Sepsis is a leading cause of death and is the most expensive condition to treat in U.S. hospitals. Despite targeted efforts to automate earlier detection of sepsis, current techniques rely exclusively on using either standard clinical data or novel biomarker measurements. In this study, we apply machine learning techniques to assess the predictive power of combining multiple biomarker measurements from a single blood sample with electronic medical record data (EMR) for the identification of patients in the early to peak phase of sepsis in a large community hospital setting. Combining biomarkers and EMR data achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.81, while EMR data alone achieved an AUC of 0.75. Furthermore, a single measurement of six biomarkers (IL-6, nCD64, IL-1ra, PCT, MCP1, and G-CSF) yielded the same predictive power as collecting an additional 16 hours of EMR data(AUC of 0.80), suggesting that the biomarkers may be useful for identifying these patients earlier. Ultimately, supervised learning using a subset of biomarker and EMR data as features may be capable of identifying patients in the early to peak phase of sepsis in a diverse population and may provide a tool for more timely identification and intervention.

Traumatic brain injury (TBI) is a global health problem that affects millions of civilians, athletes, and military personnel yearly. Sleeping disorders are one of the underrecognized sequalae even though they affect 46% of individuals with TBI. After a mild TBI, 29% of patients have insomnia, 25% have sleep apnea, 28% have hypersomnia, and 4% have narcolepsy. The type of sleep disturbance may also vary according to the number of TBIs sustained. Diffuse axonal injury within the sleep regulation system, disruption of hormones involved in sleep, and insults to the hypothalamus, brain stem, and reticular activating system are some of the proposed theories for the pathophysiology of sleep disorders after TBI. Genetic and anatomical factors also come to play in the development and severity of these sleeping disorders. Untreated sleep disturbances following TBI can lead to serious consequences with respect to an individual’s cognitive functioning. Initial management focuses on conservative measures with progression to more aggressive options if necessary. Future research should attempt to establish the effectiveness of the treatments currently used, as well as identify manageable co-existing factors that could be exacerbating sleep disorders.

Background: In response to the COVID-19 pandemic, internal medicine residencies have had to develop new teaching strategies and attend to wellness concerns. Providing front-line care for patients in a time of widespread crisis while maintaining attention to training has created unprecedented challenges. Objective: Our large community hospital based internal medicine residency sought to develop and evaluate a crisis response to the demands of the COVID-19 pandemic to meet our residents' educational and wellness needs. Methods: In March 2020, our residency developed a crisis plan for functioning during the COVID-19 pandemic. A brief survey was sent via email to our 149 residents to obtain their evaluation of how well their needs were being met by this response. Results: 92 (62%) residents completed the survey. 88% indicated their well-being needs were well met. Other components were also rated as successful: effective communication (86%), scheduling/staffing (78%), preparing residents for clinical service (77%), and educational needs (76%). Conclusions: Our residency crisis response to the COVID-19 pandemic was favorably evaluated by our residents in meeting their training and well-being needs. In future work we plan to seek longer-term and more objective measures to assess how residents fare during these challenging times, and to use lessons learned to prepare for future crisis situations.

Aortoesophageal fistula (AEF) is a rare cause of massive upper gastrointestinal hemorrhage. Thoracic aortic aneurysm, esophageal foreign body, esophageal cancer and post-surgical complications are common causes of AEF; however, AEF induced by radiation therapy is a rare phenomenon and seldom described in the literature. It is a catastrophic condition which requires rapid implementation of resuscitative measures, broad-spectrum antibiotics and surgical or endovascular intervention. Transthoracic endovascular aortic repair (TEVAR) is a newer and less invasive technique, which helps to achieve rapid hemostasis in patients with severe hemodynamic instability and offers advantages over conventional repair of the aorta in emergency situations. However initial TEVAR should be followed up with a more definitive surgical repair of the aorta and the esophagus, to lower the mortality rate and achieve better outcomes. We describe here a case of a seventy-year-old male who presented with massive upper gastrointestinal bleeding due to AEF induced by radiation therapy, and his subsequent successful initial management with TEVAR.