From complex questionnaire and interviewing data to intelligent Bayesian network models for medical decision support

Abstract

Objectives1) To develop a rigorous and repeatable method for building effective Bayesian network (BN) models for medical decision support from complex, unstructured and incomplete patient questionnaires and interviews that inevitably contain examples of repetitive, redundant and contradictory responses; 2) To exploit expert knowledge in the BN development since further data acquisition is usually not possible; 3) To ensure the BN model can be used for interventional analysis; 4) To demonstrate why using data alone to learn the model structure and parameters is often unsatisfactory even when extensive data is available.MethodThe method is based on applying a range of recent BN developments targeted at helping experts build BNs given limited data. While most of the components of the method are based on established work, its novelty is that it provides a rigorous consolidated and generalised framework that addresses the whole life-cycle of BN model development. The method is based on two original and recent validated BN models in forensic psychiatry, known as DSVM-MSS and DSVM-P.ResultsWhen employed with the same datasets, the DSVM-MSS demonstrated competitive to superior predictive performance (AUC scores 0.708 and 0.797) against the state-of-the-art (AUC scores ranging from 0.527 to 0.705), and the DSVM-P demonstrated superior predictive performance (cross-validated AUC score of 0.78) against the state-of-the-art (AUC scores ranging from 0.665 to 0.717). More importantly, the resulting models go beyond improving predictive accuracy and into usefulness for risk management purposes through intervention, and enhanced decision support in terms of answering complex clinical questions that are based on unobserved evidence.ConclusionsThis development process is applicable to any application domain which involves large-scale decision analysis based on such complex information, rather than based on data with hard facts, and in conjunction with the incorporation of expert knowledge for decision support via intervention. The novelty extends to challenging the decision scientists to reason about building models based on what information is really required for inference, rather than based on what data is available and hence, forces decision scientists to use available data in a much smarter way.

Towards next-generation energy planning decision-making: An expert-based framework for intelligent decision support

“…The proposed framework is a brainstorming attempt to orient the EPDM research community to get fully involved towards activating this paper's future vision of more interactive and intelligent next-generation strategic EPDM solutions as it is the case within other disciplines such as (intelligent sustainable) manufacturing and Industry 4.0 [238,239], (green) supply chain management [240,241], and more significantly in (participative and intelligent) healthcare and medical decision support [242,243]. Thus, all involved energy planning stakeholders' are expected to express their feedbacks, agreements/disagreements, and more importantly their concerns for enhanced, sustainability-oriented strategic EPDM.…”

Ontology-driven Bayesian Network Model for Semantic Expression

“…In the Hypertension Bayesian network model, there are two nodes that need to use the Noisy-Or algorithm. The conditional probability formula for the node Obesity is shown in equation (2). Where the odds 0.30 for p (Obesity | Overnutation) = 0.30, that is, Overnutrition (yes) is yes, Obesity is the probability of yes.…”

“…Understanding and extracting information from EHRs enables reasoning with clinical variables and supports decision making [1][2][3]. Electronic Health records are store the patient information as data coded in structured format, as well as in the form of free text for clinical documentation.…”

Learning and inference in knowledge-based probabilistic model for medical diagnosis

“…The support vector machine [6][7][8] has a solid theoretical basis for the classification task; because of its efficient selection of features, it has higher predictive accuracy than decision trees. Bayesian networks [9][10], which are based on Bayesian theory [11][12], describe the dependence relationship between the symptom variables and the disease variables; these can be used in medical diagnosis. Other diagnostic models include neural Learning and inference in knowledge-based probabilistic model for medical diagnosis 4 networks (NN) [13][14][15], fuzzy logic (FL) [16][17], and genetic algorithms (GAs) [18][19][20].…”