Ageing has become a worldwide challenge, especially in China, and mental disorders are always associated with ageing. Although previous studies have focused on a certain issue or a certain group of the population, more research on the mental health of the seniors needs to be done from a comprehensive perspective. This paper studies the mental health information communication among the Chinese seniors. Text mining methods were used for content analysis to find the main topic of mental health and social network analysis was applied to explore the connection between the seniors to study their communication. Results show that the senior online communities develop several active networks to communicate their mental health concerns, however their information communication remains at a shallow stage. This study could assist researchers on further study and provide practitioners with pertinent measures.
{"title":"Understanding the Mental Health Information Communication among the Seniors in China: Text Mining Analysis","authors":"Wenxuan Gui","doi":"10.1145/3560071.3560083","DOIUrl":"https://doi.org/10.1145/3560071.3560083","url":null,"abstract":"Ageing has become a worldwide challenge, especially in China, and mental disorders are always associated with ageing. Although previous studies have focused on a certain issue or a certain group of the population, more research on the mental health of the seniors needs to be done from a comprehensive perspective. This paper studies the mental health information communication among the Chinese seniors. Text mining methods were used for content analysis to find the main topic of mental health and social network analysis was applied to explore the connection between the seniors to study their communication. Results show that the senior online communities develop several active networks to communicate their mental health concerns, however their information communication remains at a shallow stage. This study could assist researchers on further study and provide practitioners with pertinent measures.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131772650","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}
Although photoplethysmogram (PPG) and electrocardiogram (ECG) signals have been used to estimate cuffless and continuous blood pressure (BP) for decades, most of the current popular methods are based on the correlated relationship between extracted features and BP. Current methods ignore causality in the system and lead to the unsatisfactory performance for BP estimation. This paper aims to infer the key features that cause BP changes and explore the feasibility of combining causal association with BP estimation problem. In the process, a total of 222 features extracted from PPG and ECG waveforms are used to infer causality with systolic BP (SBP) and diastolic BP (DBP) through fast causal inference (FCI) algorithm. The obtained causal graph suggests that the feature AMPPG(PPGvalley-sdPPGd) is the effect of SBP and AMPPG(PPGvalley-sdPPGb) is the effect of DBP, where AMPPG refers to the amplitude difference of PPG signal between two fiducial points and sdPPG is the second derivative of PPG signal. Moreover, the result provides new insights on features of amplitude class, in addition to the commonly studied pulse transit time (PTT). Inspired by Granger causality, time-lagged causal links are used to bridge the gap between causal graph and BP estimation and a causality-based multiple linear regression model for cuffless BP estimation is built. Compared with the corresponding correlation-based model, causality-based regression model achieves better performance for BP estimation, with mean error (ME) being 1.58±12.02, -4.67±9.03 mmHg and mean absolute difference (MAD) being 9.51, 7.54 mmHg for SBP and DBP, respectively.
{"title":"Causal Inference in Cuffless Blood Pressure Estimation: A Pilot Study","authors":"Lei Liu, Yifan Chen, Xiaorong Ding","doi":"10.1145/3560071.3560073","DOIUrl":"https://doi.org/10.1145/3560071.3560073","url":null,"abstract":"Although photoplethysmogram (PPG) and electrocardiogram (ECG) signals have been used to estimate cuffless and continuous blood pressure (BP) for decades, most of the current popular methods are based on the correlated relationship between extracted features and BP. Current methods ignore causality in the system and lead to the unsatisfactory performance for BP estimation. This paper aims to infer the key features that cause BP changes and explore the feasibility of combining causal association with BP estimation problem. In the process, a total of 222 features extracted from PPG and ECG waveforms are used to infer causality with systolic BP (SBP) and diastolic BP (DBP) through fast causal inference (FCI) algorithm. The obtained causal graph suggests that the feature AMPPG(PPGvalley-sdPPGd) is the effect of SBP and AMPPG(PPGvalley-sdPPGb) is the effect of DBP, where AMPPG refers to the amplitude difference of PPG signal between two fiducial points and sdPPG is the second derivative of PPG signal. Moreover, the result provides new insights on features of amplitude class, in addition to the commonly studied pulse transit time (PTT). Inspired by Granger causality, time-lagged causal links are used to bridge the gap between causal graph and BP estimation and a causality-based multiple linear regression model for cuffless BP estimation is built. Compared with the corresponding correlation-based model, causality-based regression model achieves better performance for BP estimation, with mean error (ME) being 1.58±12.02, -4.67±9.03 mmHg and mean absolute difference (MAD) being 9.51, 7.54 mmHg for SBP and DBP, respectively.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130315586","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}
Septic patients admitted to the intensive care unit (ICU) are highly susceptible to acute kidney injury (AKI), which leads to reduced survival in these patients. It is thus necessary to develop a model that can predict the risk of AKI in septic patients in real time. Although continuous or near-continuous risk assessment is likely necessary, few risk models have been designed for this purpose. Therefore, we constructed a model to continuously predict sepsis-induced AKI in ICU. Our proposed model optimally achieved an area under the receiver operating characteristic curve (AUROC) of 79.5 and an area under the precision-recall curve (AUPRC) of 65.0, performed better than other methods, including logistic regression, XGBoost, and RNN, on a full set of performance evaluation processes. Discrimination as well as DCA were also shown the proposed algorithm performed superior to other methods.
{"title":"Continuous Prediction of Acute Kidney Injury from Patients with Sepsis in ICU Settings: A Sequential Transduction Model Based on Attention","authors":"Guang-Long Zeng, Jinhu Zhuang, Haofan Huang, Yihang Gao, Yong Liu, Xiaxia Yu","doi":"10.1145/3560071.3560077","DOIUrl":"https://doi.org/10.1145/3560071.3560077","url":null,"abstract":"Septic patients admitted to the intensive care unit (ICU) are highly susceptible to acute kidney injury (AKI), which leads to reduced survival in these patients. It is thus necessary to develop a model that can predict the risk of AKI in septic patients in real time. Although continuous or near-continuous risk assessment is likely necessary, few risk models have been designed for this purpose. Therefore, we constructed a model to continuously predict sepsis-induced AKI in ICU. Our proposed model optimally achieved an area under the receiver operating characteristic curve (AUROC) of 79.5 and an area under the precision-recall curve (AUPRC) of 65.0, performed better than other methods, including logistic regression, XGBoost, and RNN, on a full set of performance evaluation processes. Discrimination as well as DCA were also shown the proposed algorithm performed superior to other methods.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115358777","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 neural networks suffer from the notorious problem of catastrophic forgetting when the tasks keep increasing. The inaccessibility of previous data due to privacy limitations and other issues directly leads to a significant drop in performance in prior tasks. Existing incremental class learning (ICL) methods in semantic segmentation are mostly regularization-based. While in this work, we incorporate a generative replay-based approach to alleviating catastrophic forgetting for the first time. We introduce SegGAN to generate both previous images and the corresponding pixel-level labels to circumvent privacy limitations and replay them to retain learned knowledge in the subsequent learning steps. Furthermore, we propose a novel filtering mechanism to select high-quality generated data by the consistency constraint of the Pseudo-Labeling and generative replay method. Specifically, we use Pseudo-Labeling to obtain the pseudo-labels of the generated images and select reliable data with high confidence by comparing generated labels with pseudo-labels.
{"title":"A New Generative Replay Approach for Incremental Class Learning of Medical Image for Semantic Segmentation","authors":"Mingyang Liu, Li Xiao, Huiqin Jiang, Qing He","doi":"10.1145/3560071.3560080","DOIUrl":"https://doi.org/10.1145/3560071.3560080","url":null,"abstract":"Deep neural networks suffer from the notorious problem of catastrophic forgetting when the tasks keep increasing. The inaccessibility of previous data due to privacy limitations and other issues directly leads to a significant drop in performance in prior tasks. Existing incremental class learning (ICL) methods in semantic segmentation are mostly regularization-based. While in this work, we incorporate a generative replay-based approach to alleviating catastrophic forgetting for the first time. We introduce SegGAN to generate both previous images and the corresponding pixel-level labels to circumvent privacy limitations and replay them to retain learned knowledge in the subsequent learning steps. Furthermore, we propose a novel filtering mechanism to select high-quality generated data by the consistency constraint of the Pseudo-Labeling and generative replay method. Specifically, we use Pseudo-Labeling to obtain the pseudo-labels of the generated images and select reliable data with high confidence by comparing generated labels with pseudo-labels.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123643105","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}
Alzheimer's disease (AD) is a neurodegenerative disease affecting at least 35 million people worldwide, creating significant health and social care challenges. In this research, I aim to investigate the molecular pathways contributing to AD pathology by using publicly available datasets generated from different in vitro models of Alzheimer's disease. To address this aim, I re-analyzed single-cell RNA-Seq datasets derived from Cakir, B. et al (2022, GSE175719) and Pérez, J.J. et al. (2020, GSE147047). Using the Seurat package in RStudio, I compared gene expression of cortical neurons from dementia groups, modelled with PITRM1 knockout or addition of amyloid-beta into the cultures, to that of untreated neurons. Combination of single-cell RNA-Seq allowing single-cell resolution with different in vitro models of Alzheimer's disease might help to elucidate the pathways involved in Alzheimer's disease pathology.
{"title":"Comparison of Different in Vitro Models of Alzheimer's Disease Using Re-Analysis of Scrna-Seq Data","authors":"Yu-Ra Kang","doi":"10.1145/3560071.3560085","DOIUrl":"https://doi.org/10.1145/3560071.3560085","url":null,"abstract":"Alzheimer's disease (AD) is a neurodegenerative disease affecting at least 35 million people worldwide, creating significant health and social care challenges. In this research, I aim to investigate the molecular pathways contributing to AD pathology by using publicly available datasets generated from different in vitro models of Alzheimer's disease. To address this aim, I re-analyzed single-cell RNA-Seq datasets derived from Cakir, B. et al (2022, GSE175719) and Pérez, J.J. et al. (2020, GSE147047). Using the Seurat package in RStudio, I compared gene expression of cortical neurons from dementia groups, modelled with PITRM1 knockout or addition of amyloid-beta into the cultures, to that of untreated neurons. Combination of single-cell RNA-Seq allowing single-cell resolution with different in vitro models of Alzheimer's disease might help to elucidate the pathways involved in Alzheimer's disease pathology.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114925463","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}
Simultaneous monitoring of heart beat (HB) and cerebral blood flow pulsation (CBFP) has important clinical significance for reducing the incidence, mortality and disability rate of cardiovascular and cerebrovascular diseases. However, there is no safe, reliable and effective method for synchronous monitoring of them in practice. Near-field coherent coupling (NCC) obtains physiological signals by demodulating the modulation information of complex impedance changes in biological tissues with the advantages of non-invasiveness, strong penetrability, and real-time monitoring. A synchronization monitoring system of HB and CBFP was constructed in this work based on the NCC principle and software defined radio programming technology. In order to investigate its feasibility of monitoring the heart-brain coupling activity (HBCA) changes in different states, the HB and CBFP signals of 6 healthy volunteers at rest and after exercise were collected synchronously and analyzed. Furthermore, the heart-brain delay time (HBDT) in the two states was compared by moving cross-correlation analysis. The results show that the size of heart rate obtained by the NCC and physiological monitor is very close with an average relative error of 4.7%. The waveforms of HB and CBFP in time domain before and after exercise were relatively consistent, which meets the heart rate and the basic characteristics of CBF impedance map. The frequency of HB and CBFP after exercise were obviously higher than that at rest. CBFP is delayed from the HB and has the same frequency. It is consistent with the mechanism of the same frequency and different phases between cardiac vibration and intracranial blood supply. The HBDTs at resting state in all 6 volunteers are less than those after exercising with an optimal consistency. These results prove the possibility of NCC monitoring HB and CBFP. In addition, it has the potential in non-invasive, real-time monitoring of HBCA.
{"title":"Synchronous Monitoring of Heart Beat and Cerebral Blood Flow Pulsation Based on Near Field Coherent Coupling","authors":"Rui Zhu, Jiaxu Li, Gen Li","doi":"10.1145/3560071.3560076","DOIUrl":"https://doi.org/10.1145/3560071.3560076","url":null,"abstract":"Simultaneous monitoring of heart beat (HB) and cerebral blood flow pulsation (CBFP) has important clinical significance for reducing the incidence, mortality and disability rate of cardiovascular and cerebrovascular diseases. However, there is no safe, reliable and effective method for synchronous monitoring of them in practice. Near-field coherent coupling (NCC) obtains physiological signals by demodulating the modulation information of complex impedance changes in biological tissues with the advantages of non-invasiveness, strong penetrability, and real-time monitoring. A synchronization monitoring system of HB and CBFP was constructed in this work based on the NCC principle and software defined radio programming technology. In order to investigate its feasibility of monitoring the heart-brain coupling activity (HBCA) changes in different states, the HB and CBFP signals of 6 healthy volunteers at rest and after exercise were collected synchronously and analyzed. Furthermore, the heart-brain delay time (HBDT) in the two states was compared by moving cross-correlation analysis. The results show that the size of heart rate obtained by the NCC and physiological monitor is very close with an average relative error of 4.7%. The waveforms of HB and CBFP in time domain before and after exercise were relatively consistent, which meets the heart rate and the basic characteristics of CBF impedance map. The frequency of HB and CBFP after exercise were obviously higher than that at rest. CBFP is delayed from the HB and has the same frequency. It is consistent with the mechanism of the same frequency and different phases between cardiac vibration and intracranial blood supply. The HBDTs at resting state in all 6 volunteers are less than those after exercising with an optimal consistency. These results prove the possibility of NCC monitoring HB and CBFP. In addition, it has the potential in non-invasive, real-time monitoring of HBCA.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124241458","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}
At the beginning of 2020, coronavirus disease (covid-19) spread all over the world, making the world face a survival and health crisis. Automatic detection of pulmonary infection through computed tomography (CT) images provides great potential for strengthening the traditional health care strategy to deal with covid-19. At present, the use of artificial intelligence technology for image classification and lesion segmentation of COVID-19CT image has become a widely concerned content in medical image analysis. Segmenting the infected area from CT image faces several challenges, including high variation of infection characteristics, low-intensity comparison between infection and normal tissue and so on. Based on the in-depth analysis of covid-19 CT image features, this paper adds a mixed attention mechanism module to the RESNETneural network model, including channel attention mechanism and spatial attention mechanism. The combination of channel attention mechanism and spatial attention mechanism makes the backbone network have the ability to pay attention to more important local features from global features, making the model more sensitive to covid CT images. In terms of implementation efficiency, the convolution layer of the model is improved with smaller convolution kernel, and the loss function is modified to adjust the data training model, so as to realize the more accurate and efficient automatic recognition of covid-19 CT image.
{"title":"AM-RESNET50 Method for CT Image Diagnosis of COVID-19","authors":"Yi Yang, Dekuang Yu, Xiao-Le Jiang, Chunwei Zhang","doi":"10.1145/3560071.3560078","DOIUrl":"https://doi.org/10.1145/3560071.3560078","url":null,"abstract":"At the beginning of 2020, coronavirus disease (covid-19) spread all over the world, making the world face a survival and health crisis. Automatic detection of pulmonary infection through computed tomography (CT) images provides great potential for strengthening the traditional health care strategy to deal with covid-19. At present, the use of artificial intelligence technology for image classification and lesion segmentation of COVID-19CT image has become a widely concerned content in medical image analysis. Segmenting the infected area from CT image faces several challenges, including high variation of infection characteristics, low-intensity comparison between infection and normal tissue and so on. Based on the in-depth analysis of covid-19 CT image features, this paper adds a mixed attention mechanism module to the RESNETneural network model, including channel attention mechanism and spatial attention mechanism. The combination of channel attention mechanism and spatial attention mechanism makes the backbone network have the ability to pay attention to more important local features from global features, making the model more sensitive to covid CT images. In terms of implementation efficiency, the convolution layer of the model is improved with smaller convolution kernel, and the loss function is modified to adjust the data training model, so as to realize the more accurate and efficient automatic recognition of covid-19 CT image.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130431395","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}
Yumin Yang, Yifan Chen, Lei Liu, Yan Zhao, Deyuan Kong, Xiaorong Ding
Noninvasive and cuffless blood pressure estimation is crucial for the early prevention, diagnosis and treatment of hypertension and related cardiovascular and cerebrovascular diseases. The noninvasive cuffless blood pressure measurement method based on pulse wave transit time (PTT) has been widely studied due to its noninvasive, low cost and simple operation. However, a single PTT cannot accurately track various changes in blood pressure. Therefore, it is necessary to explore new parameters other than PTT that can reflect blood pressure changes and be used for blood pressure estimation. This paper proposes the use of systolic area (SA) to estimate blood pressure, a feature that can be obtained from the photoplethysmographic signal (PPG). At the same time, we try to compare this feature with the pulse wave at half amplitude (PWHA) and the pulse wave amplitude (AM), which are also obtained from PPG, and use the method of multiple linear regression to fuse them. In addition, we did a controlled experiment to compare the traditional PTT-based method with the method based on these feature fusions. The results showed that when SA is used alone for BP estimation, for SBP and DBP, the accuracy is 0.004±6.55 mmHg and -0.09±3.52 mmHg, respectively. When PWHA, SA, AM and PTT are combined, for SBP and DBP, the accuracy is 0.29±4.97 mmHg and -0.14±3.06 mmHg, respectively. These results demonstrate that SA is a promising feature, and the method based on the above four features fusion can greatly improve the accuracy of blood pressure estimation. At the same time, it is also possible to rely solely on PPG signal to estimate blood pressure.
{"title":"Noninvasive and Cuffless Blood Pressure Estimation Using Photoplethysmography Index","authors":"Yumin Yang, Yifan Chen, Lei Liu, Yan Zhao, Deyuan Kong, Xiaorong Ding","doi":"10.1145/3560071.3560075","DOIUrl":"https://doi.org/10.1145/3560071.3560075","url":null,"abstract":"Noninvasive and cuffless blood pressure estimation is crucial for the early prevention, diagnosis and treatment of hypertension and related cardiovascular and cerebrovascular diseases. The noninvasive cuffless blood pressure measurement method based on pulse wave transit time (PTT) has been widely studied due to its noninvasive, low cost and simple operation. However, a single PTT cannot accurately track various changes in blood pressure. Therefore, it is necessary to explore new parameters other than PTT that can reflect blood pressure changes and be used for blood pressure estimation. This paper proposes the use of systolic area (SA) to estimate blood pressure, a feature that can be obtained from the photoplethysmographic signal (PPG). At the same time, we try to compare this feature with the pulse wave at half amplitude (PWHA) and the pulse wave amplitude (AM), which are also obtained from PPG, and use the method of multiple linear regression to fuse them. In addition, we did a controlled experiment to compare the traditional PTT-based method with the method based on these feature fusions. The results showed that when SA is used alone for BP estimation, for SBP and DBP, the accuracy is 0.004±6.55 mmHg and -0.09±3.52 mmHg, respectively. When PWHA, SA, AM and PTT are combined, for SBP and DBP, the accuracy is 0.29±4.97 mmHg and -0.14±3.06 mmHg, respectively. These results demonstrate that SA is a promising feature, and the method based on the above four features fusion can greatly improve the accuracy of blood pressure estimation. At the same time, it is also possible to rely solely on PPG signal to estimate blood pressure.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134346638","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 purpose of this study was to compare the lower limb kinematic characteristics of individuals with different arch stiffness during unexpected gait termination (UGT) and to investigate the functional biomechanical adjustment and human compensation mechanism of gait termination related to the morphological characteristics of the foot arch. Sixty-five healthy male subjects were recruited to complete this biomechanical test. An Easy-Foot-Scan scanner was used to acquire the morphological parameters of the foot arch in standing and sitting positions, and the subjects were divided into stiff and flexible arch groups according to the calculated arch stiffness index (ASI). A Vicon motion capture system was used to capture hip, knee, ankle, and metatarsophalangeal joint (MPJ) kinematic data during the UGT task. It was found that the flexible arch had a significantly greater range of motion (ROM) in the frontal plane of the knee compared to the stiff arch. The stiff arch group showed a greater ROM in the sagittal plane of the ankle joint. The ROM was greater in the flexible arch group in the frontal plane. For the MPJ, the joint angle in the frontal plane was significantly greater in the stiff arch group than in the flexible arch group. The differences in biomechanical characteristics due to different arch stiffnesses were mainly concentrated in the distal joints. During UGT, the arch must bear and distribute the impact load transmitted to the foot. The flexible arch is more easily compressed, thus reducing the medial longitudinal arch height and leading to a limited windlass mechanism.
{"title":"Impacts of Different Arch Stiffness on Lower Extremity Joint Kinematics during Unexpected Gait Termination","authors":"Xuanzhen Cen, István Bíró, Yaodong Gu","doi":"10.1145/3560071.3560074","DOIUrl":"https://doi.org/10.1145/3560071.3560074","url":null,"abstract":"The purpose of this study was to compare the lower limb kinematic characteristics of individuals with different arch stiffness during unexpected gait termination (UGT) and to investigate the functional biomechanical adjustment and human compensation mechanism of gait termination related to the morphological characteristics of the foot arch. Sixty-five healthy male subjects were recruited to complete this biomechanical test. An Easy-Foot-Scan scanner was used to acquire the morphological parameters of the foot arch in standing and sitting positions, and the subjects were divided into stiff and flexible arch groups according to the calculated arch stiffness index (ASI). A Vicon motion capture system was used to capture hip, knee, ankle, and metatarsophalangeal joint (MPJ) kinematic data during the UGT task. It was found that the flexible arch had a significantly greater range of motion (ROM) in the frontal plane of the knee compared to the stiff arch. The stiff arch group showed a greater ROM in the sagittal plane of the ankle joint. The ROM was greater in the flexible arch group in the frontal plane. For the MPJ, the joint angle in the frontal plane was significantly greater in the stiff arch group than in the flexible arch group. The differences in biomechanical characteristics due to different arch stiffnesses were mainly concentrated in the distal joints. During UGT, the arch must bear and distribute the impact load transmitted to the foot. The flexible arch is more easily compressed, thus reducing the medial longitudinal arch height and leading to a limited windlass mechanism.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130619311","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}
Herein, we focus on the problem of automatically medical concept normalization in social media posts. Specifically, the task is to map medical mentions within social media texts to the suitable concepts in a reference knowledge base. We propose a new medical concept normalization model using multi-task learning. The model uses BioBERT to encode mentions and their contexts, and classifies their concept IDs and types of mention. We evaluate our approach on two datasets and achieve new state-of-the-art performance.
{"title":"Enriching Pre-Trained Language Model with Multi-Task Learning and Context for Medical Concept Normalization","authors":"Yiling Cao, Lu Fang, Zhongguang Zheng","doi":"10.1145/3560071.3560084","DOIUrl":"https://doi.org/10.1145/3560071.3560084","url":null,"abstract":"Herein, we focus on the problem of automatically medical concept normalization in social media posts. Specifically, the task is to map medical mentions within social media texts to the suitable concepts in a reference knowledge base. We propose a new medical concept normalization model using multi-task learning. The model uses BioBERT to encode mentions and their contexts, and classifies their concept IDs and types of mention. We evaluate our approach on two datasets and achieve new state-of-the-art performance.","PeriodicalId":249276,"journal":{"name":"Proceedings of the 2022 International Conference on Intelligent Medicine and Health","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127137348","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：