Development and external validation of deep learning clinical prediction models using variable-length time series data.
J Am Med Inform Assoc
; 31(6): 1322-1330, 2024 May 20.
Article
em En
| MEDLINE
| ID: mdl-38679906
ABSTRACT
OBJECTIVES:
To compare and externally validate popular deep learning model architectures and data transformation methods for variable-length time series data in 3 clinical tasks (clinical deterioration, severe acute kidney injury [AKI], and suspected infection). MATERIALS ANDMETHODS:
This multicenter retrospective study included admissions at 2 medical centers that spanned 2007-2022. Distinct datasets were created for each clinical task, with 1 site used for training and the other for testing. Three feature engineering methods (normalization, standardization, and piece-wise linear encoding with decision trees [PLE-DTs]) and 3 architectures (long short-term memory/gated recurrent unit [LSTM/GRU], temporal convolutional network, and time-distributed wrapper with convolutional neural network [TDW-CNN]) were compared in each clinical task. Model discrimination was evaluated using the area under the precision-recall curve (AUPRC) and the area under the receiver operating characteristic curve (AUROC).RESULTS:
The study comprised 373 825 admissions for training and 256 128 admissions for testing. LSTM/GRU models tied with TDW-CNN models with both obtaining the highest mean AUPRC in 2 tasks, and LSTM/GRU had the highest mean AUROC across all tasks (deterioration 0.81, AKI 0.92, infection 0.87). PLE-DT with LSTM/GRU achieved the highest AUPRC in all tasks.DISCUSSION:
When externally validated in 3 clinical tasks, the LSTM/GRU model architecture with PLE-DT transformed data demonstrated the highest AUPRC in all tasks. Multiple models achieved similar performance when evaluated using AUROC.CONCLUSION:
The LSTM architecture performs as well or better than some newer architectures, and PLE-DT may enhance the AUPRC in variable-length time series data for predicting clinical outcomes during external validation.Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Aprendizado Profundo
Limite:
Female
/
Humans
/
Male
/
Middle aged
Idioma:
En
Revista:
J Am Med Inform Assoc
Assunto da revista:
INFORMATICA MEDICA
Ano de publicação:
2024
Tipo de documento:
Article
País de afiliação:
Estados Unidos