Predicting disease progression from short biomarker series using expert advice algorithm

Kai Morino, Yoshito Hirata, Ryota Tomioka, Hisashi Kashima, Kenji Yamanishi, Norihiro Hayashi, Shin Egawa, Kazuyuki Aihara

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Well-trained clinicians may be able to provide diagnosis and prognosis from very short biomarker series using information and experience gained from previous patients. Although mathematical methods can potentially help clinicians to predict the progression of diseases, there is no method so far that estimates the patient state from very short time-series of a biomarker for making diagnosis and/or prognosis by employing the information of previous patients. Here, we propose a mathematical framework for integrating other patients' datasets to infer and predict the state of the disease in the current patient based on their short history. We extend a machine-learning framework of "prediction with expert advice" to deal with unstable dynamics. We construct this mathematical framework by combining expert advice with a mathematical model of prostate cancer. Our model predicted well the individual biomarker series of patients with prostate cancer that are used as clinical samples.

Original languageEnglish
Article number8953
JournalScientific reports
Volume5
DOIs
Publication statusPublished - May 20 2015

Fingerprint

Disease Progression
Biomarkers
Prostatic Neoplasms
Theoretical Models
History

All Science Journal Classification (ASJC) codes

  • General

Cite this

Morino, K., Hirata, Y., Tomioka, R., Kashima, H., Yamanishi, K., Hayashi, N., ... Aihara, K. (2015). Predicting disease progression from short biomarker series using expert advice algorithm. Scientific reports, 5, [8953]. https://doi.org/10.1038/srep08953

Predicting disease progression from short biomarker series using expert advice algorithm. / Morino, Kai; Hirata, Yoshito; Tomioka, Ryota; Kashima, Hisashi; Yamanishi, Kenji; Hayashi, Norihiro; Egawa, Shin; Aihara, Kazuyuki.

In: Scientific reports, Vol. 5, 8953, 20.05.2015.

Research output: Contribution to journalArticle

Morino, K, Hirata, Y, Tomioka, R, Kashima, H, Yamanishi, K, Hayashi, N, Egawa, S & Aihara, K 2015, 'Predicting disease progression from short biomarker series using expert advice algorithm', Scientific reports, vol. 5, 8953. https://doi.org/10.1038/srep08953
Morino, Kai ; Hirata, Yoshito ; Tomioka, Ryota ; Kashima, Hisashi ; Yamanishi, Kenji ; Hayashi, Norihiro ; Egawa, Shin ; Aihara, Kazuyuki. / Predicting disease progression from short biomarker series using expert advice algorithm. In: Scientific reports. 2015 ; Vol. 5.
@article{b250f62bbf9846f4aed55bf462e1ca58,
title = "Predicting disease progression from short biomarker series using expert advice algorithm",
abstract = "Well-trained clinicians may be able to provide diagnosis and prognosis from very short biomarker series using information and experience gained from previous patients. Although mathematical methods can potentially help clinicians to predict the progression of diseases, there is no method so far that estimates the patient state from very short time-series of a biomarker for making diagnosis and/or prognosis by employing the information of previous patients. Here, we propose a mathematical framework for integrating other patients' datasets to infer and predict the state of the disease in the current patient based on their short history. We extend a machine-learning framework of {"}prediction with expert advice{"} to deal with unstable dynamics. We construct this mathematical framework by combining expert advice with a mathematical model of prostate cancer. Our model predicted well the individual biomarker series of patients with prostate cancer that are used as clinical samples.",
author = "Kai Morino and Yoshito Hirata and Ryota Tomioka and Hisashi Kashima and Kenji Yamanishi and Norihiro Hayashi and Shin Egawa and Kazuyuki Aihara",
year = "2015",
month = "5",
day = "20",
doi = "10.1038/srep08953",
language = "English",
volume = "5",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Predicting disease progression from short biomarker series using expert advice algorithm

AU - Morino, Kai

AU - Hirata, Yoshito

AU - Tomioka, Ryota

AU - Kashima, Hisashi

AU - Yamanishi, Kenji

AU - Hayashi, Norihiro

AU - Egawa, Shin

AU - Aihara, Kazuyuki

PY - 2015/5/20

Y1 - 2015/5/20

N2 - Well-trained clinicians may be able to provide diagnosis and prognosis from very short biomarker series using information and experience gained from previous patients. Although mathematical methods can potentially help clinicians to predict the progression of diseases, there is no method so far that estimates the patient state from very short time-series of a biomarker for making diagnosis and/or prognosis by employing the information of previous patients. Here, we propose a mathematical framework for integrating other patients' datasets to infer and predict the state of the disease in the current patient based on their short history. We extend a machine-learning framework of "prediction with expert advice" to deal with unstable dynamics. We construct this mathematical framework by combining expert advice with a mathematical model of prostate cancer. Our model predicted well the individual biomarker series of patients with prostate cancer that are used as clinical samples.

AB - Well-trained clinicians may be able to provide diagnosis and prognosis from very short biomarker series using information and experience gained from previous patients. Although mathematical methods can potentially help clinicians to predict the progression of diseases, there is no method so far that estimates the patient state from very short time-series of a biomarker for making diagnosis and/or prognosis by employing the information of previous patients. Here, we propose a mathematical framework for integrating other patients' datasets to infer and predict the state of the disease in the current patient based on their short history. We extend a machine-learning framework of "prediction with expert advice" to deal with unstable dynamics. We construct this mathematical framework by combining expert advice with a mathematical model of prostate cancer. Our model predicted well the individual biomarker series of patients with prostate cancer that are used as clinical samples.

UR - http://www.scopus.com/inward/record.url?scp=84930226442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930226442&partnerID=8YFLogxK

U2 - 10.1038/srep08953

DO - 10.1038/srep08953

M3 - Article

C2 - 25989741

AN - SCOPUS:84930226442

VL - 5

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 8953

ER -