Search

Objective The timely stratification of trauma injury severity can enhance the quality of trauma care but it requires intense manual annotation from certified trauma coders. The objective of this study is to develop machine learning models for the stratification of trauma injury severity across various body regions using clinical text and structured electronic health records (EHRs) data. Materials and Methods Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create 2 machine learning models with different approaches to representing text. The first one fuses concept unique identifiers (CUIs) extracted from free text with structured EHR variables, while the second one integrates free text with structured EHR variables. Temporal validation was undertaken to ensure the models' temporal generalizability. Additionally, analyses to assess the variable importance were conducted. Results Both models demonstrated impressive performance in categorizing leg injuries, achieving high accuracy with macro-F1 scores of over 0.8. Additionally, they showed considerable accuracy, with macro-F1 scores exceeding or near 0.7, in assessing injuries in the areas of the chest and head. We showed in our variable importance analysis that the most important features in the model have strong face validity in determining clinically relevant trauma injuries. Discussion The CUI-based model achieves comparable performance, if not higher, compared to the free-text-based model, with reduced complexity. Furthermore, integrating structured EHR data improves performance, particularly when the text modalities are insufficiently indicative. Conclusions Our multi-modal, multiclass models can provide accurate stratification of trauma injury severity and clinically relevant interpretations. [ABSTRACT FROM AUTHOR]

College-provided scholarships, or tuition discounts, are in the news. The National Association of College and University Business Officers recently estimated that the average discount for full-time, first-year undergraduates at private nonprofit colleges and universities hit 50 percent in the fall of 2017. In other words, these institutions provide scholarship grants that reduce a typical new student's tuition and fees by half. In one sense, this is good news for students. Scholarships lower college costs for their recipients and make college a possibility for those who could not otherwise afford it. On the other hand, tuition discounting can reduce schools' revenues and undermine the quality of their academic and extracurricular programs. There are also concerns that colleges that offer extensive merit scholarships are likely to reduce need-based scholarships to offset the loss in revenue from merit-based tuition discounts. If so, many students from lower-income families may find college unaffordable as colleges compete to attract highly-desired, more-affluent students who would attend some college, with or without a discount. Using data from U.S. Department of Education's Integrated Post-Secondary Educational Survey (IPEDS) and the Common Data Set (CDS), a collaborative data-gathering project of the College Board, "Peterson's", and "U.S. News and World Report", the author examines discounting practices at 125 private liberal arts colleges (Caskey, 2018). He found two striking, and initially puzzling, patterns in the data: (1) colleges that depend heavily on tuition revenue commonly provide scholarships to much larger percentages of their students than do the colleges with substantial budget support from large endowments. How can the tuition-dependent colleges afford to do this? and (2) although all colleges offer need-based scholarships, the use of merit-based scholarships is highly variable. Some colleges offer them to all entering students who do not have need-based scholarships. Others offer no merit scholarships. He argues that these patterns emerge as colleges in different circumstances trade off the costs and benefits of tuition discounting. Specifically, most endowment-rich colleges would see no net benefit from merit scholarships and do not offer them or offer very limited merit scholarships. All colleges gain from need-based scholarships, and all offer them. But the scholarships provided by tuition-dependent colleges can force reductions in per-student spending and encourage further discounting.

This article describes the budget crisis that the School District of Philadelphia has faced for the past few years. Three specific events triggered the 2012 crisis: an abrupt reduction in federal and state funding, the inability of the district to cut many of its costs, and political pressures on the district to spend available revenues in a given year. Philadelphia is the ninth-poorest U.S. city with a population over 250,000. Relative to Pittsburgh and the Philadelphia suburbs, the school district is significantly underfunded by the state and its city government, especially when one adjusts for the comparatively large percentages of special education, English language learners, and low-income students. In short, the district faces huge challenges with limited resources. In addition to this fundamental fiscal weakness, the district is undermined by its governance structure. With no independent taxing authority, every year the district administration must plead for funding from the state and city.

Each year, as predictably as classes end in June, the School District of Philadelphia faces a budget crisis for the coming school year. In 2014, the School Reform Commission, the [...]