Early Changes in Billing and Notes After Evaluation and Management Guideline Change.

BACKGROUND: The American Medical Association updated guidance in 2021 for frequently used billing codes for outpatient evaluation and management (E/M) visits. The intent was to account for provider time outside of face-to-face encounters and to reduce onerous documentation requirements. OBJECTIVE: To analyze E/M visit use, documentation length, and time spent in the electronic health record (EHR) before and after the guideline change. DESIGN: Observational, retrospective, pre-post study. SETTING: U.S.-based ambulatory practices using the Epic Systems EHR. PARTICIPANTS: 303 547 advanced practice providers and physicians across 389 organizations. MEASUREMENTS: Data from September 2020 through April 2021 containing weekly provider-level E/M code and EHR use metadata were extracted from the Epic Signal database. We descriptively analyzed overall and specialty-specific changes in E/M visit use, note length, and time spent in the EHR before and after the new guidelines using provider-level paired t tests. RESULTS: Following the new guidelines, level 3 visits decreased by 2.41 percentage points (95% CI, -2.48 to -2.34 percentage points) to 38.5% of all E/M visits, a 5.9% relative decrease from fall 2020. Level 4 visits increased by 0.89 percentage points (CI, 0.82 to 0.96 percentage points) to 40.9% of E/M visits, a 2.2% relative increase. Level 5 visits (the highest acuity level) increased by 1.85 percentage points (CI, 1.81 to 1.89 percentage points) to 10.1% of E/M visits, a 22.6% relative increase. These changes varied by specialty. We found no meaningful changes in measures of note length or time spent in the EHR. LIMITATION: The Epic ambulatory client base may underrepresent smaller and independent practices. CONCLUSION: Immediate changes in E/M coding contrast with null findings for changes in both note length and EHR time. Provider organizations are positioned to respond more rapidly to billing process changes than to changes in care delivery and associated EHR use behaviors. Fully realizing the intended benefits of this guideline change will require more time, facilitation, and scaling of best practices that more directly address EHR documentation practices and associated burden. PRIMARY FUNDING SOURCE: None.

Using Machine Learning to Make Predictions in Patients Who Fall.

BACKGROUND: As the population ages, the incidence of traumatic falls has been increasing. We hypothesize that a machine learning algorithm can more accurately predict mortality after a fall compared with a standard logistic regression (LR) model based on immediately available admission data. Secondary objectives were to predict who would be discharged home and determine which variables had the largest effect on prediction. METHODS: All patients who were admitted for fall between 2012 and 2017 at our level 1 trauma center were reviewed. Fourteen variables describing patient demographics, injury characteristics, and physiology were collected at the time of admission and were used for prediction modeling. Algorithms assessed included LR, decision tree classifier (DTC), and random forest classifier (RFC). Area under the receiver operating characteristic curve (AUC) values were calculated for each algorithm for mortality and discharge to home. RESULTS: About 4725 patients met inclusion criteria. The mean age was 61 ± 20.5 y, Injury Severity Score 8 ± 7, length of stay 5.8 ± 7.6 d, intensive care unit length of stay 1.8± 5.2 d, and ventilator days 0.7 ± 4.2 d. The mortality rate was 3% and three times greater for elderly (aged 65 y and older) patients (5.0% versus 1.6%, P < 0.001). The AUC for predicting mortality for LR, DTC, and RFC was 0.78, 0.64, and 0.86, respectively. The AUC for predicting discharge to home for LR, DTC, and RFC was 0.72, 0.61, and 0.74, respectively. The top five variables that contribute to the prediction of mortality in descending order of importance are the Glasgow Coma Score (GCS) motor, GCS verbal, respiratory rate, GCS eye, and temperature. CONCLUSIONS: RFC can accurately predict mortality and discharge home after a fall. This predictive model can be implemented at the time of patient arrival and may help identify candidates for targeted intervention as well as improve prognostication and resource utilization.

Using State Data to Predict a Single Institution Mortality for Patients That Fall.

BACKGROUND: Falls are the most common cause of injury-related death for patients older than 45.  We hypothesized that a machine learning algorithm developed from state-level registry data could make accurate outcome predictions at a level 1 trauma hospital. METHODS: Data for all patients admitted for fall injury during 2009 - 2019 in the state of Pennsylvania were derived from the state trauma registry.  Thirteen variables that were immediately available upon patient arrival were used for prediction modeling.  Data for the test institution were withheld from model creation.  Algorithms assessed included logistic regression (LR), random forest (RF), and extreme gradient boost (XGB).  Model discrimination for mortality was assessed with area under the curve (AUC) for each algorithm at our level 1 trauma center. RESULTS: 180,284 patients met inclusion criteria.  The mean age was 69 years ± 18.5 years with a mortality rate of 4.0%.  The AUC for predicting mortality in patients that fall for LR, RF, and XGB were 0.797, 0.876, and 0.880, respectively.  The variables which contributed to the prediction in descending order of importance for XGB were respiratory rate, pulse, systolic blood pressure, ethnicity, weight, sex, age, temperature, Glasgow Coma Scale (GCS) eye, race, GCS voice, GCS motor, and blood alcohol level. CONCLUSIONS: An extreme gradient boost model developed using state-wide trauma data can accurately predict mortality after fall at a single center within the state.  This machine learning model can be implemented by local trauma systems within the state of Pennsylvania to identify patients injured by fall that require greater attention, transfer to a higher level of care, and higher resource allocation.

The Role of Behavioral Economics in Improving Cardiovascular Health Behaviors and Outcomes.

PURPOSE OF REVIEW: Behavioral economics represents a promising set of principles to inform the design of health-promoting interventions. Techniques from the field have the potential to increase quality of cardiovascular care given suboptimal rates of guideline-directed care delivery and patient adherence to optimal health behaviors across the spectrum of cardiovascular care delivery. RECENT FINDINGS: Cardiovascular health-promoting interventions have demonstrated success in using a wide array of principles from behavioral economics, including loss framing, social norms, and gamification. Such approaches are becoming increasingly sophisticated and focused on clinical cardiovascular outcomes in addition to health behaviors as a primary endpoint. Many approaches can be used to improve patient decisions remotely, which is particularly useful given the shift to virtual care in the context of the COVID-19 pandemic. Numerous applications for behavioral economics exist in the cardiovascular care delivery space, though more work is needed before we will have a full understanding of ways to best leverage such applications in each clinical context.

Age-related effect of cell death on fiber morphology and number in tongue muscle.

INTRODUCTION: Multiple pathways may exist for age-related tongue muscle degeneration. Cell death is one mechanism contributing to muscle atrophy and decreased function. We hypothesized with aging, apoptosis, and apoptotic regulators would be increased, and muscle fiber size and number would be reduced in extrinsic tongue muscles. METHODS: Cell death indices, expression of caspase-3 and Bcl-2, and measures of muscle morphology and number were determined in extrinsic tongue muscles of young and old rats. RESULTS: Significant increases in cell death, caspase-3, and Bcl-2 were observed in all extrinsic tongue muscles along with reductions in muscle fiber number in old rats. DISCUSSION: We demonstrated that apoptosis indices increase with age in lingual muscles and that alterations in apoptotic regulators may be associated with age-related degeneration in muscle fiber size and number. These observed apoptotic processes may be detrimental to muscle function, and may contribute to degradation of cranial functions with age. Muscle Nerve 57: E29-E37, 2018.

I had not time to make it shorter: an exploratory analysis of how physicians reduce note length and time in notes.

OBJECTIVE: We analyze observed reductions in physician note length and documentation time, 2 contributors to electronic health record (EHR) burden and burnout. MATERIALS AND METHODS: We used EHR metadata from January to May, 2021 for 130 079 ambulatory physician Epic users. We identified cohorts of physicians who decreased note length and/or documentation time and analyzed changes in their note composition. RESULTS: 37 857 physicians decreased either note length (n = 15 647), time in notes (n = 15 417), or both (n = 6793). Note length decreases were primarily attributable to reductions in copy/paste text (average relative change of -18.9%) and templated text (-17.2%). Note time decreases were primarily attributable to reductions in manual text (-27.3%) and increases in note content from other care team members (+21.1%). DISCUSSION: Organizations must consider priorities and tradeoffs in the distinct approaches needed to address different contributors to EHR burden. CONCLUSION: Future research should explore scalable burden-reduction initiatives responsive to both note bloat and documentation time.

Patient perspectives on technology-based approaches to social needs screening.

OBJECTIVES: Social determinants have an outsized impact on health outcomes. Given the increasing awareness of this impact and the adoption of alternative payment models that incentivize addressing social needs, expectations are growing that health systems will appropriately screen for patients' social needs. However, there is limited evidence on how patients would like their health systems to engage with them around these needs. Our objective was to understand patient perspectives on completing social needs screening through technology-based modalities. STUDY DESIGN: We performed a qualitative study with semistructured patient interviews from November 2021 to April 2022. METHODS: Patients were eligible for our health system's standardized social needs screening survey if they had not completed it in the past year and were scheduled for a nonacute primary care visit. Patients were selected for interview if they completed the survey via portal or tablet or if they were eligible for but did not complete the survey. Interviews were analyzed using an integrated approach. Domains, subdomains, and themes were identified. RESULTS: We completed interviews with 54 participants. Participants were broadly accepting of screening, and most were comfortable with portal or tablet-based screening. They were motivated to complete the screening and recognized the connection between social needs and health. Having a trusting relationship with their clinician and feeling that their information was private were noted by patients as important factors for process endorsement. CONCLUSIONS: This qualitative study provides insight into patient-centered approaches for identifying patients' social needs.

Training digital natives to transform healthcare: a 5-tiered approach for integrating clinical informatics into undergraduate medical education.

Expansive growth in the use of health information technology (HIT) has dramatically altered medicine without translating to fully realized improvements in healthcare delivery. Bridging this divide will require healthcare professionals with all levels of expertise in clinical informatics. However, due to scarce opportunities for exposure and training in informatics, medical students remain an underdeveloped source of potential informaticists. To address this gap, our institution developed and implemented a 5-tiered clinical informatics curriculum at the undergraduate medical education level: (1) a practical orientation to HIT for rising clerkship students; (2) an elective for junior students; (3) an elective for senior students; (4) a longitudinal area of concentration; and (5) a yearlong predoctoral fellowship in operational informatics at the health system level. Most students found these offerings valuable for their training and professional development. We share lessons and recommendations for medical schools and health systems looking to implement similar opportunities.

Novel Digital Technologies for Blood Pressure Monitoring and Hypertension Management.

PURPOSE OF REVIEW: Hypertension is common, impacting an estimated 108 million US adults, and deadly, responsible for the deaths of one in six adults annually. Optimal management includes frequent blood pressure monitoring and antihypertensive medication titration, but in the traditional office-based care delivery model, patients have their blood pressure measured only intermittently and in a way that is subject to misdiagnosis with white coat or masked hypertension. There is a growing opportunity to leverage our expanding repository of digital technology to reimagine hypertension care delivery. This paper reviews existing and emerging digital tools available for hypertension management, as well as behavioral economic insights that could supercharge their impact. RECENT FINDINGS: Digitally connected blood pressure monitors offer an alternative to office-based blood pressure monitoring. A number of cuffless blood pressure monitors are in development but require further validation before they can be deployed for widespread clinical use. Patient-facing hubs and applications offer a means to transmit blood pressure data to clinicians. Though artificial intelligence could allow for curation of this data, its clinical use for hypertension remains limited to assessing risk factors at this time. Finally, text-based and telemedicine platforms are increasingly being employed to translate hypertension data into clinical outcomes with promising results. SUMMARY: The digital management of hypertension shows potential as an avenue for increasing patient engagement and improving clinical efficiency and outcomes. It is important for clinicians to understand the benefits, limitations, and future directions of digital health to optimize management of hypertension.