BackgroundIn health research, several chronic diseases are susceptible to competing risks (CRs). Initially, statistical models (SM) were developed to estimate the cumulative incidence of an event... Show moreBackgroundIn health research, several chronic diseases are susceptible to competing risks (CRs). Initially, statistical models (SM) were developed to estimate the cumulative incidence of an event in the presence of CRs. As recently there is a growing interest in applying machine learning (ML) for clinical prediction, these techniques have also been extended to model CRs but literature is limited. Here, our aim is to investigate the potential role of ML versus SM for CRs within non-complex data (small/medium sample size, low dimensional setting).MethodsA dataset with 3826 retrospectively collected patients with extremity soft-tissue sarcoma (eSTS) and nine predictors is used to evaluate model-predictive performance in terms of discrimination and calibration. Two SM (cause-specific Cox, Fine-Gray) and three ML techniques are compared for CRs in a simple clinical setting. ML models include an original partial logistic artificial neural network for CRs (PLANNCR original), a PLANNCR with novel specifications in terms of architecture (PLANNCR extended), and a random survival forest for CRs (RSFCR). The clinical endpoint is the time in years between surgery and disease progression (event of interest) or death (competing event). Time points of interest are 2, 5, and 10 years.ResultsBased on the original eSTS data, 100 bootstrapped training datasets are drawn. Performance of the final models is assessed on validation data (left out samples) by employing as measures the Brier score and the Area Under the Curve (AUC) with CRs. Miscalibration (absolute accuracy error) is also estimated. Results show that the ML models are able to reach a comparable performance versus the SM at 2, 5, and 10 years regarding both Brier score and AUC (95% confidence intervals overlapped). However, the SM are frequently better calibrated.ConclusionsOverall, ML techniques are less practical as they require substantial implementation time (data preprocessing, hyperparameter tuning, computational intensity), whereas regression methods can perform well without the additional workload of model training. As such, for non-complex real life survival data, these techniques should only be applied complementary to SM as exploratory tools of model's performance. More attention to model calibration is urgently needed. Show less
This thesis sprang from an interdisciplinary collaboration between the European Organisation for Research and Treatment of Cancer (EORTC), the Mathematical Institute of Leiden University, and the... Show moreThis thesis sprang from an interdisciplinary collaboration between the European Organisation for Research and Treatment of Cancer (EORTC), the Mathematical Institute of Leiden University, and the Leiden University Medical Center (LUMC) Department of Medical Oncology. Research was split into two separate parts. In Part I, the main goal was to provide modern efficacy thresholds for designing new phase II clinical trials for common histotypes of locally advanced or metastatic soft-tissue sarcoma patients. An update was necessary as well-established values were reported back in 2002 by the EORTC – Soft Tissue and Bone Sarcoma Group.Nowadays, there is a growing interest by the medical community in applying machine learning to predict clinical outcomes. In Part II, the main goal was to investigate the potential of existing and novel machine learning techniques compared with traditional statistical benchmarks for real-life clinical data (small/medium or large sample sizes, low- or high-dimensional settings) with time-to-event endpoints. Findings indicate an urgent need to pay closer attention to calibration (absolute predictive accuracy) of machine learning techniques to achieve a complete comparison with statistical models. Show less
Background: Financial codes are often used to extract diagnoses from electronic health records. This approach is prone to false positives. Alternatively, queries are constructed, but these are... Show moreBackground: Financial codes are often used to extract diagnoses from electronic health records. This approach is prone to false positives. Alternatively, queries are constructed, but these are highly center and language specific. A tantalizing alternative is the automatic identification of patients by employing machine learning on format-free text entries.Objective: The aim of this study was to develop an easily implementable workflow that builds a machine learning algorithm capable of accurately identifying patients with rheumatoid arthritis from format-free text fields in electronic health records.Methods: Two electronic health record data sets were employed: Leiden (n=3000) and Erlangen (n=4771). Using a portion of the Leiden data (n=2000), we compared 6 different machine learning methods and a naive word-matching algorithm using 10-fold cross-validation. Performances were compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPRC), and F1 score was used as the primary criterion for selecting the best method to build a classifying algorithm. We selected the optimal threshold of positive predictive value for case identification based on the output of the best method in the training data. This validation workflow was subsequently applied to a portion of the Erlangen data (n=4293). For testing, the best performing methods were applied to remaining data (Leiden n=1000; Erlangen n=478) for an unbiased evaluation.Results: For the Leiden data set, the word-matching algorithm demonstrated mixed performance (AUROC 0.90; AUPRC 0.33; F1 score 0.55), and 4 methods significantly outperformed word-matching, with support vector machines performing best (AUROC 0.98; AUPRC 0.88; F1 score 0.83). Applying this support vector machine classifier to the test data resulted in a similarly high performance (F1 score 0.81; positive predictive value [PPV] 0.94), and with this method, we could identify 2873 patients with rheumatoid arthritis in less than 7 seconds out of the complete collection of 23,300 patients in the Leiden electronic health record system. For the Erlangen data set, gradient boosting performed best (AUROC 0.94; AUPRC 0.85; F1 score 0.82) in the training set, and applied to the test data, resulted once again in good results (F1 score 0.67; PPV 0.97).Conclusions: We demonstrate that machine learning methods can extract the records of patients with rheumatoid arthritis from electronic health record data with high precision, allowing research on very large populations for limited costs. Our approach is language and center independent and could be applied to any type of diagnosis. We have developed our pipeline into a universally applicable and easy-to-implement workflow to equip centers with their own high-performing algorithm. This allows the creation of observational studies of unprecedented size covering different countries for low cost from already available data in electronic health record systems. Show less
