Discovering causal relationships among symptoms is a topical issue in the analysis of observational patient datasets. A Causal Bayesian Network (CBN) is a popular analytical framework for causal inference. While there are many methods and algorithms capable of learning a Bayesian network, they are reliant on the complexity and thoroughness of the algorithm and do not consider prior expertise from authoritative sources. This paper proposes a novel method of extracting prior causal knowledge contained in Authoritative Medical Ontologies (AMOs) and using this prior knowledge to orient arcs in a CBN learned from observational patient data. Since AMOs are robust biomedical ontologies containing the collective knowledge of the experts who created them, utilizing the ordering information contained within them produces improved CBNs which provide additional insight into the disease domain. To demonstrate our method, we obtained prior causal ordering information among symptoms from three AMOs: 1) the Medical Dictionary for Regulatory Activities Terminology (MedDRA), 2) the International Classification of Diseases Version 10 Clinical Modification (ICD-10-CM), and 3) Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT). The prior ontological knowledge from these three AMOs is then used to orient arcs in a series of CBNs learned from the National Institutes of Mental Health study on Sequenced Treatment Alternatives to Relieve Depression (STAR*D) patient dataset using the Max-Min Hill-Climbing (MMHC) algorithm. Six distinct CBNs are generated using MMHC: an unmodified baseline model using only the algorithm, three CBNs oriented with ordered-variable pairs from MedDRA, ICD-10-CM, and SNOMED CT, and two more with ordered pairs from a combination of these AMOs. The resulting CBNs modified using ordered-variable pairs significantly change the structure of the network. The agreement between the Modified networks and the Baseline ranges from 50% to 90%. A modified network using ordering information from all ontologies obtained an agreement of 50% (10 out of 20 arcs exist in both the Baseline and Modified models) while maintaining comparable predictive accuracy. This indicates that the Modified CBN reflects the causal claims in the AMOs and agrees with both the AMOs and the observational STAR*D dataset. Furthermore, the Modified models discovered new potentially causal relationships among symptoms in the model, while eliminating weaker edges in a qualitative analysis of the significance of these relationships in existing epidemiological research.
{"title":"Improving Causal Bayesian Networks using Expertise in Authoritative Medical Ontologies","authors":"Hengyi Hu, L. Kerschberg","doi":"10.1145/3604561","DOIUrl":"https://doi.org/10.1145/3604561","url":null,"abstract":"Discovering causal relationships among symptoms is a topical issue in the analysis of observational patient datasets. A Causal Bayesian Network (CBN) is a popular analytical framework for causal inference. While there are many methods and algorithms capable of learning a Bayesian network, they are reliant on the complexity and thoroughness of the algorithm and do not consider prior expertise from authoritative sources. This paper proposes a novel method of extracting prior causal knowledge contained in Authoritative Medical Ontologies (AMOs) and using this prior knowledge to orient arcs in a CBN learned from observational patient data. Since AMOs are robust biomedical ontologies containing the collective knowledge of the experts who created them, utilizing the ordering information contained within them produces improved CBNs which provide additional insight into the disease domain. To demonstrate our method, we obtained prior causal ordering information among symptoms from three AMOs: 1) the Medical Dictionary for Regulatory Activities Terminology (MedDRA), 2) the International Classification of Diseases Version 10 Clinical Modification (ICD-10-CM), and 3) Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT). The prior ontological knowledge from these three AMOs is then used to orient arcs in a series of CBNs learned from the National Institutes of Mental Health study on Sequenced Treatment Alternatives to Relieve Depression (STAR*D) patient dataset using the Max-Min Hill-Climbing (MMHC) algorithm. Six distinct CBNs are generated using MMHC: an unmodified baseline model using only the algorithm, three CBNs oriented with ordered-variable pairs from MedDRA, ICD-10-CM, and SNOMED CT, and two more with ordered pairs from a combination of these AMOs. The resulting CBNs modified using ordered-variable pairs significantly change the structure of the network. The agreement between the Modified networks and the Baseline ranges from 50% to 90%. A modified network using ordering information from all ontologies obtained an agreement of 50% (10 out of 20 arcs exist in both the Baseline and Modified models) while maintaining comparable predictive accuracy. This indicates that the Modified CBN reflects the causal claims in the AMOs and agrees with both the AMOs and the observational STAR*D dataset. Furthermore, the Modified models discovered new potentially causal relationships among symptoms in the model, while eliminating weaker edges in a qualitative analysis of the significance of these relationships in existing epidemiological research.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45804692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article presents a resource-efficient adaptive sampling methodology for classifying electrocardiogram (ECG) signals into different heart rhythms. We present our methodology in two folds: (i) the design of a novel real-time adaptive neural network architecture capable of classifying ECG signals with different sampling rates and (ii) a runtime implementation of sampling rate control using deep reinforcement learning (DRL). By using essential morphological details contained in the heartbeat waveform, the DRL agent can control the sampling rate and effectively reduce energy consumption at runtime. To evaluate our adaptive classifier, we use the MIT-BIH database and the recommendation of the AAMI to train the classifiers. The classifier is designed to recognize three major types of arrhythmias, which are supraventricular ectopic beats (SVEB), ventricular ectopic beats (VEB), and normal beats (N). The performance of the arrhythmia classification reaches an accuracy of 97.2% for SVEB and 97.6% for VEB beats. Moreover, the designed system is 7.3× more energy-efficient compared to the baseline architecture, where the adaptive sampling rate is not utilized. The proposed methodology can provide reliable and accurate real-time ECG signal analysis with performances comparable to state-of-the-art methods. Given its time-efficient, low-complexity, and low-memory-usage characteristics, the proposed methodology is also suitable for practical ECG applications, in our case for arrhythmia classification, using resource-constrained devices, especially wearable healthcare devices and implanted medical devices.
{"title":"Data-driven Energy-efficient Adaptive Sampling Using Deep Reinforcement Learning","authors":"Berken Utku Demirel, Luke Chen, M. A. Al Faruque","doi":"10.1145/3598301","DOIUrl":"https://doi.org/10.1145/3598301","url":null,"abstract":"This article presents a resource-efficient adaptive sampling methodology for classifying electrocardiogram (ECG) signals into different heart rhythms. We present our methodology in two folds: (i) the design of a novel real-time adaptive neural network architecture capable of classifying ECG signals with different sampling rates and (ii) a runtime implementation of sampling rate control using deep reinforcement learning (DRL). By using essential morphological details contained in the heartbeat waveform, the DRL agent can control the sampling rate and effectively reduce energy consumption at runtime. To evaluate our adaptive classifier, we use the MIT-BIH database and the recommendation of the AAMI to train the classifiers. The classifier is designed to recognize three major types of arrhythmias, which are supraventricular ectopic beats (SVEB), ventricular ectopic beats (VEB), and normal beats (N). The performance of the arrhythmia classification reaches an accuracy of 97.2% for SVEB and 97.6% for VEB beats. Moreover, the designed system is 7.3× more energy-efficient compared to the baseline architecture, where the adaptive sampling rate is not utilized. The proposed methodology can provide reliable and accurate real-time ECG signal analysis with performances comparable to state-of-the-art methods. Given its time-efficient, low-complexity, and low-memory-usage characteristics, the proposed methodology is also suitable for practical ECG applications, in our case for arrhythmia classification, using resource-constrained devices, especially wearable healthcare devices and implanted medical devices.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"4 1","pages":"1 - 19"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45164128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Retinopathy of prematurity (ROP) is a leading cause of blindness in premature infants worldwide, particularly in developing countries. In this research, we propose a Deep Convolutional Neural Network (DCNN) and image processing-based approach for the automatic detection of retinal features, including the optical disc (OD) and retinal blood vessels (BV), as well as disease classification using a rule-based method for ROP patients. Our DCNN model uses YOLO-v5 for OD detection and either Pix2Pix or a U-Net for BV segmentation. We trained our DCNN models on publicly available fundus image datasets of size 1,117 and 288 for OD detection and BV segmentation, respectively. We evaluated our approach on a dataset of 439 preterm neonatal retinal images, testing for ROP Zone and 6 BV masks. Our proposed system achieved excellent results, with the OD detection module achieving an overall accuracy of 98.94% (when IoU 0.5) and the BV segmentation module achieving an accuracy of 96.69% and a Dice coefficient between 0.60 and 0.64. Moreover, our system accurately diagnosed ROP in Zone-1 with 88.23% accuracy. Our approach offers a promising solution for accurate ROP screening and diagnosis, particularly in low-resource settings, where it has the potential to improve healthcare outcomes.
{"title":"Deep Learning-assisted Retinopathy of Prematurity (ROP) Screening","authors":"Vijay Kumar, Het Patel, Kolin Paul, S. Azad","doi":"10.1145/3596223","DOIUrl":"https://doi.org/10.1145/3596223","url":null,"abstract":"Retinopathy of prematurity (ROP) is a leading cause of blindness in premature infants worldwide, particularly in developing countries. In this research, we propose a Deep Convolutional Neural Network (DCNN) and image processing-based approach for the automatic detection of retinal features, including the optical disc (OD) and retinal blood vessels (BV), as well as disease classification using a rule-based method for ROP patients. Our DCNN model uses YOLO-v5 for OD detection and either Pix2Pix or a U-Net for BV segmentation. We trained our DCNN models on publicly available fundus image datasets of size 1,117 and 288 for OD detection and BV segmentation, respectively. We evaluated our approach on a dataset of 439 preterm neonatal retinal images, testing for ROP Zone and 6 BV masks. Our proposed system achieved excellent results, with the OD detection module achieving an overall accuracy of 98.94% (when IoU 0.5) and the BV segmentation module achieving an accuracy of 96.69% and a Dice coefficient between 0.60 and 0.64. Moreover, our system accurately diagnosed ROP in Zone-1 with 88.23% accuracy. Our approach offers a promising solution for accurate ROP screening and diagnosis, particularly in low-resource settings, where it has the potential to improve healthcare outcomes.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"4 1","pages":"1 - 32"},"PeriodicalIF":0.0,"publicationDate":"2023-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48553373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-01Epub Date: 2023-04-18DOI: 10.1145/3578556
Mahya Saffarpour, Debraj Basu, Fatemeh Radaei, Kourosh Vali, Jason Y Adams, Chen-Nee Chuah, Soheil Ghiasi
Dicrotic Notch (DN), one of the most significant and indicative features of the arterial blood pressure (ABP) waveform, becomes less pronounced and thus harder to identify as a matter of aging and pathological vascular stiffness. Generalizable and automatic DN identification for such edge cases is even more challenging in the presence of unexpected ABP waveform deformations that happen due to internal and external noise sources or pathological conditions that cause hemodynamic instability. We propose a physics-aware approach, named Physiowise (PW), that first employs a cardiovascular model to augment the original ABP waveform and reduce unexpected deformations, then apply a set of predefined rules on the augmented signal to find DN locations. We have tested the proposed method on in-vivo data gathered from 14 pigs under hemorrhage and sepsis study. Our result indicates 52% overall mean error improvement with 16% higher detection accuracy within the lowest permitted error range of 30ms. An additional hybrid methodology is also proposed to allow combining augmentation with any application-specific user-defined rule set.
{"title":"Physiowise: A Physics-aware Approach to Dicrotic Notch Identification.","authors":"Mahya Saffarpour, Debraj Basu, Fatemeh Radaei, Kourosh Vali, Jason Y Adams, Chen-Nee Chuah, Soheil Ghiasi","doi":"10.1145/3578556","DOIUrl":"10.1145/3578556","url":null,"abstract":"<p><p>Dicrotic Notch (DN), one of the most significant and indicative features of the arterial blood pressure (ABP) waveform, becomes less pronounced and thus harder to identify as a matter of aging and pathological vascular stiffness. Generalizable and automatic DN identification for such edge cases is even more challenging in the presence of unexpected ABP waveform deformations that happen due to internal and external noise sources or pathological conditions that cause hemodynamic instability. We propose a physics-aware approach, named Physiowise (PW), that first employs a cardiovascular model to augment the original ABP waveform and reduce unexpected deformations, then apply a set of predefined rules on the augmented signal to find DN locations. We have tested the proposed method on in-vivo data gathered from 14 pigs under hemorrhage and sepsis study. Our result indicates 52% overall mean error improvement with 16% higher detection accuracy within the lowest permitted error range of 30<i>ms</i>. An additional hybrid methodology is also proposed to allow combining augmentation with any application-specific user-defined rule set.</p>","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10861158/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45194779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Photoplethysmography (PPG) is a non-invasive technique for recording human vital signs. PPG is normally recorded by wearable devices that are prone to artifacts. This results in signal corruption that decreases measurement accuracy. Thus, a signal quality assessment (SQA) system is essential in obtaining reliable measurements. Conventionally, SQA is mainly driven by human-knowledge and supervised through experts’ annotations. However, they are not tailored for the particularities of the domain applications. Hence, we propose a machine-aided SQA framework that generates respective quality criteria for applications. By using the proposed approach, quality criteria can be easily trained for different applications. Then, quality assessment can be applied to several PPG-based physiological signals telemonitoring. Compared with conventional approaches, the proposed system has a higher rejection rate for high-error signals and a lower mean absolute error is achieved when estimating heart rate (-3.06 BPM), determining respiration rate (–1.36 BPM), and predicting hypertension (+24%). The proposed method enhances accuracy in monitoring physiological signals and thus is suitable for healthcare applications.
{"title":"Machine-aided PPG Signal Quality Assessment (SQA) for Multi-mode Physiological Signal Monitoring","authors":"Win-Ken Beh, Yu-Chia Yang, Yi-Cheng Lo, Yun-Chieh Lee, An-Yeu Wu","doi":"10.1145/3587256","DOIUrl":"https://doi.org/10.1145/3587256","url":null,"abstract":"Photoplethysmography (PPG) is a non-invasive technique for recording human vital signs. PPG is normally recorded by wearable devices that are prone to artifacts. This results in signal corruption that decreases measurement accuracy. Thus, a signal quality assessment (SQA) system is essential in obtaining reliable measurements. Conventionally, SQA is mainly driven by human-knowledge and supervised through experts’ annotations. However, they are not tailored for the particularities of the domain applications. Hence, we propose a machine-aided SQA framework that generates respective quality criteria for applications. By using the proposed approach, quality criteria can be easily trained for different applications. Then, quality assessment can be applied to several PPG-based physiological signals telemonitoring. Compared with conventional approaches, the proposed system has a higher rejection rate for high-error signals and a lower mean absolute error is achieved when estimating heart rate (-3.06 BPM), determining respiration rate (–1.36 BPM), and predicting hypertension (+24%). The proposed method enhances accuracy in monitoring physiological signals and thus is suitable for healthcare applications.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"4 1","pages":"1 - 20"},"PeriodicalIF":0.0,"publicationDate":"2023-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43082979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Bardram, C. Cramer-Petersen, Alban Maxhuni, Mads V. S. Christensen, Per Bækgaard, Dan R. Persson, Nanna Lind, M. B. Christensen, Kirsten Nørgaard, Jayden Khakurel, T. Skinner, D. Kownatka, Allan Jones
Type 2 diabetes (T2D) is a large disease burden worldwide and represents an increasing and complex challenge for all societies. For the individual, T2D is a complex, multi-dimensional, and long-term challenge to manage, and it is challenging to establish and maintain good communication between the patient and healthcare professionals. This article presents DiaFocus, which is a mobile health sensing application for long-term ambulatory management of T2D. DiaFocus supports an adaptive collection of physiological, behavioral, and contextual data in combination with ecological assessments of psycho-social factors. This data is used for improving patient-clinician communication during consultations. DiaFocus is built using a generic data collection framework for mobile and wearable sensing and is highly extensible and customizable. We deployed DiaFocus in a 6-week feasibility study involving 12 patients with T2D. The patients found the DiaFocus approach and system useful and usable for diabetes management. Most patients would use such a system, if available as part of their treatment. Analysis of the collected data shows that mobile sensing is feasible for longitudinal ambulatory assessment of T2D, and helped identify the most appropriate target users being early diagnosed and technically literate T2D patients.
{"title":"DiaFocus: A Personal Health Technology for Adaptive Assessment in Long-Term Management of Type 2 Diabetes","authors":"J. Bardram, C. Cramer-Petersen, Alban Maxhuni, Mads V. S. Christensen, Per Bækgaard, Dan R. Persson, Nanna Lind, M. B. Christensen, Kirsten Nørgaard, Jayden Khakurel, T. Skinner, D. Kownatka, Allan Jones","doi":"10.1145/3586579","DOIUrl":"https://doi.org/10.1145/3586579","url":null,"abstract":"Type 2 diabetes (T2D) is a large disease burden worldwide and represents an increasing and complex challenge for all societies. For the individual, T2D is a complex, multi-dimensional, and long-term challenge to manage, and it is challenging to establish and maintain good communication between the patient and healthcare professionals. This article presents DiaFocus, which is a mobile health sensing application for long-term ambulatory management of T2D. DiaFocus supports an adaptive collection of physiological, behavioral, and contextual data in combination with ecological assessments of psycho-social factors. This data is used for improving patient-clinician communication during consultations. DiaFocus is built using a generic data collection framework for mobile and wearable sensing and is highly extensible and customizable. We deployed DiaFocus in a 6-week feasibility study involving 12 patients with T2D. The patients found the DiaFocus approach and system useful and usable for diabetes management. Most patients would use such a system, if available as part of their treatment. Analysis of the collected data shows that mobile sensing is feasible for longitudinal ambulatory assessment of T2D, and helped identify the most appropriate target users being early diagnosed and technically literate T2D patients.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"4 1","pages":"1 - 43"},"PeriodicalIF":0.0,"publicationDate":"2023-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42436545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tommi Gröhn, S. Liikkanen, T. Huttunen, Mika Mäkinen, P. Liljeberg, P. Marttinen
Chronic low back pain (CLBP) is a globally common musculoskeletal problem. Measuring the sensation of pain and the effect of a treatment has always been a challenge for healthcare. Here, we study how the movement data, collected while using a virtual reality (VR) program, could be used as an objective measurement in patients with CLBP. A specific data collection method based on VR was developed and used with CLBP patients and healthy volunteers. We demonstrate that the movement data in VR can be used to classify individuals in these two groups with a high accuracy by using logistic regression. The most discriminative features are the duration of the movements and the total variation of movement velocity. Furthermore, we show that hidden Markov models can divide movement data into meaningful segments, which creates possibilities for defining even more detailed features, with potential to improve accuracy, when larger datasets become available in the future.
{"title":"Quantifying Movement Behavior of Chronic Low Back Pain Patients in Virtual Reality","authors":"Tommi Gröhn, S. Liikkanen, T. Huttunen, Mika Mäkinen, P. Liljeberg, P. Marttinen","doi":"10.1145/3582487","DOIUrl":"https://doi.org/10.1145/3582487","url":null,"abstract":"Chronic low back pain (CLBP) is a globally common musculoskeletal problem. Measuring the sensation of pain and the effect of a treatment has always been a challenge for healthcare. Here, we study how the movement data, collected while using a virtual reality (VR) program, could be used as an objective measurement in patients with CLBP. A specific data collection method based on VR was developed and used with CLBP patients and healthy volunteers. We demonstrate that the movement data in VR can be used to classify individuals in these two groups with a high accuracy by using logistic regression. The most discriminative features are the duration of the movements and the total variation of movement velocity. Furthermore, we show that hidden Markov models can divide movement data into meaningful segments, which creates possibilities for defining even more detailed features, with potential to improve accuracy, when larger datasets become available in the future.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"4 1","pages":"1 - 24"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47268117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deep learning has achieved significant success on intelligent medical treatments, such as automatic diagnosis and analysis of medical data. To train an automatic diagnosis system with high accuracy and strong robustness in healthcare, sufficient training data are required when using deep learning-based methods. However, given that the data collected by sensors that are embedded in medical or mobile devices are inadequate, it is challenging to train an effective and efficient classification model with state-of-the-art performance. Inspired by generative adversarial networks (GANs), we propose TS-GAN, a Time-series GAN architecture based on long short-term memory (LSTM) networks for sensor-based health data augmentation, thereby improving the performance of deep learning-based classification models. TS-GAN aims to learn a generative model that creates time-series data with the same space and time dependence as the real data. Specifically, we design an LSTM-based generator for creating realistic data and an LSTM-based discriminator for determining how similar the generated data are to real data. In particular, we design a sequential-squeeze-and-excitation module in the LSTM-based discriminator to better understand space dependence of real data, and apply the gradient penalty originated from Wasserstein GANs in the training process to stabilize the optimization. We conduct comparative experiments to evaluate the performance of TS-GAN with TimeGAN, C-RNN-GAN and Conditional Wasserstein GANs through discriminator loss, maximum mean discrepancy, visualization methods and classification accuracy on health datasets of ECG_200, NonInvasiveFatalECG_Thorax1, and mHealth, respectively. The experimental results show that TS-GAN exceeds other state-of-the-art time-series GANs in almost all the evaluation metrics, and the classifier trained on synthetic datasets generated by TS-GAN achieves the highest classification accuracy of 97.50% on ECG_200, 94.12% on NonInvasiveFatalECG_Thorax1, and 98.12% on mHealth, respectively.
{"title":"TS-GAN: Time-series GAN for Sensor-based Health Data Augmentation","authors":"Zhenyu Yang, Yantao Li, Gang Zhou","doi":"10.1145/3583593","DOIUrl":"https://doi.org/10.1145/3583593","url":null,"abstract":"Deep learning has achieved significant success on intelligent medical treatments, such as automatic diagnosis and analysis of medical data. To train an automatic diagnosis system with high accuracy and strong robustness in healthcare, sufficient training data are required when using deep learning-based methods. However, given that the data collected by sensors that are embedded in medical or mobile devices are inadequate, it is challenging to train an effective and efficient classification model with state-of-the-art performance. Inspired by generative adversarial networks (GANs), we propose TS-GAN, a Time-series GAN architecture based on long short-term memory (LSTM) networks for sensor-based health data augmentation, thereby improving the performance of deep learning-based classification models. TS-GAN aims to learn a generative model that creates time-series data with the same space and time dependence as the real data. Specifically, we design an LSTM-based generator for creating realistic data and an LSTM-based discriminator for determining how similar the generated data are to real data. In particular, we design a sequential-squeeze-and-excitation module in the LSTM-based discriminator to better understand space dependence of real data, and apply the gradient penalty originated from Wasserstein GANs in the training process to stabilize the optimization. We conduct comparative experiments to evaluate the performance of TS-GAN with TimeGAN, C-RNN-GAN and Conditional Wasserstein GANs through discriminator loss, maximum mean discrepancy, visualization methods and classification accuracy on health datasets of ECG_200, NonInvasiveFatalECG_Thorax1, and mHealth, respectively. The experimental results show that TS-GAN exceeds other state-of-the-art time-series GANs in almost all the evaluation metrics, and the classifier trained on synthetic datasets generated by TS-GAN achieves the highest classification accuracy of 97.50% on ECG_200, 94.12% on NonInvasiveFatalECG_Thorax1, and 98.12% on mHealth, respectively.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"4 1","pages":"1 - 21"},"PeriodicalIF":0.0,"publicationDate":"2023-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43220955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Population health monitoring is a fundamental component of the public health system. Due to the high-cost nature of traditional population-wise health-data collection methods, a class of sparse-sampling-completion algorithms are proposed to exploit the spatio-temporal correlation buried under the observed examples. However, for the population health data, a huge challenge for the state-of-the-art completion methods is the unstationary environment. Specifically, the underlying temporal correlation of the population health data are evolving from year to year. To this end, we propose a GAN-based year-by-year completion framework: uncertainty-aware augmented generative adversarial imputation nets (UAA-GAIN), to address the problem of unstationary environment. To further restrain the error accumulation, we develop a stronger generator as well as a stronger discriminator in the min-max equilibrium. A by-product of the augmented GAIN model allows weighting the difficulty of examples. Inspired by the idea of curriculum learning, a better training schedule is implemented in the proposed framework. We evaluate the proposed method on three real-world chronic disease datasets and the results show that UAA-GAIN outperforms other baseline methods in various settings.
{"title":"Towards Sustainable Compressive Population Health: A GAN-based Year-By-Year Imputation Method","authors":"Yujie Feng, Jiangtao Wang, Yasha Wang, Xu Chu","doi":"10.1145/3571159","DOIUrl":"https://doi.org/10.1145/3571159","url":null,"abstract":"Population health monitoring is a fundamental component of the public health system. Due to the high-cost nature of traditional population-wise health-data collection methods, a class of sparse-sampling-completion algorithms are proposed to exploit the spatio-temporal correlation buried under the observed examples. However, for the population health data, a huge challenge for the state-of-the-art completion methods is the unstationary environment. Specifically, the underlying temporal correlation of the population health data are evolving from year to year. To this end, we propose a GAN-based year-by-year completion framework: uncertainty-aware augmented generative adversarial imputation nets (UAA-GAIN), to address the problem of unstationary environment. To further restrain the error accumulation, we develop a stronger generator as well as a stronger discriminator in the min-max equilibrium. A by-product of the augmented GAIN model allows weighting the difficulty of examples. Inspired by the idea of curriculum learning, a better training schedule is implemented in the proposed framework. We evaluate the proposed method on three real-world chronic disease datasets and the results show that UAA-GAIN outperforms other baseline methods in various settings.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"4 1","pages":"1 - 18"},"PeriodicalIF":0.0,"publicationDate":"2022-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41685727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Argyris Constantinides, Marios Belk, C. Fidas, R. Beumers, David Vidal, Wanting Huang, J. Bowles, Thais Webber, Agastya Silvina, A. Pitsillides
This article proposes a user-adaptable and personalized authentication paradigm for healthcare organizations, which anticipates to seamlessly reflect patients’ episodic and autobiographical memories to graphical and textual passwords aiming to improve the security strength of user-selected passwords and provide a positive user experience. We report on a longitudinal study that spanned over 3 years in which three public European healthcare organizations participated to design and evaluate the aforementioned paradigm. Three studies were conducted (n = 169) with different stakeholders: (1) a verification study aiming to identify existing authentication practices of the three healthcare organizations with diverse stakeholders (n = 9), (2) a patient-centric feasibility study during which users interacted with the proposed authentication system (n = 68), and (3) a human guessing attack study focusing on vulnerabilities among people sharing common experiences within location-aware images used for graphical passwords (n = 92). Results revealed that the suggested paradigm scored high with regard to users’ likeability, perceived security, usability, and trust, but more importantly it assists the creation of more secure passwords. On the downside, the suggested paradigm introduces password guessing vulnerabilities by individuals sharing common experiences with the end users. Findings are expected to scaffold the design of more patient-centric knowledge-based authentication mechanisms within today's dynamic computation realms.
{"title":"Security and Usability of a Personalized User Authentication Paradigm: Insights from a Longitudinal Study with Three Healthcare Organizations","authors":"Argyris Constantinides, Marios Belk, C. Fidas, R. Beumers, David Vidal, Wanting Huang, J. Bowles, Thais Webber, Agastya Silvina, A. Pitsillides","doi":"10.1145/3564610","DOIUrl":"https://doi.org/10.1145/3564610","url":null,"abstract":"This article proposes a user-adaptable and personalized authentication paradigm for healthcare organizations, which anticipates to seamlessly reflect patients’ episodic and autobiographical memories to graphical and textual passwords aiming to improve the security strength of user-selected passwords and provide a positive user experience. We report on a longitudinal study that spanned over 3 years in which three public European healthcare organizations participated to design and evaluate the aforementioned paradigm. Three studies were conducted (n = 169) with different stakeholders: (1) a verification study aiming to identify existing authentication practices of the three healthcare organizations with diverse stakeholders (n = 9), (2) a patient-centric feasibility study during which users interacted with the proposed authentication system (n = 68), and (3) a human guessing attack study focusing on vulnerabilities among people sharing common experiences within location-aware images used for graphical passwords (n = 92). Results revealed that the suggested paradigm scored high with regard to users’ likeability, perceived security, usability, and trust, but more importantly it assists the creation of more secure passwords. On the downside, the suggested paradigm introduces password guessing vulnerabilities by individuals sharing common experiences with the end users. Findings are expected to scaffold the design of more patient-centric knowledge-based authentication mechanisms within today's dynamic computation realms.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"4 1","pages":"1 - 40"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42631776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：