Latent Class Analysis of Prescribing Behavior of Primary Care Physicians in the Veterans Health Administration.

BACKGROUND: Benzodiazepines, opioids, proton-pump inhibitors (PPIs), and antibiotics are frequently prescribed inappropriately by primary care physicians (PCPs), without sufficient consideration of alternative options or adverse effects. We hypothesized that distinct groups of PCPs could be identified based on their propensity to prescribe these medications. OBJECTIVE: To identify PCP groups based on their propensity to prescribe benzodiazepines, opioids, PPIs, and antibiotics, and patient and PCP characteristics associated with identified prescribing patterns. DESIGN: Retrospective cohort study using VA data and latent class regression analyses to identify prescribing patterns among PCPs and examine the association of patient and PCP characteristics with class membership. PARTICIPANTS: A total of 2524 full-time PCPs and their patient panels (n = 2,939,636 patients), from January 1, 2017, to December 31, 2018. MAIN MEASURES: We categorized PCPs based on prescribing volume quartiles for the four drug classes, based on total days' supply dispensed of each medication by the PCP to their patients (expressed as days' supply per 1000 panel patient-days). We used latent class analysis to group PCPs based on prescribing and used multinomial logistic regression to examine patient and PCP characteristics associated with latent class membership. KEY RESULTS: PCPs were categorized into four groups (latent classes): low intensity (23% of cohort), medium-intensity overall/high-intensity PPI (36%), medium-intensity overall/high-intensity opioid (20%), and high intensity (21%). PCPs in the high-intensity group were predominantly in the highest quartile of prescribers for all four drugs (68% in the highest quartile for benzodiazepine, 86% opioids, 64% PPIs, 62% antibiotics). High-intensity PCPs (vs. low intensity) were substantially less likely to be female (OR: 0.30, 95% CI: 0.21-0.42) or practice in the northeast versus other census regions (OR: 0.10, 95% CI: 0.06-0.17). CONCLUSIONS: VA PCPs can be classified into four clearly differentiated groups based on their prescribing of benzodiazepines, opioids, PPIs, and antibiotics, suggesting an underlying typology of prescribing. High-intensity PCPs were more likely to be male.

Predicting clinical outcomes among hospitalized COVID-19 patients using both local and published models.

BACKGROUND: Many models are published which predict outcomes in hospitalized COVID-19 patients. The generalizability of many is unknown. We evaluated the performance of selected models from the literature and our own models to predict outcomes in patients at our institution. METHODS: We searched the literature for models predicting outcomes in inpatients with COVID-19. We produced models of mortality or criticality (mortality or ICU admission) in a development cohort. We tested external models which provided sufficient information and our models using a test cohort of our most recent patients. The performance of models was compared using the area under the receiver operator curve (AUC). RESULTS: Our literature review yielded 41 papers. Of those, 8 were found to have sufficient documentation and concordance with features available in our cohort to implement in our test cohort. All models were from Chinese patients. One model predicted criticality and seven mortality. Tested against the test cohort, internal models had an AUC of 0.84 (0.74-0.94) for mortality and 0.83 (0.76-0.90) for criticality. The best external model had an AUC of 0.89 (0.82-0.96) using three variables, another an AUC of 0.84 (0.78-0.91) using ten variables. AUC's ranged from 0.68 to 0.89. On average, models tested were unable to produce predictions in 27% of patients due to missing lab data. CONCLUSION: Despite differences in pandemic timeline, race, and socio-cultural healthcare context some models derived in China performed well. For healthcare organizations considering implementation of an external model, concordance between the features used in the model and features available in their own patients may be important. Analysis of both local and external models should be done to help decide on what prediction method is used to provide clinical decision support to clinicians treating COVID-19 patients as well as what lab tests should be included in order sets.

Similar burden of type 2 diabetes among adult patients with sickle cell disease relative to African Americans in the U.S. population: a six-year population-based cohort analysis.

Conflicting evidence exists on the epidemiology of type 2 diabetes mellitus (T2DM) among patients with sickle cell disease (SCD). This study measured the prevalence, incidence and clinical outcomes associated with T2DM in a large US population of commercially-insured adults aged ≥20 years with SCD between 2009 and 2014. Among 7070 patients with SCD, the mean age (median) was 39 (37) years and 60·8% were female. The standardized prevalence of T2DM among patients with SCD showed a modest increase, from 15·7% to 16·5% (P trend = 0·026), and was comparable to African-American respondents to the National Health and Nutrition Examination Survey (18·2%). Over 17 024 person-years, the crude incidence rate for T2DM was 25·4 per 1000 person-years. Incident T2DM was associated with comorbid hypertension (hazard ratio [HR] = 1·45, 95% confidence interval [CI] 1·14-1·83), and dyslipidaemia (HR = 1·43, 95%CI 1·04-1·96). Compared to SCD patients without T2DM, more SCD patients with T2DM had diagnoses of nephropathy (28·0% vs. 9·5%; P < 0·001), neuropathy (17·7% vs. 5·2%; P < 0·001) and stroke (24·1% vs. 9·2%; P < 0·001). Prevalence of T2DM in SCD patients is similar to the general African American population with an increasing trend in recent years. These trends support routine screening for T2DM in aging patients with SCD, especially those with comorbid hypertension and/or dyslipidaemia.

Effect of Restriction of the Number of Concurrently Open Records in an Electronic Health Record on Wrong-Patient Order Errors: A Randomized Clinical Trial.

Importance: Recommendations in the United States suggest limiting the number of patient records displayed in an electronic health record (EHR) to 1 at a time, although little evidence supports this recommendation. Objective: To assess the risk of wrong-patient orders in an EHR configuration limiting clinicians to 1 record vs allowing up to 4 records opened concurrently. Design, Setting, and Participants: This randomized clinical trial included 3356 clinicians at a large health system in New York and was conducted from October 2015 to April 2017 in emergency department, inpatient, and outpatient settings. Interventions: Clinicians were randomly assigned in a 1:1 ratio to an EHR configuration limiting to 1 patient record open at a time (restricted; n = 1669) or allowing up to 4 records open concurrently (unrestricted; n = 1687). Main Outcomes and Measures: The unit of analysis was the order session, a series of orders placed by a clinician for a single patient. The primary outcome was order sessions that included 1 or more wrong-patient orders identified by the Wrong-Patient Retract-and-Reorder measure (an electronic query that identifies orders placed for a patient, retracted, and then reordered shortly thereafter by the same clinician for a different patient). Results: Among the 3356 clinicians who were randomized (mean [SD] age, 43.1 [12.5] years; mean [SD] experience at study site, 6.5 [6.0] years; 1894 females [56.4%]), all provided order data and were included in the analysis. The study included 12 140 298 orders, in 4 486 631 order sessions, placed for 543 490 patients. There was no significant difference in wrong-patient order sessions per 100 000 in the restricted vs unrestricted group, respectively, overall (90.7 vs 88.0; odds ratio [OR], 1.03 [95% CI, 0.90-1.20]; P = .60) or in any setting (ED: 157.8 vs 161.3, OR, 1.00 [95% CI, 0.83-1.20], P = .96; inpatient: 185.6 vs 185.1, OR, 0.99 [95% CI, 0.89-1.11]; P = .86; or outpatient: 7.9 vs 8.2, OR, 0.94 [95% CI, 0.70-1.28], P = .71). The effect did not differ among settings (P for interaction = .99). In the unrestricted group overall, 66.2% of the order sessions were completed with 1 record open, including 34.5% of ED, 53.7% of inpatient, and 83.4% of outpatient order sessions. Conclusions and Relevance: A strategy that limited clinicians to 1 EHR patient record open compared with a strategy that allowed up to 4 records open concurrently did not reduce the proportion of wrong-patient order errors. However, clinicians in the unrestricted group placed most orders with a single record open, limiting the power of the study to determine whether reducing the number of records open when placing orders reduces the risk of wrong-patient order errors. Trial Registration: clinicaltrials.gov Identifier: NCT02876588.

Measuring content overlap during handoff communication using distributional semantics: An exploratory study.

OBJECTIVE: We develop and evaluate a methodological approach to measure the degree and nature of overlap in handoff communication content within and across clinical professions. This extensible, exploratory approach relies on combining techniques from conversational analysis and distributional semantics. MATERIALS AND METHODS: We audio-recorded handoff communication of residents and nurses on the General Medicine floor of a large academic hospital (n=120 resident and n=120 nurse handoffs). We measured semantic similarity, a proxy for content overlap, between resident-resident and nurse-nurse communication using multiple steps: a qualitative conversational content analysis; an automated semantic similarity analysis using Reflective Random Indexing (RRI); and comparing semantic similarity generated by RRI analysis with human ratings of semantic similarity. RESULTS: There was significant association between the semantic similarity as computed by the RRI method and human rating (ρ=0.88). Based on the semantic similarity scores, content overlap was relatively higher for content related to patient active problems, assessment of active problems, patient-identifying information, past medical history, and medications/treatments. In contrast, content overlap was limited on content related to allergies, family-related information, code status, and anticipatory guidance. CONCLUSIONS: Our approach using RRI analysis provides new opportunities for characterizing the nature and degree of overlap in handoff communication. Although exploratory, this method provides a basis for identifying content that can be used for determining shared understanding across clinical professions. Additionally, this approach can inform the development of flexibly standardized handoff tools that reflect clinical content that are most appropriate for fostering shared understanding during transitions of care.

High number of newly initiated direct oral anticoagulant users switch to alternate anticoagulant therapy.

Real-world evidence focusing on medication switching patterns amongst direct oral anticoagulant (DOACs) has not been well studied. The objective of this study is to evaluate patterns of prescription switching in non-valvular atrial fibrillation (NVAF) patients initiated on a DOAC and previously naïve to anticoagulation (AC) therapy. Data was obtained from Truven Health MarketScan® Commercial and Medicare Supplemental database (2009-2013). AC naïve (those without prior anticoagulant use) NVAF patients initiated on a DOAC, with 6 months of continuous health plan enrollment before and after treatment initiation and maintained on continuous therapy for a minimum of 6 months were included. Of 34,022 AC naïve NVAF patients initiating a DOAC, 6613 (19.4%) patients switched from an index DOAC prescription to an alternate anticoagulant and 27,409 (80.6%) remained on the DOAC [age: 68.5 ± 11.7 vs. 67.1 ± 12.7 years, p < 0.001; males: 3781 (57.2%) vs. 17,160 (62.6%), p < 0.001]. Amongst those that switched medication, 3196 (48.3%) did so within the first 6 months of therapy. Overall, 2945 (44.5%) patients switched to warfarin, 2912 (44.0%) switched to another DOAC and 756 (11.4%) switched to an injectable anticoagulant. The highest proportion of patients switched from dabigatran to warfarin (N = 2320; 42.5%) or rivaroxaban (N = 2252; 41.3%). The median time to switch from the index DOAC to another DOAC was 309.5 days versus 118.0 days (p < 0.001) to switch to warfarin. In NVAF patients newly initiated on DOAC therapy, one in five patients switch to an alternate anticoagulant and one of every two patients do so within the first 6 months of therapy. Switching from an initial DOAC prescription to traditional anticoagulants occurs as frequently as switching to an alternate DOAC.

The Effectiveness of a Physician-Only and Physician-Patient Intervention on Colorectal Cancer Screening Discussions Between Providers and African American and Latino Patients.

BACKGROUND: Physician recommendation of colorectal cancer (CRC) screening is a critical facilitator of screening completion. Providing patients a choice of screening options may increase CRC screening completion, particularly among racial and ethnic minorities. OBJECTIVE: Our purpose was to assess the effectiveness of physician-only and physician-patient interventions on increasing rates of CRC screening discussions as compared to usual care. DESIGN: This study was quasi-experimental. Clinics were allocated to intervention or usual care; patients in intervention clinics were randomized to receipt of patient intervention. PARTICIPANTS: Patients aged 50 to 75 years, due for CRC screening, receiving care at either a federally qualified health care center or an academic health center participated in the study. INTERVENTION: Intervention physicians received continuous quality improvement and communication skills training. Intervention patients watched an educational video immediately before their appointment. MAIN MEASURES: Rates of patient-reported 1) CRC screening discussions, and 2) discussions of more than one screening test. KEY RESULTS: The physician-patient intervention (n = 167) resulted in higher rates of CRC screening discussions compared to both physician-only intervention (n = 183; 61.1 % vs.50.3 %, p = 0.008) and usual care (n = 153; 61.1 % vs. 34.0 % p = 0.03). More discussions of specific CRC screening tests and discussions of more than one test occurred in the intervention arms than in usual care (44.6 % vs. 22.9 %,p = 0.03) and (5.1 % vs. 2.0 %, p = 0.036), respectively, but discussion of more than one test was uncommon. Across all arms, 143 patients (28.4 %) reported discussion of colonoscopy only; 21 (4.2 %) reported discussion of both colonoscopy and stool tests. CONCLUSIONS: Compared to usual care and a physician-only intervention, a physician-patient intervention increased rates of CRC screening discussions, yet discussions overwhelmingly focused solely on colonoscopy. In underserved patient populations where access to colonoscopy may be limited, interventions encouraging discussions of both stool tests and colonoscopy may be needed.

Migration of patients between five urban teaching hospitals in Chicago.

To quantify the extent of patient sharing and inpatient care fragmentation among patients discharged from a cohort of Chicago hospitals. Admission and discharge dates and patient ZIP codes from 5 hospitals over 2 years were matched with an encryption algorithm. Admission to more than one hospital was considered fragmented care. The association between fragmentation and socio-economic variables using ZIP-code data from the 2000 US Census was measured. Using validation from one hospital, patient matching using encrypted identifiers had a sensitivity of 99.3 % and specificity of 100 %. The cohort contained 228,151 unique patients and 334,828 admissions. Roughly 2 % of the patients received fragmented care, accounting for 5.8 % of admissions and 6.4 % of hospital days. In 3 of 5 hospitals, and overall, the length of stay of patients with fragmented care was longer than those without. Fragmentation varied by hospital and was associated with the proportion of non-Caucasian persons, the proportion of residents whose income fell in the lowest quartile, and the proportion of residents with more children being raised by mothers alone in the zip code of the patient. Patients receiving fragmented care accounted for 6.4 % of hospital days. This percentage is a low estimate for our region, since not all regional hospitals participated, but high enough to suggest value in creating Health Information Exchange. Fragmentation varied by hospital, per capita income, race and proportion of single mother homes. This secure methodology and fragmentation analysis may prove useful for future analyses.

Lessons learned: Development of COVID-19 clinical staging models at a large urban research institution.

Background/Objective: The University of Illinois at Chicago (UIC), along with many academic institutions worldwide, made significant efforts to address the many challenges presented during the COVID-19 pandemic by developing clinical staging and predictive models. Data from patients with a clinical encounter at UIC from July 1, 2019 to March 30, 2022 were abstracted from the electronic health record and stored in the UIC Center for Clinical and Translational Science Clinical Research Data Warehouse, prior to data analysis. While we saw some success, there were many failures along the way. For this paper, we wanted to discuss some of these obstacles and many of the lessons learned from the journey. Methods: Principle investigators, research staff, and other project team members were invited to complete an anonymous Qualtrics survey to reflect on the project. The survey included open-ended questions centering on participants' opinions about the project, including whether project goals were met, project successes, project failures, and areas that could have been improved. We then identified themes among the results. Results: Nine project team members (out of 30 members contacted) completed the survey. The responders were anonymous. The survey responses were grouped into four key themes: Collaboration, Infrastructure, Data Acquisition/Validation, and Model Building. Conclusion: Through our COVID-19 research efforts, the team learned about our strengths and deficiencies. We continue to work to improve our research and data translation capabilities.

Pharmacist-guided pharmacogenetic service lowered warfarin-related hospitalizations.

Background: The authors aimed to assess outcomes with a pharmacogenetic (PGx)-informed, pharmacist-guided, personalized consult service for warfarin dosing. Methods: This retrospective cohort study included patients admitted with thromboembolic events. Eligible subjects received either PGx-informed (n = 389) or historical non-PGx pharmacist-guided warfarin dosing (Hx; n = 308) before hospital discharge. The composite of admission with bleeding or thromboembolic events over 90 days after the discharge was compared between the PGx and Hx groups. Results: The rate ratio (95% CI) of the composite of bleeding or thromboembolic admissions for PGx versus Hx was 0.32 (0.12-0.82). The estimated hazard ratio was 0.43 (0.16-1.12). Conclusion: A PGx-informed warfarin dosing service was associated with decreased bleeding and thromboembolic encounters.

Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs.

Deep learning (DL) models can harness electronic health records (EHRs) to predict diseases and extract radiologic findings for diagnosis. With ambulatory chest radiographs (CXRs) frequently ordered, we investigated detecting type 2 diabetes (T2D) by combining radiographic and EHR data using a DL model. Our model, developed from 271,065 CXRs and 160,244 patients, was tested on a prospective dataset of 9,943 CXRs. Here we show the model effectively detected T2D with a ROC AUC of 0.84 and a 16% prevalence. The algorithm flagged 1,381 cases (14%) as suspicious for T2D. External validation at a distinct institution yielded a ROC AUC of 0.77, with 5% of patients subsequently diagnosed with T2D. Explainable AI techniques revealed correlations between specific adiposity measures and high predictivity, suggesting CXRs' potential for enhanced T2D screening.

Improving the In-Hospital Mortality Prediction of Diabetes ICU Patients Using a Process Mining/Deep Learning Architecture.

Diabetes intensive care unit (ICU) patients are at increased risk of complications leading to in-hospital mortality. Assessing the likelihood of death is a challenging and time-consuming task due to a large number of influencing factors. Healthcare providers are interested in the detection of ICU patients at higher risk, such that risk factors can possibly be mitigated. While such severity scoring methods exist, they are commonly based on a snapshot of the health conditions of a patient during the ICU stay and do not specifically consider a patient's prior medical history. In this paper, a process mining/deep learning architecture is proposed to improve established severity scoring methods by incorporating the medical history of diabetes patients. First, health records of past hospital encounters are converted to event logs suitable for process mining. The event logs are then used to discover a process model that describes the past hospital encounters of patients. An adaptation of Decay Replay Mining is proposed to combine medical and demographic information with established severity scores to predict the in-hospital mortality of diabetes ICU patients. Significant performance improvements are demonstrated compared to established risk severity scoring methods and machine learning approaches using the Medical Information Mart for Intensive Care III dataset.

Telemedicine Readiness Across Medical Conditions in a US National Representative Sample of Older Adults.

Telemedicine has provided older adults the ability to seek care remotely during the coronavirus disease (COVID-19) pandemic. However, it is unclear how diverse medical conditions play a role in telemedicine uptake. A total of 3379 participants (≥65 years) were interviewed in 2018 as part of the National Health and Aging Trends Study. We assessed telemedicine readiness across multiple medical conditions. Most chronic medical conditions and mood symptoms were significantly associated with telemedicine unreadiness, for physical or technical reasons or both, while cancer, hypertension, and arthritis were significantly associated with telemedicine readiness. Our findings suggest that multiple medical conditions play a substantial role in telemedicine uptake among older adults in the US. Therefore, comorbidities should be taken into consideration when promoting and adopting telemedicine technologies among older adults.

Changing from mandatory to optional genotyping results in higher acceptance of pharmacist-guided warfarin dosing.

Aim: We evaluated the clinical acceptance and feasibility of a pharmacist-guided personalized consult service following its transition from a mandatory (mPGx) to optional (oPGx) CYP2C9/VKORC1/CYP4F2 genotyping for warfarin. Methods: A total of 1105 patients were included. Clinical acceptance and feasibility outcomes were analyzed using bivariate and multivariable analyses. Results: After transitioning to optional genotyping, genotype testing was still ordered in a large segment of the eligible population (52.1%). Physician acceptance of pharmacist-recommended doses improved from 83.9% (mPGx) to 86.6% (oPGx; OR: 1.3; 95% CI: 1.1-1.5; p = 0.01) with a shorter median genotype result turnaround time (oPGX: 23.6 h vs mPGX: 25.1 h; p < 0.01). Conclusion: Ordering of genotype testing and provider acceptance of dosing recommendations remained high after transitioning to optional genotyping.

Detecting Racial/Ethnic Health Disparities Using Deep Learning From Frontal Chest Radiography.

PURPOSE: The aim of this study was to assess racial/ethnic and socioeconomic disparities in the difference between atherosclerotic vascular disease prevalence measured by a multitask convolutional neural network (CNN) deep learning model using frontal chest radiographs (CXRs) and the prevalence reflected by administrative hierarchical condition category codes in two cohorts of patients with coronavirus disease 2019 (COVID-19). METHODS: A CNN model, previously published, was trained to predict atherosclerotic disease from ambulatory frontal CXRs. The model was then validated on two cohorts of patients with COVID-19: 814 ambulatory patients from a suburban location (presenting from March 14, 2020, to October 24, 2020, the internal ambulatory cohort) and 485 hospitalized patients from an inner-city location (hospitalized from March 14, 2020, to August 12, 2020, the external hospitalized cohort). The CNN model predictions were validated against electronic health record administrative codes in both cohorts and assessed using the area under the receiver operating characteristic curve (AUC). The CXRs from the ambulatory cohort were also reviewed by two board-certified radiologists and compared with the CNN-predicted values for the same cohort to produce a receiver operating characteristic curve and the AUC. The atherosclerosis diagnosis discrepancy, Δvasc, referring to the difference between the predicted value and presence or absence of the vascular disease HCC categorical code, was calculated. Linear regression was performed to determine the association of Δvasc with the covariates of age, sex, race/ethnicity, language preference, and social deprivation index. Logistic regression was used to look for an association between the presence of any hierarchical condition category codes with Δvasc and other covariates. RESULTS: The CNN prediction for vascular disease from frontal CXRs in the ambulatory cohort had an AUC of 0.85 (95% confidence interval, 0.82-0.89) and in the hospitalized cohort had an AUC of 0.69 (95% confidence interval, 0.64-0.75) against the electronic health record data. In the ambulatory cohort, the consensus radiologists' reading had an AUC of 0.89 (95% confidence interval, 0.86-0.92) relative to the CNN. Multivariate linear regression of Δvasc in the ambulatory cohort demonstrated significant negative associations with non-English-language preference (ß = -0.083, P < .05) and Black or Hispanic race/ethnicity (ß = -0.048, P < .05) and positive associations with age (ß = 0.005, P < .001) and sex (ß = 0.044, P < .05). For the hospitalized cohort, age was also significant (ß = 0.003, P < .01), as was social deprivation index (ß = 0.002, P < .05). The Δvasc variable (odds ratio [OR], 0.34), Black or Hispanic race/ethnicity (OR, 1.58), non-English-language preference (OR, 1.74), and site (OR, 0.22) were independent predictors of having one or more hierarchical condition category codes (P < .01 for all) in the combined patient cohort. CONCLUSIONS: A CNN model was predictive of aortic atherosclerosis in two cohorts (one ambulatory and one hospitalized) with COVID-19. The discrepancy between the CNN model and the administrative code, Δvasc, was associated with language preference in the ambulatory cohort; in the hospitalized cohort, this discrepancy was associated with social deprivation index. The absence of administrative code(s) was associated with Δvasc in the combined cohorts, suggesting that Δvasc is an independent predictor of health disparities. This may suggest that biomarkers extracted from routine imaging studies and compared with electronic health record data could play a role in enhancing value-based health care for traditionally underserved or disadvantaged patients for whom barriers to care exist.

Effect of Electronic Health Record Clinical Decision Support on Contextualization of Care: A Randomized Clinical Trial.

Importance: Contextualizing care is a process of incorporating information about the life circumstances and behavior of individual patients, termed contextual factors, into their plan of care. In 4 steps, clinicians recognize clues (termed contextual red flags), clinicians ask about them (probe for context), patients disclose contextual factors, and clinicians adapt care accordingly. The process is associated with a desired outcome resolution of the presenting contextual red flag. Objective: To determine whether contextualized clinical decision support (CDS) tools in the electronic health record (EHR) improve clinician contextual probing, attention to contextual factors in care planning, and the presentation of contextual red flags. Design, Setting, and Participants: This randomized clinical trial was performed at the primary care clinics of 2 academic medical centers with different EHR systems. Participants were adults 18 years or older consenting to audio record their visits and their physicians between September 6, 2018, and March 4, 2021. Patients were randomized to an intervention or a control group. Analyses were performed on an intention-to-treat basis. Interventions: Patients completed a previsit questionnaire that elicited contextual red flags and factors and appeared in the clinician's note template in a contextual care box. The EHR also culled red flags from the medical record, included them in the contextual care box, used passive and interruptive alerts, and proposed relevant orders. Main Outcomes and Measures: Proportion of contextual red flags noted at the index visit that resolved 6 months later (primary outcome), proportion of red flags probed (secondary outcome), and proportion of contextual factors addressed in the care plan by clinicians (secondary outcome), adjusted for study site and for multiple red flags and factors within a visit. Results: Four hundred fifty-two patients (291 women [65.1%]; mean [SD] age, 55.6 [15.1] years) completed encounters with 39 clinicians (23 women [59.0%]). Contextual red flags were not more likely to resolve in the intervention vs control group (adjusted odds ratio [aOR], 0.96 [95% CI, 0.57-1.63]). However, the intervention increased both contextual probing (aOR, 2.12 [95% CI, 1.14-3.93]) and contextualization of the care plan (aOR, 2.67 [95% CI, 1.32-5.41]), controlling for whether a factor was identified by probing or otherwise. Across study groups, contextualized care plans were more likely than noncontextualized plans to result in improvement in the presenting red flag (aOR, 2.13 [95% CI, 1.38-3.28]). Conclusions and Relevance: This randomized clinical trial found that contextualized CDS did not improve patients' outcomes but did increase contextualization of their care, suggesting that use of this technology could ultimately help improve outcomes. Trial Registration: ClinicalTrials.gov Identifier: NCT03244033.

Indication alerts to improve problem list documentation.

BACKGROUND: Problem lists represent an integral component of high-quality care. However, they are often inaccurate and incomplete. We studied the effects of alerts integrated into the inpatient and outpatient computerized provider order entry systems to assist in adding problems to the problem list when ordering medications that lacked a corresponding indication. METHODS: We analyzed medication orders from 2 healthcare systems that used an innovative indication alert. We collected data at site 1 between December 2018 and January 2020, and at site 2 between May and June 2021. We reviewed random samples of 100 charts from each site that had problems added in response to the alert. Outcomes were: (1) alert yield, the proportion of triggered alerts that led to a problem added and (2) problem accuracy, the proportion of problems placed that were accurate by chart review. RESULTS: Alerts were triggered 131 134, and 6178 times at sites 1 and 2, respectively, resulting in a yield of 109 055 (83.2%) and 2874 (46.5%), P< .001. Orders were abandoned, for example, not completed, in 11.1% and 9.6% of orders, respectively, P<.001. Of the 100 sample problems, reviewers deemed 88% ± 3% and 91% ± 3% to be accurate, respectively, P = .65, with a mean of 90% ± 2%. CONCLUSIONS: Indication alerts triggered by medication orders initiated in the absence of a justifying diagnosis were useful for populating problem lists, with yields of 83.2% and 46.5% at 2 healthcare systems. Problems were placed with a reasonable level of accuracy, with 90% ± 2% of problems deemed accurate based on chart review.

Validation of a deep learning, value-based care model to predict mortality and comorbidities from chest radiographs in COVID-19.

We validate a deep learning model predicting comorbidities from frontal chest radiographs (CXRs) in patients with coronavirus disease 2019 (COVID-19) and compare the model's performance with hierarchical condition category (HCC) and mortality outcomes in COVID-19. The model was trained and tested on 14,121 ambulatory frontal CXRs from 2010 to 2019 at a single institution, modeling select comorbidities using the value-based Medicare Advantage HCC Risk Adjustment Model. Sex, age, HCC codes, and risk adjustment factor (RAF) score were used. The model was validated on frontal CXRs from 413 ambulatory patients with COVID-19 (internal cohort) and on initial frontal CXRs from 487 COVID-19 hospitalized patients (external cohort). The discriminatory ability of the model was assessed using receiver operating characteristic (ROC) curves compared to the HCC data from electronic health records, and predicted age and RAF score were compared using correlation coefficient and absolute mean error. The model predictions were used as covariables in logistic regression models to evaluate the prediction of mortality in the external cohort. Predicted comorbidities from frontal CXRs, including diabetes with chronic complications, obesity, congestive heart failure, arrhythmias, vascular disease, and chronic obstructive pulmonary disease, had a total area under ROC curve (AUC) of 0.85 (95% CI: 0.85-0.86). The ROC AUC of predicted mortality for the model was 0.84 (95% CI,0.79-0.88) for the combined cohorts. This model using only frontal CXRs predicted select comorbidities and RAF score in both internal ambulatory and external hospitalized COVID-19 cohorts and was discriminatory of mortality, supporting its potential use in clinical decision making.