Anderson F. B. F. da Costa, Larissa Moreira, D. Andrade, Adriano Veloso, N. Ziviani
Modeling from data usually has two distinct facets: building sound explanatory models or creating powerful predictive models for a system or phenomenon. Most of recent literature does not exploit the relationship between explanation and prediction while learning models from data. Recent algorithms are not taking advantage of the fact that many phenomena are actually defined by diverse sub-populations and local structures, and thus there are many possible predictive models providing contrasting interpretations or competing explanations for the same phenomenon. In this article, we propose to explore a complementary link between explanation and prediction. Our main intuition is that models having their decisions explained by the same factors are likely to perform better predictions for data points within the same local structures. We evaluate our methodology to model the evolution of pain relief in patients suffering from chronic pain under usual guideline-based treatment. The ensembles generated using our framework are compared with all-in-one approaches of robust algorithms to high-dimensional data, such as Random Forests and XGBoost. Chronic pain can be primary or secondary to diseases. Its symptomatology can be classified as nociceptive, nociplastic, or neuropathic, and is generally associated with many different causal structures, challenging typical modeling methodologies. Our data includes 631 patients receiving pain treatment. We considered 338 features providing information about pain sensation, socioeconomic status, and prescribed treatments. Our goal is to predict, using data from the first consultation only, if the patient will be successful in treatment for chronic pain relief. As a result of this work, we were able to build ensembles that are able to consistently improve performance by up to 33% when compared to models trained using all the available features. We also obtained relevant gains in interpretability, with resulting ensembles using only 15% of the total number of features. We show we can effectively generate ensembles from competing explanations, promoting diversity in ensemble learning and leading to significant gains in accuracy by enforcing a stable scenario in which models that are dissimilar in terms of their predictions are also dissimilar in terms of their explanation factors.
{"title":"Predicting the Evolution of Pain Relief","authors":"Anderson F. B. F. da Costa, Larissa Moreira, D. Andrade, Adriano Veloso, N. Ziviani","doi":"10.1145/3466781","DOIUrl":"https://doi.org/10.1145/3466781","url":null,"abstract":"Modeling from data usually has two distinct facets: building sound explanatory models or creating powerful predictive models for a system or phenomenon. Most of recent literature does not exploit the relationship between explanation and prediction while learning models from data. Recent algorithms are not taking advantage of the fact that many phenomena are actually defined by diverse sub-populations and local structures, and thus there are many possible predictive models providing contrasting interpretations or competing explanations for the same phenomenon. In this article, we propose to explore a complementary link between explanation and prediction. Our main intuition is that models having their decisions explained by the same factors are likely to perform better predictions for data points within the same local structures. We evaluate our methodology to model the evolution of pain relief in patients suffering from chronic pain under usual guideline-based treatment. The ensembles generated using our framework are compared with all-in-one approaches of robust algorithms to high-dimensional data, such as Random Forests and XGBoost. Chronic pain can be primary or secondary to diseases. Its symptomatology can be classified as nociceptive, nociplastic, or neuropathic, and is generally associated with many different causal structures, challenging typical modeling methodologies. Our data includes 631 patients receiving pain treatment. We considered 338 features providing information about pain sensation, socioeconomic status, and prescribed treatments. Our goal is to predict, using data from the first consultation only, if the patient will be successful in treatment for chronic pain relief. As a result of this work, we were able to build ensembles that are able to consistently improve performance by up to 33% when compared to models trained using all the available features. We also obtained relevant gains in interpretability, with resulting ensembles using only 15% of the total number of features. We show we can effectively generate ensembles from competing explanations, promoting diversity in ensemble learning and leading to significant gains in accuracy by enforcing a stable scenario in which models that are dissimilar in terms of their predictions are also dissimilar in terms of their explanation factors.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"2 1","pages":"1 - 28"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47662891","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}
We develop a model of infection spread that takes into account the existence of a vulnerable group as well as the variability of the social relations of individuals. We develop a compartmentalized power-law model, with power-law connections between the vulnerable and the general population, considering these connections as well as the connections among the vulnerable as parameters that we vary in our tests. We use the model to study a number of vaccination strategies under two hypotheses: first, we assume a limited availability of vaccine but an infinite vaccination capacity, so all the available doses can be administered in a short time (negligible with respect to the evolution of the epidemic). Then, we assume a limited vaccination capacity, so the doses are administered in a time non-negligible with respect to the evolution of the epidemic. We develop optimal strategies for the various social parameters, where a strategy consists of (1) the fraction of vaccine that is administered to the vulnerable population and (2) the criterion that is used to administer it to the general population. In the case of a limited vaccination capacity, the fraction (1) is a function of time, and we study how to optimize it to obtain a maximal reduction in the number of fatalities.
{"title":"Optimal COVID-19 Vaccination Strategies with Limited Vaccine and Delivery Capabilities","authors":"S. Santini","doi":"10.1145/3466622","DOIUrl":"https://doi.org/10.1145/3466622","url":null,"abstract":"We develop a model of infection spread that takes into account the existence of a vulnerable group as well as the variability of the social relations of individuals. We develop a compartmentalized power-law model, with power-law connections between the vulnerable and the general population, considering these connections as well as the connections among the vulnerable as parameters that we vary in our tests. We use the model to study a number of vaccination strategies under two hypotheses: first, we assume a limited availability of vaccine but an infinite vaccination capacity, so all the available doses can be administered in a short time (negligible with respect to the evolution of the epidemic). Then, we assume a limited vaccination capacity, so the doses are administered in a time non-negligible with respect to the evolution of the epidemic. We develop optimal strategies for the various social parameters, where a strategy consists of (1) the fraction of vaccine that is administered to the vulnerable population and (2) the criterion that is used to administer it to the general population. In the case of a limited vaccination capacity, the fraction (1) is a function of time, and we study how to optimize it to obtain a maximal reduction in the number of fatalities.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"2 1","pages":"1 - 16"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44165555","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}
M. R. Ali, Taylan K. Sen, Qianyi Li, Raina Langevin, Taylor Myers, E. Dorsey, Saloni Sharma, E. Hoque
We developed an intelligent web interface that guides users to perform several Parkinson’s disease (PD) motion assessment tests in front of their webcam. After gathering data from 329 participants (N = 199 with PD, N = 130 without PD), we developed a methodology for measuring head motion randomness based on the frequency distribution of the motion. We found PD is associated with significantly higher randomness in side-to-side head motion as measured by the variance and number of large frequency components compared to the age-matched non-PD control group (p = 0.001, d = 0.13). Additionally, in participants taking levodopa (N = 151), the most common drug to treat Parkinson’s, the degree of random side-to-side head motion was found to follow an exponential-decay activity model following the time of the last dose taken (r = −0.404, p = 6e-5). A logistic regression model for classifying PD vs. non-PD groups identified that higher frequency components are more associated with PD. Our findings could potentially be useful toward objectively quantifying differences in head motions that may be due to either PD or PD medications.
我们开发了一个智能网络界面，指导用户在他们的网络摄像头前进行几项帕金森病(PD)运动评估测试。在收集了329名参与者(N = 199患有PD, N = 130没有PD)的数据后，我们开发了一种基于运动频率分布的测量头部运动随机性的方法。我们发现，与年龄匹配的非PD对照组相比，PD与侧对侧头部运动的随机性显著更高(p = 0.001, d = 0.13)。此外，在服用左旋多巴(N = 151)(治疗帕金森病最常见的药物)的参与者中，发现随机左右头部运动的程度随最后一次服用剂量的时间呈指数衰减活动模型(r = - 0.404, p = 6e-5)。对PD组和非PD组进行分类的逻辑回归模型发现，高频成分与PD的关联更大。我们的研究结果可能有助于客观地量化PD或PD药物引起的头部运动差异。
{"title":"Analyzing Head Pose in Remotely Collected Videos of People with Parkinson’s Disease","authors":"M. R. Ali, Taylan K. Sen, Qianyi Li, Raina Langevin, Taylor Myers, E. Dorsey, Saloni Sharma, E. Hoque","doi":"10.1145/3459669","DOIUrl":"https://doi.org/10.1145/3459669","url":null,"abstract":"We developed an intelligent web interface that guides users to perform several Parkinson’s disease (PD) motion assessment tests in front of their webcam. After gathering data from 329 participants (N = 199 with PD, N = 130 without PD), we developed a methodology for measuring head motion randomness based on the frequency distribution of the motion. We found PD is associated with significantly higher randomness in side-to-side head motion as measured by the variance and number of large frequency components compared to the age-matched non-PD control group (p = 0.001, d = 0.13). Additionally, in participants taking levodopa (N = 151), the most common drug to treat Parkinson’s, the degree of random side-to-side head motion was found to follow an exponential-decay activity model following the time of the last dose taken (r = −0.404, p = 6e-5). A logistic regression model for classifying PD vs. non-PD groups identified that higher frequency components are more associated with PD. Our findings could potentially be useful toward objectively quantifying differences in head motions that may be due to either PD or PD medications.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"2 1","pages":"1 - 13"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42904975","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}
Maura Bellio, D. Furniss, N. Oxtoby, Sara Garbarino, Nicholas C. Firth, A. Ribbens, D. Alexander, A. Blandford
Clinical decision-support tools (DSTs) represent a valuable resource in healthcare. However, lack of Human Factors considerations and early design research has often limited their successful adoption. To complement previous technically focused work, we studied adoption opportunities of a future DST built on a predictive model of Alzheimer’s Disease (AD) progression. Our aim is two-fold: exploring adoption opportunities for DSTs in AD clinical care, and testing a novel combination of methods to support this process. We focused on understanding current clinical needs and practices, and the potential for such a tool to be integrated into the setting, prior to its development. Our user-centred approach was based on field observations and semi-structured interviews, analysed through workflow analysis, user profiles, and a design-reality gap model. The first two are common practice, whilst the latter provided added value in highlighting specific adoption needs. We identified the likely early adopters of the tool as being both psychiatrists and neurologists based in research-oriented clinical settings. We defined ten key requirements for the translation and adoption of DSTs for AD around IT, user, and contextual factors. Future works can use and build on these requirements to stand a greater chance to get adopted in the clinical setting.
{"title":"Opportunities and Barriers for Adoption of a Decision-Support Tool for Alzheimer’s Disease","authors":"Maura Bellio, D. Furniss, N. Oxtoby, Sara Garbarino, Nicholas C. Firth, A. Ribbens, D. Alexander, A. Blandford","doi":"10.1145/3462764","DOIUrl":"https://doi.org/10.1145/3462764","url":null,"abstract":"Clinical decision-support tools (DSTs) represent a valuable resource in healthcare. However, lack of Human Factors considerations and early design research has often limited their successful adoption. To complement previous technically focused work, we studied adoption opportunities of a future DST built on a predictive model of Alzheimer’s Disease (AD) progression. Our aim is two-fold: exploring adoption opportunities for DSTs in AD clinical care, and testing a novel combination of methods to support this process. We focused on understanding current clinical needs and practices, and the potential for such a tool to be integrated into the setting, prior to its development. Our user-centred approach was based on field observations and semi-structured interviews, analysed through workflow analysis, user profiles, and a design-reality gap model. The first two are common practice, whilst the latter provided added value in highlighting specific adoption needs. We identified the likely early adopters of the tool as being both psychiatrists and neurologists based in research-oriented clinical settings. We defined ten key requirements for the translation and adoption of DSTs for AD around IT, user, and contextual factors. Future works can use and build on these requirements to stand a greater chance to get adopted in the clinical setting.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"2 1","pages":"1 - 19"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44384201","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}
Zhaohong Sun, Wei Dong, Jinlong Shi, K. He, Zhengxing Huang
Survival analysis exhibits profound effects on health service management. Traditional approaches for survival analysis have a pre-assumption on the time-to-event probability distribution and seldom consider sequential visits of patients on medical facilities. Although recent studies leverage the merits of deep learning techniques to capture non-linear features and long-term dependencies within multiple visits for survival analysis, the lack of interpretability prevents deep learning models from being applied to clinical practice. To address this challenge, this article proposes a novel attention-based deep recurrent model, named AttenSurv, for clinical survival analysis. Specifically, a global attention mechanism is proposed to extract essential/critical risk factors for interpretability improvement. Thereafter, Bi-directional Long Short-Term Memory is employed to capture the long-term dependency on data from a series of visits of patients. To further improve both the prediction performance and the interpretability of the proposed model, we propose another model, named GNNAttenSurv, by incorporating a graph neural network into AttenSurv, to extract the latent correlations between risk factors. We validated our solution on three public follow-up datasets and two electronic health record datasets. The results demonstrated that our proposed models yielded consistent improvement compared to the state-of-the-art baselines on survival analysis.
{"title":"Attention-Based Deep Recurrent Model for Survival Prediction","authors":"Zhaohong Sun, Wei Dong, Jinlong Shi, K. He, Zhengxing Huang","doi":"10.1145/3466782","DOIUrl":"https://doi.org/10.1145/3466782","url":null,"abstract":"Survival analysis exhibits profound effects on health service management. Traditional approaches for survival analysis have a pre-assumption on the time-to-event probability distribution and seldom consider sequential visits of patients on medical facilities. Although recent studies leverage the merits of deep learning techniques to capture non-linear features and long-term dependencies within multiple visits for survival analysis, the lack of interpretability prevents deep learning models from being applied to clinical practice. To address this challenge, this article proposes a novel attention-based deep recurrent model, named AttenSurv, for clinical survival analysis. Specifically, a global attention mechanism is proposed to extract essential/critical risk factors for interpretability improvement. Thereafter, Bi-directional Long Short-Term Memory is employed to capture the long-term dependency on data from a series of visits of patients. To further improve both the prediction performance and the interpretability of the proposed model, we propose another model, named GNNAttenSurv, by incorporating a graph neural network into AttenSurv, to extract the latent correlations between risk factors. We validated our solution on three public follow-up datasets and two electronic health record datasets. The results demonstrated that our proposed models yielded consistent improvement compared to the state-of-the-art baselines on survival analysis.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"2 1","pages":"1 - 18"},"PeriodicalIF":0.0,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41328605","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}
Pratyay Banerjee, Kuntal Kumar Pal, M. Devarakonda, Chitta Baral
In this work, we formulated the named entity recognition (NER) task as a multi-answer knowledge guided question-answer task (KGQA) and showed that the knowledge guidance helps to achieve state-of-the-art results for 11 of 18 biomedical NER datasets. We prepended five different knowledge contexts—entity types, questions, definitions, and examples—to the input text and trained and tested BERT-based neural models on such input sequences from a combined dataset of the 18 different datasets. This novel formulation of the task (a) improved named entity recognition and illustrated the impact of different knowledge contexts, (b) reduced system confusion by limiting prediction to a single entity-class for each input token (i.e., B, I, O only) compared to multiple entity-classes in traditional NER (i.e., Bentity1, Bentity2, Ientity1, I, O), (c) made detection of nested entities easier, and (d) enabled the models to jointly learn NER-specific features from a large number of datasets. We performed extensive experiments of this KGQA formulation on the biomedical datasets, and through the experiments, we showed when knowledge improved named entity recognition. We analyzed the effect of the task formulation, the impact of the different knowledge contexts, the multi-task aspect of the generic format, and the generalization ability of KGQA. We also probed the model to better understand the key contributors for these improvements.
在这项工作中，我们将命名实体识别(NER)任务制定为多答案知识引导问答任务(KGQA)，并表明知识引导有助于18个生物医学NER数据集中的11个获得最先进的结果。我们为输入文本准备了五种不同的知识上下文——实体类型、问题、定义和示例，并在来自18个不同数据集的组合数据集的输入序列上训练和测试了基于bert的神经模型。这种任务的新公式(a)改进了命名实体识别，并说明了不同知识上下文的影响;(b)通过将每个输入标记的预测限制为单个实体类(即，b, I, O)，而不是传统NER中的多个实体类(即，Bentity1, Bentity2, Ientity1, I, O)，减少了系统混淆;(c)使嵌套实体的检测更容易;(d)使模型能够从大量数据集中共同学习NER特定的特征。我们在生物医学数据集上对这个KGQA公式进行了大量的实验，通过实验，我们展示了知识在什么时候提高了命名实体的识别。我们分析了任务制定的影响、不同知识背景的影响、通用格式的多任务方面的影响以及KGQA的泛化能力。我们还研究了该模型，以便更好地理解这些改进的关键贡献者。
{"title":"Biomedical Named Entity Recognition via Knowledge Guidance and Question Answering","authors":"Pratyay Banerjee, Kuntal Kumar Pal, M. Devarakonda, Chitta Baral","doi":"10.1145/3465221","DOIUrl":"https://doi.org/10.1145/3465221","url":null,"abstract":"In this work, we formulated the named entity recognition (NER) task as a multi-answer knowledge guided question-answer task (KGQA) and showed that the knowledge guidance helps to achieve state-of-the-art results for 11 of 18 biomedical NER datasets. We prepended five different knowledge contexts—entity types, questions, definitions, and examples—to the input text and trained and tested BERT-based neural models on such input sequences from a combined dataset of the 18 different datasets. This novel formulation of the task (a) improved named entity recognition and illustrated the impact of different knowledge contexts, (b) reduced system confusion by limiting prediction to a single entity-class for each input token (i.e., B, I, O only) compared to multiple entity-classes in traditional NER (i.e., Bentity1, Bentity2, Ientity1, I, O), (c) made detection of nested entities easier, and (d) enabled the models to jointly learn NER-specific features from a large number of datasets. We performed extensive experiments of this KGQA formulation on the biomedical datasets, and through the experiments, we showed when knowledge improved named entity recognition. We analyzed the effect of the task formulation, the impact of the different knowledge contexts, the multi-task aspect of the generic format, and the generalization ability of KGQA. We also probed the model to better understand the key contributors for these improvements.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":" ","pages":"1 - 24"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/3465221","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48654752","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}
Seyma Kucukozer-Cavdar, T. Taşkaya-Temizel, Abhinav Mehrotra, Mirco Musolesi, P. Tiňo
Understanding in which circumstances office workers take rest breaks is important for delivering effective mobile notifications and make inferences about their daily lifestyle, e.g., whether they are active and/or have a sedentary life. Previous studies designed for office workers show the effectiveness of rest breaks for preventing work-related conditions. In this article, we propose a hybrid personalised model involving a kernel density estimation model and a generalised linear mixed model to model office workers’ available moments for rest breaks during working hours. We adopt the experience-based sampling method through which we collected office workers’ responses regarding their availability through a mobile application with contextual information extracted by means of the mobile phone sensors. The experiment lasted 10 workdays and involved 19 office workers with a total of 528 responses. Our results show that time, location, ringer mode, and activity are effective features for predicting office workers’ availability. Our method can address sparse sample issues for building individual predictive behavioural models based on limited and unbalanced data. In particular, the proposed method can be considered as a potential solution to the “cold-start problem,” i.e., the negative impact of the lack of individual data when a new application is installed.
{"title":"Designing Robust Models for Behaviour Prediction Using Sparse Data from Mobile Sensing","authors":"Seyma Kucukozer-Cavdar, T. Taşkaya-Temizel, Abhinav Mehrotra, Mirco Musolesi, P. Tiňo","doi":"10.1145/3458753","DOIUrl":"https://doi.org/10.1145/3458753","url":null,"abstract":"Understanding in which circumstances office workers take rest breaks is important for delivering effective mobile notifications and make inferences about their daily lifestyle, e.g., whether they are active and/or have a sedentary life. Previous studies designed for office workers show the effectiveness of rest breaks for preventing work-related conditions. In this article, we propose a hybrid personalised model involving a kernel density estimation model and a generalised linear mixed model to model office workers’ available moments for rest breaks during working hours. We adopt the experience-based sampling method through which we collected office workers’ responses regarding their availability through a mobile application with contextual information extracted by means of the mobile phone sensors. The experiment lasted 10 workdays and involved 19 office workers with a total of 528 responses. Our results show that time, location, ringer mode, and activity are effective features for predicting office workers’ availability. Our method can address sparse sample issues for building individual predictive behavioural models based on limited and unbalanced data. In particular, the proposed method can be considered as a potential solution to the “cold-start problem,” i.e., the negative impact of the lack of individual data when a new application is installed.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":" ","pages":"1 - 33"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/3458753","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47583665","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}
Konstantinos Malavazos, M. Papadogiorgaki, Pavlos Malakonakis, I. Papaefstathiou
An emerging trend in biomedical systems research is the development of models that take full advantage of the increasing available computational power to manage and analyze new biological data as well as to model complex biological processes. Such biomedical models require significant computational resources, since they process and analyze large amounts of data, such as medical image sequences. We present a family of advanced computational models for the prediction of the spatio-temporal evolution of glioma and their novel implementation in state-of-the-art FPGA devices. Glioma is a rapidly evolving type of brain cancer, well known for its aggressive and diffusive behavior. The developed system simulates the glioma tumor growth in the brain tissue, which consists of different anatomic structures, by utilizing MRI slices. The presented models have been proved highly accurate in predicting the growth of the tumor, whereas the developed innovative hardware system, when implemented on a low-end, low-cost FPGA, is up to 85% faster than a high-end server consisting of 20 physical cores (and 40 virtual ones) and more than 28× more energy-efficient than it; the energy efficiency grows up to 50× and the speedup up to 14× if the presented designs are implemented in a high-end FPGA. Moreover, the proposed reconfigurable system, when implemented in a large FPGA, is significantly faster than a high-end GPU (i.e., from 80% and up to 250% faster), for the majority of the models, while it is also significantly better (i.e., from 80% to over 1,600%) in terms of power efficiency, for all the implemented models.
{"title":"Novel Reconfigurable Hardware Systems for Tumor Growth Prediction","authors":"Konstantinos Malavazos, M. Papadogiorgaki, Pavlos Malakonakis, I. Papaefstathiou","doi":"10.1145/3454126","DOIUrl":"https://doi.org/10.1145/3454126","url":null,"abstract":"An emerging trend in biomedical systems research is the development of models that take full advantage of the increasing available computational power to manage and analyze new biological data as well as to model complex biological processes. Such biomedical models require significant computational resources, since they process and analyze large amounts of data, such as medical image sequences. We present a family of advanced computational models for the prediction of the spatio-temporal evolution of glioma and their novel implementation in state-of-the-art FPGA devices. Glioma is a rapidly evolving type of brain cancer, well known for its aggressive and diffusive behavior. The developed system simulates the glioma tumor growth in the brain tissue, which consists of different anatomic structures, by utilizing MRI slices. The presented models have been proved highly accurate in predicting the growth of the tumor, whereas the developed innovative hardware system, when implemented on a low-end, low-cost FPGA, is up to 85% faster than a high-end server consisting of 20 physical cores (and 40 virtual ones) and more than 28× more energy-efficient than it; the energy efficiency grows up to 50× and the speedup up to 14× if the presented designs are implemented in a high-end FPGA. Moreover, the proposed reconfigurable system, when implemented in a large FPGA, is significantly faster than a high-end GPU (i.e., from 80% and up to 250% faster), for the majority of the models, while it is also significantly better (i.e., from 80% to over 1,600%) in terms of power efficiency, for all the implemented models.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":"2 1","pages":"1 - 27"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/3454126","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44700547","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}
With an aging and growing population, the number of women receiving mammograms is increasing. However, existing techniques for autonomous diagnosis do not surpass a well-trained radiologist. Therefore, to reduce the number of mammograms that require examination by a radiologist, subject to preserving the diagnostic accuracy observed in current clinical practice, we develop Man and Machine Mammography Oracle (MAMMO)—a clinical decision support system capable of determining whether its predicted diagnoses require further radiologist examination. We first introduce a novel multi-view convolutional neural network (CNN) trained using multi-task learning (MTL) to diagnose mammograms and predict the radiological assessments known to be associated with cancer. MTL improves diagnostic performance and triage efficiency while providing an additional layer of model interpretability. Furthermore, we introduce a novel triage network that takes as input the radiological assessment and diagnostic predictions of the multi-view CNN and determines whether the radiologist or CNN will most likely provide the correct diagnosis. Results obtained on a dataset of over 7,000 patients show that MAMMO reduced the number of diagnostic mammograms requiring radiologist reading by 42.8% while improving the overall diagnostic accuracy in comparison to readings done by radiologists alone.
{"title":"Triage of 2D Mammographic Images Using Multi-view Multi-task Convolutional Neural Networks","authors":"T. Kyono, F. Gilbert, M. Schaar","doi":"10.1145/3453166","DOIUrl":"https://doi.org/10.1145/3453166","url":null,"abstract":"With an aging and growing population, the number of women receiving mammograms is increasing. However, existing techniques for autonomous diagnosis do not surpass a well-trained radiologist. Therefore, to reduce the number of mammograms that require examination by a radiologist, subject to preserving the diagnostic accuracy observed in current clinical practice, we develop Man and Machine Mammography Oracle (MAMMO)—a clinical decision support system capable of determining whether its predicted diagnoses require further radiologist examination. We first introduce a novel multi-view convolutional neural network (CNN) trained using multi-task learning (MTL) to diagnose mammograms and predict the radiological assessments known to be associated with cancer. MTL improves diagnostic performance and triage efficiency while providing an additional layer of model interpretability. Furthermore, we introduce a novel triage network that takes as input the radiological assessment and diagnostic predictions of the multi-view CNN and determines whether the radiologist or CNN will most likely provide the correct diagnosis. Results obtained on a dataset of over 7,000 patients show that MAMMO reduced the number of diagnostic mammograms requiring radiologist reading by 42.8% while improving the overall diagnostic accuracy in comparison to readings done by radiologists alone.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":" ","pages":"1 - 24"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/3453166","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46394461","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}
The electrocardiogram (ECG) has been proven as an efficient diagnostic tool to monitor the electrical activity of the heart and has become a widely used clinical approach to diagnose heart diseases. In a practical way, the ECG signal can be decomposed into P, Q, R, S, and T waves. Based on the information of the features in these waves, such as the amplitude and the interval between each wave, many types of heart diseases can be detected by using the neural network (NN)-based ECG analysis approach. However, because of a large amount of computing to preprocess the raw ECG signal, it is time consuming to analyze the ECG signal in the time domain. In addition, the non-linear ECG signal analysis worsens the difficulty to diagnose the ECG signal. To solve the problem, we propose a fast ECG diagnosis approach based on spectral analysis and the artificial neural network. Compared with the conventional time-domain approaches, the proposed approach analyzes the ECG signal only in the frequency domain. However, because most of the noises in the raw ECG signal belong to high-frequency signals, it is necessary to acquire more features in the low-frequency spectrum and fewer features in the high-frequency spectrum. Hence, a non-uniform feature extraction approach is proposed in this article. According to less data preprocessing in the frequency domain than the one in the time domain, the proposed approach not only reduces the total diagnosis latency but also reduces the computing power consumption of the ECG diagnosis. To verify the proposed approach, the well-known MIT-BIH arrhythmia database is involved in this work. The experimental results show that the proposed approach can reduce ECG diagnosis latency by 47% to 52% compared with conventional ECG analysis methods under similar diagnostic accuracy of heart diseases. In addition, because of less data preprocessing, the proposed approach can achieve lower area overhead by 22% to 29% and lower computing power consumption by 29% to 34% compared with the related works, which is proper for applying this approach to portable medical devices.
{"title":"A Fast ECG Diagnosis by Using Non-Uniform Spectral Analysis and the Artificial Neural Network","authors":"K. Chen, Po-Chen Chien, Zi-Jie Gao, Chi-Hsun Wu","doi":"10.1145/3453174","DOIUrl":"https://doi.org/10.1145/3453174","url":null,"abstract":"The electrocardiogram (ECG) has been proven as an efficient diagnostic tool to monitor the electrical activity of the heart and has become a widely used clinical approach to diagnose heart diseases. In a practical way, the ECG signal can be decomposed into P, Q, R, S, and T waves. Based on the information of the features in these waves, such as the amplitude and the interval between each wave, many types of heart diseases can be detected by using the neural network (NN)-based ECG analysis approach. However, because of a large amount of computing to preprocess the raw ECG signal, it is time consuming to analyze the ECG signal in the time domain. In addition, the non-linear ECG signal analysis worsens the difficulty to diagnose the ECG signal. To solve the problem, we propose a fast ECG diagnosis approach based on spectral analysis and the artificial neural network. Compared with the conventional time-domain approaches, the proposed approach analyzes the ECG signal only in the frequency domain. However, because most of the noises in the raw ECG signal belong to high-frequency signals, it is necessary to acquire more features in the low-frequency spectrum and fewer features in the high-frequency spectrum. Hence, a non-uniform feature extraction approach is proposed in this article. According to less data preprocessing in the frequency domain than the one in the time domain, the proposed approach not only reduces the total diagnosis latency but also reduces the computing power consumption of the ECG diagnosis. To verify the proposed approach, the well-known MIT-BIH arrhythmia database is involved in this work. The experimental results show that the proposed approach can reduce ECG diagnosis latency by 47% to 52% compared with conventional ECG analysis methods under similar diagnostic accuracy of heart diseases. In addition, because of less data preprocessing, the proposed approach can achieve lower area overhead by 22% to 29% and lower computing power consumption by 29% to 34% compared with the related works, which is proper for applying this approach to portable medical devices.","PeriodicalId":72043,"journal":{"name":"ACM transactions on computing for healthcare","volume":" ","pages":"1 - 21"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/3453174","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47935708","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：