Leveraging auxiliary measures: a deep multi-task neural network for predictive modeling in clinical research
Abstract Background Accurate predictive modeling in clinical research enables effective early intervention that patients are most likely to benefit from. However, due to the complex biological nature of disease progression, capturing the highly non-linear information from low-level input features is...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-12-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12911-018-0676-9 |
| _version_ | 1818294692483170304 |
|---|---|
| author | Xiangrui Li Dongxiao Zhu Phillip Levy |
| author_facet | Xiangrui Li Dongxiao Zhu Phillip Levy |
| author_sort | Xiangrui Li |
| collection | DOAJ |
| description | Abstract Background Accurate predictive modeling in clinical research enables effective early intervention that patients are most likely to benefit from. However, due to the complex biological nature of disease progression, capturing the highly non-linear information from low-level input features is quite challenging. This requires predictive models with high-capacity. In practice, clinical datasets are often of limited size, bringing danger of overfitting for high-capacity models. To address these two challenges, we propose a deep multi-task neural network for predictive modeling. Methods The proposed network leverages clinical measures as auxiliary targets that are related to the primary target. The predictions for the primary and auxiliary targets are made simultaneously by the neural network. Network structure is specifically designed to capture the clinical relevance by learning a shared feature representation between the primary and auxiliary targets. We apply the proposed model in a hypertension dataset and a breast cancer dataset, where the primary tasks are to predict the left ventricular mass indexed to body surface area and the time of recurrence of breast cancer. Moreover, we analyze the weights of the proposed neural network to rank input features for model interpretability. Results The experimental results indicate that the proposed model outperforms other different models, achieving the best predictive accuracy (mean squared error 199.76 for hypertension data, 860.62 for Wisconsin prognostic breast cancer data) with the ability to rank features according to their contributions to the targets. The ranking is supported by previous related research. Conclusion We propose a novel effective method for clinical predictive modeling by combing the deep neural network and multi-task learning. By leveraging auxiliary measures clinically related to the primary target, our method improves the predictive accuracy. Based on featue ranking, our model is interpreted and shows consistency with previous studies on cardiovascular diseases and cancers. |
| first_indexed | 2024-12-13T03:35:47Z |
| format | Article |
| id | doaj.art-9e4df23e68d2458d8c66ccbd289cd28e |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-12-13T03:35:47Z |
| publishDate | 2018-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-9e4df23e68d2458d8c66ccbd289cd28e2022-12-22T00:01:03ZengBMCBMC Medical Informatics and Decision Making1472-69472018-12-0118S4455310.1186/s12911-018-0676-9Leveraging auxiliary measures: a deep multi-task neural network for predictive modeling in clinical researchXiangrui Li0Dongxiao Zhu1Phillip Levy2Department of Computer Science, Wayne State UniversityDepartment of Computer Science, Wayne State UniversityDepartment of Emergency Medicine, Wayne State UniversityAbstract Background Accurate predictive modeling in clinical research enables effective early intervention that patients are most likely to benefit from. However, due to the complex biological nature of disease progression, capturing the highly non-linear information from low-level input features is quite challenging. This requires predictive models with high-capacity. In practice, clinical datasets are often of limited size, bringing danger of overfitting for high-capacity models. To address these two challenges, we propose a deep multi-task neural network for predictive modeling. Methods The proposed network leverages clinical measures as auxiliary targets that are related to the primary target. The predictions for the primary and auxiliary targets are made simultaneously by the neural network. Network structure is specifically designed to capture the clinical relevance by learning a shared feature representation between the primary and auxiliary targets. We apply the proposed model in a hypertension dataset and a breast cancer dataset, where the primary tasks are to predict the left ventricular mass indexed to body surface area and the time of recurrence of breast cancer. Moreover, we analyze the weights of the proposed neural network to rank input features for model interpretability. Results The experimental results indicate that the proposed model outperforms other different models, achieving the best predictive accuracy (mean squared error 199.76 for hypertension data, 860.62 for Wisconsin prognostic breast cancer data) with the ability to rank features according to their contributions to the targets. The ranking is supported by previous related research. Conclusion We propose a novel effective method for clinical predictive modeling by combing the deep neural network and multi-task learning. By leveraging auxiliary measures clinically related to the primary target, our method improves the predictive accuracy. Based on featue ranking, our model is interpreted and shows consistency with previous studies on cardiovascular diseases and cancers.http://link.springer.com/article/10.1186/s12911-018-0676-9Predictive modelingDeep neural networkAuxiliary taskMulti-task learning |
| spellingShingle | Xiangrui Li Dongxiao Zhu Phillip Levy Leveraging auxiliary measures: a deep multi-task neural network for predictive modeling in clinical research BMC Medical Informatics and Decision Making Predictive modeling Deep neural network Auxiliary task Multi-task learning |
| title | Leveraging auxiliary measures: a deep multi-task neural network for predictive modeling in clinical research |
| title_full | Leveraging auxiliary measures: a deep multi-task neural network for predictive modeling in clinical research |
| title_fullStr | Leveraging auxiliary measures: a deep multi-task neural network for predictive modeling in clinical research |
| title_full_unstemmed | Leveraging auxiliary measures: a deep multi-task neural network for predictive modeling in clinical research |
| title_short | Leveraging auxiliary measures: a deep multi-task neural network for predictive modeling in clinical research |
| title_sort | leveraging auxiliary measures a deep multi task neural network for predictive modeling in clinical research |
| topic | Predictive modeling Deep neural network Auxiliary task Multi-task learning |
| url | http://link.springer.com/article/10.1186/s12911-018-0676-9 |
| work_keys_str_mv | AT xiangruili leveragingauxiliarymeasuresadeepmultitaskneuralnetworkforpredictivemodelinginclinicalresearch AT dongxiaozhu leveragingauxiliarymeasuresadeepmultitaskneuralnetworkforpredictivemodelinginclinicalresearch AT philliplevy leveragingauxiliarymeasuresadeepmultitaskneuralnetworkforpredictivemodelinginclinicalresearch |