Modeling Physicians' Utterances to Explore Diagnostic Decision-making
Authors: Xuan Guo, Rui Li, Qi Yu, Anne Haake
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiments to collect verbal narratives from dermatologists while they are examining and describing dermatology images towards diagnoses. Our evaluation shows that these patterns provide key information to classify narratives by diagnostic correctness levels. |
| Researcher Affiliation | Academia | Xuan Guo, Rui Li, Qi Yu, Anne R. Haake Rochester Institute of Technology {xxg3358, rxlics, qi.yu, arhics}@rit.edu |
| Pseudocode | No | The paper describes algorithms and equations but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | No | The paper describes the data collection process for Experiment I and Experiment II ("48 dermatology images", "30 images") but does not provide access information (link, DOI, repository, or formal citation for public access) for these datasets or the collected verbal narratives. An example image is attributed to "Dr. Cara Calvelli" but this is not a general dataset source. |
| Dataset Splits | Yes | We use cross-validation to tune the trade-off parameter of the lasso-regularized logistic regression. Cross-validation is also used to determine the optimal number of hidden states for the canonical HMM. |
| Hardware Specification | No | The paper does not provide any specific hardware details used for running its experiments. |
| Software Dependencies | No | The paper mentions software tools like "Praat [Boersma and Weenink, 2009]" and "Meta Map [Aronson, 2001]" and UMLS, but it does not specify the exact version numbers of these or any other software libraries or dependencies used for the experiments. It lacks specific versioning required for reproducibility (e.g., "Praat 5.1.05"). |
| Experiment Setup | Yes | We use cross-validation to tune the trade-off parameter of the lasso-regularized logistic regression. Cross-validation is also used to determine the optimal number of hidden states for the canonical HMM. We use 2000 iterations as burn-in and empirically choose various hyperpriors for α and γ according to the convergence behaviors in previous runs. |