Jaehun Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jaehun Choi has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Heung-Il Suk
Korea University, Seoul, Republic of Korea
4 shared publications - Hwin Dol Park
Medical Information Research Section, Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea
3 shared publications - Soo Jun Park
Digital Biomedical Research Division, Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea
3 shared publications - Ahmad Wisnu Mulyadi
Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea
2 shared publications - Eunji Jun
Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea
2 shared publications - Gil-Jin Jang
School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of Korea
2 shared publications
Latest Publications
- Open Access
- 11 November 2026
- Published by MDPI AG in Healthcare
- Vol. 14  (22) , 3869
Multi-Type Clinical Interaction Modeling for Identifying Factors Associated with Cardiovascular Disease in Obstructive Sleep Apnea via an Interpretable Heterogeneous Graph Transformer
Background/Objectives: Obstructive sleep apnea (OSA) is a prevalent sleep disorder strongly associated with an increased risk of cardiovascular disease (CVD). The relationship between OSA and CVD is complex, involving multiple physiological and clinical factors. Identifying key contributors to cardiovascular risk in OSA patients is essential for early intervention, personalized treatment, and improved patient outcomes. Methods: We propose a heterogeneous graph learning model, RiskHGT, to identify influential clinical factors and interaction patterns associated with CVD in a cross-sectional analysis distinguishing OSA patients with and without prevalent CVD. By leveraging the advantages of heterogeneous graphs in modeling multi-relational medical data, RiskHGT captures intricate relationships among clinical factors and enables interpretation of the most influential factors associated with CVD in OSA patients. The model was trained and evaluated on two large-scale clinical sleep cohorts, the Sleep Heart Health Study (SHHS) and the Multi-Ethnic Study of Atherosclerosis (MESA), with predictive performance assessed using the area under the receiver operating characteristic curve (AUROC) and the area under the precision–recall curve (AUPRC). Results: RiskHGT achieved superior predictive performance compared with baseline machine learning and graph-based models, reaching an AUROC of up to 0.94 and an AUPRC of up to 0.90. Fasting glucose, diastolic blood pressure, smoking status, and age were identified as the factors most strongly associated with CVD in OSA patients. Conclusions: RiskHGT provides interpretable, attention-based insights into clinical factors associated with CVD in patients with OSA. The framework may have potential for clinical use, but external and prospective validation is required before any clinical application.
- 11 November 2026
- Published by MDPI AG in Healthcare
- Vol. 14  (22) , 3869
Open AccessMulti-Type Clinical Interaction Modeling for Identifying Factors Associated with Cardiovascular Disease in Obstructive Sleep Apnea via an Interpretable Heterogeneous Graph Transformer
Background/Objectives: Obstructive sleep apnea (OSA) is a prevalent sleep disorder strongly associated with an increased risk of cardiovascular disease (CVD). The relationship between OSA and CVD is complex, involving multiple physiological and clinical factors. Identifying key contributors to cardiovascular risk in OSA patients is essential for early intervention, personalized treatment, and improved patient outcomes. Methods: We propose a heterogeneous graph learning model, RiskHGT, to identify influential clinical factors and interaction patterns associated with CVD in a cross-sectional analysis distinguishing OSA patients with and without prevalent CVD. By leveraging the advantages of heterogeneous graphs in modeling multi-relational medical data, RiskHGT captures intricate relationships among clinical factors and enables interpretation of the most influential factors associated with CVD in OSA patients. The model was trained and evaluated on two large-scale clinical sleep cohorts, the Sleep Heart Health Study (SHHS) and the Multi-Ethnic Study of Atherosclerosis (MESA), with predictive performance assessed using the area under the receiver operating characteristic curve (AUROC) and the area under the precision–recall curve (AUPRC). Results: RiskHGT achieved superior predictive performance compared with baseline machine learning and graph-based models, reaching an AUROC of up to 0.94 and an AUPRC of up to 0.90. Fasting glucose, diastolic blood pressure, smoking status, and age were identified as the factors most strongly associated with CVD in OSA patients. Conclusions: RiskHGT provides interpretable, attention-based insights into clinical factors associated with CVD in patients with OSA. The framework may have potential for clinical use, but external and prospective validation is required before any clinical application.
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP  (21682194) , 1-14
DDRL:Dyna-Based Discriminative Reinforcement Learning for Optimizing Sepsis Treatment Pathways in Offline Environments
Optimizing automated sepsis treatment policies using Reinforcement Learning (RL) has gained attention for improving quality of medical care and address physician shortages. However, in an offline setting, an RL agent cannot explore all possible treatment episodes, leading to an overestimation of Q-values for unexplored treatments. This causes a significant deviation from the physician's policy and results in the RL policy converging to a suboptimal policy. To address this problem, we propose Dyna-Based Discriminative Reinforcement Learning (DDRL), which aims to learn an optimal treatment policy that aligns with physician treatment policy. Our method utilizes both Electronic Medical Record (EMR) data and simulated treatment episodes to mitigate the limitations of restricted treatment exploration. Additionally, by leveraging a Discriminator, we suppress the Q-values of out-of-distribution treatments, preventing overestimation and reducing deviation from the physician treatment policies. The method was evaluated using data from Ajou University Hospital and Asan Medical Center. The expected return of the DDRL policy was 7.29 for Asan Medical Center and 4.55 for Ajou University Hospital, outperforming the Conservative Q-Learning (CQL) method by 3.4% and 5.6%, and surpassing the physician's policy by 18.7% and 8.3% respectively. The cosine similarity between DDRL and physician policies was 81.68% for Asan Medical Center and 90.90% for Ajou University Hospital, which is 0.73% and 26.11% higher, respectively, than the CQL method.
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP  (21682194) , 1-14
DDRL:Dyna-Based Discriminative Reinforcement Learning for Optimizing Sepsis Treatment Pathways in Offline Environments
Optimizing automated sepsis treatment policies using Reinforcement Learning (RL) has gained attention for improving quality of medical care and address physician shortages. However, in an offline setting, an RL agent cannot explore all possible treatment episodes, leading to an overestimation of Q-values for unexplored treatments. This causes a significant deviation from the physician's policy and results in the RL policy converging to a suboptimal policy. To address this problem, we propose Dyna-Based Discriminative Reinforcement Learning (DDRL), which aims to learn an optimal treatment policy that aligns with physician treatment policy. Our method utilizes both Electronic Medical Record (EMR) data and simulated treatment episodes to mitigate the limitations of restricted treatment exploration. Additionally, by leveraging a Discriminator, we suppress the Q-values of out-of-distribution treatments, preventing overestimation and reducing deviation from the physician treatment policies. The method was evaluated using data from Ajou University Hospital and Asan Medical Center. The expected return of the DDRL policy was 7.29 for Asan Medical Center and 4.55 for Ajou University Hospital, outperforming the Conservative Q-Learning (CQL) method by 3.4% and 5.6%, and surpassing the physician's policy by 18.7% and 8.3% respectively. The cosine similarity between DDRL and physician policies was 81.68% for Asan Medical Center and 90.90% for Ajou University Hospital, which is 0.73% and 26.11% higher, respectively, than the CQL method.
- 29 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (5) , 8554-8564
ADT²R: Adaptive Decision Transformer for Dynamic Treatment Regimes in Sepsis
Dynamic treatment regimes (DTRs), which comprise a series of decisions taken to select adequate treatments, have attracted considerable attention in the clinical domain, especially from sepsis researchers. Existing sepsis DTR learning studies are mainly based on offline reinforcement learning (RL) approaches working on electronic healthcare records data. However, a trained policy may choose a treatment different from a human clinician’s prescription. Furthermore, most of them do not consider: 1) heterogeneity in sepsis; 2) short-term transitions; and 3) the relationship between a patient’s health state and the prescription. We propose a novel framework, an adaptive decision transformer for DTR (ADT $^2$ R), which recommends an optimal treatment action for each time step depending on the heterogeneity of the sepsis and a patient’s evolving health states. Specifically, we devise a trajectory-optimization-based module to be trained with supervision for treatments and adaptively aggregate the multihead self-attentions by deliberating on various inherent time-varying patterns among sepsis patients. Furthermore, we estimate the patient’s health state by adopting an actor–critic (AC) algorithm and inform the treatment recommendation by learning about its short-term changes. We validated the effectiveness of the proposed framework on the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, an extensive intensive care database, by demonstrating performance comparable to the state-of-the-art methods.
- 29 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36  (5) , 8554-8564
ADT²R: Adaptive Decision Transformer for Dynamic Treatment Regimes in Sepsis
Dynamic treatment regimes (DTRs), which comprise a series of decisions taken to select adequate treatments, have attracted considerable attention in the clinical domain, especially from sepsis researchers. Existing sepsis DTR learning studies are mainly based on offline reinforcement learning (RL) approaches working on electronic healthcare records data. However, a trained policy may choose a treatment different from a human clinician’s prescription. Furthermore, most of them do not consider: 1) heterogeneity in sepsis; 2) short-term transitions; and 3) the relationship between a patient’s health state and the prescription. We propose a novel framework, an adaptive decision transformer for DTR (ADT $^2$ R), which recommends an optimal treatment action for each time step depending on the heterogeneity of the sepsis and a patient’s evolving health states. Specifically, we devise a trajectory-optimization-based module to be trained with supervision for treatments and adaptively aggregate the multihead self-attentions by deliberating on various inherent time-varying patterns among sepsis patients. Furthermore, we estimate the patient’s health state by adopting an actor–critic (AC) algorithm and inform the treatment recommendation by learning about its short-term changes. We validated the effectiveness of the proposed framework on the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, an extensive intensive care database, by demonstrating performance comparable to the state-of-the-art methods.
- Open Access
- 23 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 68138-68150
Classifying Gas Data Measured Under Multiple Conditions Using Deep Learning
Gas classification is a machine learning problem that is important for various applications including monitoring systems, health care, public security, etc. Since measuring the characteristic of gas molecules is greatly affected by external factors such as wind speed and the internal setting of detecting sensors, classification should be done by taking into account the combination of these individual factors, which we call a condition in this paper. In particular, when classifying gas data measured under multiple conditions, the data from each condition need to be integrated, which we call multi-conditioned gas classification . While there have been some studies on gas classification for a single condition, no previous approach deals with the multi-conditioned gas classification problem to the best of our knowledge. In this paper, we propose a novel multi-conditioned gas classification method for the first time. We present a new deep learning network structure that can efficiently extract features from the data of multiple conditions and effectively integrate them, which is referred to as a multi-conditioned gas classification network (MCGCN). We also propose a new training loss function to guarantee good performance reliably for the varying number of given conditions. Experimental results demonstrate the superiority of the proposed method, which achieves accuracies of 99.15% ± 0.41 regardless of the number of conditions with 15 times fewer model parameters in comparison to the existing method.
- 23 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 68138-68150
Open AccessClassifying Gas Data Measured Under Multiple Conditions Using Deep Learning
Gas classification is a machine learning problem that is important for various applications including monitoring systems, health care, public security, etc. Since measuring the characteristic of gas molecules is greatly affected by external factors such as wind speed and the internal setting of detecting sensors, classification should be done by taking into account the combination of these individual factors, which we call a condition in this paper. In particular, when classifying gas data measured under multiple conditions, the data from each condition need to be integrated, which we call multi-conditioned gas classification . While there have been some studies on gas classification for a single condition, no previous approach deals with the multi-conditioned gas classification problem to the best of our knowledge. In this paper, we propose a novel multi-conditioned gas classification method for the first time. We present a new deep learning network structure that can efficiently extract features from the data of multiple conditions and effectively integrate them, which is referred to as a multi-conditioned gas classification network (MCGCN). We also propose a new training loss function to guarantee good performance reliably for the varying number of given conditions. Experimental results demonstrate the superiority of the proposed method, which achieves accuracies of 99.15% ± 0.41 regardless of the number of conditions with 15 times fewer model parameters in comparison to the existing method.
- 5 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26  (8) , 4270-4280
Multi-View Integrative Attention-Based Deep Representation Learning for Irregular Clinical Time-Series Data
Electronic health record (EHR) data are sparse and irregular as they are recorded at irregular time intervals, and different clinical variables are measured at each observation point. In this work, to handle irregular multivariate time-series data, we consider the human knowledge of the aspects to be measured and time to measure them in different situations, known as multi-view features, which are indirectly represented in the data. We propose a scheme to realize multi-view features integration learning via a self-attention mechanism. Specifically, we devise a novel multi-integration attention module (MIAM) to extract complex information that is inherent in irregular time-series data. We explicitly learn the relationships among the observed values, missing indicators, and time interval between the consecutive observations in a simultaneous manner. In addition, we build an attention-based decoder as a missing value imputer that helps empower the representation learning of the interrelations among multi-view observations for the prediction task this decoder operates only in the training phase so that the final model is implemented in an imputation-free manner. We validated the effectiveness of our method over the public MIMIC-III and PhysioNet challenge 2012 datasets by comparing with and outperforming the state-of-the-art methods in three downstream tasks i.e. , prediction of the in-hospital mortality, prediction of the length of stay, and phenotyping. Moreover, we conduct a layer-wise relevance propagation (LRP) analysis based on case studies to highlight the explainability of the trained model.
- 5 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26  (8) , 4270-4280
Multi-View Integrative Attention-Based Deep Representation Learning for Irregular Clinical Time-Series Data
Electronic health record (EHR) data are sparse and irregular as they are recorded at irregular time intervals, and different clinical variables are measured at each observation point. In this work, to handle irregular multivariate time-series data, we consider the human knowledge of the aspects to be measured and time to measure them in different situations, known as multi-view features, which are indirectly represented in the data. We propose a scheme to realize multi-view features integration learning via a self-attention mechanism. Specifically, we devise a novel multi-integration attention module (MIAM) to extract complex information that is inherent in irregular time-series data. We explicitly learn the relationships among the observed values, missing indicators, and time interval between the consecutive observations in a simultaneous manner. In addition, we build an attention-based decoder as a missing value imputer that helps empower the representation learning of the interrelations among multi-view observations for the prediction task this decoder operates only in the training phase so that the final model is implemented in an imputation-free manner. We validated the effectiveness of our method over the public MIMIC-III and PhysioNet challenge 2012 datasets by comparing with and outperforming the state-of-the-art methods in three downstream tasks i.e. , prediction of the in-hospital mortality, prediction of the length of stay, and phenotyping. Moreover, we conduct a layer-wise relevance propagation (LRP) analysis based on case studies to highlight the explainability of the trained model.
- 25 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32  (9) , 4052-4062
Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction
Electronic health records (EHRs) are characterized as nonstationary, heterogeneous, noisy, and sparse data; therefore, it is challenging to learn the regularities or patterns inherent within them. In particular, sparseness caused mostly by many missing values has attracted the attention of researchers who have attempted to find a better use of all available samples for determining the solution of a primary target task through defining a secondary imputation problem. Methodologically, existing methods, either deterministic or stochastic, have applied different assumptions to impute missing values. However, once the missing values are imputed, most existing methods do not consider the fidelity or confidence of the imputed values in the modeling of downstream tasks. Undoubtedly, an erroneous or improper imputation of missing variables can cause difficulties in the modeling as well as a degraded performance. In this study, we present a novel variational recurrent network that: 1) estimates the distribution of missing variables (e.g., the mean and variance) allowing to represent uncertainty in the imputed values; 2) updates hidden states by explicitly applying fidelity based on a variance of the imputed values during a recurrence (i.e., uncertainty propagation over time); and 3) predicts the possibility of in-hospital mortality. It is noteworthy that our model can conduct these procedures in a single stream and learn all network parameters jointly in an end-to-end manner. We validated the effectiveness of our method using the public data sets of MIMIC-III and PhysioNet challenge 2012 by comparing with and outperforming other state-of-the-art methods for mortality prediction considered in our experiments. In addition, we identified the behavior of the model that well represented the uncertainties for the imputed estimates, which showed a high correlation between the uncertainties and mean absolute error (MAE) scores for imputation.
- 25 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32  (9) , 4052-4062
Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction
Electronic health records (EHRs) are characterized as nonstationary, heterogeneous, noisy, and sparse data; therefore, it is challenging to learn the regularities or patterns inherent within them. In particular, sparseness caused mostly by many missing values has attracted the attention of researchers who have attempted to find a better use of all available samples for determining the solution of a primary target task through defining a secondary imputation problem. Methodologically, existing methods, either deterministic or stochastic, have applied different assumptions to impute missing values. However, once the missing values are imputed, most existing methods do not consider the fidelity or confidence of the imputed values in the modeling of downstream tasks. Undoubtedly, an erroneous or improper imputation of missing variables can cause difficulties in the modeling as well as a degraded performance. In this study, we present a novel variational recurrent network that: 1) estimates the distribution of missing variables (e.g., the mean and variance) allowing to represent uncertainty in the imputed values; 2) updates hidden states by explicitly applying fidelity based on a variance of the imputed values during a recurrence (i.e., uncertainty propagation over time); and 3) predicts the possibility of in-hospital mortality. It is noteworthy that our model can conduct these procedures in a single stream and learn all network parameters jointly in an end-to-end manner. We validated the effectiveness of our method using the public data sets of MIMIC-III and PhysioNet challenge 2012 by comparing with and outperforming other state-of-the-art methods for mortality prediction considered in our experiments. In addition, we identified the behavior of the model that well represented the uncertainties for the imputed estimates, which showed a high correlation between the uncertainties and mean absolute error (MAE) scores for imputation.
- Open Access
Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction
Electronic health records (EHR) are characterized as non-stationary, heterogeneous, noisy, and sparse data; therefore, it is challenging to learn the regularities or patterns inherent within them. In particular, sparseness caused mostly by many missing values has attracted the attention of researchers, who have attempted to find a better use of all available samples for determining the solution of a primary target task through the defining a secondary imputation problem. Methodologically, existing methods, either deterministic or stochastic, have applied different assumptions to impute missing values. However, once the missing values are imputed, most existing methods do not consider the fidelity or confidence of the imputed values in the modeling of downstream tasks. Undoubtedly, an erroneous or improper imputation of missing variables can cause difficulties in modeling as well as a degraded performance. In this study, we present a novel variational recurrent network that (i) estimates the distribution of missing variables allowing to represent uncertainty in the imputed values, (ii) updates hidden states by explicitly applying fidelity based on a variance of the imputed values during a recurrence (i.e., uncertainty propagation over time), and (iii) predicts the possibility of in-hospital mortality. It is noteworthy that our model can conduct these procedures in a single stream and learn all network parameters jointly in an end-to-end manner. We validated the effectiveness of our method using the public datasets of MIMIC-III and PhysioNet challenge 2012 by comparing with and outperforming other state-of-the-art methods for mortality prediction considered in our experiments. In addition, we identified the behavior of the model that well represented the uncertainties for the imputed estimates, which indicated a high correlation between the calculated MAE and the uncertainty.
Open AccessUncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction
Electronic health records (EHR) are characterized as non-stationary, heterogeneous, noisy, and sparse data; therefore, it is challenging to learn the regularities or patterns inherent within them. In particular, sparseness caused mostly by many missing values has attracted the attention of researchers, who have attempted to find a better use of all available samples for determining the solution of a primary target task through the defining a secondary imputation problem. Methodologically, existing methods, either deterministic or stochastic, have applied different assumptions to impute missing values. However, once the missing values are imputed, most existing methods do not consider the fidelity or confidence of the imputed values in the modeling of downstream tasks. Undoubtedly, an erroneous or improper imputation of missing variables can cause difficulties in modeling as well as a degraded performance. In this study, we present a novel variational recurrent network that (i) estimates the distribution of missing variables allowing to represent uncertainty in the imputed values, (ii) updates hidden states by explicitly applying fidelity based on a variance of the imputed values during a recurrence (i.e., uncertainty propagation over time), and (iii) predicts the possibility of in-hospital mortality. It is noteworthy that our model can conduct these procedures in a single stream and learn all network parameters jointly in an end-to-end manner. We validated the effectiveness of our method using the public datasets of MIMIC-III and PhysioNet challenge 2012 by comparing with and outperforming other state-of-the-art methods for mortality prediction considered in our experiments. In addition, we identified the behavior of the model that well represented the uncertainties for the imputed estimates, which indicated a high correlation between the calculated MAE and the uncertainty.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1359-1361
Medical Time-series Prediction With LSTM-MDN-ATTN
We introduce the LSTM-MDN-ATTN model for predicting the medical time-series data. The LSTM-MDN-ATTN model predicts the future value of medical data by approximating the distribution of target data. Since medical data is multivariate data with various test items, attention mechanism is used to model the distribution suitable for target data. The attention layer used in this study predicts target data by focusing on the distribution that is related to the target data. The proposed LSTM-MDN-ATTN model shows better results compared to baseline models using lab test data from Asan Medical Center in Seoul.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1359-1361
Medical Time-series Prediction With LSTM-MDN-ATTN
We introduce the LSTM-MDN-ATTN model for predicting the medical time-series data. The LSTM-MDN-ATTN model predicts the future value of medical data by approximating the distribution of target data. Since medical data is multivariate data with various test items, attention mechanism is used to model the distribution suitable for target data. The attention layer used in this study predicts target data by focusing on the distribution that is related to the target data. The proposed LSTM-MDN-ATTN model shows better results compared to baseline models using lab test data from Asan Medical Center in Seoul.
- 1 January 2017
- Published by Inderscience Publishers in International Journal of Data Mining and Bioinformatics
- Vol. 19  (3) , 202-220
Medical examination data prediction with missing information imputation based on recurrent neural networks
In this work, the recurrent neural networks (RNNs) for medical examination data prediction with missing information are proposed. Simple recurrent network (SRN), long short-term memory (LSTM) and gated recurrent unit (GRU) are selected among many variations of RNNs for the missing information imputation while they are also used to predict the future medical examination data. Besides, the missing information imputation based on bidirectional LSTM is also proposed to consider past information as well as the future information in the imputation process, while the traditional RNNs can only consider the past information during the imputation. We implemented medical examination results prediction experiment using the examination database of Koreans. The experimental results showed that the proposed RNNs worked better than the baseline linear regression method. Besides, the bidirectional LSTM performed best for missing information imputation.
- 1 January 2017
- Published by Inderscience Publishers in International Journal of Data Mining and Bioinformatics
- Vol. 19  (3) , 202-220
Medical examination data prediction with missing information imputation based on recurrent neural networks
In this work, the recurrent neural networks (RNNs) for medical examination data prediction with missing information are proposed. Simple recurrent network (SRN), long short-term memory (LSTM) and gated recurrent unit (GRU) are selected among many variations of RNNs for the missing information imputation while they are also used to predict the future medical examination data. Besides, the missing information imputation based on bidirectional LSTM is also proposed to consider past information as well as the future information in the imputation process, while the traditional RNNs can only consider the past information during the imputation. We implemented medical examination results prediction experiment using the examination database of Koreans. The experimental results showed that the proposed RNNs worked better than the baseline linear regression method. Besides, the bidirectional LSTM performed best for missing information imputation.
- 1 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Prediction of medical examination results using radial-basis function networks
This paper proposes a method of predicting future medical examination measurements given the past values. The medical examinations considered in this paper are blood sugar level, low and high blood pressures, and cholesterol level. This paper uses a specific type of artificial neural networks, radial-basis function network (RBFN), to approximate mapping from the past medical measurements to that of the upcoming year, in order to help the subjects be aware of the signs of unusual health states without consulting with doctors. Experimental results show that the RBFN-based estimation is superior to the conventional linear regression in terms of prediction accuracy of the future examination measurements. The proposed method is expected to be implemented in a handy consumer electronic devices such as Smartphones without adding extra hardware parts provided that the history of the medical examination measurements are available.
- 1 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Prediction of medical examination results using radial-basis function networks
This paper proposes a method of predicting future medical examination measurements given the past values. The medical examinations considered in this paper are blood sugar level, low and high blood pressures, and cholesterol level. This paper uses a specific type of artificial neural networks, radial-basis function network (RBFN), to approximate mapping from the past medical measurements to that of the upcoming year, in order to help the subjects be aware of the signs of unusual health states without consulting with doctors. Experimental results show that the RBFN-based estimation is superior to the conventional linear regression in terms of prediction accuracy of the future examination measurements. The proposed method is expected to be implemented in a handy consumer electronic devices such as Smartphones without adding extra hardware parts provided that the history of the medical examination measurements are available.