Online transfer learning for differential diagnosis determination

Jie Xu, Daby Sow, Deepak Turaga, Mihaela Van Der Schaar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this paper we present a novel online transfer learning approach to determine the set of tests to perform, and the sequence in which they need to be performed, in order to develop an accurate diagnosis while minimizing the cost of performing the tests. Our learning approach can be incorporated as part of a clinical decision support system (CDSS) with which clinicians can interact. The approach builds on a contextual bandit framework and uses online transfer learning to overcome limitations with the availability of rich training data sets that capture different conditions, context, test results as well as outcomes. We provide confidence bounds for our recommended policies, which is essential in order to build the trust of clinicians. We evaluate the algorithm against different transfer learning approaches on real-world patient alarm datasets collected from Neurological Intensive Care Units (with reduced costs by 20%).

Original languageEnglish (US)
Title of host publicationAAAI Workshop - Technical Report
PublisherAI Access Foundation
Pages25-29
Number of pages5
VolumeWS-15-15
ISBN (Print)9781577357261
StatePublished - 2015
Externally publishedYes
Event29th AAAI Conference on Artificial Intelligence, AAAI 2015 - Austin, United States
Duration: Jan 25 2015Jan 30 2015

Other

Other29th AAAI Conference on Artificial Intelligence, AAAI 2015
CountryUnited States
CityAustin
Period1/25/151/30/15

Fingerprint

Intensive care units
Decision support systems
Costs
Availability

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Xu, J., Sow, D., Turaga, D., & Van Der Schaar, M. (2015). Online transfer learning for differential diagnosis determination. In AAAI Workshop - Technical Report (Vol. WS-15-15, pp. 25-29). AI Access Foundation.

Online transfer learning for differential diagnosis determination. / Xu, Jie; Sow, Daby; Turaga, Deepak; Van Der Schaar, Mihaela.

AAAI Workshop - Technical Report. Vol. WS-15-15 AI Access Foundation, 2015. p. 25-29.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xu, J, Sow, D, Turaga, D & Van Der Schaar, M 2015, Online transfer learning for differential diagnosis determination. in AAAI Workshop - Technical Report. vol. WS-15-15, AI Access Foundation, pp. 25-29, 29th AAAI Conference on Artificial Intelligence, AAAI 2015, Austin, United States, 1/25/15.
Xu J, Sow D, Turaga D, Van Der Schaar M. Online transfer learning for differential diagnosis determination. In AAAI Workshop - Technical Report. Vol. WS-15-15. AI Access Foundation. 2015. p. 25-29
Xu, Jie ; Sow, Daby ; Turaga, Deepak ; Van Der Schaar, Mihaela. / Online transfer learning for differential diagnosis determination. AAAI Workshop - Technical Report. Vol. WS-15-15 AI Access Foundation, 2015. pp. 25-29
@inproceedings{95b62ae9035047ecbfa13fc47ce00aef,
title = "Online transfer learning for differential diagnosis determination",
abstract = "In this paper we present a novel online transfer learning approach to determine the set of tests to perform, and the sequence in which they need to be performed, in order to develop an accurate diagnosis while minimizing the cost of performing the tests. Our learning approach can be incorporated as part of a clinical decision support system (CDSS) with which clinicians can interact. The approach builds on a contextual bandit framework and uses online transfer learning to overcome limitations with the availability of rich training data sets that capture different conditions, context, test results as well as outcomes. We provide confidence bounds for our recommended policies, which is essential in order to build the trust of clinicians. We evaluate the algorithm against different transfer learning approaches on real-world patient alarm datasets collected from Neurological Intensive Care Units (with reduced costs by 20{\%}).",
author = "Jie Xu and Daby Sow and Deepak Turaga and {Van Der Schaar}, Mihaela",
year = "2015",
language = "English (US)",
isbn = "9781577357261",
volume = "WS-15-15",
pages = "25--29",
booktitle = "AAAI Workshop - Technical Report",
publisher = "AI Access Foundation",

}

TY - GEN

T1 - Online transfer learning for differential diagnosis determination

AU - Xu, Jie

AU - Sow, Daby

AU - Turaga, Deepak

AU - Van Der Schaar, Mihaela

PY - 2015

Y1 - 2015

N2 - In this paper we present a novel online transfer learning approach to determine the set of tests to perform, and the sequence in which they need to be performed, in order to develop an accurate diagnosis while minimizing the cost of performing the tests. Our learning approach can be incorporated as part of a clinical decision support system (CDSS) with which clinicians can interact. The approach builds on a contextual bandit framework and uses online transfer learning to overcome limitations with the availability of rich training data sets that capture different conditions, context, test results as well as outcomes. We provide confidence bounds for our recommended policies, which is essential in order to build the trust of clinicians. We evaluate the algorithm against different transfer learning approaches on real-world patient alarm datasets collected from Neurological Intensive Care Units (with reduced costs by 20%).

AB - In this paper we present a novel online transfer learning approach to determine the set of tests to perform, and the sequence in which they need to be performed, in order to develop an accurate diagnosis while minimizing the cost of performing the tests. Our learning approach can be incorporated as part of a clinical decision support system (CDSS) with which clinicians can interact. The approach builds on a contextual bandit framework and uses online transfer learning to overcome limitations with the availability of rich training data sets that capture different conditions, context, test results as well as outcomes. We provide confidence bounds for our recommended policies, which is essential in order to build the trust of clinicians. We evaluate the algorithm against different transfer learning approaches on real-world patient alarm datasets collected from Neurological Intensive Care Units (with reduced costs by 20%).

UR - http://www.scopus.com/inward/record.url?scp=84964615091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964615091&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577357261

VL - WS-15-15

SP - 25

EP - 29

BT - AAAI Workshop - Technical Report

PB - AI Access Foundation

ER -