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 language | English (US) |
|---|---|
| Title of host publication | AAAI Workshop - Technical Report |
| Publisher | AI Access Foundation |
| Pages | 25-29 |
| Number of pages | 5 |
| Volume | WS-15-15 |
| ISBN (Print) | 9781577357261 |
| State | Published - 2015 |
| Externally published | Yes |
| Event | 29th AAAI Conference on Artificial Intelligence, AAAI 2015 - Austin, United States Duration: Jan 25 2015 → Jan 30 2015 |
Other
| Other | 29th AAAI Conference on Artificial Intelligence, AAAI 2015 |
|---|---|
| Country | United States |
| City | Austin |
| Period | 1/25/15 → 1/30/15 |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
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 proceeding › Conference contribution
}
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
AN - SCOPUS:84964615091
SN - 9781577357261
VL - WS-15-15
SP - 25
EP - 29
BT - AAAI Workshop - Technical Report
PB - AI Access Foundation
ER -