ABSTRACT Introduction The emergence of more complex Prolonged Field Care in austere settings and the need to assist inexperienced providers’ ability to treat patients create an urgent need for effective tools to support care. We report on a project to develop a phone-/tablet-based decision support system for prehospital tactical combat casualty care that collects physiologic and other clinical data and uses machine learning to detect and differentiate shock manifestation. Materials and Methods Software interface development methods included literature review, rapid prototyping, and subject matter expert design requirements reviews. Machine learning algorithm methods included development of a model trained on publicly available Medical Information Mart for Intensive Care data, then on de-identified data from Mayo Clinic Intensive Care Unit. Results The project team interviewed 17 Army, Air Force, and Navy medical subject matter experts during design requirements review sessions. They had an average of 17 years of service in military medicine and an average of 4 deployments apiece and all had performed tactical combat casualty care on live patients during deployment. Comments provided requirements for shock identification and management in prehospital settings, including support for indication of shock probability and shock differentiation. The machine learning algorithm based on logistic regression performed best among other algorithms we tested and was able to predict shock onset 90 minutes before it occurred with better than 75% accuracy in the test dataset. Conclusions We expect the Trauma Triage, Treatment, and Training Decision Support system will augment a medic’s ability to make informed decisions based on salient patient data and to diagnose multiple types of shock through remotely trained, field deployed ML models.
Akt and CHIP coregulate tau degradation through coordinated interactions
A hallmark of the pathology of Alzheimer's disease is the accumulation of the microtubule-associated protein tau into fibrillar aggregates. Recent studies suggest that they accumulate because cytosolic chaperones fail to clear abnormally phosphorylated tau, preserving a pool of toxic tau intermediates within the neuron. We describe a mechanism for tau clearance involving a major cellular kinase, Akt. During stress, Akt is ubiquitinated and degraded by the tau ubiquitin ligase CHIP, and this largely depends on the Hsp90 complex. Akt also prevents CHIP-induced tau ubiquitination and its subsequent degradation, either by regulating the Hsp90/CHIP complex directly or by competing as a client protein with tau for binding. Akt levels tightly regulate the expression of CHIP, such that, as Akt levels are suppressed, CHIP levels also decrease, suggesting a potential stress response feedback mechanism between ligase and kinase activity. We also show that Akt and the microtubule affinity-regulating kinase 2 (PAR1/MARK2), a known tau kinase, interact directly. Akt enhances the activity of PAR1 to promote tau hyperphosphorylation at S262/S356, a tau species that is not recognized by the CHIP/Hsp90 complex. Moreover, Akt1 knockout mice have reduced levels of tau phosphorylated at PAR1/MARK2 consensus sites. Hence, Akt serves as a major regulator of tau biology by manipulating both tau kinases and protein quality control, providing a link to several common pathways that have demonstrated dysfunction in Alzheimer's disease.