Exploring the Preprocessing of a Time-Series Healthcare Administrative Dataset on Deep Learning to Improve Prediction
Preprocessing methods are important in enhancing prediction performance for time-series administrative data. This study underscores the importance of preprocessing methods by comparing two data representation techniques, that can be used with sliding window techniques for time-series administrative...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10807221/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554046390894592 |
|---|---|
| author | Faezehsadat Shahidi M. Ethan Macdonald Dallas Seitz Rebecca Barry Geoffrey Messier |
| author_facet | Faezehsadat Shahidi M. Ethan Macdonald Dallas Seitz Rebecca Barry Geoffrey Messier |
| author_sort | Faezehsadat Shahidi |
| collection | DOAJ |
| description | Preprocessing methods are important in enhancing prediction performance for time-series administrative data. This study underscores the importance of preprocessing methods by comparing two data representation techniques, that can be used with sliding window techniques for time-series administrative healthcare data, for use with gated recurrent unit (GRU) networks. The first method uses a sequence event representation and the second employs a sequence matrix representation. The evaluation was conducted through a retrospective administrative healthcare data case study to predict multiple outcomes. The target outcomes were cases where a person’s First Healthcare Encounter indicated they were experiencing Homelessness (FHE-H) or involved Police (FHE-P), as recorded in the healthcare data. Results reveal that the GRU combined with sequence matrix representation and sliding window outperformed the sequence of events with the sliding window by over 20% in the area under the curve (AUC) and sensitivity for both outcomes. Given the data used in this analysis, sequence matrix representation was superior to sequence event representation while using GRU models. The results remained consistent across the evaluation in real-world clinical frameworks using two trigger methods for prediction time, such as the sliding window and clinical demand window structures. |
| format | Article |
| id | doaj-art-837342adf93b413892fd9e0863e3aaf8 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-837342adf93b413892fd9e0863e3aaf82025-01-09T00:01:41ZengIEEEIEEE Access2169-35362025-01-01133485349610.1109/ACCESS.2024.352042510807221Exploring the Preprocessing of a Time-Series Healthcare Administrative Dataset on Deep Learning to Improve PredictionFaezehsadat Shahidi0https://orcid.org/0000-0001-5745-4300M. Ethan Macdonald1https://orcid.org/0000-0001-5421-3536Dallas Seitz2Rebecca Barry3https://orcid.org/0000-0001-6647-2703Geoffrey Messier4https://orcid.org/0000-0002-9825-3238Department of Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, CanadaDepartment of Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, CanadaHotchkiss Brain Institute, University of Calgary, Calgary, AB, CanadaHotchkiss Brain Institute, University of Calgary, Calgary, AB, CanadaDepartment of Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, CanadaPreprocessing methods are important in enhancing prediction performance for time-series administrative data. This study underscores the importance of preprocessing methods by comparing two data representation techniques, that can be used with sliding window techniques for time-series administrative healthcare data, for use with gated recurrent unit (GRU) networks. The first method uses a sequence event representation and the second employs a sequence matrix representation. The evaluation was conducted through a retrospective administrative healthcare data case study to predict multiple outcomes. The target outcomes were cases where a person’s First Healthcare Encounter indicated they were experiencing Homelessness (FHE-H) or involved Police (FHE-P), as recorded in the healthcare data. Results reveal that the GRU combined with sequence matrix representation and sliding window outperformed the sequence of events with the sliding window by over 20% in the area under the curve (AUC) and sensitivity for both outcomes. Given the data used in this analysis, sequence matrix representation was superior to sequence event representation while using GRU models. The results remained consistent across the evaluation in real-world clinical frameworks using two trigger methods for prediction time, such as the sliding window and clinical demand window structures.https://ieeexplore.ieee.org/document/10807221/Gated recurrent unit networkson clinical demand window structuresliding windowsequence of events and sequence matrix representationstime-series healthcare administrative data |
| spellingShingle | Faezehsadat Shahidi M. Ethan Macdonald Dallas Seitz Rebecca Barry Geoffrey Messier Exploring the Preprocessing of a Time-Series Healthcare Administrative Dataset on Deep Learning to Improve Prediction IEEE Access Gated recurrent unit networks on clinical demand window structure sliding window sequence of events and sequence matrix representations time-series healthcare administrative data |
| title | Exploring the Preprocessing of a Time-Series Healthcare Administrative Dataset on Deep Learning to Improve Prediction |
| title_full | Exploring the Preprocessing of a Time-Series Healthcare Administrative Dataset on Deep Learning to Improve Prediction |
| title_fullStr | Exploring the Preprocessing of a Time-Series Healthcare Administrative Dataset on Deep Learning to Improve Prediction |
| title_full_unstemmed | Exploring the Preprocessing of a Time-Series Healthcare Administrative Dataset on Deep Learning to Improve Prediction |
| title_short | Exploring the Preprocessing of a Time-Series Healthcare Administrative Dataset on Deep Learning to Improve Prediction |
| title_sort | exploring the preprocessing of a time series healthcare administrative dataset on deep learning to improve prediction |
| topic | Gated recurrent unit networks on clinical demand window structure sliding window sequence of events and sequence matrix representations time-series healthcare administrative data |
| url | https://ieeexplore.ieee.org/document/10807221/ |
| work_keys_str_mv | AT faezehsadatshahidi exploringthepreprocessingofatimeserieshealthcareadministrativedatasetondeeplearningtoimproveprediction AT methanmacdonald exploringthepreprocessingofatimeserieshealthcareadministrativedatasetondeeplearningtoimproveprediction AT dallasseitz exploringthepreprocessingofatimeserieshealthcareadministrativedatasetondeeplearningtoimproveprediction AT rebeccabarry exploringthepreprocessingofatimeserieshealthcareadministrativedatasetondeeplearningtoimproveprediction AT geoffreymessier exploringthepreprocessingofatimeserieshealthcareadministrativedatasetondeeplearningtoimproveprediction |