Computational simulation of virtual patients reduces dataset bias and improves machine learning-based detection of ARDS from noisy heterogeneous ICU datasets

Goal Machine learning (ML) technologies that leverage large-scale patient data are promising tools predicting disease evolution in individual patients. However, the limited generalizability of ML models developed on single-center datasets, and their unproven performance in real-world settings, remain significant constraints to their widespread adoption in clinical practice. One approach to tackle this issue is to base learning on large multi-center datasets. However, such heterogeneous datasets can introduce further biases driven by data origin, as data structures and patient cohorts may differ between hospitals. Methods In this paper, we demonstrate how mechanistic virtual patient (VP) modeling can be used to capture specific features of patients’ states and dynamics, while reducing biases introduced by heterogeneous datasets. We show how VP modeling can be used to extract relevant medical information on individual patients with suspected acute respiratory distress syndrome (ARDS) from observational data of mixed origin. We compare the results of an unsupervised learning method (clustering) in two cases: where the learning is based on original patient data and on data ‘filtered’ through a VP model. Results More robust cluster configurations were observed in clustering using the VP model-based filtered data. VP model-based clustering also reduced biases introduced by the inclusion of data from different hospitals and was able to discover an additional cluster with significant ARDS enrichment. Conclusions Our results indicate that mechanistic VP modeling can be used as a filter to significantly reduce biases introduced by learning from heterogeneous datasets and to allow improved discovery of patient cohorts driven exclusively by medical conditions. IMPACT STATEMENT Mechanistic virtual patient modeling can be used as a filter to extract relevant medical information on individual patients, significantly reducing biases introduced by learning from heterogeneous datasets and allowing improved discovery of patient cohorts driven exclusively by medical conditions. ### Competing Interest Statement All authors declare no conflicts of interest in this paper. HM is an employee of Bayer AG, Germany. HM has stock ownership with Bayer AG, Germany. ### Funding Statement This publication of the SMITH consortium was supported by the German Federal Ministry of Education and Research (Grant Nos. 01ZZ1803B and 01ZZ1803M). ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Ethics Committee (EC) at the RWTH Aachen Faculty of Medicine gave ethical approval for this work within the ASIC project(local EC reference number: EK 102/19, date of approval: 26.03.2019). I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors.