Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “decision intelligence”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 631 records · Page 35Linked to original sources

The use of a computer-based decision support system facilitates primary care physicians' management of chronic pain.

We tested whether computer-based decision support (CBDS) could enhance the ability of primary care physicians (PCPs) to manage chronic pain. Structured summaries were generated for 50 chronic pain patients referred by PCPs to a pain clinic. A pain specialist used a decision support system to determine appropriate pain therapy and sent letters to the referring physicians outlining these recommendations. Separately, five board-certified PCPs used a CBDS system to "treat" the 50 cases. A successful outcome was defined as one in which new or adjusted therapies recommended by the software were acceptable to the PCPs (i.e., they would have prescribed it to the patient in actual practice). Two pain specialists reviewed the PCPs' outcomes and assigned medical appropriateness scores (0 = totally inappropriate to 10 = totally appropriate). One year later, the hospital database provided information on how the actual patients' pain was managed and the number of patients re-referred by their PCP to the pain clinic. On the basis of CBDS recommendations, the PCP subjects "prescribed" additional pain therapy in 213 of 250 evaluations (85%), with a medical appropriateness score of 5.5 +/- 0.1. Only 25% of these chronic pain patients were subsequently re-referred to the pain clinic within 1 yr. The use of a CBDS system may improve the ability of PCPs to manage chronic pain and may also facilitate screening of consults to optimize specialist utilization.

Adult↗

Computerized decision support for concurrent utilization review using the HELP system.

OBJECTIVE: Development and evaluation of computerized concurrent utilization review (UR) support taking advantage of a clinically rich computerized patient database. DESIGN: The Automated Support System for Utilization Review (ASSURE) applies the Appropriateness Evaluation Protocol (AEP) Day of Care criteria to computerized patient data in the HELP hospital information system. This paper reports the development, verification, and validation of ASSURE. MEASUREMENTS: Implementation correctness was verified by measuring agreement with a nurse reviewer, using separate sample sets for all 20 criteria for a total of 560 current inpatients. Usefulness in detecting inappropriate days of care was validated by two nurse reviewers who were crossed with manual and computer-assisted review methods in a blocked design for 168 current inpatients. Agreement with reviewers, sensitivity, specificity, positive predictive value, and negative predictive value were measured. RESULTS: Agreement was very good for satisfaction of criteria, and good for appropriateness of day of care. A patient day identified by ASSURE as potentially inappropriate would be twice as likely to be judged inappropriate by a reviewer as a randomly selected patient day. Review of the 10% of patient days identified as potentially inappropriate by ASSURE would identify approximately 21% of the inappropriate days of care. CONCLUSION: ASSURE is a clinically useful tool for screening adult acute care patients for inappropriate days of care, and promises to make a major contribution to reducing health care costs. The prognosis for successful routine clinical use is good.

Artificial Intelligence↗

Integrated decision support in a hospital cancer registry.

In this paper we present (a) a shell for integrated knowledge-based functions that is destined to support decision processes of the users of the Giessener Tumordokumentationssystem (GTDS) and (b) some results we obtained during a 6-month observation period at one of the customers of the GTDS. A special characteristic of the provided decision support is the high degree of integration in the underlying information system GTDS, i.e. the functions are triggered by events in the patient database, existing patient data is reused as input for the reasoning process and generated alerts are presented instantly to the end-user. The first routine field of application was supporting registrars to adhere to integrity constraints as defined by the International Agency of Research on Cancer (IARC) during the documentation process. This information is important for the registrars since the checks of the IARC are an accepted standard for data quality in cancer registries. The expected benefit of this application area is less effort in achieving adherence to the specification of the IARC by preventing the costly rectification at a later time. During the last 5 months of the observation period 164 alerts were displayed. About 65% of the assessed alerts were considered to be correct. Especially, the analysis of the incorrect alerts revealed some shortcomings in the knowledge behind some of the integrity constraints of the IARC. The general feedback from the end-users indicate positive user satisfaction. Currently, the shell is in use in six hospital cancer registries.

Artificial Intelligence↗

How Following Medical Artificial Intelligence Advice Can Mitigate Malpractice Liability: Cross-National Insights from a Randomized Trial.

Artificial intelligence (AI) increasingly influences clinical decision-making, yet its recommendations may diverge from standard care. Although malpractice concerns are thought to discourage physicians from following AI advice, experimental evidence from the United States suggests the opposite: lay jurors are more likely to hold physicians liable when they reject AI recommendations. Whether this pattern extends to systems in which court-appointed experts, not lay jurors, determine liability remains unknown. Methods: To examine how physicians and laypeople in expert-based and lay-juror legal systems evaluate physicians' acceptance or rejection of AI recommendations, particularly when those recommendations deviate from standard care, we designed a randomized vignette study: a 2 &#xd7; 2 factorial design varying the AI recommendation (standard vs. nonstandard care) and a fictional physician's decision (accept vs. reject). The study was conducted online in 2023 among nationally representative samples of U.S. and German adults and from 2023 to 2024 among German physicians. In total, 387 German physicians, 2291 U.S. adults, and 2283 German adults participated; those not completing the survey or failing attention checks were excluded per preregistered criteria. Participants were randomly assigned to 1 of 4 vignettes, varying the AI recommendation (standard vs. nonstandard care) and physician's decision (accept vs. reject). The reasonableness of the fictional physician's decision was measured, rated by participants on a Likert scale. Results: Analysis, following preregistered exclusion criteria, included 248 German physicians, 1202 U.S. adults, and 1358 German adults. Physicians accepting standard-care AI recommendations were rated more reasonable than those rejecting them (U.S. laypeople: t = 5.36; 95% CI, 0.45-0.97; P < 0.001; German physicians: t = 2.47; 95% CI, 0.14-1.30; P = 0.02; German laypeople: t = 4.14; 95% CI, 0.27-0.76; P < 0.001). Ratings of physicians accepting versus rejecting AI nonstandard-care recommendations were statistically equivalent. Equivalence was tested at an &#x3b1;-value of 0.05 using a two 1-sided tests procedure, reported with 90% CIs per standard convention (U.S. laypeople: t = -4.90; 90% CI, -0.1 to 0.36; P < 0.001; German physicians: t = -1.76; 90% CI, -0.12 to 0.67; P = 0.04; German laypeople: t = 5.35; 90% CI, -0.35 to 0.06; P < 0.001). Conclusion: Across the United States and Germany, samples representative of lay jurors and court-appointed experts viewed accepting standard-care AI advice as more reasonable, whereas accepting or rejecting nonstandard-care AI advice was judged similarly. Contrary to predictions, malpractice liability regimes do not necessarily pose a barrier to AI use in precision medicine.

Artificial Intelligence↗

Kave: a tool for knowledge acquisition to support artificial ventilation.

A decision support system for artificial ventilation is being developed. One of the fundamental goals for this system is the application of the system when a domain expert is not present. Such a system requires a rich knowledge base. The knowledge acquisition process is often considered to be the bottleneck in acquiring such a complete knowledge base. Since no single available method, for example interviewing domain experts, is sufficient for removing this bottleneck, we have chosen a combination of different methods. The different backgrounds of knowledge engineers and domain experts could cause communication restrictions and difficulties between them, e.g. they might not understand each others knowledge domain and this will affect formulation of the knowledge. To solve this problem we needed a tool which supports both the knowledge engineer and the domain expert already from the initial phase of developing the knowledge base. We have developed a knowledge acquisition system called KAVE to elicit knowledge from domain experts and storing it in the knowledge base. KAVE is based on a domain specific conceptual model which is a result of cooperation between knowledge engineers and domain experts during identification, design and structuring of knowledge for this domain. KAVE includes a patient simulator to help validate knowledge in the knowledge base and a knowledge editor to facilitate refinement and maintenance of the knowledge base.

Artificial Intelligence↗

A temporal-abstraction mediator for protocol-based decision-support systems.

The inability of many clinical decision-support applications to integrate with existing databases limits the wide-scale deployment of such systems. To overcome this obstacle, we have designed a data-interpretation module that can be embedded in a general architecture for protocol-based reasoning and that can support the fundamental task of detecting temporal abstractions. We have developed this software module by coupling two existing systems--RESUME and Chronus--that provide complementary temporal-abstraction techniques at the application and the database levels, respectively. Their encapsulation into a single module thus can resolve the temporal queries of protocol planners with the domain-specific knowledge needed for the temporal-abstraction task and with primary time-stamped data stored in autonomous clinical databases. We show that other computer methods for the detection of temporal abstractions do not scale up to the data- and knowledge-intensive environments of protocol-based decision-support systems.

Artificial Intelligence↗

Relationships among performance scores of four diagnostic decision support systems.

OBJECTIVE: To examine the relationships among different performance scores for each of four diagnostic decision support systems (DDSSs). DESIGN: Intercorrelations among seven performance scores on a set of 105 cases for each of four DDSSs (DXplain, Iliad, Meditel, QMR) were computed. METHODS: The performance scores for each case reflected: 1) presence or absence of the case diagnosis in the DDSS knowledge base; 2) presence or absence of the correct diagnosis anywhere on the DDSS diagnosis list; 3) presence or absence of the correct diagnosis in the top ten diagnoses; 4) relevance of the DDSS diagnosis list; 5) comprehensiveness of the DDSS diagnosis list; 6) whether the DDSS suggested additional diagnoses to the experts' list; and 7) the length of the DDSS diagnosis list. RESULTS: For all DDSSs, the two Correct Diagnosis scores (top ten and total list) were significantly related: 1) to the presence of the correct diagnosis in the knowledge base; 2) to the Comprehensiveness score; and 3) to each other. There were significant differences among the four DDSSs on the magnitude and/or direction of the relationships between: 1) the two Correct Diagnosis scores; 2) the Relevance and Length scores; and 3) the Relevance and Additional Diagnoses scores. CONCLUSION: The production of a correct diagnosis for a given case is not related to the number of diagnoses suggested by the DDSS and, across different DDSSs, is not consistently related to other measures of performance. These data indicate that multiple measures are needed to fully describe the performance of a DDSS.

Algorithms↗

The problem-oriented system, problem-knowledge coupling, and clinical decision making.

The information tool to aid us in making the clinical decisions discussed in this presentation is called the PKC. Our goal with patients should be to couple the knowledge of the unique patient to the knowledge in the literature and get the best possible match. This approach requires combinatorial versus probabilistic thinking. In the real world, ideal matches are not found. Therefore, it is critical to exhaust the patient's uniqueness first and only then use probabilities to settle further uncertainties. It is an error to teach people how to deal with uncertainty instead of teaching them to clean up a great deal of the uncertainty first. Patients must be involved in this endeavor. In essence, they have a PhD in their own uniqueness, and it is this uniqueness that is very powerful in solving complex problems. This method of patient evaluation and management cannot be used with the unaided mind. It requires new and powerful information tools like the PKC. All information that is relevant to a problem should be included in the coupler. It should encompass differing points of view, and the rationale should be made explicit to clinician and patient alike. When complete, the coupler should represent an interdisciplinary compilation of questions and tests that are expected to be collected every time in the clinic for the type of problem the coupler represents. This method will provide a basis for quality control because the contents of the coupler now have defined what we expect to occur in every patient encounter.(ABSTRACT TRUNCATED AT 250 WORDS)

Artificial Intelligence↗

The effect of incomplete knowledge on the diagnoses of a computer consultant system.

The knowledge bases (KBs) of diagnostic decision support systems are often incomplete, and gaps in the KB could potentially lead systems to reach diagnoses that are implausible to physicians. To investigate this possibility we studied Iliad (Version 2.01), a computer consultant system that generates differential diagnosis across the domain of internal medicine. Data from the history, physical examination, and laboratory findings of 50 grand-rounds cases were entered into Iliad by a computer consultant aware of the diagnosis but blinded to its presence or absence in Iliad's KB. Two experienced internists were asked to diagnose these cases before and after seeing the results of the computer consultation, and to assess the plausibility of the computer's diagnoses. Twenty-eight of the 50 cases (56.0%) were diseases contained in Iliad's KB. After seeing Iliad's diagnoses for cases in the KB, physicians assigned to their correct diagnoses a higher mean ranked position (1.5 versus 2.0, p less than 0.008) and a higher mean probability (84.0% versus 77.6%, p less than 0.008) compared with their pre-Iliad values, whereas for cases not in the KB, mean position and probability for correct diagnoses did not change. Physician diagnostic accuracy did not change after consultation on cases included or not included in the KB. After adjusting for case difficulty, mean plausibility of Iliad's diagnoses was judged significantly higher (on a seven-point scale) for cases in the KB than for cases not in the KB (4.2 versus 3.2, p less than 0.02).(ABSTRACT TRUNCATED AT 250 WORDS)

Artificial Intelligence↗

Context-sensitive autoassociative memories as expert systems in medical diagnosis.

BACKGROUND: The complexity of our contemporary medical practice has impelled the development of different decision-support aids based on artificial intelligence and neural networks. Distributed associative memories are neural network models that fit perfectly well to the vision of cognition emerging from current neurosciences. METHODS: We present the context-dependent autoassociative memory model. The sets of diseases and symptoms are mapped onto a pair of basis of orthogonal vectors. A matrix memory stores the associations between the signs and symptoms, and their corresponding diseases. A minimal numerical example is presented to show how to instruct the memory and how the system works. In order to provide a quick appreciation of the validity of the model and its potential clinical relevance we implemented an application with real data. A memory was trained with published data of neonates with suspected late-onset sepsis in a neonatal intensive care unit (NICU). A set of personal clinical observations was used as a test set to evaluate the capacity of the model to discriminate between septic and non-septic neonates on the basis of clinical and laboratory findings. RESULTS: We show here that matrix memory models with associations modulated by context can perform automatic medical diagnosis. The sequential availability of new information over time makes the system progress in a narrowing process that reduces the range of diagnostic possibilities. At each step the system provides a probabilistic map of the different possible diagnoses to that moment. The system can incorporate the clinical experience, building in that way a representative database of historical data that captures geo-demographical differences between patient populations. The trained model succeeds in diagnosing late-onset sepsis within the test set of infants in the NICU: sensitivity 100%; specificity 80%; percentage of true positives 91%; percentage of true negatives 100%; accuracy (true positives plus true negatives over the totality of patients) 93,3%; and Cohen's kappa index 0,84. CONCLUSION: Context-dependent associative memories can operate as medical expert systems. The model is presented in a simple and tutorial way to encourage straightforward implementations by medical groups. An application with real data, presented as a primary evaluation of the validity and potentiality of the model in medical diagnosis, shows that the model is a highly promising alternative in the development of accuracy diagnostic tools.

Decision Support Systems, Clinical↗

How AI-supported intelligent systems support infection prevention and control training in healthcare: A systematic review of educational functions and outcomes.

AIMS: Artificial intelligence (AI)-supported intelligent systems have been increasingly incorporated into infection prevention and control (IPC) education and training, primarily to support the monitoring of observable behaviors and the provision of feedback. However, existing evidence has focused largely on short-term compliance outcomes, with limited synthesis of the educational role of AI-supported intelligent systems in supporting sustained IPC competence. This systematic review examined how AI-supported intelligent systems have been designed and used to support IPC education and training, with a focus on system characteristics, educational functions, and reported outcomes. DESIGN: A systematic literature search was conducted across the PubMed/MEDLINE, Embase, Cochrane, and CINAHL databases. DATA SOURCES: A total of 18 studies met the inclusion criteria. Findings were qualitatively synthesized according to system design characteristics, educational functions, and outcome domains. REVIEW METHODS: Methodological quality was appraised using the Mixed Methods Appraisal Tool. RESULTS: Most AI-supported intelligent systems focused on hand hygiene and relied on fully automated monitoring systems to capture behaviors and provide performance feedback. Educational functions were predominantly limited to performance assessment, automated feedback, and reminders. Outcomes were mainly measured using compliance or performance metrics, whereas sustained behavioral change and decision quality were rarely assessed. CONCLUSIONS: AI-supported intelligent systems have been used primarily to reinforce short-term IPC performance and compliance. However, their current applications for supporting sustained competence over time remain limited. The findings of this review suggest that AI-supported intelligent systems may serve as maintenance-oriented educational support by extending learning beyond initial instruction through repeated practice and feedback. Future research should prioritize outcome measures that capture the durability of performance and decision-making processes to better align AI-supported intelligent systems used in IPC education and training with the educational demands of clinical practice.

Humans↗

The role of protocols and professional judgement in emergency medical dispatching.

The task of evaluating incoming calls to Emergency Medical Services (EMS) systems in order to determine the most appropriate response is performed in many different ways in current EMS systems. At one end of the spectrum, the process is entirely dependent on the judgement of professionals, while at the other end protocols specify the exact questions to be asked and corresponding decisions. This case study describes the experience of the Montreal EMS system, Urgences santé, where professional telephone evaluation performed by nurses since 1981 was replaced by a protocolized system in 1992. During the professional era, there were many attempts to formalize the nurses' decision-making process. These first revealed that professional judgement tended to override decision-support tools that did not allow a flexible processing of the information spontaneously provided by callers. Second, the choice of a single protocol for each call was unnatural for professionals who could spontaneously integrate multiple aspects of a problem in parallel. Third, when protocols were used by professionals, it was a posteriori in order to document their decisions rather than actually support them. Fourth, the use of Artificial Intelligence (AI) methods in order to formalize professional judgement revealed its great complexity, which was confirmed by cognitive analyses of the nurses' decision-making processes. In particular, decisions of not sending EMS resources seemed to be the most difficult. These unsuccessful attempts at formalizing professional judgement led to an evaluation of its performance in terms of results, i.e. to which extent actual decisions minimized errors (both false positives and false negatives) and decision times. A random sample of 1006 calls was collected and the ideal decision was determined by concensus of experts for each call based on the patient's clinical condition. This theoretical decision was considered as a goal standard to which actual decisions were compared. Data analysis revealed that sensitivity of telephone triage (i.e. decision to send EMS resources or not) was almost perfect and specificity was 0.55. The necessary compromise between sensitivity and specificity varied with the types of decisions. Decision times were related to the urgency of the situations, more urgent calls being processed more rapidly. These results were interpreted as representing sophisticated optimization processes in professional judgement. The professional system was replaced by a non-professional protocolized system in 1992. This new system has not yet been formally evaluated in terms of results, but many sources of evidence suggest that it was accompanied by a deterioration of performance. Many contextual factors influence the organization of telephone assessment in EMS systems. This case study suggests that professional judgement may be most useful in contexts where the demand for EMS services often exceeds the availability of resources. On the other hand, protocolized systems may be more appropriate in the absence of such constraints, and where the litigation context prohibits the occurrence of any false negative.

Artificial Intelligence↗

Disambiguating ambiguous biomedical terms in biomedical narrative text: an unsupervised method.

With the growing use of Natural Language Processing (NLP) techniques for information extraction and concept indexing in the biomedical domain, a method that quickly and efficiently assigns the correct sense of an ambiguous biomedical term in a given context is needed concurrently. The current status of word sense disambiguation (WSD) in the biomedical domain is that handcrafted rules are used based on contextual material. The disadvantages of this approach are (i) generating WSD rules manually is a time-consuming and tedious task, (ii) maintenance of rule sets becomes increasingly difficult over time, and (iii) handcrafted rules are often incomplete and perform poorly in new domains comprised of specialized vocabularies and different genres of text. This paper presents a two-phase unsupervised method to build a WSD classifier for an ambiguous biomedical term W. The first phase automatically creates a sense-tagged corpus for W, and the second phase derives a classifier for W using the derived sense-tagged corpus as a training set. A formative experiment was performed, which demonstrated that classifiers trained on the derived sense-tagged corpora achieved an overall accuracy of about 97%, with greater than 90% accuracy for each individual ambiguous term.

Algorithms↗

Artificial intelligence research in anesthesia and intensive care.

This article describes several research directions exploring the application of artificial intelligence techniques in anesthesia and intensive care. Artificial intelligence can be loosely defined as the discipline of designing computer systems that exhibit "intelligent" behavior. This article first introduces artificial intelligence and computer science research and discusses why medicine has proved to be a challenging domain for applying artificial intelligence techniques. A discussion of the central research themes that arise in medical artificial intelligence, many of which are common to different projects and to different medical settings, is followed by a description of specific research projects that apply artificial intelligence techniques in anesthesiology, ventilatory management, and cardiovascular management. Finally, further comments are made on the current state of the field.

Anesthesia↗

Object-oriented development of a concept learning system for time-centered clinical data.

A concept learning system is expected to be a powerful tool for filtering and analyzing a large amount of data in a variety of scientific fields. A simple application of it to clinical data, however, fails to mine medical information and knowledge. One of the major obstacles in mining a clinical database is time, which is a very important concept in clinical medicine. To be successful in data mining in clinical medicine, an efficient model of clinical data with time and a flexible concept learning system augmented to handle the model are both necessary. Herein we modeled clinical data to easily express and manipulate time and extended a concept learning system to utilize a time-centered clinical data model. The modified concept learning system is based on the message-value method rather than the traditional attribute-value method. The object-oriented technology was of great help in modeling time-centered clinical data and in developing a modified concept learning system.

Algorithms↗

Suitability of artificial neural networks for feature extraction from cardiotocogram during labour.

Fetal condition during labour is inferred from a continuous display of fetal heart rate and uterine contractions called the cardiotocogram (CTG). The CTG requires a considerable expertise for correct interpretation, which is not always available. We are developing an intelligent system to support clinical decision-making during labour. The system's performance depends on its ability to classify features from the CTG similarly to experts. Artificial neural networks (NNs) can be taught by experts for such tasks, and so may be particularly suitable. We found NNs suitable for feature extraction when the problem was reduced to small well defined tasks, and numerical algorithms were used to pre-process the raw data before application to the NNs. A NN with optimised dimensions was used in this way to classify the magnitude of decelerations, a feature clinicians find particularly difficult. The NN was compared with the algorithm used in a commercial antenatal monitor and six reviewers which included two CTG experts. The experts were consistent (89.7% and 97.0%) and agreed well with each other (81.0%), whereas the non-experts were less consistent and agreed less well. The NN agreed well with the experts (75.0% and 81.9%) but the algorithm agreed poorly (56.5% and 68.9%). It was found that the algorithm's performance could be improved (72.1% and 76.7%) when modified to use additional information. Our earlier attempts to fully classify the raw CTG using a single NN were unsuccessful because of the large number of data patterns. A simplified approach to classify the magnitude and timing of decelerations was also unsuitable when contraction data was of poor quality or absent.(ABSTRACT TRUNCATED AT 250 WORDS)

Algorithms↗

A comparative study of fuzzy classification methods on breast cancer data.

In this paper, we examine the performance of four fuzzy rule generation methods on Wisconsin breast cancer data. The first method generates fuzzy if-then rules using the mean and the standard deviation of attribute values with 92.2% correct classification rate. The second approach generates fuzzy if-then rules using the histogram of attributes values with 86.7% correct classification rate. The third procedure generates fuzzy if-then rules with certainty of each attribute into homogeneous fuzzy sets with 99.73% correct classification rate. In the fourth approach, only overlapping areas are partitioned with 62.57% correct classification rate. The first two approaches generate a single fuzzy if-then rule for each class by specifying the membership function of each antecedent fuzzy set using the information about attribute values of training patterns. The other two approaches are based on fuzzy grids with homogeneous fuzzy partitions of each attribute. The performance of each approach is evaluated on breast cancer data sets. Simulation results show that the simple grid approach has a high classification rate of 99.73%.

Algorithms↗

Artificial consciousness, artificial emotions, and autonomous robots.

Nowadays for robots, the notion of behavior is reduced to a simple factual concept at the level of the movements. On another hand, consciousness is a very cultural concept, founding the main property of human beings, according to themselves. We propose to develop a computable transposition of the consciousness concepts into artificial brains, able to express emotions and consciousness facts. The production of such artificial brains allows the intentional and really adaptive behavior for the autonomous robots. Such a system managing the robot's behavior will be made of two parts: the first one computes and generates, in a constructivist manner, a representation for the robot moving in its environment, and using symbols and concepts. The other part achieves the representation of the previous one using morphologies in a dynamic geometrical way. The robot's body will be seen for itself as the morphologic apprehension of its material substrata. The model goes strictly by the notion of massive multi-agent's organizations with a morphologic control.

Adaptation, Psychological↗