PURPOSE Circulating tumor DNA (ctDNA) detection is a minimally invasive technique that offers dynamic molecular snapshots of genomic alterations in cancer. Although ctDNA markers can be used for early detection of cancers or for monitoring treatment efficacy, the value of ctDNA in guiding treatment decisions in solid cancers is controversial. Here, we monitored ctDNA to detect clinically actionable alterations during treatment of high-grade serous ovarian cancer, the most common and aggressive form of epithelial ovarian cancer with a 5-year survival rate of 43%. PATIENTS AND METHODS We implemented a clinical ctDNA workflow to detect clinically actionable alterations in more than 500 cancer-related genes. We applied the workflow to a prospective cohort consisting of 78 ctDNA samples from 12 patients with high-grade serous ovarian cancer before, during, and after treatment. These longitudinal data sets were analyzed using our open-access ctDNA-tailored bioinformatics analysis pipeline and in-house Translational Oncology Knowledgebase to detect clinically actionable genomic alterations. The alterations were ranked according to the European Society for Medical Oncology scale for clinical actionability of molecular targets. RESULTS Our results show good concordance of mutations and copy number alterations in ctDNA and tumor samples, and alterations associated with clinically available drugs were detected in seven patients (58%). Treatment of one chemoresistant patient was changed on the basis of detection of ERBB2 amplification, and this ctDNA-guided decision was followed by significant tumor shrinkage and complete normalization of the cancer antigen 125 tumor marker. CONCLUSION Our results demonstrate a proof of concept for using ctDNA to guide clinical decisions. Furthermore, our results show that longitudinal ctDNA samples can be used to identify poor-responding patients after first cycles of chemotherapy. We provide what we believe to be the first comprehensive, open-source ctDNA workflow for detecting clinically actionable alterations in solid cancers.

is a more sensitive indicator of tumor load than conventional CA125. • The nadir value of CA125-STn is a predictor of progression free survival. • The CA125-STn assay detects relapse more precisely than the conventional CA125 assay.

PURPOSE We have created a cloud-based machine learning system (CLOBNET) that is an open-source, lean infrastructure for electronic health record (EHR) data integration and is capable of extract, transform, and load (ETL) processing. CLOBNET enables comprehensive analysis and visualization of structured EHR data. We demonstrate the utility of CLOBNET by predicting primary therapy outcomes of patients with high-grade serous ovarian cancer (HGSOC) on the basis of EHR data. MATERIALS AND METHODS CLOBNET is built using open-source software to make data preprocessing, analysis, and model training user friendly. The source code of CLOBNET is available in GitHub. The HGSOC data set was based on a prospective cohort of 208 patients with HGSOC who were treated at Turku University Hospital, Finland, from 2009 to 2019 for whom comprehensive clinical and EHR data were available. RESULTS We trained machine learning (ML) models using clinical data, including a herein developed dissemination score that quantifies the disease burden at the time of diagnosis, to identify patients with progressive disease (PD) or a complete response (CR) on the basis of RECIST (version 1.1). The best performance was achieved with a logistic regression model, which resulted in an area under receiver operating characteristic curve (AUROC) of 0.86, with a specificity of 73% and a sensitivity of 89%, when it classified between patients who experienced PD and CR. CONCLUSION We have developed an open-source computational infrastructure, CLOBNET, that enables effective and rapid analysis of EHR and other clinical data. Our results demonstrate that CLOBNET allows predictions to be made on the basis of EHR data to address clinically relevant questions.