MOTIVATION: Circulating-cell free DNA (cfDNA) is widely explored as a noninvasive biomarker for cancer screening and diagnosis. The ability to decode the cells of origin in cfDNA would provide biological insights into pathophysiological mechanisms, aiding in cancer characterization and directing clinical management and follow-up. RESULTS: We developed a DNA methylation signature-based deconvolution algorithm, MetDecode, for cancer tissue origin identification. We built a reference atlas exploiting de novo and published whole-genome methylation sequencing data for colorectal, breast, ovarian, and cervical cancer, and blood-cell-derived entities. MetDecode models the contributors absent in the atlas with methylation patterns learnt on-the-fly from the input cfDNA methylation profiles. In addition, our model accounts for the coverage of each marker region to alleviate potential sources of noise. In-silico experiments showed a limit of detection down to 2.88% of tumor tissue contribution in cfDNA. MetDecode produced Pearson correlation coefficients above 0.95 and outperformed other methods in simulations (P < 0.001; T-test; one-sided). In plasma cfDNA profiles from cancer patients, MetDecode assigned the correct tissue-of-origin in 84.2% of cases. In conclusion, MetDecode can unravel alterations in the cfDNA pool components by accurately estimating the contribution of multiple tissues, while supplied with an imperfect reference atlas. AVAILABILITY AND IMPLEMENTATION: MetDecode is available at https://github.com/JorisVermeeschLab/MetDecode.

OBJECTIVE: Methods to correct class imbalance (imbalance between the frequency of outcome events and nonevents) are receiving increasing interest for developing prediction models. We examined the effect of imbalance correction on the performance of logistic regression models. MATERIAL AND METHODS: Prediction models were developed using standard and penalized (ridge) logistic regression under 4 methods to address class imbalance: no correction, random undersampling, random oversampling, and SMOTE. Model performance was evaluated in terms of discrimination, calibration, and classification. Using Monte Carlo simulations, we studied the impact of training set size, number of predictors, and the outcome event fraction. A case study on prediction modeling for ovarian cancer diagnosis is presented. RESULTS: The use of random undersampling, random oversampling, or SMOTE yielded poorly calibrated models: the probability to belong to the minority class was strongly overestimated. These methods did not result in higher areas under the ROC curve when compared with models developed without correction for class imbalance. Although imbalance correction improved the balance between sensitivity and specificity, similar results were obtained by shifting the probability threshold instead. DISCUSSION: Imbalance correction led to models with strong miscalibration without better ability to distinguish between patients with and without the outcome event. The inaccurate probability estimates reduce the clinical utility of the model, because decisions about treatment are ill-informed. CONCLUSION: Outcome imbalance is not a problem in itself, imbalance correction may even worsen model performance.

There is increasing awareness that the methodology and findings of research should be transparent. This includes studies using artificial intelligence to develop predictive algorithms that make individualized diagnostic or prognostic risk predictions. We argue that it is paramount to make the algorithm behind any prediction publicly available. This allows independent external validation, assessment of performance heterogeneity across settings and over time, and algorithm refinement or updating. Online calculators and apps may aid uptake if accompanied with sufficient information. For algorithms based on "black box" machine learning methods, software for algorithm implementation is a must. Hiding algorithms for commercial exploitation is unethical, because there is no possibility to assess whether algorithms work as advertised or to monitor when and how algorithms are updated. Journals and funders should demand maximal transparency for publications on predictive algorithms, and clinical guidelines should only recommend publicly available algorithms.

This paper presents our activities towards the development of a clinical decision support (CDS) system for the early diagnosis of pregnancies of unknown location (PULs). PULs are pregnancies that are not visualized on ultrasound. Generally, they turn out to be failing, normal intra-uterine, or ectopic pregnancies. Using 856 PULs collected at a London hospital, we developed probabilistic multi-class models. At the moment, a large multi-center data set is being collected. Data are entered using stand-alone software, and are sent to the database server by ftp. These data will be used to prospectively test existing models, and to build new, hopefully more robust, models. The ultimate aim is to select one model for implementation in a CDS system that is easy to use in routine clinical practice.

The area under the receiver operating characteristic curve (AUC) is a useful and widely used measure to evaluate the performance of binary and multi-class classification models. However, it does not take into account the exact numerical output of the models, but rather looks at how the output ranks the cases. AUC metrics that incorporate the exact numerical output have been developed for binary classification. In this paper, we try to extend such weighted metrics to the multi-class case. Several metrics are suggested. Using real world data, we investigate intercorrelations between these metrics and demonstrate their use.

We have developed a World Wide Web application for the collection of EPRs (electronic patient records) from uterine adnexal masses pre-operatively examined with transvaginal ultrasonography. The application has been used intensively since November 2000 by nine of the 19 international centers that joined the International Ovarian Tumor Analysis (IOTA) consortium. The IOTA database contains 68 parameters for 1,150 masses. We report the design and implementation of the generic Web-based clinical data entry system and describe the advantages and drawbacks that we have experienced while developing, using and maintaining the system. The data model, the user interface, the help system, the constraints (mandatory/optional) and the quality checking were all based on the medical protocol created by the IOTA consortium. The data collection system has become an open and transparent implementation of the formalized protocol. It covers the complete path of the patient data from the clinical situation to the finalized database. This approach provides new types of possibilities for the data analysis, since all aspects of the data collection are documented and formally available to the data analyst. The IOTA Web site can be found at, which also serves as the entry point for the secure EPR application.

The increasing amount and variety of domain knowledge and the availability of increasingly large quantities of electronic literature requires new types of support for the development of complex knowledge models. P. Antal et al. (2001) proposed the application of so-called annotated Bayesian networks (ABNs), which are textually-enriched probabilistic domain models that help knowledge engineers and medical experts to find and organize the information that is necessary in model-building. In this paper, we describe an information retrieval language in which the formalized domain knowledge and the attached textual information can be accessed in an integrated fashion and can be used to define various retrieval schemes and relevance measures. This language on the one hand provides maximum flexibility for knowledge engineers to exploit the available annotated domain model as contextual information. On the other hand, it allows the definition of complex, high-level queries, in which the contextual use of the annotated domain model can be optimized for clinical situations. We compare the performance of the standard and the proposed query language in the ovarian cancer domain.

The pre-operative discrimination between malignant and benign masses is a crucial issue in gynaecology. Next to the large amount of background knowledge, there is a growing amount of collected patient data that can be used in inductive techniques. These two sources of information result in two different modelling strategies. Based on the background knowledge, various discrimination models have been constructed by leading experts in the field, tuned and tested by observations. Based on the patient observations, various statistical models have been developed, such as logistic regression models and artificial neural network models. For the efficient combination of prior background knowledge and observations, Bayesian network models are suggested. We summarize the applicability of this technique, report the performance of such models in ovarian cancer diagnosis and outline a possible hybrid usage of this technique.