Limits...
Leveraging Expert Knowledge to Improve Machine-Learned Decision Support Systems.

Kuusisto F, Dutra I, Elezaby M, Mendonça EA, Shavlik J, Burnside ES - AMIA Jt Summits Transl Sci Proc (2015)

Bottom Line: While the use of machine learning methods in clinical decision support has great potential for improving patient care, acquiring standardized, complete, and sufficient training data presents a major challenge for methods relying exclusively on machine learning techniques.Domain experts possess knowledge that can address these challenges and guide model development.By applying ABLe to this task, we demonstrate a statistically significant improvement in specificity (24.0% with p=0.004) without missing a single malignancy.

View Article: PubMed Central - PubMed

Affiliation: University of Wisconsin, Madison, USA.

ABSTRACT
While the use of machine learning methods in clinical decision support has great potential for improving patient care, acquiring standardized, complete, and sufficient training data presents a major challenge for methods relying exclusively on machine learning techniques. Domain experts possess knowledge that can address these challenges and guide model development. We present Advice-Based-Learning (ABLe), a framework for incorporating expert clinical knowledge into machine learning models, and show results for an example task: estimating the probability of malignancy following a non-definitive breast core needle biopsy. By applying ABLe to this task, we demonstrate a statistically significant improvement in specificity (24.0% with p=0.004) without missing a single malignancy.

No MeSH data available.


Related in: MedlinePlus

The ABLe Framework.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4525246&req=5

f1-2089777: The ABLe Framework.

Mentions: Our ABLe framework (Figure 1) includes: (1) definitions and (2) iterative steps.


Leveraging Expert Knowledge to Improve Machine-Learned Decision Support Systems.

Kuusisto F, Dutra I, Elezaby M, Mendonça EA, Shavlik J, Burnside ES - AMIA Jt Summits Transl Sci Proc (2015)

The ABLe Framework.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4525246&req=5

f1-2089777: The ABLe Framework.
Mentions: Our ABLe framework (Figure 1) includes: (1) definitions and (2) iterative steps.

Bottom Line: While the use of machine learning methods in clinical decision support has great potential for improving patient care, acquiring standardized, complete, and sufficient training data presents a major challenge for methods relying exclusively on machine learning techniques.Domain experts possess knowledge that can address these challenges and guide model development.By applying ABLe to this task, we demonstrate a statistically significant improvement in specificity (24.0% with p=0.004) without missing a single malignancy.

View Article: PubMed Central - PubMed

Affiliation: University of Wisconsin, Madison, USA.

ABSTRACT
While the use of machine learning methods in clinical decision support has great potential for improving patient care, acquiring standardized, complete, and sufficient training data presents a major challenge for methods relying exclusively on machine learning techniques. Domain experts possess knowledge that can address these challenges and guide model development. We present Advice-Based-Learning (ABLe), a framework for incorporating expert clinical knowledge into machine learning models, and show results for an example task: estimating the probability of malignancy following a non-definitive breast core needle biopsy. By applying ABLe to this task, we demonstrate a statistically significant improvement in specificity (24.0% with p=0.004) without missing a single malignancy.

No MeSH data available.


Related in: MedlinePlus