Papers of interest
A novel protocol for a "Citizen Panel" for diverse Public and Participant Involvement in the review and development of the process to access data in the UK Longitudinal Linkage Collaboration Trusted Research Environment – view it here >
Considerations for selecting and implementing comorbidity indices when using secondary data sources: a guide for health researchers – view it here >
Promising algorithms to perilous applications: a systematic review of risk stratification tools for predicting healthcare utilisation – view it here >
Targeted validation: validating clinical prediction models in their intended population and setting – view it here >
The human role to guarantee an ethical AI in healthcare: a five-facts approach – view it here >
The value of standards for health datasets in artificial intelligence-based applications – view it here >
Five critical quality criteria for artificial intelligence-based prediction models – view it here >
Mapping and evaluating national data flows: transparency, privacy, and guiding infrastructural transformation – view it here >
Concept libraries for automatic electronic health record based phenotyping – view it here >
Characterizing and Managing Missing Structured Data in Electronic Health Records: Data Analysis – view it here >
Informative missingness in electronic health record systems: the curse of knowing – view it here >
Strategies for handling missing data in electronic health record derived data – view it here >
Accounting for missing data in statistical analyses: multiple imputation is not always the answer – view it here >
Sick patients have more data: the non-random completeness of electronic health records – view it here >
There is no such thing as a validated prediction model – view it here >
Rethink reporting of evaluation results in AI – view it here >
Learning from data with structured missingness – view it here >
Secondary use of routinely collected administrative health data for epidemiologic research: Answering research questions using data collected for a different purpose – view it here >