Improving Prediction of Late Symptoms using LSTM and Patient-reported Outcomes for Head and Neck Cancer Patients

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

doi:10.1109/ICHI57859.2023.00047

Conference proceeding

Improving Prediction of Late Symptoms using LSTM and Patient-reported Outcomes for Head and Neck Cancer Patients

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

2023 IEEE 11th International Conference on Healthcare Informatics (ICHI), pp.292-300

06/26/2023

DOI: 10.1109/ICHI57859.2023.00047

Files and links (1)

url

https://pmc.ncbi.nlm.nih.gov/articles/PMC10853990/pdf/nihms-1960493.pdfView

Open Access

Abstract

Patient-Reported Outcomes (PRO) are collected directly from the patients using symptom questionnaires. In the case of head and neck cancer patients, PRO surveys are recorded every week during treatment with each patient's visit to the clinic and at different follow-up times after the treatment has concluded. PRO surveys can be very informative regarding the patient's status and the effect of treatment on the patient's quality of life (QoL). Processing PRO data is challenging for several reasons. First, missing data is frequent as patients might skip a question or a questionnaire altogether. Second, PROs are patient-dependent, a rating of 5 for one patient might be a rating of 10 for another patient. Finally, most patients experience severe symptoms during treatment which usually subside over time. However, for some patients, late toxicities persist negatively affecting the patient's QoL. These long-term severe symptoms are hard to predict and are the focus of this study. In this work, we model PRO data collected from head and neck cancer patients treated at the MD Anderson Cancer Center using the MD Anderson Symptom Inventory (MDASI) questionnaire as time series. We impute missing values with a combination of K nearest neighbor (KNN) and Long Short-Term Memory (LSTM) neural networks, and finally, apply LSTM to predict late symptom severity 12 months after treatment. We compare performance against clinical and ARIMA models. We show that the LSTM model combined with KNN imputation is effective in predicting late-stage symptom ratings for occurrence and severity under the AUC and F1 score metrics.

Time Series Analysis

Toxicology

KNN Baseline Imputation

Late Toxicity

Long Short-Term Memory (LSTM)

Magnetic heads

Measurement

Neural networks

Patient Reported Outcomes (PRO)

Predictive models

Surveys

Symptom Severity Prediction

Details

Title: Subtitle: Improving Prediction of Late Symptoms using LSTM and Patient-reported Outcomes for Head and Neck Cancer Patients
Creators: Yaohua Wang - University of Iowa
Lisanne Van Dijk - UT M. D. Anderson Cancer Center,Radiation Oncology,Houston,United States
Abdallah S. R. Mohamed - The University of Texas MD Anderson Cancer Center
Mohamed Naser - The University of Texas MD Anderson Cancer Center
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 Canahuate - University of Iowa
Resource Type: Conference proceeding
Publication Details: 2023 IEEE 11th International Conference on Healthcare Informatics (ICHI), pp.292-300
DOI: 10.1109/ICHI57859.2023.00047
eISSN: 2575-2634
Publisher: IEEE
Language: English
Date published: 06/26/2023
Academic Unit: Electrical and Computer Engineering; Internal Medicine
Record Identifier: 9984532055702771

Metrics

14 Record Views