No abstract

BackgroundThe FOLFOXIRI regimen (irinotecan, oxaliplatin, fluorouracil [5-FU] and folinic acid [FA]) increased the response rate and overall survival compared to FOLFIRI in patients with metastatic colorectal cancer (mCRC). Adding cetuximab to FOLFOX or FOLFIRI increased efficacy in patients with k-ras wild type mCRC. We explored the dose limiting toxicity and feasibility of the combination cetuximab, irinotecan, oxaliplatin, 5-FU and FA in mCRC patients.MethodsIn a dose-escalation study patients with previously untreated mCRC and a WHO performance status 0–1 received cetuximab (500 mg/m2, 2 h), followed by irinotecan (95, 125, and 165 mg/m2 in the dose levels [DL] 1, 2, and 3 respectively), followed by oxaliplatin (85 mg/m2, 2 h) which was given parallel to FA (400 mg/m2, 2 h) and followed by 5-FU (3200 mg/m2, 46 h) in an outpatient setting every two weeks. The primary endpoints were the maximum tolerable dose and the safety. The trial was approved by the local ethics committee.ResultsFrom 2007 to 2008, twenty patients were treated in this trial. In the first dose level (irinotecan 95 mg/m2) one patient developed neutropenia grade 4. One patient experienced diarrhoea grade 3 as DLT in dose level 2 (irinotecan 125 mg/m2). In dose level 3 (irinotecan 165 mg/m2), three patients experienced a DLT (diarrhoea grade 3 and two patients with neutropenia grade 4). Thus, the recommended dose for a phase II trial is 125 mg/m2 irinotecan in combination with oxaliplatin, 5-FU/FA and cetuximab. Most common grade ≥3 toxicities were neutropenia (40%), diarrhoea (25%) and acne-like rash (15%). No therapy associated death occurred.The confirmed overall response rate in all cohorts was 75% (95%-CI 51-91%). The best response was reached after a median of 3.0 (95%-CI 2.2 to 3.7) months. Median progression free survival (PFS) is 16 (95%-CI 12.6-19.4) months, overall survival (OS) 33 (95%-CI 26.2-39.8) months.ConclusionsThe combination of cetuximab and FOLFOXIRIis feasible and has an acceptable toxicity profile in patients with a good performance status. The observed clinical activity with a confirmed response rate of 75% is promising and further evaluated in the ongoing CELIM2.Trial registrationhttp://www.clinicaltrials.gov: NCT00422773.

AI model development for synthetic data generation to improve Machine Learning (ML) methodologies is an integral part of research in Computer Science and is currently being transferred to related medical fields, such as Systems Medicine and Medical Informatics. In general, the idea of personalized decision-making support based on patient data has driven the motivation of researchers in the medical domain for more than a decade, but the overall sparsity and scarcity of data are still major limitations. This is in contrast to currently applied technology that allows us to generate and analyze patient data in diverse forms, such as tabular data on health records, medical images, genomics data, or even audio and video. One solution arising to overcome these data limitations in relation to medical records is the synthetic generation of tabular data based on real world data. Consequently, ML-assisted decision-support can be interpreted more conveniently, using more relevant patient data at hand. At a methodological level, several state-of-the-art ML algorithms generate and derive decisions from such data. However, there remain key issues that hinder a broad practical implementation in real-life clinical settings. In this review, we will give for the first time insights towards current perspectives and potential impacts of using synthetic data generation in palliative care screening because it is a challenging prime example of highly individualized, sparsely available patient information. Taken together, the reader will obtain initial starting points and suitable solutions relevant for generating and using synthetic data for ML-based screenings in palliative care and beyond.