Mobile and tablet apps, ubiquitous and pervasive computing, wearable computing and domotics for health.

To bridge the translational gap between recent discoveries of distinct molecular phenotypes of pancreatic cancer and tangible improvements in patient outcome, there is an urgent need to develop strategies and tools informing and improving the clinical decision process. Radiomics and machine learning approaches can offer non-invasive whole tumor analytics for clinical imaging data-based classification. The retrospective study assessed baseline computed tomography (CT) from 207 patients with proven pancreatic ductal adenocarcinoma (PDAC). Following expert level manual annotation, Pyradiomics was used for the extraction of 1474 radiomic features. The molecular tumor subtype was defined by immunohistochemical staining for KRT81 and HNF1a as quasi-mesenchymal (QM) vs. non-quasi-mesenchymal (non-QM). A Random Forest machine learning algorithm was developed to predict the molecular subtype from the radiomic features. The algorithm was then applied to an independent cohort of histopathologically unclassifiable tumors with distinct clinical outcomes. The classification algorithm achieved a sensitivity, specificity and ROC-AUC (area under the receiver operating characteristic curve) of 0.84 ± 0.05, 0.92 ± 0.01 and 0.93 ± 0.01, respectively. The median overall survival for predicted QM and non-QM tumors was 16.1 and 20.9 months, respectively, log-rank-test p = 0.02, harzard ratio (HR) 1.59. The application of the algorithm to histopathologically unclassifiable tumors revealed two groups with significantly different survival (8.9 and 39.8 months, log-rank-test p < 0.001, HR 4.33). The machine learning-based analysis of preoperative (CT) imaging allows the prediction of molecular PDAC subtypes highly relevant for patient survival, allowing advanced pre-operative patient stratification for precision medicine applications.

Despite our growing knowledge about the pathomechanisms of cancer cachexia, a whole clinical picture of the cachectic patient is still missing. Our objective was to evaluate the clinical characteristics in cancer patients with and without cachexia to get the whole picture of a cachectic patient. Cancer patients of the University Clinic “Klinikum rechts der Isar” with gastrointestinal, gynecological, hematopoietic, lung and some other tumors were offered the possibility to take part in the treatment concept including a nutrition intervention and an individual training program according to their capability. We now report on the first 503 patients at the time of inclusion in the program between March 2011 and October 2015. We described clinical characteristics such as physical activity, quality of life, clinical dates and food intake. Of 503 patients with cancer, 131 patients (26.0%) were identified as cachectic, 369 (73.4%) as non-cachectic. The change in cachexia were 23% reduced capacity performance (108 Watt for non-cachectic-patients and 83 Watt for cachectic patients) and 12% reduced relative performance (1.53 Watt/kg for non-cachectic and 1.34 Watt/kg for cachectic patients) in ergometry test. 75.6% of non-cachectic and 54.3% of cachectic patients still received curative treatment. Cancer cachectic patients have multiple symptoms such as anemia, impaired kidney function and impaired liver function with elements of mild cholestasis, lower performance and a poorer quality of life in the EORTC questionnaire. Our study reveals biochemical and clinical specific features of cancer cachectic patients.