An empirical analysis of likelihood-weighting simulation on a large, multiply connected medical belief network

Shwe, Michael; Cooper, Gregory F.

doi:10.1016/0010-4809(91)90020-w

Cited by 54 publications

(32 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early Bayesian methods involved manually constructing models as an alternative to rule-based expert systems [9]. Perhaps the best known Bayesian network method is the "Quick Medical Reference-Decision Theoretic" model [10]. The QMR-DT model was a "bi-partite" network where diagnoses were root nodes and tests/observations were leaf nodes.…”

Section: Related Workmentioning

confidence: 99%

Distributional Smoothing in Bayesian Fault Diagnosis

Butcher

Sheppard

2009

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Abstract-Previously, we demonstrated the potential value of constructing asset-specific models for fault diagnosis. We also examined the effects of using split probabilities where prior probabilities come from asset-specific statistics and likelihoods from fleet-wide statistics. In this paper, we build upon that work to examine the efficacy of smoothing probability distributions between asset-specific and fleet-wide distributions to improve diagnostic accuracy further. In the current experiments, we also add environmental differentiation to asset differentiation under an assumption that data is acquired in the context of online health monitoring. We hypothesize that overall diagnostic accuracy will be increased with the smoothing approach relative to a fleet-wide model or a set of asset-specific models. The hypothesis is largely supported by the results. Future work will concentrate on improving the smoothing mechanism and in the context of small data sets.

show abstract

Section: Related Workmentioning

confidence: 99%

Distributional Smoothing in Bayesian Fault Diagnosis

Butcher

Sheppard

2009

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…c. Application of heuristics to make inferences in a formal but computationally intractable model to become more tractable. Example: the QMR-DT/BN system [44] (a belief network differen-e tial diagnosis system using the INTERNIST-I/QMR KB relies on heuristic inference algorithms extensively, to cope with the computational complexity of the huge belief network QMR-DT/BN utilized.…”

Section: A Proposed Qualitative Theory Of Heuristic Systemsmentioning

confidence: 99%

On the Heuristic Nature of Medical Decision-Support Systems

Aliferis

Miller

1995

Methods Inf Med

View full text Add to dashboard Cite

Abstract:In the realm of medical decision-support systems, the term “heuristic systems” is often considered to be synonymous with “medical artificial intelligence systems” or with “systems employing informal model(s) of problem solving”. Such a view may be inaccurate and possibly impede the conceptual development of future systems. This article examines the nature of heuristics and the levels at which heuristic solutions are introduced during system design and implementation. The authors discuss why heuristics are ubiquitous in all medical decision-support systems operating at non-trivial domains, and propose a unifying definition of heuristics that encompasses formal and ad hoc systems. System developers should be aware of the heuristic nature of all problem solving done in complex real world domains, and characterize their own use of heuristics in describing system development and implementation.

show abstract

“…One canonical use of this model is to model the relationship between diseases and symptoms, as in the classical human-constructed tool for medical diagnosis called Quick Medical Reference (QMR-DT) by (Miller et al [MPJM82], Shwe et al [SC91]) This textbook example ( [JGJS99]) of a Bayes net captures relationships between 570 binary disease variables (latent variables) and 4075 observed binary symptom variables, with 45, 470 directed edges, and the W ij 's are small integers. 1 The name "noisy-or "derives from the fact that the probability that the OR of m independent binary variables y 1 , y 2 , .…”

Section: Introductionmentioning

confidence: 99%

Provable learning of noisy-OR networks

Arora

et al. 2017

Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing

View full text Add to dashboard Cite

Many machine learning applications use latent variable models to explain structure in data, whereby visible variables (= coordinates of the given datapoint) are explained as a probabilistic function of some hidden variables. Finding parameters with the maximum likelihood is NP-hard even in very simple settings. In recent years, provably efficient algorithms were nevertheless developed for models with linear structures: topic models, mixture models, hidden markov models, etc. These algorithms use matrix or tensor decomposition, and make some reasonable assumptions about the parameters of the underlying model.But matrix or tensor decomposition seems of little use when the latent variable model has nonlinearities. The current paper shows how to make progress: tensor decomposition is applied for learning the single-layer noisy or network, which is a textbook example of a Bayes net, and used for example in the classic QMR-DT software for diagnosing which disease(s) a patient may have by observing the symptoms he/she exhibits.The technical novelty here, which should be useful in other settings in future, is analysis of tensor decomposition in presence of systematic error (i.e., where the noise/error is correlated with the signal, and doesn't decrease as number of samples goes to infinity). This requires rethinking all steps of tensor decomposition methods from the ground up.For simplicity our analysis is stated assuming that the network parameters were chosen from a probability distribution but the method seems more generally applicable.

show abstract

An empirical analysis of likelihood-weighting simulation on a large, multiply connected medical belief network

Cited by 54 publications

References 8 publications

Distributional Smoothing in Bayesian Fault Diagnosis

Distributional Smoothing in Bayesian Fault Diagnosis

On the Heuristic Nature of Medical Decision-Support Systems

Provable learning of noisy-OR networks

Contact Info

Product

Resources

About