Drivers of Moral Distress in Surgical Intensive Care Providers: A Mixed Methods Study.

BACKGROUND: Moral distress is common among healthcare providers, leading to staff burnout and attrition. This study aimed to identify root causes of and potential solutions to moral distress experienced by surgical intensive care unit (SICU) providers. MATERIALS AND METHODS: This is a mixed methods study of physicians and nurses from a single, academic SICU. We obtained quantitative data from the Measures of Moral Distress for Healthcare Professionals (MMD-HP) survey and qualitative data from semi-structured interviews. The MMD-HP is a 27 question, validated survey on triggers of moral distress. Survey and interview data were analyzed to identify drivers of moral distress using a convergent design. RESULTS: 21 nurses and 25 physicians were surveyed and 17 providers interviewed. MMD-HP data demonstrated high levels of moral distress for nurses (mean total MMD-HP 132 ± 63.5) and physicians (121.7 ± 64.7), P = 0.68. The most frequent root cause of moral distress for all providers was participating in the delivery of aggressive care perceived to be futile. Nurses also reported caring for patients with unclear goals of care as a key driver of moral distress. Interview data supported these findings. Providers recommended improving access to palliative care to increase early communication on patient goals of care and end-of-life as a solution. Culture in the SICU often promotes supporting aggressive care however, acting as a potential barrier to increasing palliative resources. CONCLUSIONS: Providing aggressive care that is perceived as futile was the primary driver of moral distress in the SICU. Interventions to improve early communication and access to end-of-life care should be prioritized to decrease moral distress in staff.

Using Natural Language Processing to improve EHR Structured Data-based Surgical Site Infection Surveillance.

Surgical Site Infection surveillance in healthcare systems is labor intensive and plagued by underreporting as current methodology relies heavily on manual chart review. The rapid adoption of electronic health records (EHRs) has the potential to allow the secondary use of EHR data for quality surveillance programs. This study aims to investigate the effectiveness of integrating natural language processing (NLP) outputs with structured EHR data to build machine learning models for SSI identification using real-world clinical data. We examined a set of models using structured data with and without NLP document-level, mention-level, and keyword features. The top-performing model was based on a Random Forest classifier enhanced with NLP document-level features achieving a 0.58 sensitivity, 0.97 specificity, 0.54 PPV, 0.98 NPV, and 0.52 F0.5 score. We further interrogated the feature contributions, analyzed the errors, and discussed future directions.