DeepPhe Software
The DeepPhe software tools use a combination of natural language processing, machine learning, visual analytics, a rich ontology and ontology-based summarization to extract longitudinal histories from cancer clinical notes.
DeepPhe can provide summary phenotype and patient information as well as facilitate retrospective cancer cohort research.
Built on the widely-used cTAKES NLP platform, DeepPhe can extract tumor characteristics, treatments, biomarkers and comorbidity information, as well as classify clinical notes in to treatment episodes.
DeepPhe can produce results many output formats, as well as store information in a graph database supported by a REST API.
DeepPhe (base)
The base DeepPhe system processes corpora of patient notes, extracting mentions and attributes of key cancer concepts from individual notes and integrating the information within and across documents to build a high-level summary of a patient’s case. DeepPhe also contains machine learning trained classifiers capable of labeling individual notes according to the phase of treatment (pre-diagnostic, diagnostic, treatment, etc.).
Supported by the National Cancer Institute’s Information Technology for Cancer Research (ITCR) initiative (Grant #U24CA248010) and the National Cancer Institute’s Surveillance, Epidemiology, and End Results (SEER) program (Grant #UH3CA243120).
DeepPhe-XN
The DeepPhe tool for Translational Research (DeepPhe-XN) builds upon the base DeepPhe platform to provide extensive information useful for translational cancer research. Results from processing are stored in a Neo4J database that can be utilized by DeepPhe-Viz.
There is a DeepPhe-XN WIKI with information on installation and use.
Supported by the National Cancer Institute’s Information Technology for Cancer Research (ITCR) initiative (Grant #U24CA248010).
DeepPhe-Viz
DeepPhe results that are stored in a Neo4J database such as those created by DeepPhe-XN can be utilized with the DeepPhe visual analytics tool (DeepPhe-Viz), which provides a web-based interface to data, supporting review of both cohorts and individual patient records.
Supported by the National Cancer Institute’s Information Technology for Cancer Research (ITCR) initiative (Grant #U24CA248010).
DeepPhe-CR
The DeepPhe tool for Cancer Registries (DeepPhe-CR)
builds upon the base DeepPhe platform to provide REST-APIs
for submissions of documents to the DeepPhe pipeline and return of extracted results,
with the goal of providing DeepPhe services to tools for cancer patient data abstraction.
Developed in support of cancer registries from the NCI
Surveillance, Epidemiology, and End Results (SEER) Program,
DeepPhe-CR provides web-services suitable for integration into existing registry
case abstraction tools.
DeepPhe-CR tools are provided as a suite of Docker containers supporting ease
of installation and operation.
DeepPhe-CR has been developed in partnership with the
Kentucky Cancer Registry.
There is a DeepPhe-CR WIKI with information on installation and use.
A collaboration with the National Cancer Institute’s Surveillance, Epidemiology, and End Results (SEER) Program (Grant #UH3CA243120).
