038 Knowledge-based systems and neural networks for clinical decision making

1994 ◽  
Vol 2 (5) ◽  
pp. 902
Keyword(s):  
Neural Networks ◽  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Knowledge Based Systems ◽  
Knowledge Based

Supporting Knowledge-Based Decision Making in the Medical Context

2011 ◽  
Vol 1 (1) ◽  
pp. 42-60 ◽  
Author(s):  
Luca Anselma ◽  
Alessio Bottrighi ◽  
Gianpaolo Molino ◽  
Stefania Montani ◽  
Paolo Terenziani ◽  
...  
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Medical Decision ◽  
Theory Analysis ◽  
Knowledge Based ◽  
Therapeutic Decisions ◽  
Computer Based ◽  
Based Medicine ◽  
Domain Independent

Knowledge-based clinical decision making is one of the most challenging activities of physicians. Clinical Practice Guidelines are commonly recognized as a useful tool to help physicians in such activities by encoding the indications provided by evidence-based medicine. Computer-based approaches can provide useful facilities to put guidelines into practice and to support physicians in decision-making. Specifically, GLARE (GuideLine Acquisition, Representation and Execution) is a domain-independent prototypical tool providing advanced Artificial Intelligence techniques to support medical decision making, including what-if analysis, temporal reasoning, and decision theory analysis. The paper describes such facilities considering a real-world running example and focusing on the treatment of therapeutic decisions.

scholarly journals A Cognitive Autopsy Approach towards Understanding Diagnostic Failure

2020 ◽  
Author(s):  
Pat Croskerry ◽  
Samuel Campbell
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Performance ◽  
Critical Role ◽  
Clinical Decision ◽  
Diagnostic Error ◽  
Diagnostic Process ◽  
Base Line ◽  
Root Cause ◽  
Knowledge Based

Diagnostic failure has emerged as one of the most significant threats to patient safety, and it is important to understand the antecedents of such failures. A consensus has developed in the literature that the majority are due to individual or system factors or some combination of the two. A major source of variance in individual clinical performance is due to cognitive and affective biases, however, their role in clinical decision making has been difficult to assess partly because they are difficult to investigate experimentally. A significant drawback has been that experimental manipulations appear to confound assessment of the context surrounding the diagnostic process itself. The present qualitative study uses a detailed narrative account of selected actual cases of diagnostic error to explore the effect of biases in the ‘real world’ emergency medicine (EM) context. Thirty anonymized EM cases were analysed in depth through a process of root cause analysis that included an assessment of error producing conditions, knowledge-based errors, and how clinicians were thinking and deciding during each case. A prominent feature of the study was the identification of specific cognitive and affective biases – through a process called cognitive autopsy. The cases covered a broad range of diagnoses across a wide variety of disciplines. A total of 24 discrete cognitive and affective biases that contributed to misdiagnosis were identified and their incidence recorded. 5-6 biases were detected per case, and observed on 168 occasions across the 30 cases. Thirteen error-producing conditions (EPCs) were identified. Knowledge-based errors were rare, occurring in only 5 definite instances. The ordinal position in which biases appeared in the diagnostic process was recorded. This study provides a base-line for understanding the critical role that biases play in clinical decision making and sheds light on important aspects of the diagnostic process.

Supporting Knowledge-Based Decision Making in the Medical Context

2011 ◽  
pp. 1721-1737
Author(s):  
Luca Anselma ◽  
Alessio Bottrighi ◽  
Gianpaolo Molino ◽  
Stefania Montani ◽  
Paolo Terenziani ◽  
...  
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Medical Decision ◽  
Evidence Based ◽  
Knowledge Based ◽  
Therapeutic Decisions ◽  
Computer Based ◽  
Based Medicine ◽  
Domain Independent

Knowledge-based clinical decision making is one of the most challenging activities of physicians. Clinical Practice Guidelines are commonly recognized as a useful tool to help physicians in such activities by encoding the indications provided by evidence-based medicine. Computer-based approaches can provide useful facilities to put guidelines into practice and to support physicians in decision-making. Specifically, GLARE (GuideLine Acquisition, Representation and Execution) is a domain-independent prototypical tool providing advanced Artificial Intelligence techniques to support medical decision making, including what-if analysis, temporal reasoning, and decision theory analysis. The paper describes such facilities considering a real-world running example and focusing on the treatment of therapeutic decisions.

scholarly journals REM: An Integrative Rule Extraction Methodology for Explainable Data Analysis in Healthcare

2021 ◽  
Author(s):  
Zohreh Shams ◽  
Botty Dimanov ◽  
Sumaiyah Kola ◽  
Nikola Simidjievski ◽  
Helena Andres Terre ◽  
...  
Keyword(s):  
Neural Networks ◽  
Decision Making ◽  
Domain Knowledge ◽  
Deep Neural Networks ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Biological Research ◽  
Cancer Subtypes ◽  
Biologically Relevant ◽  
Human In The Loop

AbstractDeep learning models are receiving increasing attention in clinical decision-making, however the lack of interpretability and explainability impedes their deployment in day-to-day clinical practice. We propose REM, an interpretable and explainable methodology for extracting rules from deep neural networks and combining them with other data-driven and knowledge-driven rules. This allows integrating machine learning and reasoning for investigating applied and basic biological research questions. We evaluate the utility of REM on the predictive tasks of classifying histological and immunohistochemical breast cancer subtypes from genotype and phenotype data. We demonstrate that REM efficiently extracts accurate, comprehensible and, biologically relevant rulesets from deep neural networks that can be readily integrated with rulesets obtained from tree-based approaches. REM provides explanation facilities for predictions and enables the clinicians to validate and calibrate the extracted rulesets with their domain knowledge. With these functionalities, REM caters for a novel and direct human-in-the-loop approach in clinical decision making.

Supporting Knowledge-Based Decision Making in the Medical Context

2012 ◽  
pp. 24-42
Author(s):  
Luca Anselma ◽  
Alessio Bottrighi ◽  
Gianpaolo Molino ◽  
Stefania Montani ◽  
Paolo Terenziani ◽  
...  
Keyword(s):  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Medical Decision ◽  
Evidence Based ◽  
Knowledge Based ◽  
Therapeutic Decisions ◽  
Computer Based ◽  
Based Medicine ◽  
Domain Independent

Knowledge-based clinical decision making is one of the most challenging activities of physicians. Clinical Practice Guidelines are commonly recognized as a useful tool to help physicians in such activities by encoding the indications provided by evidence-based medicine. Computer-based approaches can provide useful facilities to put guidelines into practice and to support physicians in decision-making. Specifically, GLARE (GuideLine Acquisition, Representation and Execution) is a domain-independent prototypical tool providing advanced Artificial Intelligence techniques to support medical decision making, including what-if analysis, temporal reasoning, and decision theory analysis. The paper describes such facilities considering a real-world running example and focusing on the treatment of therapeutic decisions.

Neural Networks and Psychiatry: Candidate Applications in Clinical Decision Making

1994 ◽  
Vol 28 (4) ◽  
pp. 651-666 ◽  
Author(s):  
Tony Florio ◽  
Stewart Einfeld ◽  
Florence Levy
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Decision Making ◽  
Computer System ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Comprehensive Search ◽  
New Type ◽  
The Brain ◽  
Computing Approach

Neural networks comprise a fundamentally new type of computer system inspired by the functioning of neurons in the brain. Such networks are good at solving problems that involve pattern recognition and categorisation. An important difference between a neural network and a traditional computer system is that in developing an application, a neural network is not programmed; instead, it is trained to solve a particular type of problem. This ability to learn to solve a problem makes neural networks adaptable to solving a wide variety of problems, some of which have proved intractable using a traditional computing approach. Neural networks are particularly suited to tasks involving the categorisation of patterns of information, such as is required in diagnosis and clinical decision making. In the last three years reports of applications involving neural networks have begun to appear in the medical literature, and these are described in this paper. However, a comprehensive search of the literature has shown that there have not as yet been reports of any applications in psychiatry. This paper discusses the nature of clinical decision making, outlines the sorts of problems in psychiatry which neural networks applications might be developed to address, and gives examples of candidate applications in clinical decision making.

scholarly journals REM: An Integrative Rule Extraction Methodology for Explainable Data Analysis in Healthcare

2021 ◽  
Author(s):  
Zohreh Shams ◽  
Botty Dimanov ◽  
Sumaiyah Kola ◽  
Nikola Simidjievski ◽  
Helena Andres Terre ◽  
...  
Keyword(s):  
Neural Networks ◽  
Decision Making ◽  
Domain Knowledge ◽  
Deep Neural Networks ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Biological Research ◽  
Cancer Subtypes ◽  
Biologically Relevant ◽  
Human In The Loop

AbstractDeep learning models are receiving increasing attention in clinical decision-making, however the lack of interpretability and explainability impedes their deployment in day-to-day clinical practice. We propose REM, an interpretable and explainable methodology for extracting rules from deep neural networks and combining them with other data-driven and knowledge-driven rules. This allows integrating machine learning and reasoning for investigating applied and basic biological research questions. We evaluate the utility of REM on the predictive tasks of classifying histological and immunohistochemical breast cancer subtypes from genotype and phenotype data. We demonstrate that REM efficiently extracts accurate, comprehensible and, biologically relevant rulesets from deep neural networks that can be readily integrated with rulesets obtained from tree-based approaches. REM provides explanation facilities for predictions and enables the clinicians to validate and calibrate the extracted rulesets with their domain knowledge. With these functionalities, REM caters for a novel and direct human-in-the-loop approach in clinical decision making.

Sign in / Sign up

Export Citation Format

Share Document