Name
Abstract | ||
|---|---|---|
Diagnosing an inherited disease often requires identifying the pattern of inheritance in a patientu0027s family. We represent family trees with genetic patterns of inheritance using hypergraphs and latent state space models to provide explainable inheritance pattern predictions. Our approach allows for exact causal inference over a patientu0027s possible genotypes given their relativesu0027 phenotypes. By design, inference can be examined at a low level to provide explainable predictions. Furthermore, we make use of human intuition by providing a method to assign hypothetical evidence to any inherited gene alleles. Our analysis supports the application of latent state space models to improve patient care in cases of rare inherited diseases where access to genetic specialists is limited. |
Year | Venue | DocType |
|---|---|---|
2018 | arXiv: Machine Learning | Journal |
Volume | Citations | PageRank |
abs/1812.00259 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Edmond Cunningham | 1 | 0 | 0.68 |
| Dana Schlegel | 2 | 0 | 0.34 |
| Andrew DeOrio | 3 | 0 | 0.34 |