Predicting late symptoms of head and neck cancer treatment using LSTM and patient reported outcomes

Yaohua Wang; Lisanne Van Dijk; Abdallah S R Mohamed; Clifton David Fuller; Xinhua Zhang; G Elisabeta Marai; Guadalupe M Canahuate

doi:10.1145/3472163.3472177

Back

Predicting late symptoms of head and neck cancer treatment using LSTM and patient reported outcomes

Conference proceeding

Open access

Predicting late symptoms of head and neck cancer treatment using LSTM and patient reported outcomes

Yaohua Wang, Lisanne Van Dijk, Abdallah S R Mohamed, Clifton David Fuller, Xinhua Zhang, G Elisabeta Marai and Guadalupe M Canahuate

IDEAS '21: Proceedings of the 25th International Database Engineering & Applications Symposium, pp.273-279

IDEAS 2021: 25th International Database Engineering & Applications Symposium (Montreal, Quebec, Canada, 07/14/2021–07/16/2021)

09/07/2021

DOI: 10.1145/3472163.3472177

PMCID: PMC8982996

PMID: 35392138

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.1145/3472163.3472177View

Published (Version of record) Open Access

Abstract

Patient-Reported Outcome (PRO) surveys are used to monitor patients' symptoms during and after cancer treatment. Late symptoms refer to those experienced after treatment. While most patients experience severe symptoms during treatment, these usually subside in the late stage. However, for some patients, late toxicities persist negatively affecting the patient's quality of life (QoL). In the case of head and neck cancer patients, PRO surveys are recorded every week during the patient's visit to the clinic and at different followup times after the treatment has concluded. In this paper, we model the PRO data as a time-series and apply Long-Short Term Memory (LSTM) neural networks for predicting symptom severity in the late stage. The PRO data used in this project corresponds to MD Anderson Symptom Inventory (MDASI) questionnaires collected from head and neck cancer patients treated at the MD Anderson Cancer Center. We show that the LSTM model is effective in predicting symptom ratings under the RMSE and NRMSE metrics. Our experiments show that the LSTM model also outperforms other machine learning models and time-series prediction models for these data.

Long Short-Term Memory (LSTM)

Late Toxicity

Symptom Severity Prediction

Patient Reported Outcomes (PRO)

UIOWA OA Agreement

Details

Title: Subtitle: Predicting late symptoms of head and neck cancer treatment using LSTM and patient reported outcomes
Creators: Yaohua Wang - University of Iowa
Lisanne Van Dijk - The University of Texas MD Anderson Cancer Center
Abdallah S R Mohamed
Clifton David Fuller - The University of Texas MD Anderson Cancer Center
Xinhua Zhang - University of Illinois Chicago
G Elisabeta Marai - University of Illinois Chicago
Guadalupe M Canahuate - University of Iowa
Contributors: B C Desai (Editor)
Resource Type: Conference proceeding
Publication Details: IDEAS '21: Proceedings of the 25th International Database Engineering & Applications Symposium, pp.273-279
Conference: IDEAS 2021: 25th International Database Engineering & Applications Symposium (Montreal, Quebec, Canada, 07/14/2021–07/16/2021)
DOI: 10.1145/3472163.3472177
PMID: 35392138
PMCID: PMC8982996
Publisher: Association for Computing Machinery (ACM)
Language: English
Date published: 09/07/2021
Academic Unit: Electrical and Computer Engineering; Iowa Technology Institute; Internal Medicine
Record Identifier: 9984231912302771

Metrics

27 Record Views

17 Times Cited - Web of Science