Machine learning approaches for predicting the onset time of
the adverse drug events in oncology

J 2022

Machine learning approaches for predicting the onset time of the adverse drug events in oncology

TIMILSINA, Mohan; Meera TANDAN a Vít NOVÁČEK

Základní údaje

Originální název

Machine learning approaches for predicting the onset time of the adverse drug events in oncology

Autoři

TIMILSINA, Mohan; Meera TANDAN a Vít NOVÁČEK

Vydání

Machine Learning with Applications, Elsevier, 2022, 2666-8270

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Nizozemské království

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14330/22:00135025

Organizační jednotka

Fakulta informatiky

DOI

https://doi.org/10.1016/j.mlwa.2022.100367

UT WoS

001221469200005

Klíčová slova anglicky

Regression; Onset; Drugs; Supervised; Embedding

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 2. 4. 2025 10:54, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

Predicting the onset time of adverse drug events can substantially lessen the negative impact on the prognosis of cancer patients who are often subject of aggressive and highly toxic treatment regimens. However, the laboratory verification of each patient case to study the mechanics of adverse drug events requires costly, time-intensive research. Thus, to alleviate the efforts required to tackle this problem, using computational models is highly desirable. To provide a suite of such applicable models, we used openly available adverse drug event data resources called FAERS and explored various machine learning paradigms to assess their performance in predicting adverse effect onset days (since the beginning of the treatment). Among various machine learning approaches, we observed that the graph-based embedding model, particularly ComplEx, performed better than other, more traditional machine learning approaches. The embedding learned from the ComplEX trained with k-NN regression for the downstream predictive task obtained the lowest root mean square error, which we consider very promising for further research.

Citovat

TIMILSINA, Mohan; Meera TANDAN a Vít NOVÁČEK. Machine learning approaches for predicting the onset time of the adverse drug events in oncology. Machine Learning with Applications. Elsevier, 2022, roč. 9, č. 100367, s. 1-14. ISSN 2666-8270. Dostupné z: https://doi.org/10.1016/j.mlwa.2022.100367.

@article{1862340,
   author = {Timilsina, Mohan and Tandan, Meera and Nováček, Vít},
   article_number = {100367},
   doi = {https://doi.org/10.1016/j.mlwa.2022.100367},
   keywords = {Regression; Onset; Drugs; Supervised; Embedding},
   language = {eng},
   issn = {2666-8270},
   journal = {Machine Learning with Applications},
   title = {Machine learning approaches for predicting the onset time of the adverse drug events in oncology},
   url = {https://doi.org/10.1016/j.mlwa.2022.100367},
   volume = {9},
   year = {2022}
}

TY  - JOUR
ID  - 1862340
AU  - Timilsina, Mohan - Tandan, Meera - Nováček, Vít
PY  - 2022
TI  - Machine learning approaches for predicting the onset time of the adverse drug events in oncology
JF  - Machine Learning with Applications
VL  - 9
IS  - 100367
SP  - 1-14
EP  - 1-14
PB  - Elsevier
SN  - 26668270
KW  - Regression
KW  - Onset
KW  - Drugs
KW  - Supervised
KW  - Embedding
UR  - https://doi.org/10.1016/j.mlwa.2022.100367
N2  - Predicting the onset time of adverse drug events can substantially lessen the negative impact on the prognosis of cancer patients who are often subject of aggressive and highly toxic treatment regimens. However, the laboratory verification of each patient case to study the mechanics of adverse drug events requires costly, time-intensive research. Thus, to alleviate the efforts required to tackle this problem, using computational models is highly desirable. To provide a suite of such applicable models, we used openly available adverse drug event data resources called FAERS and explored various machine learning paradigms to assess their performance in predicting adverse effect onset days (since the beginning of the treatment). Among various machine learning approaches, we observed that the graph-based embedding model, particularly ComplEx, performed better than other, more traditional machine learning approaches. The embedding learned from the ComplEX trained with k-NN regression for the downstream predictive task obtained the lowest root mean square error, which we consider very promising for further research.
ER  -

TIMILSINA, Mohan; Meera TANDAN a Vít NOVÁČEK. Machine learning approaches for predicting the onset time of the adverse drug events in oncology. \textit{Machine Learning with Applications}. Elsevier, 2022, roč.~9, č.~100367, s.~1-14. ISSN~2666-8270. Dostupné z: https://doi.org/10.1016/j.mlwa.2022.100367.

Přehled o publikaci