Temporal Poisson Square Root Graphical Models
Authors: Sinong Geng, Zhaobin Kuang, Peggy Peissig, David Page
ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirically, we learn TPSQRs from Marshfield Clinic electronic health records (EHRs) with millions of drug prescription and condition diagnosis events, for adverse drug reaction (ADR) detection. Experimental results demonstrate that the learned TPSQRs can recover ADR signals from the EHR effectively and efficiently. and In what follows, we will compare the performances of TPSQR, MSCCS, and Hawkes process (Bao et al., 2017) in the OMOP task. The experiments are conducted using Marshfield Clinic EHRs with millions of drug prescription and condition diagnosis events from 200,000 patients. |
| Researcher Affiliation | Collaboration | 1The University of Wisconsin, Madison 2Marshfield Clinic Research Institute. |
| Pseudocode | No | Information is insufficient. The paper describes the models and estimation procedures mathematically and in prose, but it does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | Information is insufficient. The paper mentions that their method can be implemented using the R package glmnet, but it does not provide any statement about releasing their own specific implementation code for TPSQR. |
| Open Datasets | No | Information is insufficient. The paper uses "Marshfield Clinic electronic health records (EHRs)" but does not provide any information about its public availability, nor does it cite a source for public access. |
| Dataset Splits | No | Information is insufficient. The paper mentions evaluating performance and experimental configurations, but it does not explicitly provide specific details on how the dataset was split into training, validation, and test sets (e.g., percentages, sample counts, or methodology for the splits). |
| Hardware Specification | No | Information is insufficient. The paper does not provide any specific details regarding the hardware (e.g., CPU, GPU, memory) used to conduct the experiments. |
| Software Dependencies | No | Information is insufficient. The paper mentions the use of "the R package glmnet" but does not specify its version number or any other software dependencies with their versions. |
| Experiment Setup | Yes | 6.1. Experimental Configuration: Minimum Duration: clinical encounter sequences from different patients might span across different time lengths. ...In our experiments, we consider two minimum duration thresholds: 0.5 year and 1 year. Maximum Time Difference: for TPSQR, in (1), τL determines the maximum time difference... In our experiments, we consider three maximum time differences: 0.5 year, 1 year, and 1.5 years. L = 3... Regularization Parameter: we use l1-regularization for TPSQR... We use L2-regularization for MSCCS... 50 regularization parameters are chosen for both TPSQR and MSCCS. |