A Data-Driven Exploration of Hypotheses on Disease Dynamics

Marcos L.P. Bueno; Arjen Hommersom; Peter J.F. Lucas; Joost Janzing

doi:10.1007/978-3-030-21642-9_23

A Data-Driven Exploration of Hypotheses on Disease Dynamics

Marcos L.P. Bueno^*, Arjen Hommersom, Peter J.F. Lucas, Joost Janzing

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Unsupervised learning is often used to obtain insight into the underlying structure of medical data. In this paper, we show that unsupervised methods, in particular hidden Markov models, can go beyond this by guiding the generation of clinical outcome measures and hypotheses, which play a crucial role in medical research. The usage of the data-driven approach facilitates selecting which hypotheses to further investigate. We demonstrate this by using clinical trial data for psychotic depression treatment as a case study. The discovered latent structure and proposed outcome are shown to provide new insight into the heterogeneity of psychotic depression in terms of predictive symptoms.

Original language	English
Title of host publication	Artificial Intelligence in Medicine
Subtitle of host publication	17th Conference on Artificial Intelligence in Medicine, AIME 2019, Poznan, Poland, June 26–29, 2019, Proceedings
Place of Publication	Cham
Publisher	Springer
Pages	170-179
ISBN (Electronic)	978-3-030-21642-9
ISBN (Print)	978-3-030-21641-2
DOIs	https://doi.org/10.1007/978-3-030-21642-9_23
Publication status	Published - 2019
Externally published	Yes
Event	17th Conference on Artificial Intelligence in Medicine, AIME 2019 - Poznan, Poland Duration: 26 Jun 2019 → 29 Jun 2019 Conference number: 17

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	11526
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	17th Conference on Artificial Intelligence in Medicine, AIME 2019
Abbreviated title	AIME
Country/Territory	Poland
City	Poznan
Period	26/06/19 → 29/06/19

Keywords

Artificial intelligence
Bayesian networks
Machine learning
Medical informatics
n/a OA procedure

Access to Document

10.1007/978-3-030-21642-9_23

Cite this

Bueno, M. L. P., Hommersom, A., Lucas, P. J. F., & Janzing, J. (2019). A Data-Driven Exploration of Hypotheses on Disease Dynamics. In Artificial Intelligence in Medicine: 17th Conference on Artificial Intelligence in Medicine, AIME 2019, Poznan, Poland, June 26–29, 2019, Proceedings (pp. 170-179). (Lecture Notes in Computer Science; Vol. 11526). Springer. https://doi.org/10.1007/978-3-030-21642-9_23

@inproceedings{581fe9ab81e744ed8c8db14aa43939c1,

title = "A Data-Driven Exploration of Hypotheses on Disease Dynamics",

abstract = "Unsupervised learning is often used to obtain insight into the underlying structure of medical data. In this paper, we show that unsupervised methods, in particular hidden Markov models, can go beyond this by guiding the generation of clinical outcome measures and hypotheses, which play a crucial role in medical research. The usage of the data-driven approach facilitates selecting which hypotheses to further investigate. We demonstrate this by using clinical trial data for psychotic depression treatment as a case study. The discovered latent structure and proposed outcome are shown to provide new insight into the heterogeneity of psychotic depression in terms of predictive symptoms.",

keywords = "Artificial intelligence, Bayesian networks, Machine learning, Medical informatics, n/a OA procedure",

author = "Bueno, {Marcos L.P.} and Arjen Hommersom and Lucas, {Peter J.F.} and Joost Janzing",

year = "2019",

doi = "10.1007/978-3-030-21642-9_23",

language = "English",

isbn = "978-3-030-21641-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "170--179",

booktitle = "Artificial Intelligence in Medicine",

address = "Germany",

note = "17th Conference on Artificial Intelligence in Medicine, AIME 2019, AIME ; Conference date: 26-06-2019 Through 29-06-2019",

}

Bueno, MLP, Hommersom, A, Lucas, PJF & Janzing, J 2019, A Data-Driven Exploration of Hypotheses on Disease Dynamics. in Artificial Intelligence in Medicine: 17th Conference on Artificial Intelligence in Medicine, AIME 2019, Poznan, Poland, June 26–29, 2019, Proceedings. Lecture Notes in Computer Science, vol. 11526, Springer, Cham, pp. 170-179, 17th Conference on Artificial Intelligence in Medicine, AIME 2019, Poznan, Poland, 26/06/19. https://doi.org/10.1007/978-3-030-21642-9_23

A Data-Driven Exploration of Hypotheses on Disease Dynamics. / Bueno, Marcos L.P.; Hommersom, Arjen; Lucas, Peter J.F. et al.
Artificial Intelligence in Medicine: 17th Conference on Artificial Intelligence in Medicine, AIME 2019, Poznan, Poland, June 26–29, 2019, Proceedings. Cham: Springer, 2019. p. 170-179 (Lecture Notes in Computer Science; Vol. 11526).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - A Data-Driven Exploration of Hypotheses on Disease Dynamics

AU - Bueno, Marcos L.P.

AU - Hommersom, Arjen

AU - Lucas, Peter J.F.

AU - Janzing, Joost

N1 - Conference code: 17

PY - 2019

Y1 - 2019

N2 - Unsupervised learning is often used to obtain insight into the underlying structure of medical data. In this paper, we show that unsupervised methods, in particular hidden Markov models, can go beyond this by guiding the generation of clinical outcome measures and hypotheses, which play a crucial role in medical research. The usage of the data-driven approach facilitates selecting which hypotheses to further investigate. We demonstrate this by using clinical trial data for psychotic depression treatment as a case study. The discovered latent structure and proposed outcome are shown to provide new insight into the heterogeneity of psychotic depression in terms of predictive symptoms.

AB - Unsupervised learning is often used to obtain insight into the underlying structure of medical data. In this paper, we show that unsupervised methods, in particular hidden Markov models, can go beyond this by guiding the generation of clinical outcome measures and hypotheses, which play a crucial role in medical research. The usage of the data-driven approach facilitates selecting which hypotheses to further investigate. We demonstrate this by using clinical trial data for psychotic depression treatment as a case study. The discovered latent structure and proposed outcome are shown to provide new insight into the heterogeneity of psychotic depression in terms of predictive symptoms.

KW - Artificial intelligence

KW - Bayesian networks

KW - Machine learning

KW - Medical informatics

KW - n/a OA procedure

U2 - 10.1007/978-3-030-21642-9_23

DO - 10.1007/978-3-030-21642-9_23

M3 - Conference contribution

SN - 978-3-030-21641-2

T3 - Lecture Notes in Computer Science

SP - 170

EP - 179

BT - Artificial Intelligence in Medicine

PB - Springer

CY - Cham

T2 - 17th Conference on Artificial Intelligence in Medicine, AIME 2019

Y2 - 26 June 2019 through 29 June 2019

ER -

A Data-Driven Exploration of Hypotheses on Disease Dynamics

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this