RESUMO
Tools that provide personalized risk prediction of outcomes after surgical procedures help patients make preference-based decisions among the available treatment options. However, it is unclear which modeling approach provides the most accurate risk estimation. We constructed and compared several parametric and nonparametric models for predicting prosthesis survivorship after knee replacement surgery for osteoarthritis. We used 430,455 patient-procedure episodes between April 2003 and September 2015 from the National Joint Registry for England, Wales, Northern Ireland, and the Isle of Man. The flexible parametric survival and random survival forest models most accurately captured the observed probability of remaining event-free. The concordance index for the flexible parametric model was the highest (0.705, 95% confidence interval (CI): 0.702, 0.707) for total knee replacement and was 0.639 (95% CI: 0.634, 0.643) for unicondylar knee replacement and 0.589 (95% CI: 0.586, 0.592) for patellofemoral replacement. The observed-to-predicted ratios for both the flexible parametric and the random survival forest approaches indicated that models tended to underestimate the risks for most risk groups. Our results show that the flexible parametric model has a better overall performance compared with other tested parametric methods and has better discrimination compared with the random survival forest approach.
Assuntos
Artroplastia do Joelho/métodos , Artroplastia do Joelho/estatística & dados numéricos , Reoperação/estatística & dados numéricos , Adulto , Idoso , Idoso de 80 Anos ou mais , Anticoagulantes/administração & dosagem , Índice de Massa Corporal , Árvores de Decisões , Inglaterra , Feminino , Nível de Saúde , Humanos , Masculino , Pessoa de Meia-Idade , Modelos Estatísticos , Falha de Prótese , Reino Unido , País de GalesRESUMO
BACKGROUND AND PURPOSE: Health information systems (HIS) are expected to be effective and efficient in improving healthcare services, but empirical observation of HIS reveals that most perform poorly in terms of these metrics. Theoretical factors of HIS performance are widely studied, and solutions to mitigate poor performance have been proposed. In this paper we implement effective methods to eliminate some common drawbacks of HIS design and demonstrate the synergy between the methods. JointCalc, the first comprehensive patient-facing web-based decision support tool for joint replacement, is used as a case study for this purpose. METHODS AND RESULTS: User-centred design and thorough end-user involvement are employed throughout the design and development of JointCalc. This is supported by modern software production paradigms, including continuous integration/continuous development, agile and service-oriented architecture. The adopted methods result in a user-approved application delivered well within the scope of project. CONCLUSION: This work supports the claims of high potential efficiency of HIS. The methods identified are shown to be applicable in the production of an effective HIS whilst aiding development efficiency.