Clinical trials

The PROMPT study is testing whether an early keyhole procedure called Medical Thoracoscopy, which lets doctors look inside the chest and remove infected fluid, works better than current standard treatment (medicines to break up thick fluid) for people with pleural infection. About 170 patients in several hospitals will be randomly assigned to one of the two treatments, and researchers will see which approach results in fewer additional procedures-such as another drain or surgery-within 30 days, as well as how quickly people recover and whether they experience any complications. Everyone in the study receives high-quality care, and the results will help doctors better understand which treatment gives patients the best chance of recovering quickly and safely

The hypothesis is that fluid-responsive patients who show signs of venous congestion experience a worsening of microcirculatory status after fluid administration compared to patients without signs of venous congestion

According to Guyton's model of venous return, the fluids that effectively increase cardiac output are those that, once administered, increase the vascular stressed volume, thereby increasing the mean systemic filling pressure (Pms) without increasing the central venous pressure (CVP). In this way, since the gradient between Pms and CVP increases, venous return-and consequently cardiac output-also increases. In cases where physiologically ineffective fluids are administered, the situation arises in which, in addition to increasing the stressed volume and thus Pms, CVP also increases. As a result, the gradient between Pms and CVP remains unchanged, and cardiac output does not increase. The hypothesis is that only a portion of the fluids administered during volume expansion are actually effective in increasing the gradient between Pms and CVP.

Current decision tools (TNM, MRI/PET, CEA, and other serum markers, as well as single-marker genomics) are insufficiently predictive of responders, fail to detect early MRD in many cases, and rarely connect molecular biology to dynamic perioperative data. SAFE-AI will build and validate multimodal, explainable GenAI models that fuse liquid/tissue multi-omics with radiology and clinical trajectories to: (i) detect MRD earlier, (ii) improve recurrence-risk calibration, and (iii) support non-invasive "virtual biopsy"-inferring tissue-level features from blood profiles, and vice-versa, to mitigate missing-modality gaps. This is grounded in the strong mechanistic premise that integrating heterogeneous molecular signals with imaging captures tumour-host biology more completely than single-modality assays, enabling actionable, calibrated risk estimates for rectal and oesophageal cancer. The clinical hypothesis is that such integrated models can improve recurrence prediction by at least 20% over guideline baselines, with transparent uncertainty and bias monitoring to meet EU AI Act/MDR expectations.