Abstract: Patient Trajectories (PTs) are a method of representing the temporal evolution of patients. They can include information from different sources and be used in socio-medical or clinical domains. PTs have generally been used to generate and study the most common trajectories in, for instance, the development of a disease. On the other hand, healthcare predictive models generally rely on static snapshots of patient information. Only a few works about prediction in healthcare have been found that use PTs, and therefore benefit from their temporal dimension. All of them, however, have used PTs created from single-source information. Therefore, the use of longitudinal multi-scale data to build PTs and use them to obtain predictions about health conditions is yet to be explored. Our hypothesis is that local similarities on small chunks of PTs can identify similar patients concerning their future morbidities. The objectives of this work are (1) to develop a methodology to identify local similarities between PTs before the occurrence of morbidities to predict these on new query individuals; and (2) to validate this methodology on risk prediction of cardiovascular diseases (CVD) occurrence in patients with diabetes. We have proposed a novel formal definition of PTs based on sequences of longitudinal multi-scale data. Moreover, a dynamic programming methodology to identify local alignments on PTs for predicting future morbidities is proposed. Both the proposed methodology for PT definition and the alignment algorithm are generic to be applied on any clinical domain. We validated this solution for predicting CVD in patients with diabetes and we achieved a precision of 0.33, a recall of 0.72 and a specificity of 0.38. Therefore, the proposed solution in the diabetes use case can result of utmost utility to secondary screening.

Abstract: Background and purpose: Brachytherapy treatment outcomes depend on the accuracy of the delivered dose distribution, which is proportional to the reference air-kerma rate (RAKR). Current societal recommendations require the medical physicist to compare the measured RAKR values to the manufacturer source calibration certificate. The purpose of this work was to report agreement observed in current clinical practice in the European Union. Materials and methods: A European survey was performed for high- and pulsed-dose-rate (HDR and PDR) highenergy sources (Ir-192 and Co-60), to quantify observed RAKR differences. Medical physicists at eighteen hospitals from eight European countries were contacted, providing 1,032 data points from 2001 to 2020. Results: Over the survey period, 77% of the Ir-192 measurements used a well chamber instead of the older Krieger phantom method. Mean differences with the manufacturer calibration certificate were 0.01% +/- 1.15% for Ir-192 and -0.1% +/- 1.3% for Co-60. Over 95% of RAKR measurements in the clinic were within 3% of the manufacturer calibration certificate. Conclusions: This study showed that the agreement level was generally better than that reflected in prior societal recommendations positing 5%. Future recommendations on high-energy HDR and PDR source calibrations in the clinic may consider tightened agreements levels.

Abstract: The IRIS group at IFIC-Valencia has developed a second version of a Compton camera prototype for hadron therapy treatment monitoring, with the aim of improving the performance with respect to its predecessor. The system is composed of three Lanthanum (III) bromide (LaBr3) crystals coupled to silicon photomultipliers (SiPMs). The detector energy resolution has been improved to 5.6% FWHM at 511 keV and an angular resolution of 8.0 degrees has been obtained. Images of a Na-22 point-like source have been reconstructed selecting two and three interaction events. Moreover, the experimental data have been reproduced with Monte Carlo simulations using a Compton camera module (CCMod) in GATE v8.2 obtaining a good correlation.