Assessing racial bias in healthcare predictive models: Practical lessons from an empirical evaluation of 30-day hospital readmission models.

OBJECTIVE: Despite increased availability of methodologies to identify algorithmic bias, the operationalization of bias evaluation for healthcare predictive models is still limited. Therefore, this study proposes a process for bias evaluation through an empirical assessment of common hospital readmission models. The process includes selecting bias measures, interpretation, determining disparity impact and potential mitigations. METHODS: This retrospective analysis evaluated racial bias of four common models predicting 30-day unplanned readmission (i.e., LACE Index, HOSPITAL Score, and the CMS readmission measure applied as is and retrained). The models were assessed using 2.4 million adult inpatient discharges in Maryland from 2016 to 2019. Fairness metrics that are model-agnostic, easy to compute, and interpretable were implemented and apprised to select the most appropriate bias measures. The impact of changing model's risk thresholds on these measures was further assessed to guide the selection of optimal thresholds to control and mitigate bias. RESULTS: Four bias measures were selected for the predictive task: zero-one-loss difference, false negative rate (FNR) parity, false positive rate (FPR) parity, and generalized entropy index. Based on these measures, the HOSPITAL score and the retrained CMS measure demonstrated the lowest racial bias. White patients showed a higher FNR while Black patients resulted in a higher FPR and zero-one-loss. As the models' risk threshold changed, trade-offs between models' fairness and overall performance were observed, and the assessment showed all models' default thresholds were reasonable for balancing accuracy and bias. CONCLUSIONS: This study proposes an Applied Framework to Assess Fairness of Predictive Models (AFAFPM) and demonstrates the process using 30-day hospital readmission model as the example. It suggests the feasibility of applying algorithmic bias assessment to determine optimized risk thresholds so that predictive models can be used more equitably and accurately. It is evident that a combination of qualitative and quantitative methods and a multidisciplinary team are necessary to identify, understand and respond to algorithm bias in real-world healthcare settings. Users should also apply multiple bias measures to ensure a more comprehensive, tailored, and balanced view. The results of bias measures, however, must be interpreted with caution and consider the larger operational, clinical, and policy context.

Evaluating Algorithmic Bias in 30-Day Hospital Readmission Models: Retrospective Analysis.

BACKGROUND: The adoption of predictive algorithms in health care comes with the potential for algorithmic bias, which could exacerbate existing disparities. Fairness metrics have been proposed to measure algorithmic bias, but their application to real-world tasks is limited. OBJECTIVE: This study aims to evaluate the algorithmic bias associated with the application of common 30-day hospital readmission models and assess the usefulness and interpretability of selected fairness metrics. METHODS: We used 10.6 million adult inpatient discharges from Maryland and Florida from 2016 to 2019 in this retrospective study. Models predicting 30-day hospital readmissions were evaluated: LACE Index, modified HOSPITAL score, and modified Centers for Medicare & Medicaid Services (CMS) readmission measure, which were applied as-is (using existing coefficients) and retrained (recalibrated with 50% of the data). Predictive performances and bias measures were evaluated for all, between Black and White populations, and between low- and other-income groups. Bias measures included the parity of false negative rate (FNR), false positive rate (FPR), 0-1 loss, and generalized entropy index. Racial bias represented by FNR and FPR differences was stratified to explore shifts in algorithmic bias in different populations. RESULTS: The retrained CMS model demonstrated the best predictive performance (area under the curve: 0.74 in Maryland and 0.68-0.70 in Florida), and the modified HOSPITAL score demonstrated the best calibration (Brier score: 0.16-0.19 in Maryland and 0.19-0.21 in Florida). Calibration was better in White (compared to Black) populations and other-income (compared to low-income) groups, and the area under the curve was higher or similar in the Black (compared to White) populations. The retrained CMS and modified HOSPITAL score had the lowest racial and income bias in Maryland. In Florida, both of these models overall had the lowest income bias and the modified HOSPITAL score showed the lowest racial bias. In both states, the White and higher-income populations showed a higher FNR, while the Black and low-income populations resulted in a higher FPR and a higher 0-1 loss. When stratified by hospital and population composition, these models demonstrated heterogeneous algorithmic bias in different contexts and populations. CONCLUSIONS: Caution must be taken when interpreting fairness measures' face value. A higher FNR or FPR could potentially reflect missed opportunities or wasted resources, but these measures could also reflect health care use patterns and gaps in care. Simply relying on the statistical notions of bias could obscure or underplay the causes of health disparity. The imperfect health data, analytic frameworks, and the underlying health systems must be carefully considered. Fairness measures can serve as a useful routine assessment to detect disparate model performances but are insufficient to inform mechanisms or policy changes. However, such an assessment is an important first step toward data-driven improvement to address existing health disparities.

Latent Class Analysis of Social Needs in Medicaid Population and Its Impact on Risk Adjustment Models.

BACKGROUND: A growing number of US states are implementing programs to address the social needs (SNs) of their Medicaid populations through managed care contracts. Incorporating SN might also improve risk adjustment methods used to reimburse Medicaid providers. OBJECTIVES: Identify classes of SN present within the Medicaid population and evaluate the performance improvement in risk adjustment models of health care utilization and cost after incorporating SN classes. RESEARCH DESIGN: A secondary analysis of Medicaid patients during the years 2018 and 2019. Latent class analysis (LCA) was used to identify SN classes. To evaluate the impact of SN classes on measures of hospitalization, emergency (ED) visits, and costs, logistic and linear regression modeling for concurrent and prospective years was used. Model performance was assessed before and after incorporating these SN classes to base models controlling for demographics and comorbidities. SUBJECTS: 262,325 Medicaid managed care program patients associated with a large urban academic medical center. RESULTS: 7.8% of the study population had at least one SN, with the most prevalent being related to safety (3.9%). Four classes of SN were determined to be optimal based on LCA, including stress-related needs, safety-related needs, access to health care-related needs, and socioeconomic status-related needs. The addition of SN classes improved the performance of concurrent base models' AUC (0.61 vs. 0.58 for predicting ED visits and 0.61 vs. 0.58 for projecting hospitalizations). CONCLUSIONS: Incorporating SN clusters significantly improved risk adjustment models of health care utilization and costs in the study population. Further investigation into the predictive value of SN for costs and utilization in different Medicaid populations is merited.

Assessing Patient and Community-Level Social Factors; The Synergistic Effect of Social Needs and Social Determinants of Health on Healthcare Utilization at a Multilevel Academic Healthcare System.

We investigated the role of both individual-level social needs and community-level social determinants of health (SDOH) in explaining emergency department (ED) utilization rates. We also assessed the potential synergies between the two levels of analysis and their combined effect on patterns of ED visits. We extracted electronic health record (EHR) data between July 2016 and June 2020 for 1,308,598 unique Maryland residents who received care at Johns Hopkins Health System, of which 28,937 (2.2%) patients had at least one documented social need. There was a negative correlation between median household income in a neighborhood with having a social need such as financial resource strain, food insecurity, and residential instability (correlation coefficient: -0.05, -0.01, and - 0.06, p = 0, respectively). In a multilevel model with random effects after adjusting for other factors, living in a more disadvantaged neighborhood was found to be significantly associated with ED utilization statewide and within Baltimore City (OR: 1.005, 95% CI: 1.003-1.007 and 1.020, 95% CI: 1.017-1.022, respectively). However, individual-level social needs appeared to enhance the statewide effect of living in a more disadvantaged neighborhood with the OR for the interaction term between social needs and SDOH being larger, and more positive, than SDOH alone (OR: 1.012, 95% CI: 1.011-1.014). No such moderation was found in Baltimore City. To our knowledge, this study is one of the first attempts by a major academic healthcare system to assess the combined impact of patient-level social needs in association with community-level SDOH on healthcare utilization and can serve as a baseline for future studies using EHR data linked to population-level data to assess such synergistic association.

Clinical, social, and policy factors in COVID-19 cases and deaths: methodological considerations for feature selection and modeling in county-level analyses.

BACKGROUND: There is a need to evaluate how the choice of time interval contributes to the lack of consistency of SDoH variables that appear as important to COVID-19 disease burden within an analysis for both case counts and death counts. METHODS: This study identified SDoH variables associated with U.S county-level COVID-19 cumulative case and death incidence for six different periods: the first 30, 60, 90, 120, 150, and 180 days since each county had COVID-19 one case per 10,000 residents. The set of SDoH variables were in the following domains: resource deprivation, access to care/health resources, population characteristics, traveling behavior, vulnerable populations, and health status. A generalized variance inflation factor (GVIF) analysis was used to identify variables with high multicollinearity. For each dependent variable, a separate model was built for each of the time periods. We used a mixed-effect generalized linear modeling of counts normalized per 100,000 population using negative binomial regression. We performed a Kolmogorov-Smirnov goodness of fit test, an outlier test, and a dispersion test for each model. Sensitivity analysis included altering the county start date to the day each county reached 10 COVID-19 cases per 10,000. RESULTS: Ninety-seven percent (3059/3140) of the counties were represented in the final analysis. Six features proved important for both the main and sensitivity analysis: adults-with-college-degree, days-sheltering-in-place-at-start, prior-seven-day-median-time-home, percent-black, percent-foreign-born, over-65-years-of-age, black-white-segregation, and days-since-pandemic-start. These variables belonged to the following categories: COVID-19 related, vulnerable populations, and population characteristics. Our diagnostic results show that across our outcomes, the models of the shorter time periods (30 days, 60 days, and 900 days) have a better fit. CONCLUSION: Our findings demonstrate that the set of SDoH features that are significant for COVID-19 outcomes varies based on the time from the start date of the pandemic and when COVID-19 was present in a county. These results could assist researchers with variable selection and inform decision makers when creating public health policy.

Examining Diurnal Differences in Multidisciplinary Care Teams at a Pediatric Trauma Center Using Electronic Health Record Data: Social Network Analysis.

BACKGROUND: The care of pediatric trauma patients is delivered by multidisciplinary care teams with high fluidity that may vary in composition and organization depending on the time of day. OBJECTIVE: This study aims to identify and describe diurnal variations in multidisciplinary care teams taking care of pediatric trauma patients using social network analysis on electronic health record (EHR) data. METHODS: Metadata of clinical activities were extracted from the EHR and processed into an event log, which was divided into 6 different event logs based on shift (day or night) and location (emergency department, pediatric intensive care unit, and floor). Social networks were constructed from each event log by creating an edge among the functional roles captured within a similar time interval during a shift. Overlapping communities were identified from the social networks. Day and night network structures for each care location were compared and validated via comparison with secondary analysis of qualitatively derived care team data, obtained through semistructured interviews; and member-checking interviews with clinicians. RESULTS: There were 413 encounters in the 1-year study period, with 65.9% (272/413) and 34.1% (141/413) beginning during day and night shifts, respectively. A single community was identified at all locations during the day and in the pediatric intensive care unit at night, whereas multiple communities corresponding to individual specialty services were identified in the emergency department and on the floor at night. Members of the trauma service belonged to all communities, suggesting that they were responsible for care coordination. Health care professionals found the networks to be largely accurate representations of the composition of the care teams and the interactions among them. CONCLUSIONS: Social network analysis was successfully used on EHR data to identify and describe diurnal differences in the composition and organization of multidisciplinary care teams at a pediatric trauma center.

A double-edged sword: The effects of social network ties on job satisfaction in primary care organizations.

BACKGROUND: Social ties between health care workers may be an important driver of job satisfaction; however, research on this topic is limited. PURPOSE: We used social network methods to collect data describing two types of social ties, (a) instrumental ties (i.e., exchange of advice that enables work) and (b) expressive ties (i.e., exchange of social support), and related those ties to workers' job satisfaction. METHODOLOGY: We surveyed 456 clinicians and staff at 23 primary care practices about their social networks and workplace attitudes. We used multivariable linear regression to estimate the relationship between an individual's job satisfaction and two network properties: (a) eigenvector centrality (a measure of the importance of an individual in a network) and (b) ego network density (a measure of the cohesiveness of an individual's network). We examined this relationship for both instrumental and expressive ties. RESULTS: Individuals who were more central in the expressive network were less satisfied in their job, b = -0.40 (0.19), p < .05, whereas individuals who had denser instrumental networks were more satisfied in their job, b = 0.49 (0.21), p < .05. CONCLUSION: Workplace relationships affect worker well-being. Centrality in an expressive network may require greater emotional labor, increasing workers' risk for job dissatisfaction. On the other hand, a dense instrumental network may promote job satisfaction by strengthening workers' access to full information, supporting competence and confidence. PRACTICE IMPLICATIONS: Efforts to increase job satisfaction should consider both the positive and negative effects of social networks on workers' sense of well-being.

Early relaxation of community mitigation policies and risk of COVID-19 resurgence in the United States.

This study aimed to assess the impact of coronavirus disease (COVID-19) prevalence in the United States in the week leading to the relaxation of the stay-at-home orders (SAH) on future prevalence across states that implemented different SAH policies. We used data on the number of confirmed COVID-19 cases as of August 21, 2020 on county level. We classified states into four groups based on the 7-day change in prevalence and the state's approach to SAH policy. The groups included: (1) High Change (19 states; 7-day prevalence change ≥50th percentile), (2) Low Change (19 states; 7-day prevalence change <50th percentile), (3) No SAH (11 states: did not adopt SAH order), and (4) No SAH End (2 states: did not relax SAH order). We performed regression modeling assessing the association between change in prevalence at the time of SAH order relaxation and COVID-19 prevalence days after the relaxation of SAH order for four selected groups. After adjusting for other factors, compared to the High Change group, counties in the Low Change group had 33.8 (per 100,000 population) fewer cases (standard error (SE): 19.8, p < 0.001) 7 days after the relaxation of SAH order and the difference was larger by time passing. On August 21, 2020, the No SAH End group had 383.1 fewer cases (per 100,000 population) than the High Change group (SE: 143.6, p < 0.01). A measured, evidence-based approach is required to safely relax the community mitigation strategies and practice phased-reopening of the country.

Behavioral Intentions to Use Patient Portals to Disclose HIV and Other Sexually Transmitted Infection Testing Histories with Sexual Partners Among U.S. Sexual Minority Men.

Disclosure of HIV and other sexually transmitted infection (HIV/STI) testing history to sexual partners is low among gay, bisexual, and other U.S. sexual minority men (SMM). Patient portals (PP) could increase HIV/STI testing history disclosure. This study estimated the predictive validity of the Enhancing Dyadic Communication (EDC) latent construct for perceived behavioral intentions to use PP for HIV/STI test disclosures. A randomized subset of SMM completed the Patient Portal Sexual Health Instrument as part of the 2018 American Men's Internet Survey. Multivariable logistic regression models estimated associations between EDC and intentions to use PP for test disclosures. Among a sample of 1,509 SMM aged 15 to 77 years, EDC was associated with intentions to use PP to disclose test history with main partners (aOR 2.17; 95% CI 1.90 to 2.47) and non-main partners (aOR 2.39; 95%CI 2.07 to 2.76). Assessing EDC could be useful in clinical settings for interventions encouraging patients to communicate with partners about testing.

RESUMEN: La divulgación del historial de pruebas del VIH y otras infecciones de transmisión sexual (VIH / ITS) a las parejas sexuales es baja entre los homosexuales, bisexuales y otros hombres de minorías sexuales (SMM) de EE. UU. Los portales de pacientes (PP) podrían aumentar la divulgación del historial de pruebas de VIH / ITS. Este estudio estimó la validez predictiva del constructo latente Mejora de la comunicación diádica (EDC) para las intenciones conductuales percibidas de usar PP para las revelaciones de pruebas de VIH / ITS. Un subconjunto aleatorio de SMM completó el Instrumento de salud sexual del portal para pacientes como parte de la Encuesta de Internet de hombres estadounidenses de 2018. Los modelos de regresión logística multivariable estimaron asociaciones entre EDC e intenciones de usar PP para divulgaciones de pruebas. Entre una muestra de 1.509 SMM de entre 15 y 77 años, la EDC se asoció con las intenciones de utilizar PP para revelar el historial de pruebas con los socios principales (ORa = 2,17; IC del 95% = 1,90 a 2,47) y socios no principales (ORa = 2,39; IC del 95% = 2,07 a 2,76). La evaluación de EDC podría ser útil en entornos clínicos para intervenciones que alienten a los pacientes a comunicarse con sus socios sobre las pruebas.

Differential impact of mitigation policies and socioeconomic status on COVID-19 prevalence and social distancing in the United States.

BACKGROUND: The spread of COVID-19 has highlighted the long-standing health inequalities across the U.S. as neighborhoods with fewer resources were associated with higher rates of COVID-19 transmission. Although the stay-at-home order was one of the most effective methods to contain its spread, residents in lower-income neighborhoods faced barriers to practicing social distancing. We aimed to quantify the differential impact of stay-at-home policy on COVID-19 transmission and residents' mobility across neighborhoods of different levels of socioeconomic disadvantage. METHODS: This was a comparative interrupted time-series analysis at the county level. We included 2087 counties from 38 states which both implemented and lifted the state-wide stay-at-home order. Every county was assigned to one of four equally-sized groups based on its levels of disadvantage, represented by the Area Deprivation Index. Prevalence of COVID-19 was calculated by dividing the daily number of cumulative confirmed COVID-19 cases by the number of residents from the 2010 Census. We used the Social Distancing Index (SDI), derived from the COVID-19 Impact Analysis Platform, to measure the mobility. For the evaluation of implementation, the observation started from Mar 1st 2020 to 1 day before lifting; and, for lifting, it ranged from 1 day after implementation to Jul 5th 2020. We calculated a comparative change of daily trends in COVID-19 prevalence and Social Distancing Index between counties with three highest disadvantage levels and those with the least level before and after the implementation and lifting of the stay-at-home order, separately. RESULTS: On both stay-at-home implementation and lifting dates, COVID-19 prevalence was much higher among counties with the highest or lowest disadvantage level, while mobility decreased as the disadvantage level increased. Mobility of the most disadvantaged counties was least impacted by stay-at-home implementation and relaxation compared to counties with the most resources; however, disadvantaged counties experienced the largest relative increase in COVID-19 infection after both stay-at-home implementation and relaxation. CONCLUSIONS: Neighborhoods with varying levels of socioeconomic disadvantage reacted differently to the implementation and relaxation of COVID-19 mitigation policies. Policymakers should consider investing more resources in disadvantaged counties as the pandemic may not stop until most neighborhoods have it under control.

Correction: Using the Patient Portal Sexual Health Instrument in Surveys and Patient Questionnaires Among Sexual Minority Men in the United States: Cross-sectional Psychometric Validation Study.

[This corrects the article DOI: 10.2196/18750.].

Using the Patient Portal Sexual Health Instrument in Surveys and Patient Questionnaires Among Sexual Minority Men in the United States: Cross-sectional Psychometric Validation Study.

BACKGROUND: Patient portal modules, including electronic personal health records, health education, and prescription refill ordering, may be leveraged to address the sexually transmitted infection (STI) burden, including HIV, among gay, bisexual, and other sexual minority men (SMM). Theoretical frameworks in the implementation sciences highlight examining constructs of innovation attributes and performance expectations as key determinants of behavioral intentions and the use of new web-based health technologies. However, behavioral intentions to use patient portals for HIV and other STI prevention and care among SMM is understudied. OBJECTIVE: The aim of this study is to develop a brief instrument for measuring attitudes focused on using patient portals for STI prevention and care among a nationwide sample of SMM. METHODS: A total of 12 items of the American Men's Internet Survey-Patient Portal Sexual Health Instrument (AMIS-PPSHI) were adapted from a previous study. Psychometric analyses of the AMIS-PPSHI items were conducted among a randomized subset of 2018 AMIS participants reporting web-based access to their health records (N=1375). Parallel analysis and inspection of eigenvalues in a principal component analysis (PCA) informed factor retention in exploratory factor analysis (EFA). After EFA, Cronbach α was used to examine the internal consistency of the scale and its subscales. Confirmatory factor analysis (CFA) was used to assess the goodness of fit of the final factor structure. We calculated the total AMIS-PPSHI scale scores for comparisons within group categories, including age, STI diagnosis history, recency of testing, serious mental illness, and anticipated health care stigma. RESULTS: The AMIS-PPSHI scale resulting from EFA consisted of 12 items and had good internal consistency (α=.84). The EFA suggested 3 subscales: sexual health engagement and awareness (α=.87), enhancing dyadic communication (α=.87), and managing sexual health care (α=.79). CFA demonstrated good fit in the 3-factor PPSHI structure: root mean square error of approximation=0.061, comparative fit index=0.964, Tucker-Lewis index=0.953, and standardized root mean square residual=0.041. The most notable differences were lower scores on the enhanced dyadic communication subscale among people living with HIV. CONCLUSIONS: PPSHI is a brief instrument with strong psychometric properties that may be adapted for use in large surveys and patient questionnaires in other settings. Scores demonstrate that patient portals are favorable web-based solutions to deliver health services focused on STI prevention and care among SMM in the United States. More attention is needed to address the privacy implications of interpersonal use of patient portals outside of traditional health settings among persons with HIV.

Performance of a Predictive Model versus Prescription-Based Thresholds in Identifying Patients at Risk of Fatal Opioid Overdose.

Background: Prescription Drug Monitoring Programs (PDMPs) collect controlled substance prescriptions dispensed within a state. Many PDMP programs perform targeted outreach (i.e., "unsolicited reporting") for patients who exceed numerical thresholds, however, the degree to which patients at highest risk of fatal opioid overdose are identified has not been compared with one another or with a predictive model. Methods: A retrospective analysis was performed using statewide PDMP data for Maryland residents aged 18 to 80 years with an opioid fill between April to June 2015. The outcome was opioid-related overdose death in 2015 or 2016. A multivariable logistic regression model and three PDMP thresholds were evaluated: (1) multiple provider episodes; (2) high daily average morphine milligram equivalents (MME); and (3) overlapping opioid and benzodiazepine prescriptions. Results: The validation cohort consisted of 170,433 individuals and 244 deaths. The predictive model captured more individuals who died (46.3% of total deaths) and had a higher death rate (7.12 per 1000) when the risk score cutoff (0.0030) was selected for a comparable size of high-risk individuals (n = 15,881) than those meeting the overlapping opioid/benzodiazepine prescriptions (n = 17,440; 33.2% of total deaths; 4.64 deaths per 1000) and high MME (n = 14,675; 24.6% of total deaths; 4.09 deaths per 1000) thresholds. Conclusions: The predictive model identified more individuals at risk of fatal opioid overdose as compared with PDMP thresholds commonly used for unsolicited reporting. PDMP programs could improve their targeting of unsolicited reports to reach more individuals at risk of overdose by using predictive models instead of simple threshold-based approaches.

Incidence and Geographic Distribution of Injuries Due to Falls Among Pediatric Communities of Maryland.

OBJECTIVES: Falls are the leading cause of pediatric injury and account for the majority of emergency department injury visits, costing US $5 billion in medical costs annually. Epidemiology of pediatric falls has primarily been studied at single hospital centers and has not been analyzed statewide. We assessed pediatric falls across Maryland and geographically mapped them by census tract and block group. METHODS: The study used Maryland Health Services Cost Review Commission discharge data to retrospectively analyze the demographics and cross-sectional incidence rates of fall injuries in Maryland from 2013 to 2015. Geographical clusters were calculated for pediatric falls in Maryland and Baltimore City. RESULTS: From 2013 to 2015, Maryland hospitals discharged 738,819 pediatric patients, of whom 77,113 had fall injuries. Falls were more prevalent among males (56%), white race (55%), and patients with public insurance (56%). Over this period, 2 children who presented with fall injuries died. The incidence of falls did not vary from 2013 (27,481 children) to 2014 (27,261) and 2015 (26,451). Mapping fall injuries across Maryland identified Baltimore City as the primary cluster and rural pockets as secondary clusters of high incidence rates. Baltimore City maps showed a stable high-incidence cluster in the southwest region across all 3 years. CONCLUSIONS: Pediatric fall injuries comprise a large volume of emergency department visits yet have a low mortality. Geographic mapping shows that fall incidence varies across the state and persists over time. Statewide geographic information can be used to focus resource management and target prevention strategies.

Internet Access, Social Risk Factors, and Web-Based Social Support Seeking Behavior: Assessing Correlates of the "Digital Divide" Across Neighborhoods in The State of Maryland.

We aimed to empirically measure the degree to which there is a "digital divide" in terms of access to the internet at the small-area community level within the State of Maryland and the City of Baltimore and to assess the relationship and association of this divide with community-level SDOH risk factors, community-based social service agency location, and web-mediated support service seeking behavior. To assess the socio-economic characteristics of the neighborhoods across the state, we calculated the Area Deprivation Index (ADI) using the U.S. Census, American Community Survey (5-year estimates) of 2017. To assess the digital divide, at the community level, we used the Federal Communications Commission (FCC) data on the number of residential fixed Internet access service connections. We assessed the availability of and web-based access to community-based social service agencies using data provided by the "Aunt Bertha" information platform. We performed community and regional level descriptive and special analyses for ADI social risk factors, connectivity, and both the availability of and web-based searches for community-based social services. To help assess potential neighborhood linked factors associated with the rates of web-based social services searches by individuals in need, we applied logistic regression using generalized estimating equation modeling. Baltimore City contained more disadvantaged neighborhoods compared to other areas in Maryland. In Baltimore City, 20.3% of neighborhoods (defined by census block groups) were disadvantaged with ADI at the 90th percentile while only 6.6% of block groups across Maryland were in this disadvantaged category. Across the State, more than half of all census tracts had 801-1000 households (per 1000 households) with internet subscription. In contrast, in Baltimore City about half of all census tracts had only 401-600 of the households (per 1000 households) with internet subscriptions. Most block groups in Maryland and Baltimore City lacked access to social services facilities (61% of block groups at the 90th percentile of disadvantage in Maryland and 61.3% of block groups at the 90th percentile of disadvantage in Baltimore City). After adjusting for other variables, a 1% increase in the ADI measure of social disadvantage, resulting in a 1.7% increase in the number of individuals seeking social services. While more work is needed, our findings support the premise that the digital divide is closely associated with other SDOH factors. The policymakers must propose policies to address the digital divide on a national level and also in disadvantaged communities experiencing the digital divide in addition to other SDOH challenges.

A method for measuring the effect of certified electronic health record technology on childhood immunization status scores among Medicaid managed care network providers.

OBJECTIVE: To provide a methodology for estimating the effect of U.S.-based Certified Electronic Health Records Technology (CEHRT) implemented by primary care physicians (PCPs) on a Healthcare Effectiveness Data and Information Set (HEDIS) measure for childhood immunization delivery. MATERIALS AND METHODS: This study integrates multiple health care administrative data sources from 2010 through 2014, analyzed through an interrupted time series design and a hierarchical Bayesian model. We compared managed care physicians using CEHRT to propensity-score matched comparisons from network physicians who did not adopt CEHRT. Inclusion criteria for physicians using CEHRT included attesting to the Childhood Immunization Status clinical quality measure in addition to meeting "Meaningful Use" (MU) during calendar year 2013. We used a first-presence patient attribution approach to develop provider-specific immunization scores. RESULTS: We evaluated 147 providers using CEHRT, with 147 propensity-score matched providers selected from a pool of 1253 PCPs practicing in Maryland. The estimate for change in odds of increasing immunization rates due to CEHRT was 1.2 (95% credible set, 0.88-1.73). DISCUSSION: We created a method for estimating immunization quality scores using Bayesian modeling. Our approach required linking separate administrative data sets, constructing a propensity-score matched cohort, and using first-presence, claims-based childhood visit information for patient attribution. In the absence of integrated data sets and precise and accurate patient attribution, this is a reusable method for researchers and health system administrators to estimate the impact of health information technology on individual, provider-level, process-based, though outcomes-focused, quality measures. CONCLUSION: This research has provided evidence for using Bayesian analysis of propensity-score matched provider populations to estimate the impact of CEHRT on outcomes-based quality measures such as childhood immunization delivery.

Healthcare Costs and Utilization among Patients Hospitalized for Malignant Pleural Effusion.

BACKGROUND: Malignant pleural effusion (MPE) poses a considerable healthcare burden, but little is known about trends in directly attributable hospital utilization. OBJECTIVE: We aimed to study national trends in healthcare utilization and outcomes among hospitalized MPE patients. METHODS: We analyzed adult hospitalizations attributable to MPE using the Healthcare Cost and Utilization Project - National Inpatient Sample (HCUP-NIS) databases from 2004, 2009, and 2014. Cases were included if MPE was coded as the principal admission diagnosis or if unspecified pleural effusion was coded as the principal admission diagnosis in the setting of metastatic cancer. Annual hospitalizations were estimated for the entire US hospital population using discharge weights. Length of stay (LOS), hospital charges, and hospital mortality were also estimated. RESULTS: We analyzed 92,034 hospital discharges spanning a decade (2004-2014). Yearly hospitalizations steadily decreased from 38,865 to 23,965 during this time frame, the mean LOS decreased from 7.7 to 6.3 days, and the adjusted hospital mortality decreased from 7.9 to 4.5% (p = 0.00 for all trend analyses). The number of pleurodesis procedures also decreased over time (p = 0.00). The mean inflation-adjusted charge per hospitalization rose from USD 41,252 to USD 56,951, but fewer hospitalizations drove the total annual charges down from USD 1.51 billion to USD 1.37 billion (p = 0.00 for both analyses). CONCLUSIONS: The burden of hospital-based resource utilization associated with MPE has decreased over time, with a reduction in attributable hospitalizations by one third in the span of 1 decade. Correspondingly, the number of inpatient pleurodesis procedures has decreased during this time frame.

Assessing the geographical distribution of comorbidity among commercially insured individuals in South Africa.

BACKGROUND: Comorbidities are strong predictors of current and future healthcare needs and costs; however, comorbidities are not evenly distributed geographically. A growing need has emerged for comorbidity surveillance that can inform decision-making. Comorbidity-derived risk scores are increasingly being used as valuable measures of individual health to describe and explain disease burden in populations. METHODS: This study assessed the geographical distribution of comorbidity and its associated financial implications among commercially insured individuals in South Africa (SA). A retrospective, cross-sectional analysis was performed comparing the geographical distribution of comorbidities for 2.6 million commercially insured individuals over 2016-2017, stratified by geographical districts in SA. We applied the Johns Hopkins ACG® System across the insurance claims data of a large health plan administrator in SA to measure comorbidity as a risk score for each individual. We aggregated individual risk scores to determine the average risk score per district, also known as the comorbidity index (CMI), to describe the overall disease burden of each district. RESULTS: We observed consistently high CMI scores in districts of the Free State and KwaZulu-Natal provinces for all population groups before and after age adjustment. Some areas exhibited almost 30% higher healthcare utilization after age adjustment. Districts in the Northern Cape and Limpopo provinces had the lowest CMI scores with 40% lower than expected healthcare utilization in some areas after age adjustment. CONCLUSIONS: Our results show underlying disparities in CMI at national, provincial, and district levels. Use of geo-level CMI scores, along with other social data affecting health outcomes, can enable public health departments to improve the management of disease burdens locally and nationally. Our results could also improve the identification of underserved individuals, hence bridging the gap between public health and population health management efforts.

A systematic approach for developing a corpus of patient reported adverse drug events: A case study for SSRI and SNRI medications.

"Psychiatric Treatment Adverse Reactions" (PsyTAR) corpus is an annotated corpus that has been developed using patients narrative data for psychiatric medications, particularly SSRIs (Selective Serotonin Reuptake Inhibitor) and SNRIs (Serotonin Norepinephrine Reuptake Inhibitor) medications. This corpus consists of three main components: sentence classification, entity identification, and entity normalization. We split the review posts into sentences and labeled them for presence of adverse drug reactions (ADRs) (2168 sentences), withdrawal symptoms (WDs) (438 sentences), sign/symptoms/illness (SSIs) (789 sentences), drug indications (517), drug effectiveness (EF) (1087 sentences), and drug infectiveness (INF) (337 sentences). In the entity identification phase, we identified and extracted ADRs (4813 mentions), WDs (590 mentions), SSIs (1219 mentions), and DIs (792). In the entity normalization phase, we mapped the identified entities to the corresponding concepts in both UMLS (918 unique concepts) and SNOMED CT (755 unique concepts). Four annotators double coded the sentences and the span of identified entities by strictly following guidelines rules developed for this study. We used the PsyTAR sentence classification component to automatically train a range of supervised machine learning classifiers to identifying text segments with the mentions of ADRs, WDs, DIs, SSIs, EF, and INF. SVMs classifiers had the highest performance with F-Score 0.90. We also measured performance of the cTAKES (clinical Text Analysis and Knowledge Extraction System) in identifying patients' expressions of ADRs and WDs with and without adding PsyTAR dictionary to the core dictionary of cTAKES. Augmenting cTAKES dictionary with PsyTAR improved the F-score cTAKES by 25%. The findings imply that PsyTAR has significant implications for text mining algorithms aimed to identify information about adverse drug events and drug effectiveness from patients' narratives data, by linking the patients' expressions of adverse drug events to medical standard vocabularies. The corpus is publicly available at Zolnoori et al. [30].

Methods for Evaluating Natural Experiments in Obesity: A Systematic Review.

Background: Given the obesity pandemic, rigorous methodological approaches, including natural experiments, are needed. Purpose: To identify studies that report effects of programs, policies, or built environment changes on obesity prevention and control and to describe their methods. Data Sources: PubMed, CINAHL, PsycINFO, and EconLit (January 2000 to August 2017). Study Selection: Natural experiments and experimental studies evaluating a program, policy, or built environment change in U.S. or non-U.S. populations by using measures of obesity or obesity-related health behaviors. Data Extraction: 2 reviewers serially extracted data on study design, population characteristics, data sources and linkages, measures, and analytic methods and independently evaluated risk of bias. Data Synthesis: 294 studies (188 U.S., 106 non-U.S.) were identified, including 156 natural experiments (53%), 118 experimental studies (40%), and 20 (7%) with unclear study design. Studies used 106 (71 U.S., 35 non-U.S.) data systems; 37% of the U.S. data systems were linked to another data source. For outcomes, 112 studies reported childhood weight and 32 adult weight; 152 had physical activity and 148 had dietary measures. For analysis, natural experiments most commonly used cross-sectional comparisons of exposed and unexposed groups (n = 55 [35%]). Most natural experiments had a high risk of bias, and 63% had weak handling of withdrawals and dropouts. Limitation: Outcomes restricted to obesity measures and health behaviors; inconsistent or unclear descriptions of natural experiment designs; and imperfect methods for assessing risk of bias in natural experiments. Conclusion: Many methodologically diverse natural experiments and experimental studies were identified that reported effects of U.S. and non-U.S. programs, policies, or built environment changes on obesity prevention and control. The findings reinforce the need for methodological and analytic advances that would strengthen evaluations of obesity prevention and control initiatives. Primary Funding Source: National Institutes of Health, Office of Disease Prevention, and Agency for Healthcare Research and Quality. (PROSPERO: CRD42017055750).