YEARS

2011-2016

AUTHORS

Elizabeth S Burnside

TITLE

Integrating Machine Learning and Physician Expertise for Breast Cancer Diagnosis

ABSTRACT

DESCRIPTION (provided by applicant): The goal of this research is to develop novel machine learning techniques to integrate physician expertise and machine learned, logical rules in a graphical model that will accurately estimate breast cancer risk after breast biopsy. Our multidisciplinary team has a track record (including NIH funding and publications in the medical and computer science literature) illustrating an innovative research program that merges cutting edge machine learning algorithms including inductive logic programming and statistical relational learning to train graphical models to predict breast cancer risk. However, in contrast to prior work, we are testing a completely new methodology which we call Advice-Based-Learning (ABLe). By developing ABLe, our team aims to establish an innovative, collaborative cycle between machine-learning and physician expertise. We propose to test the hypothesis that this cycle will increase accuracy beyond what either the machine or human can accomplish alone. Specifically, we hypothesize first that a conventionally-trained graphical model trained with conventional machine learning first algorithms can accurately predict the risk of breast cancer after core biopsy and perform better than current clinical practice; a critical aim that is favorably foreshadowed by our new preliminary data but is labor intensive because we must perfect our unique clinical data that accurately represents clinical experience. Second, a graphical model trained using ABLe can incorporate multi-relational data with physician expertise and significantly improve the predictive accuracy over conventionally trained graphical models and current clinical practice. Third, our best graphical model trained with ABLe will accurately estimate the probability of malignancy after breast biopsy on new clinical cases better than physicians alone resulting in a tool that has the potential to improve care. Our clinical application is as compelling as our algorithmic work. Image-guided core needle biopsy of the breast is a common procedure that is imperfect, has high-stakes, and is particularly amenable to improvement with automated decision support. Breast core biopsy, the standard of care for breast cancer diagnosis, can be non-definitive in 5-15% of women undergoing this procedure. This means that between 35,000-105,000 women will require additional biopsies or radiologic follow-up to cement a diagnosis and risk the possibility of missed breast cancers, delays in diagnosis, and unnecessary surgeries. This important problem is emblematic of a plethora of clinical situations where rigorous and accurate risk estimation of rare events provides the opportunity for automated decisions support tools to personalize and strategically target health care interventions to improve decision-making for health-care providers and patients. This award will enable us not only to produce graphical models that provide improved decision support in the breast cancer clinic, but also, and more significantly, to develop a methodology that integrates heterogeneous predictive data and physician knowledge within a graphical model, thereby developing and validating a new algorithmic paradigm for creating accurate, comprehensible, adaptable decision support tools well-suited for clinical translation.

FUNDED PUBLICATIONS

  • Pursuing optimal thresholds to recommend breast biopsy by quantifying the value of tomosynthesis.
  • Online support: Impact on anxiety in women who experience an abnormal screening mammogram.
  • Development of an online, publicly accessible naive Bayesian decision support tool for mammographic mass lesions based on the American College of Radiology (ACR) BI-RADS lexicon
  • Predicting invasive breast cancer versus DCIS in different age groups.
  • A comprehensive methodology for determining the most informative mammographic features.
  • Predicting invasive breast cancer versus DCIS in different age groups
  • Predicting malignancy from mammography findings and image-guided core biopsies.
  • Artificial neural networks in mammography interpretation and diagnostic decision making.
  • Automatic classification of mammography reports by BI-RADS breast tissue composition class.
  • What is the optimal threshold at which to recommend breast biopsy?
  • Optimal Policies for Reducing Unnecessary Follow-up Mammography Exams in Breast Cancer Diagnosis.
  • Predicting Malignancy from Mammography Findings and Surgical Biopsies.
  • A Comprehensive Methodology for Determining the Most Informative Mammographic Features
  • Addressing the challenge of assessing physician-level screening performance: mammography as an example.
  • Development of an online, publicly accessible naive Bayesian decision support tool for mammographic mass lesions based on the American College of Radiology (ACR) BI-RADS lexicon.
  • How to use: Click on a object to move its position. Double click to open its homepage. Right click to preview its contents.

    Download the RDF metadata as:   json-ld nt turtle xml License info


    34 TRIPLES      17 PREDICATES      35 URIs      9 LITERALS

    Subject Predicate Object
    1 grants:2c666ce4764c2a55044f0555fac079ac sg:abstract DESCRIPTION (provided by applicant): The goal of this research is to develop novel machine learning techniques to integrate physician expertise and machine learned, logical rules in a graphical model that will accurately estimate breast cancer risk after breast biopsy. Our multidisciplinary team has a track record (including NIH funding and publications in the medical and computer science literature) illustrating an innovative research program that merges cutting edge machine learning algorithms including inductive logic programming and statistical relational learning to train graphical models to predict breast cancer risk. However, in contrast to prior work, we are testing a completely new methodology which we call Advice-Based-Learning (ABLe). By developing ABLe, our team aims to establish an innovative, collaborative cycle between machine-learning and physician expertise. We propose to test the hypothesis that this cycle will increase accuracy beyond what either the machine or human can accomplish alone. Specifically, we hypothesize first that a conventionally-trained graphical model trained with conventional machine learning first algorithms can accurately predict the risk of breast cancer after core biopsy and perform better than current clinical practice; a critical aim that is favorably foreshadowed by our new preliminary data but is labor intensive because we must perfect our unique clinical data that accurately represents clinical experience. Second, a graphical model trained using ABLe can incorporate multi-relational data with physician expertise and significantly improve the predictive accuracy over conventionally trained graphical models and current clinical practice. Third, our best graphical model trained with ABLe will accurately estimate the probability of malignancy after breast biopsy on new clinical cases better than physicians alone resulting in a tool that has the potential to improve care. Our clinical application is as compelling as our algorithmic work. Image-guided core needle biopsy of the breast is a common procedure that is imperfect, has high-stakes, and is particularly amenable to improvement with automated decision support. Breast core biopsy, the standard of care for breast cancer diagnosis, can be non-definitive in 5-15% of women undergoing this procedure. This means that between 35,000-105,000 women will require additional biopsies or radiologic follow-up to cement a diagnosis and risk the possibility of missed breast cancers, delays in diagnosis, and unnecessary surgeries. This important problem is emblematic of a plethora of clinical situations where rigorous and accurate risk estimation of rare events provides the opportunity for automated decisions support tools to personalize and strategically target health care interventions to improve decision-making for health-care providers and patients. This award will enable us not only to produce graphical models that provide improved decision support in the breast cancer clinic, but also, and more significantly, to develop a methodology that integrates heterogeneous predictive data and physician knowledge within a graphical model, thereby developing and validating a new algorithmic paradigm for creating accurate, comprehensible, adaptable decision support tools well-suited for clinical translation.
    2 sg:endYear 2016
    3 sg:fundingAmount 1235240.0
    4 sg:fundingCurrency USD
    5 sg:hasContribution contributions:d9b45d0cdc5942191b3a38333534c3c5
    6 sg:hasFieldOfResearchCode anzsrc-for:01
    7 anzsrc-for:0104
    8 anzsrc-for:08
    9 anzsrc-for:0801
    10 sg:hasFundedPublication articles:09fec7d3dbaa1417384c23912f428568
    11 articles:1eb6780d02e73a143091bc7e939b1c0b
    12 articles:2c19f4f1114b77d3f753c2ad6f57b0d5
    13 articles:31acebab5d64a67d8af469a7f05ebb18
    14 articles:44a5739af34c4bd3f728b84e2df3374f
    15 articles:47a6c034000c9c2ca7ee9c728a574787
    16 articles:4d6454c15a43077a3e5db543f10edd1c
    17 articles:5c930be2fb2d9fef685350f5913494b6
    18 articles:7bd9e6ade4d4e1b139425c824778ffc7
    19 articles:a4955fd094313d1adf7326a1f70db91c
    20 articles:abf90f154c80867fbd9d10cd60a54e1a
    21 articles:ac5ba3164c8baea22a33a654579a19de
    22 articles:c6b8b6f63c0b4078fe5d2a4dbfbdebb3
    23 articles:d7cb5b4f90979a4eb03cd2a1e32e05cb
    24 articles:e3cbad0b72ccf2af8b0f8cd6c0dd69c4
    25 sg:hasFundingOrganization grid-institutes:grid.280285.5
    26 sg:hasRecipientOrganization grid-institutes:grid.14003.36
    27 sg:language English
    28 sg:license http://scigraph.springernature.com/explorer/license/
    29 sg:scigraphId 2c666ce4764c2a55044f0555fac079ac
    30 sg:startYear 2011
    31 sg:title Integrating Machine Learning and Physician Expertise for Breast Cancer Diagnosis
    32 sg:webpage http://projectreporter.nih.gov/project_info_description.cfm?aid=8707554
    33 rdf:type sg:Grant
    34 rdfs:label Grant: Integrating Machine Learning and Physician Expertise for Breast Cancer Diagnosis
    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular JSON format for linked data.

    curl -H 'Accept: application/ld+json' 'http://scigraph.springernature.com/things/grants/2c666ce4764c2a55044f0555fac079ac'

    N-Triples is a line-based linked data format ideal for batch operations .

    curl -H 'Accept: application/n-triples' 'http://scigraph.springernature.com/things/grants/2c666ce4764c2a55044f0555fac079ac'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'http://scigraph.springernature.com/things/grants/2c666ce4764c2a55044f0555fac079ac'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'http://scigraph.springernature.com/things/grants/2c666ce4764c2a55044f0555fac079ac'






    Preview window. Press ESC to close (or click here)


    ...