TY  - JOUR
AU  - Chiu, I-Min
AU  - Cheng, Jhu-Yin
AU  - Chen, Tien-Yu
AU  - Wang, Yi-Min
AU  - Cheng, Chi-Yung
AU  - Kung, Chia-Te
AU  - Cheng, Fu-Jen
AU  - Yau, Fei-Fei Flora
AU  - Lin, Chun-Hung Richard
PY  - 2022
DA  - 2022/12/5
TI  - Using Deep Transfer Learning to Detect Hyperkalemia From Ambulatory Electrocardiogram Monitors in Intensive Care Units: Personalized Medicine Approach
JO  - J Med Internet Res
SP  - e41163
VL  - 24
IS  - 12
KW  - deep learning
KW  - transfer learning
KW  - hyperkalemia
KW  - electrocardiogram
KW  - ECG monitor
KW  - ICU
KW  - personalized medicine
AB  - Background: Hyperkalemia is a critical condition, especially in intensive care units. So far, there have been no accurate and noninvasive methods for recognizing hyperkalemia events on ambulatory electrocardiogram monitors. Objective: This study aimed to improve the accuracy of hyperkalemia predictions from ambulatory electrocardiogram (ECG) monitors using a personalized transfer learning method; this would be done by training a generic model and refining it with personal data. Methods: This retrospective cohort study used open source data from the Waveform Database Matched Subset of the Medical Information Mart From Intensive Care III (MIMIC-III). We included patients with multiple serum potassium test results and matched ECG data from the MIMIC-III database. A 1D convolutional neural network–based deep learning model was first developed to predict hyperkalemia in a generic population. Once the model achieved a state-of-the-art performance, it was used in an active transfer learning process to perform patient-adaptive heartbeat classification tasks. Results: The results show that by acquiring data from each new patient, the personalized model can improve the accuracy of hyperkalemia detection significantly, from an average of 0.604 (SD 0.211) to 0.980 (SD 0.078), when compared with the generic model. Moreover, the area under the receiver operating characteristic curve level improved from 0.729 (SD 0.240) to 0.945 (SD 0.094). Conclusions: By using the deep transfer learning method, we were able to build a clinical standard model for hyperkalemia detection using ambulatory ECG monitors. These findings could potentially be extended to applications that continuously monitor one’s ECGs for early alerts of hyperkalemia and help avoid unnecessary blood tests. 
SN  - 1438-8871
UR  - https://www.jmir.org/2022/12/e41163
UR  - https://doi.org/10.2196/41163
UR  - http://www.ncbi.nlm.nih.gov/pubmed/36469396
DO  - 10.2196/41163
ID  - info:doi/10.2196/41163
ER  -