An uncertainty-based interpretable deep learning framework for predicting breast cancer outcome
© 2024. The Author(s)..
BACKGROUND: Predicting outcome of breast cancer is important for selecting appropriate treatments and prolonging the survival periods of patients. Recently, different deep learning-based methods have been carefully designed for cancer outcome prediction. However, the application of these methods is still challenged by interpretability. In this study, we proposed a novel multitask deep neural network called UISNet to predict the outcome of breast cancer. The UISNet is able to interpret the importance of features for the prediction model via an uncertainty-based integrated gradients algorithm. UISNet improved the prediction by introducing prior biological pathway knowledge and utilizing patient heterogeneity information.
RESULTS: The model was tested in seven public datasets of breast cancer, and showed better performance (average C-index = 0.691) than the state-of-the-art methods (average C-index = 0.650, ranged from 0.619 to 0.677). Importantly, the UISNet identified 20 genes as associated with breast cancer, among which 11 have been proven to be associated with breast cancer by previous studies, and others are novel findings of this study.
CONCLUSIONS: Our proposed method is accurate and robust in predicting breast cancer outcomes, and it is an effective way to identify breast cancer-associated genes. The method codes are available at: https://github.com/chh171/UISNet.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:25 |
---|---|
Enthalten in: |
BMC bioinformatics - 25(2024), 1 vom: 29. Feb., Seite 88 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Chai, Hua [VerfasserIn] |
---|
Links: |
---|
Themen: |
Breast cancer |
---|
Anmerkungen: |
Date Completed 01.03.2024 Date Revised 02.03.2024 published: Electronic Citation Status MEDLINE |
---|
doi: |
10.1186/s12859-024-05716-7 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM369088581 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM369088581 | ||
003 | DE-627 | ||
005 | 20240302232645.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240229s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1186/s12859-024-05716-7 |2 doi | |
028 | 5 | 2 | |a pubmed24n1314.xml |
035 | |a (DE-627)NLM369088581 | ||
035 | |a (NLM)38418940 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Chai, Hua |e verfasserin |4 aut | |
245 | 1 | 3 | |a An uncertainty-based interpretable deep learning framework for predicting breast cancer outcome |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 01.03.2024 | ||
500 | |a Date Revised 02.03.2024 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2024. The Author(s). | ||
520 | |a BACKGROUND: Predicting outcome of breast cancer is important for selecting appropriate treatments and prolonging the survival periods of patients. Recently, different deep learning-based methods have been carefully designed for cancer outcome prediction. However, the application of these methods is still challenged by interpretability. In this study, we proposed a novel multitask deep neural network called UISNet to predict the outcome of breast cancer. The UISNet is able to interpret the importance of features for the prediction model via an uncertainty-based integrated gradients algorithm. UISNet improved the prediction by introducing prior biological pathway knowledge and utilizing patient heterogeneity information | ||
520 | |a RESULTS: The model was tested in seven public datasets of breast cancer, and showed better performance (average C-index = 0.691) than the state-of-the-art methods (average C-index = 0.650, ranged from 0.619 to 0.677). Importantly, the UISNet identified 20 genes as associated with breast cancer, among which 11 have been proven to be associated with breast cancer by previous studies, and others are novel findings of this study | ||
520 | |a CONCLUSIONS: Our proposed method is accurate and robust in predicting breast cancer outcomes, and it is an effective way to identify breast cancer-associated genes. The method codes are available at: https://github.com/chh171/UISNet | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Breast cancer | |
650 | 4 | |a Deep learning | |
650 | 4 | |a Prognosis analysis | |
650 | 4 | |a Survival analysis | |
700 | 1 | |a Lin, Siyin |e verfasserin |4 aut | |
700 | 1 | |a Lin, Junqi |e verfasserin |4 aut | |
700 | 1 | |a He, Minfan |e verfasserin |4 aut | |
700 | 1 | |a Yang, Yuedong |e verfasserin |4 aut | |
700 | 1 | |a OuYang, Yongzhong |e verfasserin |4 aut | |
700 | 1 | |a Zhao, Huiying |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t BMC bioinformatics |d 2000 |g 25(2024), 1 vom: 29. Feb., Seite 88 |w (DE-627)NLM109215982 |x 1471-2105 |7 nnns |
773 | 1 | 8 | |g volume:25 |g year:2024 |g number:1 |g day:29 |g month:02 |g pages:88 |
856 | 4 | 0 | |u http://dx.doi.org/10.1186/s12859-024-05716-7 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 25 |j 2024 |e 1 |b 29 |c 02 |h 88 |