Effect of Medicaid Expansion on Visit Composition in a Louisiana Health Care System.

Background: In 2016, Louisiana expanded Medicaid to low-income adults under the Patient Protection and Affordable Care Act. By 2020, the uninsured rate of adults in Louisiana had dropped from 22.7% to 8.9%; however, few reports describe the effect Medicaid expansion has had on access and utilization of health care services in Louisiana. Methods: For this study, we collected all-payer emergency department and clinic visits from one health care system in Louisiana from 2015 to 2019. We used a time series analysis to compare trends before and after Medicaid expansion in health insurance coverage and emergency department visit type. Results: The changes in payer mix in the urgent care and primary care clinics and emergency departments after Medicaid expansion was driven by the uptake of Medicaid coverage in the previously uninsured. Medicaid expansion had a limited impact on the number of urgent care and emergent and nonemergent emergency department visits, but an increase in primary care visits was observed. Conclusion: Medicaid expansion reduced uncompensated care in our patient population and expanded the access to primary care clinics. Ongoing research is needed to understand the effect of nonfinancial barriers to care on access to and utilization of services in Louisiana.

Detection of affective states from text and speech for real-time human--computer interaction.

OBJECTIVE: The goal of this work is to develop and test an automated system methodology that can detect emotion from text and speech features. BACKGROUND: Affective human-computer interaction will be critical for the success of new systems that will be prevalent in the 21st century. Such systems will need to properly deduce human emotional state before they can determine how to best interact with people. METHOD: Corpora and machine learning classification models are used to train and test a methodology for emotion detection. The methodology uses a stepwise approach to detect sentiment in sentences by first filtering out neutral sentences, then distinguishing among positive, negative, and five emotion classes. RESULTS: Results of the classification between emotion and neutral sentences achieved recall accuracies as high as 77% in the University of Illinois at Urbana-Champaign (UIUC) corpus and 61% in the Louisiana State University medical drama (LSU-MD) corpus for emotion samples. Once neutral sentences were filtered out, the methodology achieved accuracy scores for detecting negative sentences as high as 92.3%. CONCLUSION: Results of the feature analysis indicate that speech spectral features are better than speech prosodic features for emotion detection. Accumulated sentiment composition text features appear to be very important as well. This work contributes to the study of human communication by providing a better understanding of how language factors help to best convey human emotion and how to best automate this process. APPLICATION: Results of this study can be used to develop better automated assistive systems that interpret human language and respond to emotions through 3-D computer graphics.