State-of-the-art machine learning algorithms for the prediction of outcomes after contemporary heart transplantation: Results from the UNOS database.

PURPOSE: We sought to develop and validate machine learning (ML) models to increase the predictive accuracy of mortality after heart transplantation (HT). METHODS AND RESULTS: We included adult HT recipients from the United Network for Organ Sharing (UNOS) database between 2010 and 2018 using solely pre-transplant variables. The study cohort comprised 18 625 patients (53 ± 13 years, 73% males) and was randomly split into a derivation and a validation cohort with a 3:1 ratio. At 1-year after HT, there were 2334 (12.5%) deaths. Out of a total of 134 pre-transplant variables, 39 were selected as highly predictive of 1-year mortality via feature selection algorithm and were used to train five ML models. AUC for the prediction of 1-year survival was .689, .642, .649, .637, .526 for the Adaboost, Logistic Regression, Decision Tree, Support Vector Machine, and K-nearest neighbor models, respectively, whereas the Index for Mortality Prediction after Cardiac Transplantation (IMPACT) score had an AUC of .569. Local interpretable model-agnostic explanations (LIME) analysis was used in the best performing model to identify the relative impact of key predictors. ML models for 3- and 5-year survival as well as acute rejection were also developed in a secondary analysis and yielded AUCs of .629, .609, and .610 using 27, 31, and 91 selected variables respectively. CONCLUSION: Machine learning models showed good predictive accuracy of outcomes after heart transplantation.

Inflammatory state of lymphatic vessels and miRNA profiles associated with relapse in ovarian cancer patients.

Lymphogenic spread is associated with poor prognosis in epithelial ovarian cancer (EOC), yet little is known regarding roles of non-peri-tumoural lymphatic vessels (LVs) outside the tumour microenvironment that may impact relapse. The aim of this feasibility study was to assess whether inflammatory status of the LVs and/or changes in the miRNA profile of the LVs have potential prognostic and predictive value for overall outcome and risk of relapse. Samples of macroscopically normal human lymph LVs (n = 10) were isolated from the external iliac vessels draining the pelvic region of patients undergoing debulking surgery. This was followed by quantification of the inflammatory state (low, medium and high) and presence of cancer-infiltration of each LV using immunohistochemistry. LV miRNA expression profiling was also performed, and analysed in the context of high versus low inflammation, and cancer-infiltrated versus non-cancer-infiltrated. Results were correlated with clinical outcome data including relapse with an average follow-up time of 13.3 months. The presence of a high degree of inflammation correlated significantly with patient relapse (p = 0.033). Cancer-infiltrated LVs showed a moderate but non-significant association with relapse (p = 0.07). Differential miRNA profiles were identified in cancer-infiltrated LVs and those with high versus low inflammation. In particular, several members of the let-7 family were consistently down-regulated in highly inflamed LVs (>1.8-fold, p<0.05) compared to the less inflamed ones. Down-regulation of the let-7 family appears to be associated with inflammation, but whether inflammation contributes to or is an effect of cancer-infiltration requires further investigation.

Using activity-related behavioural features towards more effective automatic stress detection.

This paper introduces activity-related behavioural features that can be automatically extracted from a computer system, with the aim to increase the effectiveness of automatic stress detection. The proposed features are based on processing of appropriate video and accelerometer recordings taken from the monitored subjects. For the purposes of the present study, an experiment was conducted that utilized a stress-induction protocol based on the stroop colour word test. Video, accelerometer and biosignal (Electrocardiogram and Galvanic Skin Response) recordings were collected from nineteen participants. Then, an explorative study was conducted by following a methodology mainly based on spatiotemporal descriptors (Motion History Images) that are extracted from video sequences. A large set of activity-related behavioural features, potentially useful for automatic stress detection, were proposed and examined. Experimental evaluation showed that several of these behavioural features significantly correlate to self-reported stress. Moreover, it was found that the use of the proposed features can significantly enhance the performance of typical automatic stress detection systems, commonly based on biosignal processing.

Real-time monitoring of behavioural parameters related to psychological stress.

We have developed a system, allowing real-time monitoring of human gestures, which can be used for the automatic recognition of behavioural correlates of psychological stress. The system is based on a low-cost camera (Microsoft Kinect), which provides video recordings capturing the subject's upper body activity. Motion History Images (MHIs) are calculated in real-time from these recordings. Appropriate algorithms are thereafter applied over the MHIs, enabling the real-time calculation of activity-related behavioural parameters. The system's efficiency in real-time calculation of behavioural parameters has been tested in a pilot trial, involving monitoring of behavioural parameters during the induction of mental stress. Results showed that our prototype is capable to effectively calculate simultaneously eight different behavioural parameters in real-time. Statistical analysis indicated significant correlations between five of these parameters and self-reported stress. The preliminary findings suggest that our approach could potentially prove useful within systems targeting automatic stress detection, through unobtrusive monitoring of subjects.