Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128985
D. Davis, Jenq-Neng Hwang, J. Lee
An improved neural network inversion technique that scales the search vector in accordance with the geometry of the problem has been developed. It searches in the direction of the gradient with a vector whose size is inversely related to the size of the gradient. To avoid unlimited growth of the search vector where the gradient is small, an upper bound is set on the size of the search vector. The network was trained by backpropagation and the training was halted when the network produced no error on the training set, where the output was categorized by binary thresholding. The results show the superior performance of the improved method. The technique was applied to automated cytology screening. A set of 400 object feature vectors randomly selected from a large database of 1929 feature vectors served as the initial training data.<>
{"title":"Improved network inversion technique for query learning application to automated cytology screening","authors":"D. Davis, Jenq-Neng Hwang, J. Lee","doi":"10.1109/CBMS.1991.128985","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128985","url":null,"abstract":"An improved neural network inversion technique that scales the search vector in accordance with the geometry of the problem has been developed. It searches in the direction of the gradient with a vector whose size is inversely related to the size of the gradient. To avoid unlimited growth of the search vector where the gradient is small, an upper bound is set on the size of the search vector. The network was trained by backpropagation and the training was halted when the network produced no error on the training set, where the output was categorized by binary thresholding. The results show the superior performance of the improved method. The technique was applied to automated cytology screening. A set of 400 object feature vectors randomly selected from a large database of 1929 feature vectors served as the initial training data.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124956019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128947
I. Nevo, A. Guez, F. Ahmed, J. Roth
A mathematical model for an adaptive expert system in anesthesia is presented. The concept of clusters that utilize clinical attributes in order to reduce the dimensionality of the patient's state-space is introduced. One goal of the model is to implement the existing categories and to identify and cluster categories as well as make the system adaptive to new and more optimal categories. Well-known techniques of pattern classification and cluster analysis are used on the measurable dataset to look for new categories or to readjust existing ones. Readjustment is required to optimize the existing categories to give the most efficient classification of the diseases.<>
{"title":"System theoretic approach to medical diagnosis","authors":"I. Nevo, A. Guez, F. Ahmed, J. Roth","doi":"10.1109/CBMS.1991.128947","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128947","url":null,"abstract":"A mathematical model for an adaptive expert system in anesthesia is presented. The concept of clusters that utilize clinical attributes in order to reduce the dimensionality of the patient's state-space is introduced. One goal of the model is to implement the existing categories and to identify and cluster categories as well as make the system adaptive to new and more optimal categories. Well-known techniques of pattern classification and cluster analysis are used on the measurable dataset to look for new categories or to readjust existing ones. Readjustment is required to optimize the existing categories to give the most efficient classification of the diseases.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124006793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128939
Chong-Yen Lee, M. Evens, L. Carmony, D. Trace, F. Naeymi-Rad
A computerized test selection module for a multimembership Bayesian diagnostic expert system built to recommend tests to further refine the differential diagnosis is described. The output of the program includes recommendations for individual tests, for groups of tests to be administered in sequence, and for groups of parallel tests. The original set of available tests is large. This generates a large number of groups of tests, any of which could possibly provide the most valuable information. Selection of the proper subset of tests from the original set is critical. A smaller proper subset of tests improves the systems response time by avoiding unnecessary calculation.<>
{"title":"Recommending tests in a multimembership Bayesian diagnostic expert system","authors":"Chong-Yen Lee, M. Evens, L. Carmony, D. Trace, F. Naeymi-Rad","doi":"10.1109/CBMS.1991.128939","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128939","url":null,"abstract":"A computerized test selection module for a multimembership Bayesian diagnostic expert system built to recommend tests to further refine the differential diagnosis is described. The output of the program includes recommendations for individual tests, for groups of tests to be administered in sequence, and for groups of parallel tests. The original set of available tests is large. This generates a large number of groups of tests, any of which could possibly provide the most valuable information. Selection of the proper subset of tests from the original set is critical. A smaller proper subset of tests improves the systems response time by avoiding unnecessary calculation.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117260184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128969
B. Blum, R. Semmel
The role of information and knowledge in medical informatics is discussed and expert system technology is examined in that context. The scope of computer-based applications in medicine is presented. This is followed by a review of the current state of the art. It is shown how the information- and knowledge-oriented applications are merging. Some of the key concepts in both information and knowledge processing are discussed in the context of medical computing.<>
{"title":"Medical informatics, knowledge, and expert systems","authors":"B. Blum, R. Semmel","doi":"10.1109/CBMS.1991.128969","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128969","url":null,"abstract":"The role of information and knowledge in medical informatics is discussed and expert system technology is examined in that context. The scope of computer-based applications in medicine is presented. This is followed by a review of the current state of the art. It is shown how the information- and knowledge-oriented applications are merging. Some of the key concepts in both information and knowledge processing are discussed in the context of medical computing.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123925678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128974
K. Kuhn, D. Roesner, T. Zemmler, W. Swobodnik, P. Janowitz, Johannes G. Wechsler, C. Heinlein, M. Reichert, Werner Doster, Hans Ditschuneit
An expert system module has been integrated into clinical workstations used for report generation and the storage and retrieval of diagnostic images. The expert system works in the background and supports the physician's decisions. The system has been created for ultrasound examinations of the abdomen. The knowledge-based system has been implemented for the same knowledge segment using two different methods: a rule-based approach with the AI-tool Joshua on a Symbolics machine for prototyping and knowledge debugging and a neural network approach based on back propagation. The results show that the neural network is robust and flexible for the mainly associative knowledge found in this application; it performed well in general and, specifically, on subsets of findings entered during the course of an examination. It was therefore decided to combine both components.<>
{"title":"A neural network expert system to support decisions in diagnostic mapping","authors":"K. Kuhn, D. Roesner, T. Zemmler, W. Swobodnik, P. Janowitz, Johannes G. Wechsler, C. Heinlein, M. Reichert, Werner Doster, Hans Ditschuneit","doi":"10.1109/CBMS.1991.128974","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128974","url":null,"abstract":"An expert system module has been integrated into clinical workstations used for report generation and the storage and retrieval of diagnostic images. The expert system works in the background and supports the physician's decisions. The system has been created for ultrasound examinations of the abdomen. The knowledge-based system has been implemented for the same knowledge segment using two different methods: a rule-based approach with the AI-tool Joshua on a Symbolics machine for prototyping and knowledge debugging and a neural network approach based on back propagation. The results show that the neural network is robust and flexible for the mainly associative knowledge found in this application; it performed well in general and, specifically, on subsets of findings entered during the course of an examination. It was therefore decided to combine both components.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121070073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128970
J. Bronzino, R. Morelli, J. Goethe
The development of a prototype system and the incorporation of a language/action model to facilitate human/computer interaction in the development of an expert system that would operate in real time and be used directly by clinicians treating psychiatric patients is described. The prototype system was implemented initially in Prolog and run on a SUN 3/50 workstation. This system was able to monitor the drug treatment of patients with any of three diagnoses: bipolar disorder, schizophrenia and major depression. The prototype was tested on subsets of patient-related data representing approximately 1200 patient-days of actual patient, laboratory, and pharmacy records, which were downloaded from the hospital's database. It was found that 100% of the clinical events of potential concern were properly identified. The language/action perspective has important implications for clinicians as end-users and the problem of acceptability of expert systems in the clinical setting.<>
{"title":"Design of an expert system for monitoring drug treatment in a psychiatric hospital","authors":"J. Bronzino, R. Morelli, J. Goethe","doi":"10.1109/CBMS.1991.128970","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128970","url":null,"abstract":"The development of a prototype system and the incorporation of a language/action model to facilitate human/computer interaction in the development of an expert system that would operate in real time and be used directly by clinicians treating psychiatric patients is described. The prototype system was implemented initially in Prolog and run on a SUN 3/50 workstation. This system was able to monitor the drug treatment of patients with any of three diagnoses: bipolar disorder, schizophrenia and major depression. The prototype was tested on subsets of patient-related data representing approximately 1200 patient-days of actual patient, laboratory, and pharmacy records, which were downloaded from the hospital's database. It was found that 100% of the clinical events of potential concern were properly identified. The language/action perspective has important implications for clinicians as end-users and the problem of acceptability of expert systems in the clinical setting.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126601652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128941
S. Robert, Sanjeev Prakash, F. Naeymi-Rad, D. Trace, L. Carmony, M. Evens
A medical record input system (MEDRIS) that makes use of hypermedia technology to provide a clinical tool for physicians to input patient data in a simple manner is described. The design of MEDRIS focuses on providing a natural working environment for the physicians. Physicians can easily learn to use MEDRIS since it eliminates the use of command-level entries and special function keys. MEDRIS comprises the following modules: history (chief complaints, review of systems, family history, etc), physical examination, laboratory, and medication. The chief complaint and the physical examination modules are discussed in detail. The software techniques adopted in building this system are explained. MEDRIS produces an immediate report of the data entered and an encounter file containing all the patient data collected during the current visit, which is added to the portable patient file.<>
{"title":"MEDRIS: the hypermedia approach to medical record input-software engineering techniques for developing a hypermedia system","authors":"S. Robert, Sanjeev Prakash, F. Naeymi-Rad, D. Trace, L. Carmony, M. Evens","doi":"10.1109/CBMS.1991.128941","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128941","url":null,"abstract":"A medical record input system (MEDRIS) that makes use of hypermedia technology to provide a clinical tool for physicians to input patient data in a simple manner is described. The design of MEDRIS focuses on providing a natural working environment for the physicians. Physicians can easily learn to use MEDRIS since it eliminates the use of command-level entries and special function keys. MEDRIS comprises the following modules: history (chief complaints, review of systems, family history, etc), physical examination, laboratory, and medication. The chief complaint and the physical examination modules are discussed in detail. The software techniques adopted in building this system are explained. MEDRIS produces an immediate report of the data entered and an encounter file containing all the patient data collected during the current visit, which is added to the portable patient file.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"46 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125700063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128979
Ö. Özdamar, I. Yaylali, P. Jayakar, C. Lopez
The design and evaluation of an artificial neural network system for the detection of epileptogenic spikes is described. The system is composed of smaller neural network modules which are trained individually and organized in two levels. The first-level modules are trained to recognize candidate spikes in single referential electroencephalogram (EEG) channels. Original digitized data with a running window of 100 ms provided the input for the first-level modules. A second-level module is used for the spatial integration of 16 first-level modules. The system was trained and tested using clinical EEG data interpreted by four expert electroencephalographers. The results show that spikes can be recognized directly from unprocessed EEG and a second-level neural network can integrate spatial EEG information and eliminate false detections.<>
{"title":"Multilevel neural network system for EEG spike detection","authors":"Ö. Özdamar, I. Yaylali, P. Jayakar, C. Lopez","doi":"10.1109/CBMS.1991.128979","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128979","url":null,"abstract":"The design and evaluation of an artificial neural network system for the detection of epileptogenic spikes is described. The system is composed of smaller neural network modules which are trained individually and organized in two levels. The first-level modules are trained to recognize candidate spikes in single referential electroencephalogram (EEG) channels. Original digitized data with a running window of 100 ms provided the input for the first-level modules. A second-level module is used for the spatial integration of 16 first-level modules. The system was trained and tested using clinical EEG data interpreted by four expert electroencephalographers. The results show that spikes can be recognized directly from unprocessed EEG and a second-level neural network can integrate spatial EEG information and eliminate false detections.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132616193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128942
D. Ayala, R. Hermida
Changes in 24-h synchronized (circadian) characteristics of blood pressure (BP) and heart rate (HP) are quantified in two consecutive pregnancies of a clinically healthy woman. BP and HR were automatically monitored, with few interruptions, at 1-h intervals, and for a total of 76 days of monitoring in each pregnancy. Circadian parameters of BP and HR were computed for each single day of measurements by the least-squares fit of a 24-h cosine curve. Regression analysis of parameters thus obtained revealed patterns of variation of circadian rhythm-adjusted means and amplitudes with gestational age. This longitudinal study confirms and extends to ambulatory everyday-life conditions the predictable pregnancy-associated variability in BP and HR, and also allows the establishment of prediction and confidence limits for cardiovascular parameters in a healthy pregnancy.<>
{"title":"Predictable blood pressure variability in clinically healthy human pregnancy","authors":"D. Ayala, R. Hermida","doi":"10.1109/CBMS.1991.128942","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128942","url":null,"abstract":"Changes in 24-h synchronized (circadian) characteristics of blood pressure (BP) and heart rate (HP) are quantified in two consecutive pregnancies of a clinically healthy woman. BP and HR were automatically monitored, with few interruptions, at 1-h intervals, and for a total of 76 days of monitoring in each pregnancy. Circadian parameters of BP and HR were computed for each single day of measurements by the least-squares fit of a 24-h cosine curve. Regression analysis of parameters thus obtained revealed patterns of variation of circadian rhythm-adjusted means and amplitudes with gestational age. This longitudinal study confirms and extends to ambulatory everyday-life conditions the predictable pregnancy-associated variability in BP and HR, and also allows the establishment of prediction and confidence limits for cardiovascular parameters in a healthy pregnancy.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130584567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1991-05-12DOI: 10.1109/CBMS.1991.128994
J. Hsieh, D. Ucci
To accurately model the complex behavior of computed tomography (CT) systems, generalized stochastic Petri nets (GSPNs) are used. This approach makes it possible to examine the concurrence and synchronization characteristics, as well as the reliability and performance of the system. To overcome the difficulties of the state space explosion associated with GSPN, an approximate superposition technique is presented. Utilizing the flexibility of the GSPN technique, the model is able to consider not only the failure of each individual processor, but also the complicated failure recovery schemes and communication protocols among processors.<>
{"title":"Design and modeling of CT systems with GSPN","authors":"J. Hsieh, D. Ucci","doi":"10.1109/CBMS.1991.128994","DOIUrl":"https://doi.org/10.1109/CBMS.1991.128994","url":null,"abstract":"To accurately model the complex behavior of computed tomography (CT) systems, generalized stochastic Petri nets (GSPNs) are used. This approach makes it possible to examine the concurrence and synchronization characteristics, as well as the reliability and performance of the system. To overcome the difficulties of the state space explosion associated with GSPN, an approximate superposition technique is presented. Utilizing the flexibility of the GSPN technique, the model is able to consider not only the failure of each individual processor, but also the complicated failure recovery schemes and communication protocols among processors.<<ETX>>","PeriodicalId":439237,"journal":{"name":"[1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124068166","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：