Over the last decades, increasingly so in the last years, epidemiological methods have been refined, making it challenging to keep abreast of all methodological developments. The choice of the data... Show moreOver the last decades, increasingly so in the last years, epidemiological methods have been refined, making it challenging to keep abreast of all methodological developments. The choice of the data analytical method directly influences the interpretation and clinical meaning of results of an analysis, yet it is undesirable that technical considerations define the subject of the investigation. Having a deeper understanding of the impact that data analytical decisions can have on the interpretation of numerical results of a study would help to apply analytical tools that are both suitable and appropriate to answer clinical questions. The aim of this thesis was to investigate the impact of choices regarding the design and statistical analysis of a study on the meaning of its numerical results in two sets of case studies in research into causal effects (Part I) and prediction research (Part II). The thesis concludes with a discussion on the role and importance of clinical research questions and estimands. Clearly defining a clinically relevant estimand ensures that data analytical decisions yield meaningful results. Making targeted research questions central to quantitative clinical research can reduce fallacious confidence in (complex) methods and can add to intelligibility of findings. Show less
Maarseveen, T.D.; Maurits, M.P.; Niemantsverdriet, E.; Helm-van Mil, A.H.M. van der; Huizinga, T.W.J.; Knevel, R. 2021
Background Electronic health records (EHRs) offer a wealth of observational data. Machine-learning (ML) methods are efficient at data extraction, capable of processing the information-rich free... Show moreBackground Electronic health records (EHRs) offer a wealth of observational data. Machine-learning (ML) methods are efficient at data extraction, capable of processing the information-rich free-text physician notes in EHRs. The clinical diagnosis contained therein represents physician expert opinion and is more consistently recorded than classification criteria components. Objectives To investigate the overlap and differences between rheumatoid arthritis patients as identified either from EHR free-text through the extraction of the rheumatologist diagnosis using machine-learning (ML) or through manual chart-review applying the 1987 and 2010 RA classification criteria. Methods Since EHR initiation, 17,662 patients have visited the Leiden rheumatology outpatient clinic. For ML, we used a support vector machine (SVM) model to identify those who were diagnosed with RA by their rheumatologist. We trained and validated the model on a random selection of 2000 patients, balancing PPV and sensitivity to define a cutoff, and assessed performance on a separate 1000 patients. We then deployed the model on our entire patient selection (including the 3000). Of those, 1127 patients had both a 1987 and 2010 EULAR/ACR criteria status at 1 year after inclusion into the local prospective arthritis cohort. In these 1127 patients, we compared the patient characteristics of RA cases identified with ML and those fulfilling the classification criteria. Results The ML model performed very well in the independent test set (sensitivity=0.85, specificity=0.99, PPV=0.86, NPV=0.99). In our selection of patients with both EHR and classification information, 373 were recognized as RA by ML and 357 and 426 fulfilled the 1987 or 2010 criteria, respectively. Eighty percent of the ML-identified cases fulfilled at least one of the criteria sets. Both demographic and clinical parameters did not differ between the ML extracted cases and those identified with EULAR/ACR classification criteria. Conclusions With ML methods, we enable fast patient extraction from the huge EHR resource. Our ML algorithm accurately identifies patients diagnosed with RA by their rheumatologist. This resulting group of RA patients had a strong overlap with patients identified using the 1987 or 2010 classification criteria and the baseline (disease) characteristics were comparable. ML-assisted case labeling enables high-throughput creation of inclusive patient selections for research purposes. Show less
Glas, N.A. de; Kiderlen, M.; Craen, A.J.M. de; Hamaker, M.E.; Portielje, J.E.A.; Velde, C.J.H. van de; ... ; Bastiaannet, E. 2015