Overview of the TREC 2020 Precision Medicine Track
By Kirk Roberts, Dina Demner-Fushman, Ellen M. Voorhees, William R. Hersh, Steven Bedrick, A. Lazar, S. Pant. 2017
49 citations recorded by the source corpus.
The precision medicine paradigm focuses on identifying treatments that are best suited to an individual patient’s unique attributes. The reasoning behind this paradigm is that diseases do not uniformly manifest in people and thus “one size fits all” treatments are often not appropriate. For many diseases, such as cancer, proper selection of a treatment strategy can drastically improve results compared to the standard, frontline treatment. Generally speaking, the issues that are taken into consideration for precision medicine are the genomic, environmental, and lifestyle contexts of the patient. While precision medicine as a paradigm can be seen to broadly apply to medicine as a whole, the area where it has seen the most attention is cancer. Many cancer treatments may be lifesaving in one patient but deadly in another, primarily based on the genetic mutations of the patient’s tumor. Different treatments for the same type of cancer often target the genetic pathways applicable to the specific tumor’s genes. As a result, there has been a significant amount of effort devoted to identifying these genetic pathways, identifying potential drugs that could target different aspects of these pathways, and assessing the clinical efficacy of these drugs in human studies. This includes the Precision Medicine Initiative (Collins and Varmus, 2015) launched by President Barack Obama in 2015, now known as the All of Us Research Program. However, the micro-targeting of patients greatly increases the space of treatment options, which results in fundamental difficulties with putting the findings of precision medicine into practice (Frey et al., 2016). The number of potential treatments and the speed at which they are developed can easily overwhelm clinicians attempting to stay up-to-date with the latest findings, and can easily inhibit a clinician’s attempts to determine the best possible treatment for a particular patient. The rate of new cancer drugs being evaluated changes as quickly as once every nine months (Araya et al., 2020), so staying up to date with the latest treatment options is quite challenging for many oncologists. However, the ability to quickly locate relevant evidence is the hallmark of information retrieval (IR), so there is much potential for IR to support precision medicine in practice. For three years the TREC Clinical Decision Support (CDS) track sought to evaluate IR systems that provide medical evidence at the point-of-care. The TREC Precision Medicine track, then, was launched to specialize the CDS track to the needs of precision medicine so IR systems can focus on this important issue.
Subfields: Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Evaluation & Benchmarks
Citations in the corpus
- Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “The Precision Medicine Track, which began in TREC 2017 [Roberts et al., 2017] and continues to this day, focuses on clinical information seeking scenarios in the context of evidence-based medicine.”