Clinical Prediction Models for Hospital-Induced Delirium Using Structured and Unstructured Electronic Health Record Data: Protocol for a Development and Validation Study

BACKGROUND

Hospital-induced delirium is one of the most common and costly iatrogenic conditions, and its incidence is predicted to increase as the population of the United States ages. An academic and clinical interdisciplinary systems approach is needed to reduce the frequency and impact of hospital-induced delirium.

OBJECTIVE

The long-term goal of our research is to enhance the safety of hospitalized older adults by reducing iatrogenic conditions through an effective learning health system. In this study, we will develop models for predicting hospital-induced delirium. In order to accomplish this objective, we will create a computable phenotype for our outcome (hospital-induced delirium), design an expert-based traditional logistic regression model, leverage machine learning techniques to generate a model using structured data, and use machine learning and natural language processing to produce an integrated model with components from both structured data and text data.

METHODS

This study will explore text-based data, such as nursing notes, to improve the predictive capability of prognostic models for hospital-induced delirium. By using supervised and unsupervised text mining in addition to structured data, we will examine multiple types of information in electronic health record data to predict medical-surgical patient risk of developing delirium. Development and validation will be compliant to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement.

RESULTS

Work on this project will take place through March 2024. For this study, we will use data from approximately 332,230 encounters that occurred between January 2012 to May 2021. Findings from this project will be disseminated at scientific conferences and in peer-reviewed journals.

CONCLUSIONS

Success in this study will yield a durable, high-performing research-data infrastructure that will process, extract, and analyze clinical text data in near real time. This model has the potential to be integrated into the electronic health record and provide point-of-care decision support to prevent harm and improve quality of care.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/48521.

Which hospital-acquired conditions matter the most in trauma? An evidence-based approach for prioritizing trauma program improvement

BACKGROUND

Prevention of hospital-acquired conditions (HACs) is a focus of trauma center quality improvement. The relative contributions of various HACs to postinjury hospital outcomes are unclear. We sought to quantify and compare the impacts of six HACs on early clinical outcomes and resource utilization in hospitalized trauma patients.

METHODS

Adult patients from the 2013 to 2016 American College of Surgeons Trauma Quality Improvement Program Participant Use Data Files who required 5 days or longer of hospitalization and had an Injury Severity Score of 9 or greater were included. Multiple imputation with chained equations was used for observations with missing data. The frequencies of six HACs and five adverse outcomes were determined. Multivariable Poisson regression with log link and robust error variance was used to produce relative risk estimates, adjusting for patient-, hospital-, and injury-related factors. Risk-adjusted population attributable fractions estimates were derived for each HAC-outcome pair, with the adjusted population attributable fraction estimate for a given HAC-outcome pair representing the estimated percentage decrease in adverse outcome that would be expected if exposure to the HAC had been prevented.

RESULTS

A total of 529,856 patients requiring 5 days or longer of hospitalization were included. The incidences of HACs were as follows: pneumonia, 5.2%; urinary tract infection, 3.4%; venous thromboembolism, 3.3%; surgical site infection, 1.3%; pressure ulcer, 1.3%; and central line-associated blood stream infection, 0.2%. Pneumonia demonstrated the strongest association with in-hospital outcomes and resource utilization. Prevention of pneumonia in our cohort would have resulted in estimated reductions of the following: 22.1% for end organ dysfunction, 7.8% for mortality, 8.7% for prolonged hospitalization, 7.1% for prolonged intensive care unit stay, and 6.8% for need for mechanical ventilation. The impact of other HACs was comparatively small.

CONCLUSION

We describe a method for comparing the contributions of HACs to outcomes of hospitalized trauma patients. Our findings suggest that trauma program improvement efforts should prioritize pneumonia prevention.

LEVEL OF EVIDENCE

Therapeutic/Care Management; Level IV.

Pragmatic review of interventions to prevent inpatient hypoglycaemia

AIMS

This pragmatic review aimed to map and summarize the literature on model of care interventions to prevent inpatient hypoglycaemia. Model of care interventions were broadly defined as interventions that either directly target the workforce or where implementation had a strong workforce effect. The review intended to provide information for decision-makers in local health care settings regarding potential interventions to prevent inpatient hypoglycaemia in their local context.

METHODS

PubMed, Embase, CINAHL Plus and Scopus were systematically searched from 2009 to 2019 using key search terms for hypoglycaemia and hospital and evaluation. Included articles had to report an inpatient hypoglycaemia-related outcome. Interventions were categorized by intervention type and setting. Dysglycaemia outcomes were extracted (severe-hypoglycaemia, hypoglycaemia, hyperglycaemia and severe-hyperglycaemia).

RESULTS

Forty-nine articles were included in the review. Interventions were categorized as: services (n = 8), role expansion (n = 6), education (n = 9), audit and feedback (n = 1), alerts and reminders (n = 3), protocol implementation methods (n = 1), order sets (n = 6), insulin charts (n = 1) and electronic glycaemic management systems (n = 14). Twenty-one articles reported on ICU-specific interventions, and 28 on interventions in non-ICU-specific settings. Study designs were predominantly non-randomized (n = 40).

CONCLUSIONS

The review found positive evidence for a diverse range of evaluated interventions to prevent inpatient hypoglycaemia. Local decision-makers can use this review to identify interventions relevant to their local context. We suggest they evaluate those interventions using a decision analytic framework that combines the published evidence on effectiveness with local prevalence data to estimate the expected cost-effectiveness of the intervention options when implemented in their local context.

Hospital Outbreaks of Middle East Respiratory Syndrome, Daejeon, South Korea, 2015

From May through July 2015, a total of 26 cases of Middle East Respiratory Syndrome were reported from 2 hospitals in Daejeon, South Korea, including 1 index case and 25 new cases. We examined the epidemiologic features of these cases and found an estimated median incubation period of 6.1 days (8.8 days in hospital A and 4.6 days in hospital B). The overall attack rate was 3.7% (4.7% in hospital A and 3.0% in hospital B), and the attack rates among inpatients and caregivers in the same ward were 12.3% and 22.5%, respectively. The overall case-fatality rate was 44.0% (28.6% in hospital A and 63.6% in hospital B). The use of cohort quarantine may have played a role in preventing community spread, but additional transmission occurred among members of the hospital cohort quarantined together. Caregivers may have contributed in part to the transmission.

The Hospital-Acquired Conditions (HAC) reduction program: using cranberry treatment to reduce catheter-associated urinary tract infections and avoid Medicare payment reduction penalties

OBJECTIVE

The Affordable Care Act (ACA) established the Hospital-Acquired Condition (HAC) Reduction Program. The Centers for Medicare and Medicaid Services (CMS) established a total HAC scoring methodology to rank hospitals based upon their HAC performance. Hospitals that rank in the lowest quartile based on their HAC score are subject to a 1% reduction in their total Medicare reimbursements. In FY 2017, 769 hospitals incurred payment reductions totaling $430 million. This study analyzes how improvements in the rate of catheter-associated urinary tract infections (CAUTI), based on the implementation of a cranberry-treatment regimen, impact hospitals' HAC scores and likelihood of avoiding the Medicare-reimbursement penalty.

METHODS

A simulation model is developed and implemented using public data from the CMS' Hospital Compare website to determine how hospitals' unilateral and simultaneous adoption of cranberry to improve CAUTI outcomes can affect HAC scores and the likelihood of a hospital incurring the Medicare payment reduction, given results on cranberry effectiveness in preventing CAUTI based on scientific trials. The simulation framework can be adapted to consider other initiatives to improve hospitals' HAC scores.

RESULTS

Nearly all simulated hospitals improved their overall HAC score by adopting cranberry as a CAUTI preventative, assuming mean effectiveness from scientific trials. Many hospitals with HAC scores in the lowest quartile of the HAC-score distribution and subject to Medicare reimbursement reductions can improve their scores sufficiently through adopting a cranberry-treatment regimen to avoid payment reduction.

LIMITATIONS

The study was unable to replicate exactly the data used by CMS to establish HAC scores for FY 2018. The study assumes that hospitals subject to the Medicare payment reduction were not using cranberry as a prophylactic treatment for their catheterized patients, but is unable to confirm that this is true in all cases. The study also assumes that hospitalized catheter patients would be able to consume cranberry in either juice or capsule form, but this may not be true in 100% of cases.

CONCLUSION

Most hospitals can improve their HAC scores and many can avoid Medicare reimbursement reductions if they are able to attain a percentage reduction in CAUTI comparable to that documented for cranberry-treatment regimes in the existing literature.

Increased Adoption of Quality Improvement Interventions to Implement Evidence-Based Practices for Pressure Ulcer Prevention in U.S. Academic Medical Centers

OBJECTIVE

In 2008, the U.S. Centers for Medicare and Medicaid Services enacted a nonpayment policy for stage III and IV hospital-acquired pressure ulcers (HAPUs), which incentivized hospitals to improve prevention efforts. In response, hospitals looked for ways to support implementation of evidence-based practices for HAPU prevention, such as adoption of quality improvement (QI) interventions. The objective of this study was to quantify adoption patterns of QI interventions for supporting evidence-based practices for HAPU prevention.

METHODS

This study surveyed wound care specialists working at hospitals within the University HealthSystem Consortium. A questionnaire was used to retrospectively describe QI adoption patterns according to 25 HAPU-specific QI interventions into four domains: leadership, staff, information technology (IT), and performance and improvement. Respondents indicated QI interventions implemented between 2007 and 2012 to the nearest quarter and year. Descriptive statistics defined patterns of QI adoption. A t-test and statistical process control chart established statistically significant increase in adoption following nonpayment policy enactment in October 2008. Increase are described in terms of scope (number of QI domains employed) and scale (number of QI interventions within domains).

RESULTS

Fifty-three of the 55 hospitals surveyed reported implementing QI interventions for HAPU prevention. Leadership interventions were most frequent, increasing in scope from 40% to 63% between 2008 and 2012; "annual programs to promote pressure ulcer prevention" showed the greatest increase in scale. Staff interventions increased in scope from 32% to 53%; "frequent consult driven huddles" showed the greatest increase in scale. IT interventions increased in scope from 31% to 55%. Performance and improvement interventions increased in scope from 18% to 40%, with "new skin care products . . ." increasing the most.

LINKING EVIDENCE TO ACTION

Academic medical centers increased adoption of QI interventions following changes in nonpayment policy. These QI interventions supported adherence to implementation of pressure ulcer prevention protocols. Changes in payment policies for prevention are effective in QI efforts.

The impact of hospital-acquired conditions on Medicare program payments

RESEARCH OBJECTIVE

Hospital-acquired conditions, or HACs, often result in additional Medicare payments, generated during the initial hospitalization and in subsequent health care encounters. The purpose of this article is to estimate the incremental cost to Medicare, as measured by Medicare program payments, of six HACs.

STUDY DESIGN

The researchers used a matched case-control design to determine the incremental increase in Medicare payments attributable to each HAC. For each HAC patient, five comparison patients were matched on diagnosis group, sex, race, and age. Using the matched sample, we estimated a hospital fixed effects log-linear regression on total Medicare payments for the episode of care, further controlling for co-morbid conditions. Care episodes included the initial hospitalization and all inpatient, outpatient, physician, home health, and hospice care that occurred within 90 days of hospital discharge.

POPULATION STUDIED

All Medicare fee-for-service patients discharged alive from a hospital between October 2008 and June 2010 with one of six HACs-severe pressure ulcer, fracture, catheter-associated urinary tract infection, vascular catheter-associated infection, surgical site infection following certain orthopedic procedures, or deep vein thrombosis/ pulmonary embolism following certain orthopedic procedures-were included in the sample and matched to five similar patients without the HACs.

PRINCIPAL FINDINGS

The multivariate analysis suggests that Medicare paid an additional $146 million per year across these HAC care episodes compared with what would have been paid without the HACs.

CONCLUSIONS

HACs create a significant financial burden for the Medicare program. We compare the incremental Medicare payments for these six HACs to the current and upcoming Medicare HAC payment penalties.