C. Bartenschlager, Stefanie S. Ebel, Sebastian Kling, J. Vehreschild, L. Zabel, C. Spinner, Andreas Schuler, Axel R. Heller, S. Borgmann, Reinhard Hoffmann, S. Rieg, H. Messmann, M. Hower, J. Brunner, F. Hanses, C. Römmele
For the fight against the COVID-19 pandemic, it is particularly important to map the course of infection, in terms of patients who have currently tested SARS-CoV-2 positive, as accurately as possible. In hospitals, this is even more important because resources have become scarce. Although polymerase chain reaction (PCR) and point of care (POC) antigen testing capacities have been massively expanded, they are often very time-consuming and cost-intensive and, in some cases, lack appropriate performance. To meet these challenges, we propose the COVIDAL classifier for AI-based diagnosis of symptomatic COVID-19 subjects in hospitals based on laboratory parameters. We evaluate the algorithm's performance by unique multicenter data with approximately 4,000 patients and an extraordinary high ratio of SARS-CoV-2-positive patients. We analyze the influence of data preparation, flexibility in optimization targets, as well as the selection of the test set on the COVIDAL outcome. The algorithm is compared with standard AI, PCR, POC antigen testing and manual classifications of seven physicians by a decision theoretic scoring model including performance metrics, turnaround times and cost. Thereby, we define health care settings in which a certain classifier for COVID-19 diagnosis is to be applied. We find sensitivities, specificities, and accuracies of the COVIDAL algorithm of up to 90 percent. Our scoring model suggests using PCR testing for a focus on performance metrics. For turnaround times, POC antigen testing should be used. If balancing performance, turnaround times, and cost is of interest, as, for example, in the emergency department, COVIDAL is superior based on the scoring model.
{"title":"COVIDAL: A Machine Learning Classifier for Digital COVID-19 Diagnosis in German Hospitals","authors":"C. Bartenschlager, Stefanie S. Ebel, Sebastian Kling, J. Vehreschild, L. Zabel, C. Spinner, Andreas Schuler, Axel R. Heller, S. Borgmann, Reinhard Hoffmann, S. Rieg, H. Messmann, M. Hower, J. Brunner, F. Hanses, C. Römmele","doi":"10.1145/3567431","DOIUrl":"https://doi.org/10.1145/3567431","url":null,"abstract":"For the fight against the COVID-19 pandemic, it is particularly important to map the course of infection, in terms of patients who have currently tested SARS-CoV-2 positive, as accurately as possible. In hospitals, this is even more important because resources have become scarce. Although polymerase chain reaction (PCR) and point of care (POC) antigen testing capacities have been massively expanded, they are often very time-consuming and cost-intensive and, in some cases, lack appropriate performance. To meet these challenges, we propose the COVIDAL classifier for AI-based diagnosis of symptomatic COVID-19 subjects in hospitals based on laboratory parameters. We evaluate the algorithm's performance by unique multicenter data with approximately 4,000 patients and an extraordinary high ratio of SARS-CoV-2-positive patients. We analyze the influence of data preparation, flexibility in optimization targets, as well as the selection of the test set on the COVIDAL outcome. The algorithm is compared with standard AI, PCR, POC antigen testing and manual classifications of seven physicians by a decision theoretic scoring model including performance metrics, turnaround times and cost. Thereby, we define health care settings in which a certain classifier for COVID-19 diagnosis is to be applied. We find sensitivities, specificities, and accuracies of the COVIDAL algorithm of up to 90 percent. Our scoring model suggests using PCR testing for a focus on performance metrics. For turnaround times, POC antigen testing should be used. If balancing performance, turnaround times, and cost is of interest, as, for example, in the emergency department, COVIDAL is superior based on the scoring model.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":"14 1","pages":"1 - 16"},"PeriodicalIF":2.5,"publicationDate":"2022-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44720109","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}
Yixiang Hu, Xiaoheng Deng, Congxu Zhu, Xuechen Chen, Laixin Chi
Integrating wireless power transfer with mobile edge computing (MEC) has become a powerful solution for increasingly complicated and dynamic industrial Internet of Things (IIOT) systems. However, the traditional approaches overlooked the heterogeneity of the tasks and the dynamic arrival of energy in wirelessly powered MEC-enabled IIOT systems. In this article, we formulate the problem of maximizing the product of the computing rate and the task execution success rate for heterogeneous tasks. To manage energy harvesting adaptively and select appropriate computing modes, we devise an online resource allocation and computation offloading approach based on deep reinforcement learning. We decompose this approach into two stages: an offloading decision stage and a stopping decision stage. The purpose of the offloading decision stage is to select the computing mode and dynamically allocate the computation round length for each task after learning from the channel state information and the task experience. This stage allows the system to support heterogeneous computing tasks. Subsequently, in the second stage, we adaptively adjust the number of fading slots devoted to energy harvesting in each round in accordance with the status of each fading slot. Simulation results show that our proposed algorithm can better allocate resources for heterogeneous tasks and reduce the ratio of failed tasks and energy consumption when compared with several existing algorithms.
{"title":"Resource Allocation for Heterogeneous Computing Tasks in Wirelessly Powered MEC-enabled IIOT Systems","authors":"Yixiang Hu, Xiaoheng Deng, Congxu Zhu, Xuechen Chen, Laixin Chi","doi":"10.1145/3571291","DOIUrl":"https://doi.org/10.1145/3571291","url":null,"abstract":"Integrating wireless power transfer with mobile edge computing (MEC) has become a powerful solution for increasingly complicated and dynamic industrial Internet of Things (IIOT) systems. However, the traditional approaches overlooked the heterogeneity of the tasks and the dynamic arrival of energy in wirelessly powered MEC-enabled IIOT systems. In this article, we formulate the problem of maximizing the product of the computing rate and the task execution success rate for heterogeneous tasks. To manage energy harvesting adaptively and select appropriate computing modes, we devise an online resource allocation and computation offloading approach based on deep reinforcement learning. We decompose this approach into two stages: an offloading decision stage and a stopping decision stage. The purpose of the offloading decision stage is to select the computing mode and dynamically allocate the computation round length for each task after learning from the channel state information and the task experience. This stage allows the system to support heterogeneous computing tasks. Subsequently, in the second stage, we adaptively adjust the number of fading slots devoted to energy harvesting in each round in accordance with the status of each fading slot. Simulation results show that our proposed algorithm can better allocate resources for heterogeneous tasks and reduce the ratio of failed tasks and energy consumption when compared with several existing algorithms.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":" ","pages":"1 - 17"},"PeriodicalIF":2.5,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46036812","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}
Patricia Akello, Naga Vemprala, Nicole Lang Beebe, Kim-Kwang Raymond Choo
In the United States and around the world, gun violence has become a long-standing public safety concern and a security threat, due to violent gun-related crimes, injuries, and fatalities. Although legislators and lawmakers have attempted to mitigate its threats through legislation, research on gun violence confirms the need for a comprehensive approach to gun violence prevention. This entails addressing the problem in as many ways as possible, such as through legislation, new technological advancements, re-engineering supply, and administrative protocols, among others. The research focuses on the technological, supply, and administrative aspects, in which we propose a manner of managing gun-related data efficiently from the point of manufacture/sale, as well as at points of transfers between secondary sellers for the improvement of criminal investigation processes. Making data more readily available with greater integrity will facilitate successful investigations and prosecutions of gun crimes. Currently, there is no single and uniform platform for firearm manufacturers, dealers, and other stakeholders involved in firearm sales, dissemination, management, and investigation. With the help of Blockchain technology, gun registry, ownership, transfers, and, most importantly, investigations, when crimes occur, can all be managed efficiently, breaking the cycle of gun violence. The identification of guns, gun tracing, and identification of gun owners/possessors rely on accuracy, integrity, and consistency in related systems to influence gun crime investigation processes. Blockchain technology, which uses a consensus-based approach to improve processes and transactions, is demonstrated in this study as a way to enhance these procedures. To the best of our knowledge, this is the first study to explore and demonstrate the utility of Blockchain for gun-related criminal investigations using a design science approach.
{"title":"Blockchain Use Case in Ballistics and Crime Gun Tracing and Intelligence: Toward Overcoming Gun Violence","authors":"Patricia Akello, Naga Vemprala, Nicole Lang Beebe, Kim-Kwang Raymond Choo","doi":"10.1145/3571290","DOIUrl":"https://doi.org/10.1145/3571290","url":null,"abstract":"In the United States and around the world, gun violence has become a long-standing public safety concern and a security threat, due to violent gun-related crimes, injuries, and fatalities. Although legislators and lawmakers have attempted to mitigate its threats through legislation, research on gun violence confirms the need for a comprehensive approach to gun violence prevention. This entails addressing the problem in as many ways as possible, such as through legislation, new technological advancements, re-engineering supply, and administrative protocols, among others. The research focuses on the technological, supply, and administrative aspects, in which we propose a manner of managing gun-related data efficiently from the point of manufacture/sale, as well as at points of transfers between secondary sellers for the improvement of criminal investigation processes. Making data more readily available with greater integrity will facilitate successful investigations and prosecutions of gun crimes. Currently, there is no single and uniform platform for firearm manufacturers, dealers, and other stakeholders involved in firearm sales, dissemination, management, and investigation. With the help of Blockchain technology, gun registry, ownership, transfers, and, most importantly, investigations, when crimes occur, can all be managed efficiently, breaking the cycle of gun violence. The identification of guns, gun tracing, and identification of gun owners/possessors rely on accuracy, integrity, and consistency in related systems to influence gun crime investigation processes. Blockchain technology, which uses a consensus-based approach to improve processes and transactions, is demonstrated in this study as a way to enhance these procedures. To the best of our knowledge, this is the first study to explore and demonstrate the utility of Blockchain for gun-related criminal investigations using a design science approach.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":"14 1","pages":"1 - 26"},"PeriodicalIF":2.5,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48830328","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}
For Internet of Vehicles applications, reliable autonomous driving systems usually perform the majority of their computations on the cloud due to the limited computing power of edge devices. The communication delay between cloud platforms and edge devices, however, can cause dangerous consequences, particularly for latency-sensitive object detection tasks. Object detection tasks are also vulnerable to significantly degraded model performance caused by unknown objects, which creates unsafe driving conditions. To address these problems, this study develops an orchestrated system that allows real-time object detection and incrementally learns unknown objects in a complex and dynamic environment. A you-only-look-once–based object detection model in edge computing mode uses thermal images to detect objects accurately in poor lighting conditions. In addition, an attention mechanism improves the system’s performance without significantly increasing model complexity. An unknown object detector automatically classifies and labels unknown objects without direct supervision on edge devices, while a roadside unit (RSU)-based mechanism is developed to update classes and ensure a secure driving experience for autonomous vehicles. Moreover, the interactions between edge devices, RSU servers, and the cloud are designed to allow efficient collaboration. The experimental results indicate that the proposed system learns uncategorized objects dynamically and detects instances accurately.
{"title":"Roadside Unit-based Unknown Object Detection in Adverse Weather Conditions for Smart Internet of Vehicles","authors":"Yu-Chia Chen, Sin-Ye Jhong, Chih-Hsien Hsia","doi":"10.1145/3554923","DOIUrl":"https://doi.org/10.1145/3554923","url":null,"abstract":"For Internet of Vehicles applications, reliable autonomous driving systems usually perform the majority of their computations on the cloud due to the limited computing power of edge devices. The communication delay between cloud platforms and edge devices, however, can cause dangerous consequences, particularly for latency-sensitive object detection tasks. Object detection tasks are also vulnerable to significantly degraded model performance caused by unknown objects, which creates unsafe driving conditions. To address these problems, this study develops an orchestrated system that allows real-time object detection and incrementally learns unknown objects in a complex and dynamic environment. A you-only-look-once–based object detection model in edge computing mode uses thermal images to detect objects accurately in poor lighting conditions. In addition, an attention mechanism improves the system’s performance without significantly increasing model complexity. An unknown object detector automatically classifies and labels unknown objects without direct supervision on edge devices, while a roadside unit (RSU)-based mechanism is developed to update classes and ensure a secure driving experience for autonomous vehicles. Moreover, the interactions between edge devices, RSU servers, and the cloud are designed to allow efficient collaboration. The experimental results indicate that the proposed system learns uncategorized objects dynamically and detects instances accurately.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":"13 1","pages":"1 - 21"},"PeriodicalIF":2.5,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46352122","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}
Xue Chen, Cheng Wang, Qing Yang, Teng Hu, Changjun Jiang
Data collection under local differential privacy (LDP) has been gradually on the stage. Compared with the implementation of LDP on the single attribute data collection, that on multi-dimensional data faces great challenges as follows: (1) Communication cost. Multivariate data collection needs to retain the correlations between attributes, which means that more complex privatization mechanisms will result in more communication costs. (2) Noise scale. More attributes have to share the privacy budget limited by data utility and privacy-preserving level, which means that less privacy budget can be allocated to each of them, resulting in more noise added to the data. In this work, we innovatively reverse the complex multi-dimensional attributes, i.e., the major negative factor that leads to the above difficulties, to act as a beneficial factor to improve the efficiency of privacy budget allocation, so as to realize a multi-dimensional data collection under LDP with high comprehensive performance. Specifically, we first present a Multivariate k-ary Randomized Response (kRR) mechanism, called Multi-kRR. It applies the RR directly to each attribute to reduce the communication cost. To deal with the impact of a large amount of noise, we propose a Markov-based dynamic privacy budget allocation mechanism Markov-kRR, which determines the present privacy budget (flipping probability) of an attribute related to the state of the previous attributes. Then, we fix the threshold of flipping times in Markov-kRR and propose an improved mechanism called MarkFixed-kRR, which can obtain more optimized utility by choosing the suitable threshold. Finally, extensive experiments demonstrate the efficiency and effectiveness of our proposed methods.
{"title":"The Opportunity in Difficulty: A Dynamic Privacy Budget Allocation Mechanism for Privacy-Preserving Multi-dimensional Data Collection","authors":"Xue Chen, Cheng Wang, Qing Yang, Teng Hu, Changjun Jiang","doi":"10.1145/3569944","DOIUrl":"https://doi.org/10.1145/3569944","url":null,"abstract":"Data collection under local differential privacy (LDP) has been gradually on the stage. Compared with the implementation of LDP on the single attribute data collection, that on multi-dimensional data faces great challenges as follows: (1) Communication cost. Multivariate data collection needs to retain the correlations between attributes, which means that more complex privatization mechanisms will result in more communication costs. (2) Noise scale. More attributes have to share the privacy budget limited by data utility and privacy-preserving level, which means that less privacy budget can be allocated to each of them, resulting in more noise added to the data. In this work, we innovatively reverse the complex multi-dimensional attributes, i.e., the major negative factor that leads to the above difficulties, to act as a beneficial factor to improve the efficiency of privacy budget allocation, so as to realize a multi-dimensional data collection under LDP with high comprehensive performance. Specifically, we first present a Multivariate k-ary Randomized Response (kRR) mechanism, called Multi-kRR. It applies the RR directly to each attribute to reduce the communication cost. To deal with the impact of a large amount of noise, we propose a Markov-based dynamic privacy budget allocation mechanism Markov-kRR, which determines the present privacy budget (flipping probability) of an attribute related to the state of the previous attributes. Then, we fix the threshold of flipping times in Markov-kRR and propose an improved mechanism called MarkFixed-kRR, which can obtain more optimized utility by choosing the suitable threshold. Finally, extensive experiments demonstrate the efficiency and effectiveness of our proposed methods.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":" ","pages":"1 - 24"},"PeriodicalIF":2.5,"publicationDate":"2022-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43565695","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 models fuel many modern decision support systems, because they typically provide high predictive performance. Among other domains, deep learning is used in real-estate appraisal, where it allows extending the analysis from hard facts only (e.g., size, age) to also consider more implicit information about the location or appearance of houses in the form of image data. However, one downside of deep learning models is their intransparent mechanic of decision making, which leads to a trade-off between accuracy and interpretability. This limits their applicability for tasks where a justification of the decision is necessary. Therefore, in this article, we first combine different perspectives on interpretability into a multi-dimensional framework for a socio-technical perspective on explainable artificial intelligence. Second, we measure the performance gains of using multi-view deep learning, which leverages additional image data (satellite images) for real estate appraisal. Third, we propose and test a novel post hoc explainability method called Grad-Ram. This modified version of Grad-Cam mitigates the intransparency of convolutional neural networks for predicting continuous outcome variables. With this, we try to reduce the accuracy-interpretability trade-off of multi-view deep learning models. Our proposed network architecture outperforms traditional hedonic regression models by 34% in terms of MAE. Furthermore, we find that the used satellite images are the second most important predictor after square feet in our model and that the network learns interpretable patterns about the neighborhood structure and density.
{"title":"Tackling the Accuracy-Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal","authors":"Jan-Peter Kucklick, Oliver Müller","doi":"10.1145/3567430","DOIUrl":"https://doi.org/10.1145/3567430","url":null,"abstract":"Deep learning models fuel many modern decision support systems, because they typically provide high predictive performance. Among other domains, deep learning is used in real-estate appraisal, where it allows extending the analysis from hard facts only (e.g., size, age) to also consider more implicit information about the location or appearance of houses in the form of image data. However, one downside of deep learning models is their intransparent mechanic of decision making, which leads to a trade-off between accuracy and interpretability. This limits their applicability for tasks where a justification of the decision is necessary. Therefore, in this article, we first combine different perspectives on interpretability into a multi-dimensional framework for a socio-technical perspective on explainable artificial intelligence. Second, we measure the performance gains of using multi-view deep learning, which leverages additional image data (satellite images) for real estate appraisal. Third, we propose and test a novel post hoc explainability method called Grad-Ram. This modified version of Grad-Cam mitigates the intransparency of convolutional neural networks for predicting continuous outcome variables. With this, we try to reduce the accuracy-interpretability trade-off of multi-view deep learning models. Our proposed network architecture outperforms traditional hedonic regression models by 34% in terms of MAE. Furthermore, we find that the used satellite images are the second most important predictor after square feet in our model and that the network learns interpretable patterns about the neighborhood structure and density.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":"14 1","pages":"1 - 24"},"PeriodicalIF":2.5,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42515829","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}
Enduring effects of the COVID-19 pandemic on healthcare systems can be preempted by identifying patterns in diseases recorded in hospital visits over time. Disease multimorbidity or simultaneous occurrence of multiple diseases is a growing global public health challenge as populations age and long-term conditions become more prevalent. We propose a graph analytics framework for analyzing disease multimorbidity in hospital visits. Within the framework, we propose a graph model to explain multimorbidity as a function of prevalence, category, and chronic nature of the underlying disease. We apply our model to examine and compare multimorbidity patterns in public hospitals in Arizona, U.S., during five six-month time periods before and during the pandemic. We observe that while multimorbidity increased by 34.26% and 41.04% during peak pandemic for mental disorders and respiratory disorders respectively, the gradients for endocrine diseases and circulatory disorders were not significant. Multimorbidity for acute conditions is observed to be decreasing during the pandemic while multimorbidity for chronic conditions remains unchanged. Our graph analytics framework provides guidelines for empirical analysis of disease multimorbidity using electronic health records. The patterns identified using our proposed graph model informs future research and healthcare policy makers for pre-emptive decision making.
{"title":"Examining Disease Multimorbidity in U.S. Hospital Visits Before and During COVID-19 Pandemic: A Graph Analytics Approach","authors":"Karthik Srinivasan, Jinhang Jiang","doi":"10.1145/3564274","DOIUrl":"https://doi.org/10.1145/3564274","url":null,"abstract":"Enduring effects of the COVID-19 pandemic on healthcare systems can be preempted by identifying patterns in diseases recorded in hospital visits over time. Disease multimorbidity or simultaneous occurrence of multiple diseases is a growing global public health challenge as populations age and long-term conditions become more prevalent. We propose a graph analytics framework for analyzing disease multimorbidity in hospital visits. Within the framework, we propose a graph model to explain multimorbidity as a function of prevalence, category, and chronic nature of the underlying disease. We apply our model to examine and compare multimorbidity patterns in public hospitals in Arizona, U.S., during five six-month time periods before and during the pandemic. We observe that while multimorbidity increased by 34.26% and 41.04% during peak pandemic for mental disorders and respiratory disorders respectively, the gradients for endocrine diseases and circulatory disorders were not significant. Multimorbidity for acute conditions is observed to be decreasing during the pandemic while multimorbidity for chronic conditions remains unchanged. Our graph analytics framework provides guidelines for empirical analysis of disease multimorbidity using electronic health records. The patterns identified using our proposed graph model informs future research and healthcare policy makers for pre-emptive decision making.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":"14 1","pages":"1 - 17"},"PeriodicalIF":2.5,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42638148","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}
Sanne van der Linden, R. Sevastjanova, M. Funk, Mennatallah El-Assady
Healthcare systems are under pressure from an aging population, rising costs, and increasingly complex conditions and treatments. Although data are determined to play a bigger role in how doctors diagnose and prescribe treatments, they struggle due to a lack of time and an abundance of structured and unstructured information. To address this challenge, we introduce MediCoSpace, a visual decision-support tool for more efficient doctor-patient consultations. The tool links patient reports to past and present diagnoses, diseases, drugs, and treatments, both for the current patient and other patients in comparable situations. MediCoSpace uses textual medical data, deep-learning supported text analysis and concept spaces to facilitate a visual discovery process. The tool is evaluated by five medical doctors. The results show that MediCoSpace facilitates a promising, yet complex way to discover unlikely relations and thus suggests a path toward the development of interactive visual tools to provide physicians with more holistic diagnoses and personalized, dynamic treatments for patients.
{"title":"MediCoSpace: Visual Decision-Support for Doctor-Patient Consultations using Medical Concept Spaces from EHRs","authors":"Sanne van der Linden, R. Sevastjanova, M. Funk, Mennatallah El-Assady","doi":"10.1145/3564275","DOIUrl":"https://doi.org/10.1145/3564275","url":null,"abstract":"Healthcare systems are under pressure from an aging population, rising costs, and increasingly complex conditions and treatments. Although data are determined to play a bigger role in how doctors diagnose and prescribe treatments, they struggle due to a lack of time and an abundance of structured and unstructured information. To address this challenge, we introduce MediCoSpace, a visual decision-support tool for more efficient doctor-patient consultations. The tool links patient reports to past and present diagnoses, diseases, drugs, and treatments, both for the current patient and other patients in comparable situations. MediCoSpace uses textual medical data, deep-learning supported text analysis and concept spaces to facilitate a visual discovery process. The tool is evaluated by five medical doctors. The results show that MediCoSpace facilitates a promising, yet complex way to discover unlikely relations and thus suggests a path toward the development of interactive visual tools to provide physicians with more holistic diagnoses and personalized, dynamic treatments for patients.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":"14 1","pages":"1 - 20"},"PeriodicalIF":2.5,"publicationDate":"2022-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45739901","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}
Wearables are an important source of big data, as they provide real-time high-resolution data logs of health indicators of individuals. Higher-order associations between pairs of variables is common in wearables data. Representing higher-order association curves as piecewise linear segments in a regression model makes them more interpretable. However, existing methods for identifying the change points for segmented modeling either overfit or have low external validity for wearables data containing repeated measures. Therefore, we propose a human-in-the-loop method for segmented modeling of higher-order pairwise associations between variables in wearables data. Our method uses the smooth function estimated by a generalized additive mixed model to allow the analyst to annotate change point estimates for a segmented mixed-effects model, and thereafter employs Brent's constrained optimization procedure to fine-tune the manually provided estimates. We validate our method using three real-world wearables datasets. Our method not only outperforms state-of-the-art modeling methods in terms of prediction performance but also provides more interpretable results. Our study contributes to health data science in terms of developing a new method for interpretable modeling of wearables data. Our analysis uncovers interesting insights on higher-order associations for health researchers.
{"title":"A Human-in-the-Loop Segmented Mixed-Effects Modeling Method for Analyzing Wearables Data","authors":"Karthik Srinivasan, Faiz Currim, S. Ram","doi":"10.1145/3564276","DOIUrl":"https://doi.org/10.1145/3564276","url":null,"abstract":"Wearables are an important source of big data, as they provide real-time high-resolution data logs of health indicators of individuals. Higher-order associations between pairs of variables is common in wearables data. Representing higher-order association curves as piecewise linear segments in a regression model makes them more interpretable. However, existing methods for identifying the change points for segmented modeling either overfit or have low external validity for wearables data containing repeated measures. Therefore, we propose a human-in-the-loop method for segmented modeling of higher-order pairwise associations between variables in wearables data. Our method uses the smooth function estimated by a generalized additive mixed model to allow the analyst to annotate change point estimates for a segmented mixed-effects model, and thereafter employs Brent's constrained optimization procedure to fine-tune the manually provided estimates. We validate our method using three real-world wearables datasets. Our method not only outperforms state-of-the-art modeling methods in terms of prediction performance but also provides more interpretable results. Our study contributes to health data science in terms of developing a new method for interpretable modeling of wearables data. Our analysis uncovers interesting insights on higher-order associations for health researchers.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":" ","pages":"1 - 17"},"PeriodicalIF":2.5,"publicationDate":"2022-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43059790","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}
Pascal Fechner, Fabian König, Wolfgang Kratsch, Jannik Lockl, Maximilian Röglinger
Patients living with neurogenic bladder dysfunction can lose the sensation of their bladder filling. To avoid over-distension of the urinary bladder and prevent long-term damage to the urinary tract, the gold standard treatment is clean intermittent catheterization at predefined time intervals. However, the emptying schedule does not consider actual bladder volume, meaning that catheterization is performed more often than necessary, which can lead to complications such as urinary tract infections. Time-consuming catheterization also interferes with patients' daily routines and, in the case of an empty bladder, uses human and material resources unnecessarily. To enable individually tailored and volume-responsive bladder management, we design a model for the continuous monitoring of bladder volume. During our design science research process, we evaluate the model's applicability and usefulness through interviews with affected patients, prototyping, and application to a real-world in vivo dataset. The developed prototype predicts bladder volume based on relevant sensor data (i.e., near-infrared spectroscopy and acceleration) and the time elapsed since the previous micturition. Our comparison of several supervised state-of-the-art machine and deep learning models reveals that a long short-term memory network architecture achieves a mean absolute error of 116.7 ml that can improve bladder management for patients.
{"title":"Near-Infrared Spectroscopy for Bladder Monitoring: A Machine Learning Approach","authors":"Pascal Fechner, Fabian König, Wolfgang Kratsch, Jannik Lockl, Maximilian Röglinger","doi":"10.1145/3563779","DOIUrl":"https://doi.org/10.1145/3563779","url":null,"abstract":"Patients living with neurogenic bladder dysfunction can lose the sensation of their bladder filling. To avoid over-distension of the urinary bladder and prevent long-term damage to the urinary tract, the gold standard treatment is clean intermittent catheterization at predefined time intervals. However, the emptying schedule does not consider actual bladder volume, meaning that catheterization is performed more often than necessary, which can lead to complications such as urinary tract infections. Time-consuming catheterization also interferes with patients' daily routines and, in the case of an empty bladder, uses human and material resources unnecessarily. To enable individually tailored and volume-responsive bladder management, we design a model for the continuous monitoring of bladder volume. During our design science research process, we evaluate the model's applicability and usefulness through interviews with affected patients, prototyping, and application to a real-world in vivo dataset. The developed prototype predicts bladder volume based on relevant sensor data (i.e., near-infrared spectroscopy and acceleration) and the time elapsed since the previous micturition. Our comparison of several supervised state-of-the-art machine and deep learning models reveals that a long short-term memory network architecture achieves a mean absolute error of 116.7 ml that can improve bladder management for patients.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":"14 1","pages":"1 - 23"},"PeriodicalIF":2.5,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43864221","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：