Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

ePoster Display

CN7 - Prediction of onset timing of breakthrough pain using deep learning model

Date

16 Sep 2021

Session

ePoster Display

Topics

Supportive and Palliative Care

Tumour Site

Presenters

Yoon Ho Choi

Citation

Annals of Oncology (2021) 32 (suppl_5): S1257-S1259. 10.1016/annonc/annonc690

Authors

Y.H. Choi1, Y.H. Bang2, M. Park3, G. Lee1, S. Shin1, S.J. Kim4

Author affiliations

  • 1 Department Of Digital Health, Samsung Advanced Institute for Health Sciences & Technology, Sungkyunkwan, 06351 - Seoul/KR
  • 2 Department Of Oncology, Asan Medical Center - University of Ulsan College of Medicine, 138-931 - Seoul/KR
  • 3 Center For Artificial Intelligence, Korea Institute of Science and Technology, 02792 - Seoul/KR
  • 4 Division Of Hematology And Oncology, Department Of Medicine, Samsung Medical Center, Sungkyunkwan University school of Medicine, 06351 - Seoul/KR

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract CN7

Background

Breakthrough cancer pain (BTcP), a transitory flare of pain that occurs on a background of relatively well-controlled baseline pain, is a challenging clinical problem in managing cancer pain. We hypothesized that the breakthrough pain could be predictable according to the patients’ previous observed patterns. In this study, we propose a deep learning model that predicts a patient’s level of BTcP per hour.

Methods

We defined the BTcP as the pain with numerical rating scale (NRS) score 4 or above and developed models predicting the onset time of BTcP with the temporal resolution of 1 hour. The dataset contains only 20 or more measured records obtained from patients admitted to the hematological oncology ward of Samsung Medical Center from July 2016 to February 2020. The model used the time windows of 3 days to predict NRS scores over the next 24 hours. To capture irregular pain patterns, we created the sequence of average pain patterns over 24 hours from the previous 3 days and used it for normalization. We trained a Bi-directional long-short term memory based deep learning model. The model was validated using the holdout method with 20% of the datasets. Its performance was assessed with the receiver operating characteristic curve (AUROC) and the precision-recall curve (AURPC).

Results

We included pain log data containing 4,660 admissions from 3,258 patients with cancer in the analysis. The median age was 57[interquartile range (IQR), 47-64], the most frequent type of cancer was lung cancer (18.0%), and most patients had stage 4 (60.7%). Among the 103,948 hours from patients in whole datasets, 1,091 (4.7%) hours were labeled as the period of BTcP. The patients have the records of NRS score with a median of 3(IQR, 2.0-4.5) and BTcP with a median of 1.1 (IQR, 0.5-2.0) per day. We allocated approximately 20% of patients (653 patients with 932 admissions) to the holdout test dataset. Our model showed AUROC of 0.719 and AUPRC 0.680 for predicting the BTcP in the test dataset.

Conclusions

Our study showed that cancer pain could be predictive by using a deep learning model. Though our exploratory study has limitation of generalization, future warranted subgroup analysis and verification research could make our model more applicable in a real-world setting.

Clinical trial identification

Editorial acknowledgement

Legal entity responsible for the study

The authors.

Funding

Has not received any funding.

Disclosure

All authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.