Projekte

Abstract: Bronchiectasis is a chronic lung condition where the airways become abnormally widened, often due to previous lung infections, immune system disorders, or genetic conditions. This widening leads to persistent coughing, excess mucus production, and frequent respiratory infections like pneumonia. In addition to pneumonia, patients with bronchiectasis are prone to recurrent exacerbations, where symptoms suddenly worsen, increasing the risk of lung damage and hospitalization. Identifying patients at high risk for pneumonia and exacerbations is crucial for timely intervention and better outcomes. Despite advances in medical imaging, current methods do not accurately predict which patients are most likely to develop pneumonia or experience exacerbations. This project aims to address this gap by developing artificial intelligence (AI) tools to predict these risks in bronchiectasis patients. By analyzing clinical data—including patient histories, comorbidities, and microbiological profiles—alongside detailed chest CT scans, the AI will identify patterns that indicate a higher likelihood of complications. […] As Switzerland prepares for a national lung cancer screening program, which will increase the number of chest CT scans, the AI tools developed in this project will help radiologists and clinicians manage the growing demand while focusing on the most vulnerable patients. […]

Partner Hospital: Kantonsspital Aarau 
Research Partner: Paul Scherrer Institut PSI

Abstract: ProSPECT-Q aims to establish a more objective approach to tracking radioligand therapy (RLT) in prostate cancer patients treated with Lutetium-177 (Lu-PSMA), an innovative therapy that targets prostate cancer cells. Lu-PSMA has already shown strong results in extending the survival of patients with advanced prostate cancer, typically as a last-resort option after chemotherapy. However, as the tendency is to introduce Lu-PSMA earlier in the treatment course, a more precise method to assess which patients will benefit from the therapy and to monitor the therapy’s effects over time are required. Currently, assessments rely mainly on visual evaluations and laboratory results, such as Prostate Specific Antigen (PSA) levels, which may miss subtle changes in tumoural activity. This project proposes the use of quantitative SPECT/CT imaging, which offers more accurate measurement of tumour volume and response than traditional visual assessments. However, interpreting this data in a clinical context is complex, so ProSPECT-Q seeks to develop new tools for analysing imaging data in combination with clinical information, using artificial intelligence. The project will collect and analyse data from past patients, measuring tumour characteristics, therapy outcomes and side effects. Advanced techniques like machine learning will be used to identify patterns and predict outcomes such as therapy success, defined as therapy completion or serious adverse effects, like bone marrow damage or decrees of renal function. By creating models that predict these risks early, doctors could better balance the risks and benefices of the treatment, helping patients avoid unnecessary side effects and improving their long-term outcomes. […]

Partner Hospital: Kantonsspital Baden
Research Partner: Paul Scherrer Institut PSI

Abstract: Endometriosis affects approximately 10% of fertile women, causing significant pain and infertility, yet non-invasive diagnostic tools remain inadequate. […] This project aims to address these challenges by developing a novel diagnostic approach using Positron Emission Tomography (PET). PET offers higher resolution and sensitivity for detecting and characterizing tissues. Recent research has shown that endometriotic lesions are rich in relaxed fibronectin (Fn), particularly in the stroma and areas of reactive fibrosis. Preliminary studies have successfully stained Fn in endometriotic tissues, suggesting it could serve as a promising target for PET imaging. The project proposes a detailed analysis of several extracellular matrix proteins, including relaxed fibronectin, fibroblast activation protein (FAP), matrix metalloproteinases, and integrins, using immunohistochemistry. These markers will be correlated with MRI and ultrasound findings, as well as intraoperative observations and histopathology results. The goal is to identify an optimal target for PET imaging that can differentiate active, painful endometriotic tissue from scar tissue, thereby improving preoperative lesion localization and surgical planning. This approach could potentially allow for earlier, more accurate diagnosis, better patient management, and improved pain relief after surgery.

Partner Hospital: Kantonsspital Baden
Research Partner: Paul Scherrer Institut PSI & ETH Zürich

Abstract: While not all patients are the same, treatment also differs. Such differences in care can be explained by patient factors but might also be the result of incognizant biases in the care teams’ minds. Especially when it comes to interventions in intensive care units (ICU), this may lead to disparities. So called causal inference frameworks offer a way to examine the fair use of treatments. We wanted to investigate the use of invasive mechanical ventilation, renal replacement therapy and vasoactive medications to identify disparities in outcomes between cancer patients with sepsis compared to non-cancer patients with sepsis. For this, we want to use a novel and powerful statistical method called targeted maximum likelihood estimation which is able to simulate a what-if world in which each patient will be treated and then compared to this digital twin who is not being treated. [… ] Detecting differences in treatment outcomes would help physicians to rethink their treatment policies and inform policy makers to place institutional checks. If there were no differences, our proposed framework could be deployed to other datasets, questions, or disparity checks at other institutions.

Partner Hospital: Kantonsspital Aarau 
Research Partner: ETH Zürich