Automated interpretable discovery of heterogeneous treatment effectiveness: A COVID-19 case study
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (ScreenIT)
Abstract
No abstract available
Article activity feed
-
-
SciScore for 10.1101/2021.10.30.21265430: (What is this?)
Please note, not all rigor criteria are appropriate for all manuscripts.
Table 1: Rigor
NIH rigor criteria are not applicable to paper type.Table 2: Resources
Software and Algorithms Sentences Resources We use tree-based GAMs [12] implemented in the Python Interpret package1. Pythonsuggested: (IPython, RRID:SCR_001658)Results from OddPub: Thank you for sharing your code.
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:Limitations: As with all analyses of observational data, this approach has several limitations. Firstly, while the machine learning optimization seeks to allocate effect sizes to most statistically reliable indicators, we do not use any side information (such as treatment mechanism of action or time-series data) to …
SciScore for 10.1101/2021.10.30.21265430: (What is this?)
Please note, not all rigor criteria are appropriate for all manuscripts.
Table 1: Rigor
NIH rigor criteria are not applicable to paper type.Table 2: Resources
Software and Algorithms Sentences Resources We use tree-based GAMs [12] implemented in the Python Interpret package1. Pythonsuggested: (IPython, RRID:SCR_001658)Results from OddPub: Thank you for sharing your code.
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:Limitations: As with all analyses of observational data, this approach has several limitations. Firstly, while the machine learning optimization seeks to allocate effect sizes to most statistically reliable indicators, we do not use any side information (such as treatment mechanism of action or time-series data) to perform causal inference. In addition, in this study we have considered only binary indicators for each treatment, choosing to assume that providers are following dosage protocols to standardize care. Finally, while additive models are interpretable and accurate, they are still susceptible to statistical biases [21] which may cause different model classes to recover different effects from a single dataset. Further works should investigate the potential for other classes of additive models to corroborate or dispute these findings.
Results from TrialIdentifier: No clinical trial numbers were referenced.
Results from Barzooka: We did not find any issues relating to the usage of bar graphs.
Results from JetFighter: We did not find any issues relating to colormaps.
Results from rtransparent:- Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
- Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
- No protocol registration statement was detected.
Results from scite Reference Check: We found no unreliable references.
-
