Search citation statements
Paper Sections
Citation Types
Publication Types
Relationship
Authors
Journals
Expert system (ES) technology may somewhat help manage the growing mass of information in the f i l d of psychiatry. but several factors prevent the systems from being widely use@. Constraints inherent in the structure and operation of available ES shells make them useful only within some subabmhs. The non-homogenous and hierarchically complex nature of the jields information makes it d@cult to construct broadly useful systems. These problems and current developments in trainable pattern detection system call for additional powerful and versatile approaches. PRESENT APPROACHESInterest in applying ES type technology in the field of psychiatry has focused mainly on two types of roles: that of consultantladvisor/teacher assisting in decision making, and that of intelligent monitoring. Expert systems or other cornputex systems might ideally help health care personnel with diagnostic interviewing[t] and differential dmgnosis[z][3], behavioral assessmentt41, assessment of suicidal risktq or homocidal risk, selection of therapeutic modalities, selection of appropriate pharmacotherapy, aSSeSSment of drug interactions161. management of drug overdoses, and others. Monitoring systems might be built into medical "smart-charts" enabling intelligent screening for prescribing ermpsp], suspicious laboratory values, or trends in activity, diet 02 weight. Other potential mental health uses are rehabilitative applications, such as training, education, systematic behavior modification and biofeedback, or embedded ES technology in health and human seMces robotics, such as smart-house or "psychorobotic" systems, which might monitor and redirect those with chronic psychiatrk or neurobehavioral disturbances. [SI.The construction of an expert system in a medical field presents many known challenges, which swngly influence the system's application and functional nature. These may be especially problematic in the field of clinical psychiatry. Several of these challenges follow:The domain must be a modest size and sharply defined. The larger and more heterogenous the domain, the more difficult it is to build the rules composing the system's knowledge base. Psychiatric knowledge is not homogenous but demonstrates hierarchical complexity: knowledge about pharmacological, cellular, anatomical, organ system, emotional, cognitive, family, social, and culrural factors all interact to make decision-making especially difficult. Unless confined to one or a few of these hierarchical information levels or to a narrow "vertical information slice" successful ES development is unlikelyt91. Users are often reluctant to accept system. Although finding ES'S interesting. health care workers have been reluctant to accepted them or incorporated them into daily use. Unless the systems dramatically extend, ease, or improve the quality of care delivery, it is unlikely they will be accepted [lo]. PsychianiSts in @cular have a reputation of little affection for computers in care delivery. The expert system shell imposes constraints on the nature of problem solving....
Expert system (ES) technology may somewhat help manage the growing mass of information in the f i l d of psychiatry. but several factors prevent the systems from being widely use@. Constraints inherent in the structure and operation of available ES shells make them useful only within some subabmhs. The non-homogenous and hierarchically complex nature of the jields information makes it d@cult to construct broadly useful systems. These problems and current developments in trainable pattern detection system call for additional powerful and versatile approaches. PRESENT APPROACHESInterest in applying ES type technology in the field of psychiatry has focused mainly on two types of roles: that of consultantladvisor/teacher assisting in decision making, and that of intelligent monitoring. Expert systems or other cornputex systems might ideally help health care personnel with diagnostic interviewing[t] and differential dmgnosis[z][3], behavioral assessmentt41, assessment of suicidal risktq or homocidal risk, selection of therapeutic modalities, selection of appropriate pharmacotherapy, aSSeSSment of drug interactions161. management of drug overdoses, and others. Monitoring systems might be built into medical "smart-charts" enabling intelligent screening for prescribing ermpsp], suspicious laboratory values, or trends in activity, diet 02 weight. Other potential mental health uses are rehabilitative applications, such as training, education, systematic behavior modification and biofeedback, or embedded ES technology in health and human seMces robotics, such as smart-house or "psychorobotic" systems, which might monitor and redirect those with chronic psychiatrk or neurobehavioral disturbances. [SI.The construction of an expert system in a medical field presents many known challenges, which swngly influence the system's application and functional nature. These may be especially problematic in the field of clinical psychiatry. Several of these challenges follow:The domain must be a modest size and sharply defined. The larger and more heterogenous the domain, the more difficult it is to build the rules composing the system's knowledge base. Psychiatric knowledge is not homogenous but demonstrates hierarchical complexity: knowledge about pharmacological, cellular, anatomical, organ system, emotional, cognitive, family, social, and culrural factors all interact to make decision-making especially difficult. Unless confined to one or a few of these hierarchical information levels or to a narrow "vertical information slice" successful ES development is unlikelyt91. Users are often reluctant to accept system. Although finding ES'S interesting. health care workers have been reluctant to accepted them or incorporated them into daily use. Unless the systems dramatically extend, ease, or improve the quality of care delivery, it is unlikely they will be accepted [lo]. PsychianiSts in @cular have a reputation of little affection for computers in care delivery. The expert system shell imposes constraints on the nature of problem solving....
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.