ABSTRACT
Structured data formats are gaining momentum in electronic health records and can be leveraged for decision support and research. Nevertheless, such structured data formats have not been explored for clinical coding, which is an essential process requiring significant manual workload in health organisations. This article explores the extent to which fully structured clinical data can support assignment of clinical codes to inpatient episodes, through a methodology that tackles high dimensionality issues, addresses the multi-label nature of coding and optimises model parameters. The methodology encompasses transformation of raw data to define a feature set, build a data matrix representation, and testing combinations of feature selection methods with machine learning models to predict code assignment. The methodology was tested with a real hospital dataset and showed varying predictive power across codes, while demonstrating the potential of leveraging structuring data to reduce workload and increase efficiency in clinical coding.
Acknowledgments
The authors wish to thank colleagues from Hospital Professor Doutor Fernando Fonseca for close collaboration and availability throughout this research. The authors also acknowledge the financial support from Fundação para a Ciência e a Tecnologia (grant SFRH/BDE/51605/2011), Siemens Healthcare, the Centre for Management Studies of Instituto Superior Técnico (CEG-IST, University of Lisbon) and the Seedcorn Bursary of the University of Cardiff.The authors sincerely thank the area editor and the anonymous referees for their careful review and excellent suggestions for improvement of this paper. The authors sincerely thank the area editor and the anonymous referees for their careful review and excellent suggestions for improvement of this paper. Also, the Data Innovation Research Institute at Cardiff University provided Seedcorn Funding to support the project and to facilitate new collaborations.
Disclosure statement
The authors declare that there are no competing interests regarding this study.