Sepsis Trajectory Prediction Using Privileged Information and Continuous Physiological Signals.

The aim of this research is to apply the learning using privileged information paradigm to sepsis prognosis. We used signal processing of electrocardiogram and electronic health record data to construct support vector machines with and without privileged information to predict an increase in a given patient's quick-Sequential Organ Failure Assessment score, using a retrospective dataset. We applied this to both a small, critically ill cohort and a broader cohort of patients in the intensive care unit. Within the smaller cohort, privileged information proved helpful in a signal-informed model, and across both cohorts, electrocardiogram data proved to be informative to creating the prediction. Although learning using privileged information did not significantly improve results in this study, it is a paradigm worth studying further in the context of using signal processing for sepsis prognosis.

Prediction of postoperative cardiac events in multiple surgical cohorts using a multimodal and integrative decision support system.

Postoperative patients are at risk of life-threatening complications such as hemodynamic decompensation or arrhythmia. Automated detection of patients with such risks via a real-time clinical decision support system may provide opportunities for early and timely interventions that can significantly improve patient outcomes. We utilize multimodal features derived from digital signal processing techniques and tensor formation, as well as the electronic health record (EHR), to create machine learning models that predict the occurrence of several life-threatening complications up to 4 hours prior to the event. In order to ensure that our models are generalizable across different surgical cohorts, we trained the models on a cardiac surgery cohort and tested them on vascular and non-cardiac acute surgery cohorts. The best performing models achieved an area under the receiver operating characteristic curve (AUROC) of 0.94 on training and 0.94 and 0.82, respectively, on testing for the 0.5-hour interval. The AUROCs only slightly dropped to 0.93, 0.92, and 0.77, respectively, for the 4-hour interval. This study serves as a proof-of-concept that EHR data and physiologic waveform data can be combined to enable the early detection of postoperative deterioration events.

Automated Classification of Osteosarcoma and Benign Tumors using RNA-seq and Plain X-ray.

Osteosarcoma is a prominent bone cancer that typically affects adolescents or people in late adulthood. Early recognition of this disease relies on imaging technologies such as x-ray radiography to detect tumor size and location. This paper aims to differentiate osteosarcoma from benign tumors by analyzing both imaging and RNA-seq data through a combination of image processing and machine learning. In experimental results, the proposed method achieved an Area Under the Receiver Operator Characteristic Curve (AUC) of 0.7272 in three-fold cross-validation, and an AUC of 0.9015 using leave-one-out cross-validation.

Predicting Poor Sleep Quality in Fibromyalgia with Wrist Sensors.

Fibromyalgia is a musculoskeletal disorder characterized by chronic, widespread muscle pain. This condition is associated with disturbed sleep, which has a direct impact on patient quality of life. Patient-reported outcomes are frequently used to assess sleep quality, but show modest correlations with objective measures of sleep, such as polysomnography. Working towards our goal of an automated ambulatory system of assessing sleep quality, we use features from blood volume pulse (BVP) and electrodermal activity (EDA) collected with a wearable device during sleep. We compare these measurements between individuals with fibromyalgia who experienced poor sleep and individuals in a control group who experienced refreshing sleep. By applying Learning Using Concave and Convex Kernels (LUCCK) and Support Vector Machines (SVM), we achieve mean Area Under the Receiver Operating Characteristic Curve (AUC) of 0.6573 and 0.6526, respectively, by using BVP data for classifying individuals to the two groups.

Differential signaling during macropinocytosis in response to M-CSF and PMA in macrophages.

The cellular movements that construct a macropinosome have a corresponding sequence of chemical transitions in the cup-shaped region of plasma membrane that becomes the macropinosome. To determine the relative positions of type I phosphatidylinositol 3-kinase (PI3K) and phospholipase C (PLC) in this pathway, we analyzed macropinocytosis in macrophages stimulated by the growth factor macrophage-colony-stimulating factor (M-CSF) and by the diacylglycerol (DAG) analog phorbol 12-myristate 13-acetate (PMA). In cells stimulated with M-CSF, microscopic imaging of fluorescent probes for intracellular lipids indicated that the PI3K product phosphatidylinositol (3,4,5)-trisphosphate (PIP3) appeared in cups just prior to DAG. We then tested the hypothesis that PMA and DAG function after PI3K and prior to Ras and protein kinase C (PKC) during macropinosome formation in macrophages. Although the PI3K target Akt was activated by M-CSF, the Akt inhibitor MK-2206 did not inhibit macropinocytosis. The phospholipase C (PLC) inhibitor U73122 blocked macropinocytosis by M-CSF but not PMA. Macropinocytosis in response to M-CSF and PMA was inhibited by the Ras inhibitor farnesyl thiosalicylate (FTS), by the PKC inhibitor Calphostin C and by the broad specificity inhibitor rottlerin. These studies support a model in which M-CSF stimulates PI3K in macropinocytic cups, and the resulting increase in PIP3 activates PLC, which in turn generates DAG necessary for activation of PKC, Ras and the late stages of macropinosome closure.