02.Causation01.Causal Bayesian networks - sporedata/researchdesigneR GitHub Wiki
- Causal conclusions that are similar -- though not identical -- to what would be obtained from a prospective, randomized controlled trial, but obtained from observational data. The latter is real-world data, and therefore with less selection bias, also more timely and less expensive. See - A data-driven approach to identify risk profiles and protective drugs in COVID-19
- Evaluation of simultaneous risk factors - see A Systems Science Approach to Understanding Polytrauma and Blast-Related Injury: Bayesian Network Model of Data From a Survey of the Florida National Guard
- Dynamic Bayesian Networks can model the progression of a given condition over time [1].
While static Bayesian Networks deal with cross-sectional data, Dynamic Bayesian Networks (DBN) model time series data with an auto-regression component - see chapter 3 of [2]. Of importance, DBN are first-order Markovian, meaning that the graph only remembers the previous node but not others. DBN also allows for feedback loops, which are often present in social, psychological, and biological phenomena.
-
- The time component of DBN allow for feedback loops, which are not possible under traditional Bayesian networks (intervals are constant)
-
- The process is stochastic markovian, or the events only depend on the previous event.
-
- Any variable at time t is dependent on the past variables only through the variables observed at time (t − 1).
-
- The rows in the dataset are not transformations of other rows [5]
- bnlearn for R [3]
- Books
- Articles
- US Food and Drug Administration Approvals of Drugs and Devices Based on Nonrandomized Clinical Trials [6].
- Common references for causation.
Networks displaying the connections between causes and effects.
Bayesian methods in health technology
[1] Zandonà A, Vasta R, Chiò A, Di Camillo B. A Dynamic Bayesian Network model for the simulation of Amyotrophic Lateral Sclerosis progression. BMC bioinformatics. 2019 Apr 1;20(4):118.
[2] Nagarajan R, Scutari M, Lèbre S. Bayesian Networks in R with Applications in Systems Biology 2013. New York, NYSpringer-Verlag.
[3] Scutari M. bnlearn-an R package for Bayesian network learning and inference. UCL Genetics Institute, University College, London, London, UK. 2011.
[4] Scutari M, Denis JB. Bayesian Networks: With Examples in R. CRC press; 2014 Jun 20.
[5] Nagarajan R, Scutari M, Lèbre S. Bayesian Networks in R: with Applications in Systems Biology. Springer. 2013;122:125-7.
[6] Razavi M, Glasziou P, Klocksieben FA, Ioannidis JP, Chalmers I, Djulbegovic B. US Food and Drug Administration Approvals of drugs and devices based on nonrandomized clinical trials: a systematic review and meta-analysis. JAMA network open. 2019 Sep 4;2(9):e1911111-.