scholarly journals Probabilistic graphical models of individual socially significant behavior on the base of incomplete data

2014 ◽  
Vol 3 (22) ◽  
pp. 101 ◽  
Author(s):  
Alena Vladimirovna Suvorova ◽  
Tatiana Valentinovna Tulupyeva ◽  
Alexander Lvovich Tulupyev ◽  
Alexander Vladimirovich Sirotkin ◽  
Anton Evgen’evich Paschenko
Keyword(s):  
Graphical Models ◽  
Incomplete Data ◽  
Probabilistic Graphical Models

Learning probabilistic networks

1999 ◽  
Vol 13 (4) ◽  
pp. 321-351 ◽  
Author(s):  
PAUL J. KRAUSE
Keyword(s):  
Probability Theory ◽  
Probability Distribution ◽  
Prior Knowledge ◽  
Graphical Models ◽  
Incomplete Data ◽  
Graphical Model ◽  
Probabilistic Graphical Models ◽  
Short Discussion ◽  
Probabilistic Networks ◽  
Probabilistic Network

A probabilistic network is a graphical model that encodes probabilistic relationships between variables of interest. Such a model records qualitative influences between variables in addition to the numerical parameters of the probability distribution. As such it provides an ideal form for combining prior knowledge, which might be limited solely to experience of the influences between some of the variables of interest, and data. In this paper, we first show how data can be used to revise initial estimates of the parameters of a model. We then progress to showing how the structure of the model can be revised as data is obtained. Techniques for learning with incomplete data are also covered. In order to make the paper as self contained as possible, we start with an introduction to probability theory and probabilistic graphical models. The paper concludes with a short discussion on how these techniques can be applied to the problem of learning causal relationships between variables in a domain of interest.

scholarly journals Prediction of short-term antidepressant response using probabilistic graphical models with replication across multiple drugs and treatment settings

2021 ◽  
Author(s):  
Arjun P. Athreya ◽  
Tanja Brückl ◽  
Elisabeth B. Binder ◽  
A. John Rush ◽  
Joanna Biernacka ◽  
...  
Keyword(s):  
Depressive Symptoms ◽  
Graphical Models ◽  
Selective Serotonin Reuptake Inhibitors ◽  
Probabilistic Graphical Models ◽  
Sociodemographic Factors ◽  
Response To Therapy ◽  
Antidepressant Response ◽  
Symptom Profiles ◽  
Poor Outcomes ◽  
Multiple Drugs

AbstractHeterogeneity in the clinical presentation of major depressive disorder and response to antidepressants limits clinicians’ ability to accurately predict a specific patient’s eventual response to therapy. Validated depressive symptom profiles may be an important tool for identifying poor outcomes early in the course of treatment. To derive these symptom profiles, we first examined data from 947 depressed subjects treated with selective serotonin reuptake inhibitors (SSRIs) to delineate the heterogeneity of antidepressant response using probabilistic graphical models (PGMs). We then used unsupervised machine learning to identify specific depressive symptoms and thresholds of improvement that were predictive of antidepressant response by 4 weeks for a patient to achieve remission, response, or nonresponse by 8 weeks. Four depressive symptoms (depressed mood, guilt feelings and delusion, work and activities and psychic anxiety) and specific thresholds of change in each at 4 weeks predicted eventual outcome at 8 weeks to SSRI therapy with an average accuracy of 77% (p = 5.5E-08). The same four symptoms and prognostic thresholds derived from patients treated with SSRIs correctly predicted outcomes in 72% (p = 1.25E-05) of 1996 patients treated with other antidepressants in both inpatient and outpatient settings in independent publicly-available datasets. These predictive accuracies were higher than the accuracy of 53% for predicting SSRI response achieved using approaches that (i) incorporated only baseline clinical and sociodemographic factors, or (ii) used 4-week nonresponse status to predict likely outcomes at 8 weeks. The present findings suggest that PGMs providing interpretable predictions have the potential to enhance clinical treatment of depression and reduce the time burden associated with trials of ineffective antidepressants. Prospective trials examining this approach are forthcoming.

Extended Probability Trees for Probabilistic Graphical Models

2014 ◽  
pp. 113-128
Author(s):  
Andrés Cano ◽  
Manuel Gómez-Olmedo ◽  
Serafín Moral ◽  
Cora B. Pérez-Ariza
Keyword(s):  
Graphical Models ◽  
Probabilistic Graphical Models ◽  
Probability Trees

scholarly journals Financial networks as directed cyclic graphs - draft

2014 ◽  
Vol 11 (4) ◽  
pp. 520-529 ◽  
Author(s):  
Alexander Denev
Keyword(s):  
Computer Science ◽  
Graphical Models ◽  
Network Theory ◽  
Probabilistic Graphical Models ◽  
Financial Networks ◽  
New Approach ◽  
Global Properties ◽  
Cyclic Graphs

Financial networks’ study and understanding has become extremely important since the global financial meltdown in 2007-2009 when the inter-connectedness of institutions has surfaced as one of the major culprits for the magnitude of the distress. This paper aims at providing a new approach to describe and better understand the networks of institutions and their global properties. It is based on Directed Cyclic Graphs - a subset of Probabilistic Graphical Models which have already found use in other domains such as physics and computer science. The paper draws some parallels and contrasts with other studies in the field of Network Theory. It then concludes with a stylized example.

Reconciling internal and external satisfaction through probabilistic graphical models

2017 ◽  
Vol 9 (3/4) ◽  
pp. 347-370 ◽  
Author(s):  
Flaminia Musella ◽  
Roberta Guglielmetti Mugion ◽  
Hendry Raharjo ◽  
Laura Di Pietro
Keyword(s):  
Customer Satisfaction ◽  
Bayesian Networks ◽  
Graphical Models ◽  
Object Oriented ◽  
Holistic Approach ◽  
Probabilistic Graphical Models ◽  
Model Parameters ◽  
Holistic View ◽  
Content Type ◽  
External Customer

Purpose This paper aims to holistically reconcile internal and external customer satisfaction using probabilistic graphical models. The models are useful not only in the identification of the most sensitive factors for the creation of both internal and external customer satisfaction but also in the generation of improvement scenarios in a probabilistic way. Design/methodology/approach Standard Bayesian networks and object-oriented Bayesian networks are used to build probabilistic graphical models for internal and external customers. For each ward, the model is used to evaluate satisfaction drivers by category, and scenarios for the improvement of overall satisfaction variables are developed. A global model that is based on an object-oriented network is modularly built to provide a holistic view of internal and external satisfaction. The linkage is created by building a global index of internal and external satisfaction based on a linear combination. The model parameters are derived from survey data from an Italian hospital. Findings The results that were achieved with the Bayesian networks are consistent with the results of previous research, and they were obtained by using a partial least squares path modelling tool. The variable ‘Experience’ is the most relevant internal factor for the improvement of overall patient satisfaction. To improve overall employee satisfaction, the variable ‘Product/service results’ is the most important. Finally, for a given target of overall internal and external satisfaction, external satisfaction is more sensitive to improvement than internal satisfaction. Originality/value The novelty of the paper lies in the efforts to link internal and external satisfaction based on a probabilistic expert system that can generate improvement scenarios. From an academic viewpoint, this study moves the service profit chain theory (Heskett et al., 1994) forward by delivering operational guidelines for jointly managing the factors that affect internal and external customer satisfaction in service organizations using a holistic approach.

scholarly journals Probabilistic Graphical Models on Multi-Core CPUs Using Java 8

2016 ◽  
Vol 11 (2) ◽  
pp. 41-54 ◽  
Author(s):  
Andres R. Masegosa ◽  
Ana M. Martinez ◽  
Hanen Borchani
Keyword(s):  
Graphical Models ◽  
Probabilistic Graphical Models
Sign in / Sign up

Export Citation Format

Share Document