Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing.

OBJECTIVE: Leverage electronic health record (EHR) audit logs to develop a machine learning (ML) model that predicts which notes a clinician wants to review when seeing oncology patients. MATERIALS AND METHODS: We trained logistic regression models using note metadata and a Term Frequency Inverse Document Frequency (TF-IDF) text representation. We evaluated performance with precision, recall, F1, AUC, and a clinical qualitative assessment. RESULTS: The metadata only model achieved an AUC 0.930 and the metadata and TF-IDF model an AUC 0.937. Qualitative assessment revealed a need for better text representation and to further customize predictions for the user. DISCUSSION: Our model effectively surfaces the top 10 notes a clinician wants to review when seeing an oncology patient. Further studies can characterize different types of clinician users and better tailor the task for different care settings. CONCLUSION: EHR audit logs can provide important relevance data for training ML models that assist with note-writing in the oncology setting.

Developing a pulse oximetry home monitoring protocol for patients suspected with COVID-19 after emergency department discharge.

OBJECTIVES: Patients with COVID-19 can present to the emergency department (ED) without immediate indication for admission, but with concern for decompensation. Clinical experience has demonstrated that critical illness may present later in the disease course and hypoxia is often the first indication of disease progression. The objectives of this study are to (a) assess feasibility and describe a protocol for ED-based outpatient pulse-oximetry monitoring with structured follow-up and (b) determine rates of ED return, hospitalisation and hypoxia among participants. METHODS: Prospective observational study of patients presenting to a single academic ED in Boston with suspected COVID-19. Eligible patients were adults being discharged from the ED with presumed COVID-19. Exclusion criteria included resting oxygen saturation <92%, ambulatory oxygen saturation <90%, heart rate >110 beats per minute or inability to use the device. Study personnel made scripted phone calls on postdischarge days 1, 3 and 7 to review the pulse-oximetry readings and to evaluate for decompensation. Return visit and admission information were collected via medical record and 28-day follow-up calls. RESULTS: 81 patients were enrolled of which 10 (12%) developed hypoxia after their initial discharge from the ED. Overall, 23 (28%) of the 81 patients returned to the ED at least once and 10 of those who returned (43%) were admitted. We successfully contacted 76/81 (94%) of subjects via phone at least once for follow-up assessment. DISCUSSION: Patients are eager and willing to participate in home monitoring systems and are comfortable with using technology, which will allow providers and health systems to extend our hospitals capabilities for tracking patient populations in times of crisis. CONCLUSIONS: It is feasible to implement an outpatient pulse-oximetry monitoring protocol to monitor patients discharged from the ED with confirmed or suspected COVID-19.

Rare Complications of Acute Appendicitis: A Case Report.

INTRODUCTION: Appendicitis is a common disease, and as we have improved in early diagnosis and management of this disease process, late stage complications have become extremely rare, but can have indolent presentations. CASE REPORT: A 37-year-old male with no past medical history presented to the emergency department (ED) with vague abdominal pain as well as 12 days of cyclical fever. He had no significant findings on laboratory workup with the exception of a mild aspartate transaminase and alanine transaminase and relative neutrophilia between outpatient, urgent care, and ultimate ED visit. His ED workup included cross-sectional imaging of his abdomen revealing multiple liver abscesses and septic thrombophlebitis secondary to ruptured appendicitis. CONCLUSION: Liver abscesses and septic thrombophlebitis are an extremely rare complication of appendicitis that has only been documented twice previously.

Point of Care Image Capture with a Custom Smartphone Application: Experience with an Encounter-Based Workflow.

Medical documentation is one of the primary methods by which physicians share clinical information and impressions over time with one another. As the adage says, "a picture is worth a thousand words," and physicians have started leveraging consumer mobile technology to share images with one another. However, image sharing often uses short message service texting and similar methods, which can be noncompliant with privacy regulations and can also limit the ability to communicate information longitudinally and across specialties. Sharing of such information is increasingly important, however, as smaller practices are joining to create large geographically spread out health care networks. To this end, we developed an application to acquire and store images via smartphone and seamlessly transfer into the patient's electronic medical record (EMR) to enable digital consults and longitudinal evaluation in a private and compliant method.

Personalized cytomic assessment of vascular health: Evaluation of the vascular health profile in diabetes mellitus.

BACKGROUND: An inexpensive and accurate blood test does not currently exist that can evaluate the cardiovascular health of a patient. This study evaluated a novel high dimensional flow cytometry approach in combination with cytometric fingerprinting (CF), to comprehensively enumerate differentially expressed subsets of pro-angiogenic circulating progenitor cells (CPCs), involved in the repair of vasculature, and microparticles (MPs), frequently involved in inflammation and thrombosis. CF enabled discovery of a unique pattern, involving both MPs and CPCs and generated a personalized signature of vascular health, the vascular health profile (VHP). METHODS: Levels of CPCs and MPs were measured with a broad panel of cell surface markers in a population with atherosclerosis and type 2 diabetes mellitus (DM) and age-similar Healthy controls (HC) using an unbiased computational approach, termed CF. RESULTS: Circulating hematopoietic stem and progenitor cell (CHSPCAng) levels were detected at significantly lower concentrations in DM (P < 0.001), whereas levels of seven phenotypically distinct MPs were present at significantly higher concentrations in DM patients and one MP subset was present at significantly lower concentration in DM patients. Collectively, the combination of CHSPC(Ang) and MP levels was more informative than any one measure alone. CONCLUSIONS: This work provides the basis for a personalized cytomic vascular health profile that may be useful for a variety of applications including drug development, clinical risk assessment and companion diagnostics.