from New York's Memorial Sloan Kettering Cancer Center [5].…”

“…Watson uses natural language processing to extract data from free text in medical records and select treatments from consensus guidelines [5]. Its selection of treatments is refined using machine learning, trained by specialists from New York's Memorial Sloan Kettering Cancer Center [5]. This combination of technologies has the potential to solve two major problems in the field of decision support: harnessing data from poorly-structured medical record data and keeping the medical knowledge base of the system upto-date [6].…”

“…months to years). By automatically integrating evidence [7], Watson has the potential to offer advice that is more up-to-date, as well as offer more personalized advice through case-based reasoning [5].…”

Text-Based Age and Gender Prediction for Online Safety Monitoring

“…The last decade has seen a large improvement in the accuracy and applicability of techniques for knowledge discovery from text (also called text mining or text analytics). The type of knowledge extracted can be factual, for example for use in medical expert systems (IBM's Watson for oncology application is a good example [ 1]), or it can be subjective as in the many sentiment analysis applications where opinions or sentiments of authors are targeted (see [ 2,3] for applications to political media coverage analysis and economic prediction). In this paper, we look at a more recent type of knowledge discovery from text, namely author profiling: the extraction of demographic and psychological characteristics of authors from text they have written [ 4,5].…”