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.

Prevalence and Correlates of Opioid-Involved Suicides in Maryland

OBJECTIVE

Involvement of opioids in suicides has doubled during the past two decades, worsening a major public health concern. This study examined the characteristics of opioid-involved suicides.

METHODS

The sample of decedents (N = 12,038) in Maryland between 2006 and 2020 was used to compare the characteristics of opioid-involved suicides (n = 947) with suicides not involving opioids (n = 6,896) and accidental opioid deaths (n = 4,125). Direct comparisons were then made between opioid-involved suicides with and without the additional presence of non-opioid substances.

RESULTS

Opioid-involved suicides were significantly more likely than suicides not involving opioids to occur among those aged 18-64 years, non-Hispanic Whites, and unemployed or disabled individuals. Opioid-involved suicides were more likely than accidental opioid deaths to occur among females, those aged <18 years, non-Hispanic Whites, and employed individuals. Of all suicides involved opioids, 45% involved other non-opioid substances. Polysubstance opioid suicides were significantly more likely than suicides involving opioids only to occur among non-Hispanic Whites.

CONCLUSIONS

Significant differences were observed in the demographic groups most at risk for opioid-involved suicide than other suicide or accidental opioid death. Among opioid-involved suicides, polysubstance involvement also represents a distinct group. These findings may enhance the targeting of prevention efforts.

Ownership and Interoperability Challenges of Alzheimer Monoclonal Antibody Registries

This Viewpoint addresses the challenges that the Centers for Medicare and Medicaid Services faces to collect real-world data on the effectiveness and safety of lecanemab from external registries to achieve its coverage with evidence development objectives.

Identifying Predictors of Nursing Home Admission by Using Electronic Health Records and Administrative Data: Scoping Review

Background

Among older adults, nursing home admissions (NHAs) are considered a significant adverse outcome and have been extensively studied. Although the volume and significance of electronic data sources are expanding, it is unclear what predictors of NHA have been systematically identified in the literature via electronic health records (EHRs) and administrative data.

Objective

This study synthesizes findings of recent literature on identifying predictors of NHA that are collected from administrative data or EHRs.

Methods

The PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines were used for study selection. The PubMed and CINAHL databases were used to retrieve the studies. Articles published between January 1, 2012, and March 31, 2023, were included.

Results

A total of 34 papers were selected for final inclusion in this review. In addition to NHA, all-cause mortality, hospitalization, and rehospitalization were frequently used as outcome measures. The most frequently used models for predicting NHAs were Cox proportional hazards models (studies: n=12, 35%), logistic regression models (studies: n=9, 26%), and a combination of both (studies: n=6, 18%). Several predictors were used in the NHA prediction models, which were further categorized into sociodemographic, caregiver support, health status, health use, and social service use factors. Only 5 (15%) studies used a validated frailty measure in their NHA prediction models.

Conclusions

NHA prediction tools based on EHRs or administrative data may assist clinicians, patients, and policy makers in making informed decisions and allocating public health resources. More research is needed to assess the value of various predictors and data sources in predicting NHAs and validating NHA prediction models externally.

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.

A risk identification model for detection of patients at risk of antidepressant discontinuation

Purpose

Between 30 and 68% of patients prematurely discontinue their antidepressant treatment, posing significant risks to patient safety and healthcare outcomes. Online healthcare forums have the potential to offer a rich and unique source of data, revealing dimensions of antidepressant discontinuation that may not be captured by conventional data sources.

Methods

We analyzed 891 patient narratives from the online healthcare forum, "askapatient.com," utilizing content analysis to create PsyRisk-a corpus highlighting the risk factors associated with antidepressant discontinuation. Leveraging PsyRisk, alongside PsyTAR [a publicly available corpus of adverse drug reactions (ADRs) related to antidepressants], we developed a machine learning-driven algorithm for proactive identification of patients at risk of abrupt antidepressant discontinuation.

Results

From the analyzed 891 patients, 232 reported antidepressant discontinuation. Among these patients, 92% experienced ADRs, and 72% found these reactions distressful, negatively affecting their daily activities. Approximately 26% of patients perceived the antidepressants as ineffective. Most reported ADRs were physiological (61%, 411/673), followed by cognitive (30%, 197/673), and psychological (28%, 188/673) ADRs. In our study, we employed a nested cross-validation strategy with an outer 5-fold cross-validation for model selection, and an inner 5-fold cross-validation for hyperparameter tuning. The performance of our risk identification algorithm, as assessed through this robust validation technique, yielded an AUC-ROC of 90.77 and an F1-score of 83.33. The most significant contributors to abrupt discontinuation were high perceived distress from ADRs and perceived ineffectiveness of the antidepressants.

Conclusion

The risk factors identified and the risk identification algorithm developed in this study have substantial potential for clinical application. They could assist healthcare professionals in identifying and managing patients with depression who are at risk of prematurely discontinuing their antidepressant treatment.

Health Disparities in Lapses in Diabetic Retinopathy Care

Objective

To develop a novel methodology to identify lapses in diabetic retinopathy care in electronic health records (EHRs) and evaluate health disparities by race and ethnicity.

Design

Retrospective cohort study.

Subjects

Adult patients with diabetes mellitus who were evaluated at the Wilmer Eye Institute from January 1, 2013 to April 2, 2022.

Methods

The methodology to identify lapses in care first identified diabetic retinopathy screening or treatment visits and then compared the providers' recommended follow-up timeframe with the patient's actual time to next encounter. The association of race and ethnicity with odds of lapses in care was evaluated using a mixed-effects logistic regression model controlling for age, sex, insurance, severity of diabetic retinopathy, presence of other retinal disorders, and glaucoma.

Main Outcome Measures

Lapses in diabetic retinopathy care.

Results

The methodology to identify diabetic retinopathy-related visits had a 95.0% (95% confidence interval, 93.0-96.6) sensitivity and 98.8% (98.1-99.3) specificity as compared with a gold standard grader. The methodology resulted in a 97.3% (96.2-98.4) sensitivity and 98.1% (97.3-98.9) specificity for detecting a follow-up recommendation, with an average error of -0.05 (-0.31 to 0.21) weeks in extracting the precise timeframe. A total of 39 561 patients with 91 104 office visits were included in the analysis. The average age was 61.4 years. More than 3 (77.6%) in 4 patients had a lapse in care. In multivariable analysis, non-Hispanic Black patients had 1.24 (1.19-1.30) odds and Hispanic patients had 1.26 (1.13-1.40) odds of ever having a lapse in care compared with non-Hispanic White patients (P < 0.001, respectively).

Conclusions

We have developed a reliable methodology for identifying lapses in diabetic retinopathy care that is tailored to a provider's recommended follow-up. Using this approach, we find that 3 in 4 patients experience a lapse in diabetic retinopathy care and that these rates are higher among non-Hispanic Black and Hispanic patients. Deploying this methodology in the EHR is one potential means by which to identify and mitigate lapses in critical ophthalmic care in patients with diabetes.

Financial Disclosures

Proprietary or commercial disclosure may be found after the references.

Trends and Patterns of Social History Data Collection Within an Electronic Health Record

There is increased acceptance that social and behavioral determinants of health (SBDH) impact health outcomes, but electronic health records (EHRs) are not always set up to capture the full range of SBDH variables in a systematic manner. The purpose of this study was to explore rates and trends of social history (SH) data collection-1 element of SBDH-in a structured portion of an EHR within a large academic integrated delivery system. EHR data for individuals with at least 1 visit in 2017 were included in this study. Completeness rates were calculated for how often SBDH variable was assessed and documented. Logistic regressions identified factors associated with assessment rates for each variable. A total of 44,166 study patients had at least 1 SH variable present. Tobacco use and alcohol use were the most frequently captured SH variables. Black individuals were more likely to have their alcohol use assessed (odds ratio [OR] 1.21) compared with White individuals, whereas White individuals were more likely to have their "smokeless tobacco use" assessed (OR 0.92). There were also differences between insurance types. Drug use was more likely to be assessed in the Medicaid population for individuals who were single (OR 0.95) compared with the commercial population (OR 1.05). SH variable assessment is inconsistent, which makes use of EHR data difficult to gain better understanding of the impact of SBDH on health outcomes. Standards and guidelines on how and why to collect SBDH information within the EHR are needed.

Measuring the geographic disparity of comorbidity in commercially insured individuals compared to the distribution of physicians in South Africa

Background

Measuring and addressing the disparity between access to healthcare resources and underlying health needs of populations is a prominent focus in health policy development. More recently, the fair distribution of healthcare resources among population subgroups have become an important indication of health inequities. Single disease outcomes are commonly used for healthcare resource allocations; however, leveraging population-level comorbidity measures for health disparity research has been limited. This study compares the geographical distribution of comorbidity and associated healthcare utilization among commercially insured individuals in South Africa (SA) relative to the distribution of physicians.

Methods

A retrospective, cross-sectional analysis was performed comparing the geographical distribution of comorbidity and physicians for 2.6 million commercially insured individuals over 2016–2017, stratified by geographical districts and population groups in SA. We applied the Johns Hopkins ACG® System across the claims data of a large health plan administrator to measure a comorbidity risk score for each individual. By aggregating individual scores, we determined the average healthcare resource need of individuals per district, known as the comorbidity index (CMI), to describe the disease burden per district. Linear regression models were constructed to test the relationship between CMI, age, gender, population group, and population density against physician density.

Results

Our results showed a tendency for physicians to practice in geographic areas with more insurance enrollees and not necessarily where disease burden may be highest. This was confirmed by a negative relationship between physician density and CMI for the overall population and for three of the four major population groups. Among the population groups, the Black African population had, on average, access to fewer physicians per capita than other population groups, before and after adjusting for confounding factors.

Conclusion

CMI is a novel measure for healthcare disparities research that considers both acute and chronic conditions contributing to current and future healthcare costs. Our study linked and compared the population-level geographical distribution of CMI to the distribution of physicians using routinely collected data. Our results could provide vital information towards the more equitable distribution of healthcare providers across population groups in SA, and to meet the healthcare needs of disadvantaged communities.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12875-022-01899-1.

Assessing the Racial and Socioeconomic Disparities in Postpartum Depression Using Population-Level Hospital Discharge Data: Longitudinal Retrospective Study

BACKGROUND

In the United States, >3.6 million deliveries occur annually. Among them, up to 20% (approximately 700,000) of women experience postpartum depression (PPD) according to the Centers for Disease Control and Prevention. Absence of accurate reporting and diagnosis has made phenotyping of patients with PPD difficult. Existing literature has shown that factors such as race, socioeconomic status, and history of substance abuse are associated with the differential risks of PPD. However, limited research has considered differential temporal associations with the outcome.

OBJECTIVE

This study aimed to estimate the disparities in the risk of PPD and time to diagnosis for patients of different racial and socioeconomic backgrounds.

METHODS

This is a longitudinal retrospective study using the statewide hospital discharge data from Maryland. We identified 160,066 individuals who had a hospital delivery from 2017 to 2019. We applied logistic regression and Cox regression to study the risk of PPD across racial and socioeconomic strata. Multinomial regression was used to estimate the risk of PPD at different postpartum stages.

RESULTS

The cumulative incidence of PPD diagnosis was highest for White patients (8779/65,028, 13.5%) and lowest for Asian and Pacific Islander patients (248/10,760, 2.3%). Compared with White patients, PPD diagnosis was less likely to occur for Black patients (odds ratio [OR] 0.31, 95% CI 0.30-0.33), Asian or Pacific Islander patients (OR 0.17, 95% CI 0.15-0.19), and Hispanic patients (OR 0.21, 95% CI 0.19-0.22). Similar findings were observed from the Cox regression analysis. Multinomial regression showed that compared with White patients, Black patients (relative risk 2.12, 95% CI 1.73-2.60) and Asian and Pacific Islander patients (relative risk 2.48, 95% CI 1.46-4.21) were more likely to be diagnosed with PPD after 8 weeks of delivery.

CONCLUSIONS

Compared with White patients, PPD diagnosis is less likely to occur in individuals of other races. We found disparate timing in PPD diagnosis across different racial groups and socioeconomic backgrounds. Our findings serve to enhance intervention strategies and policies for phenotyping patients at the highest risk of PPD and to highlight needs in data quality to support future work on racial disparities in PPD.

Assessing the Added Value of Vital Signs Extracted from Electronic Health Records in Healthcare Risk Adjustment Models

Purpose

Patient vital signs are related to specific health risks and outcomes but are underutilized in the prediction of health-care utilization and cost. To measure the added value of electronic health record (EHR) extracted Body Mass Index (BMI) and blood pressure (BP) values in improving healthcare risk and utilization predictions.

Patients and Methods

A sample of 12,820 adult outpatients from the Johns Hopkins Health System (JHHS) were identified between 2016 and 2017, having high data quality and recorded values for BMI and BP. We evaluated the added value of BMI and BP in predicting health-care utilization and cost through a retrospective cohort design. BMI, mean arterial pressure (MAP), systolic and diastolic BPs were summarized as annual aggregated values. Concurrent annual BMI and MAP changes were quantified as the difference between maximum and minimum recorded values. Model performance estimates consisted of repeated 10-fold cross validation, compared to base model point estimates for demographic and diagnostic, coded events: (1) patient age and sex, (2) age, sex, and the Charlson weighted index, (3) age, sex and the Johns Hopkins ACG system’s DxPM risk score.

Results

Both categorical BMI and BP were progressively indicative of disease comorbidity, but not uniformly related to health-care utilization or cost. Annual change in BMI and MAP improved predictions for most concurrent year outcomes when compared to base models.

Conclusion

When a healthcare system lacks relevant diagnostic or risk assessment information for a patient, vital signs may be useful for a simple estimation of disease risk, cost and utilization.

Challenges and Strategies for Patient Safety in Primary Care: A Qualitative Study

Although most health care occurs in the ambulatory setting, limited research examines how providers and patients think about and enact ambulatory patient safety. This multimethod qualitative study seeks to identify perceived challenges and strategies to improve ambulatory safety from the perspectives of clinicians, staff, and patients. Data included interviews (N = 101), focus groups (N = 65), and observations of safety processes (N = 79) collected from 10 patient-centered medical homes. Key safety issues included the lack of interoperability among health information systems, clinician-patient communication failures, and challenges with medication reconciliation. Commonly cited safety strategies leveraged health information systems or involved dedicated resources (eg, providing access to social workers). Patients also identified strategies not mentioned by clinicians, emphasizing the need for their involvement in developing safety solutions. This work provides insight into safety issues of greatest concern to clinicians, staff, and patients and strategies to improve safety in the ambulatory setting.

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.

Impact of Social Needs in Electronic Health Records and Claims on Health Care Utilization and Costs Risk-Adjustment Models Within Medicaid Population

Patients enrolled in Medicaid have significantly higher social needs (SNs) than others. Using claims and electronic health records (EHRs) data, managed care organizations (MCOs) could systemically identify high-risk patients with SNs and develop population health management interventions. Impact of SNs on models predicting health care utilization and costs was assessed. This retrospective study included claims and EHRs data on 39,267 patients younger than age 65 years who were continuously enrolled during 2018-2019 in a Medicaid-managed care plan. SN marker was developed suggesting presence of International Classification of Diseases, 10th revision codes in any of the 5 SN domains. Impact of SN marker was compared across demographic and 2 diagnosis-based (ie, Charlson and Adjusted Clinical Groups risk score) prediction models of emergency department (ED) visit and hospitalizations, and total, medical, and pharmacy costs. After combining data sources, prevalence of documented SN marker increased from 11% and 13% to 18% of the study population across claims, EHRs, and both combined, respectively. SN marker improved predictions of demographic models for all utilization and total costs outcomes (area under the curve [AUC] of ED model increased from 0.57 to 0.61 and R² of total cost model increased from 10.9 to 12.2). In both diagnosis-based models, adding SN marker marginally improved outcomes prediction (AUC of ED model increased from 0.65 to 0.66). This study demonstrated feasibility of using claims and EHRs data to systematically capture SNs and incorporate in prediction models that could enable MCOs and policy makers to adjust and develop effective population health interventions.

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.

Impact of social determinants of health on improving the LACE index for 30-day unplanned readmission prediction

Objective

Early and accurate prediction of patients at risk of readmission is key to reducing costs and improving outcomes. LACE is a widely used score to predict 30-day readmissions. We examine whether adding social determinants of health (SDOH) to LACE can improve its predictive performance.

Methods

This is a retrospective study that included all inpatient encounters in the state of Maryland in 2019. We constructed predictive models by fitting Logistic Regression (LR) on LACE and different sets of SDOH predictors. We used the area under the curve (AUC) to evaluate discrimination and SHapley Additive exPlanations values to assess feature importance.

Results

Our study population included 316 558 patients of whom 35 431 (11.19%) patients were readmitted after 30 days. Readmitted patients had more challenges with individual-level SDOH and were more likely to reside in communities with poor SDOH conditions. Adding a combination of individual and community-level SDOH improved LACE performance from AUC = 0.698 (95% CI [0.695–0.7]; ref) to AUC = 0.708 (95% CI [0.705–0.71]; P < .001). The increase in AUC was highest in black patients (+1.6), patients aged 65 years or older (+1.4), and male patients (+1.4).

Discussion

We demonstrated the value of SDOH in improving the LACE index. Further, the additional predictive value of SDOH on readmission risk varies by subpopulations. Vulnerable populations like black patients and the elderly are likely to benefit more from the inclusion of SDOH in readmission prediction.

Conclusion

These findings provide potential SDOH factors that health systems and policymakers can target to reduce overall readmissions.

Comparing and validating medication complexity from insurance claims against electronic health records

BACKGROUND: Patient effort to comply with complex medication instructions is known to be related to nonadherence and subsequent medical complications or health care costs. A widely used Medication Regimen Complexity Index (MRCI) has been used with electronic health records (EHRs) to identify patients who could benefit from pharmacist intervention. A similar claims-derived measure may be better suited for clinical decision support, since claims offer a more complete view of patient care and health utilization. OBJECTIVE: To define and validate a novel insurance claims-based medication complexity score (MCS) patterned after the widely used MRCI, derived from EHRs. METHODS: Insurance claims and EHR data were provided by HealthPartners (N = 54,988) (Bloomington, Minnesota) and The Johns Hopkins Health System (N = 28,589) (Baltimore, Maryland) for years 2013 and 2017, respectively. Yearly measures of medication complexity were developed for each patient and evaluated with one another using rank correlation within different clinical subgroupings. Indicators for the presence of individually complex prescriptions were also developed and assessed using exact agreement. Complexity measures were then correlated with select covariates to further validate the concordance between MCS and MRCI with respect to clinical metrics. These included demographic, comorbidity, and health care utilization markers. Prescribed medications in each system's EHR were coded using the previously validated MRCI weighting rules. Insurance claims for retail pharmacy medications were coded using our novel MCS, which closely followed MRCI scoring rules. RESULTS: EHR-based MRCI and claims-based MCS were significantly correlated with one another for most clinical subgroupings. Likewise, both measures were correlated with several covariates, including count of active medications and chronic conditions. The MCS was, in most cases, more associated with key health covariates than was MRCI, although both were consistently significant. We found that the highest correlation between MCS and MRCI is obtained with patients who have similar counts of pharmacy records between EHRs and claims (HealthPartners: P = 0.796; Johns Hopkins Health System: P = 0.779). CONCLUSIONS: The findings suggest good correspondence between MCS and MRCI and that claims data represent a useful resource for assessing medication complexity. Claims data also have major practical advantages, such as interoperability across health care systems, although they lack the detailed clinical context of EHRs. DISCLOSURES: The Johns Hopkins University holds the copyright to the Adjusted Clinical Groups (ACG) system and receives royalties from the global distribution of the ACG system. This revenue supports a portion of the authors' salary. No additional or external funding supported this work. The authors have no conflict of interest to disclose.

Comparing person-level matching algorithms to identify risk across disparate datasets among patients with a controlled substance prescription: retrospective analysis

Background

The opioid epidemic in the United States has precipitated a need for public health agencies to better understand risk factors associated with fatal overdoses. Matching person-level information stored in public health, medical, and human services datasets can enhance the understanding of opioid overdose risk factors and interventions.

Objective

This study compares approximate match versus exact match algorithms to link disparate datasets together for identifying persons at risk from an applied perspective.

Methods

This study used statewide prescription drug monitoring program (PDMP), arrest, and mortality data matched at the person-level using an approximate match and 2 exact match algorithms. Impact of matching was assessed by analyzing 3 independent concepts: (1) the prevalence of key risk indicators used by PDMP programs in practice, (2) the prevalence of arrests and fatal opioid overdose, and (3) the performance of a multivariate logistic regression for fatal opioid overdose. The PDMP key risk indicators included (1) multiple provider episodes (MPE), or patients with prescriptions from multiple prescribers and dispensers, (2) high morphine milligram equivalents (MMEs), which represents an opioid’s potency relative to morphine, and (3) overlapping opioid and benzodiazepine prescriptions.

Results

Prevalence of PDMP-based risk indicators were higher in the approximate match population for MPEs (n = 4893/1 859 445 [0.26%]) and overlapping opioid/benzodiazepines (n = 57 888/1 859 445 [4.71%]), but the exact-basic match population had the highest prevalence of individuals with high MMEs (n = 664/1 910 741 [3.11%]). Prevalence of arrests and deaths were highest for the approximate match population compared with the exact match populations. Model performance was comparable across the 3 matching algorithms (exact-basic validation area under the receiver operating characteristic curve [AUC]: 0.854; approximate validation AUC: 0.847; exact + zip validation AUC: 0.826) but resulted in different cutoff points balancing sensitivity and specificity.

Conclusions

Our study illustrates the specific tradeoffs of different matching methods. Further research should be performed to compare matching algorithms and its impact on the prevalence of key risk indicators in an applied setting that can improve understanding of risk within a population.

Improving the Prediction of Persistent High Healthcare Utilizers: Using an Ensemble Methodology

Background

A small proportion of high-need patients persistently use the bulk of health care services and incur disproportionate costs. Population health management (PHM) programs often refer to these patients as persistent high utilizers (PHUs). Accurate PHU prediction enables PHM programs to better align scarce health care resources with high-need PHUs while generally improving outcomes. While prior research in PHU prediction has shown promise, traditional regression methods used in these studies have yielded limited accuracy.

Objective

We are seeking to improve PHU predictions with an ensemble approach in a retrospective observational study design using insurance claim records.

Methods

We defined a PHU as a patient with health care costs in the top 20% of all patients for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in next 24 months. Our study population included 165,595 patients in the Johns Hopkins Health Care plan, with 8359 (5.1%) patients identified as PHUs in 2014 and 2015. We assessed the performance of several standalone machine learning methods and then an ensemble approach combining multiple models.

Results

The candidate ensemble with complement naïve Bayes and random forest layers produced increased sensitivity and positive predictive value (PPV; 49.0% and 50.3%, respectively) compared to logistic regression (46.8% and 46.1%, respectively).

Conclusions

Our results suggest that ensemble machine learning can improve prediction of care management needs. Improved PPV implies reduced incorrect referral of low-risk patients. With the improved sensitivity/PPV balance of this approach, resources may be directed more efficiently to patients needing them most.

Development and assessment of a natural language processing model to identify residential instability in electronic health records’ unstructured data: a comparison of 3 integrated healthcare delivery systems

Objective

To evaluate whether a natural language processing (NLP) algorithm could be adapted to extract, with acceptable validity, markers of residential instability (ie, homelessness and housing insecurity) from electronic health records (EHRs) of 3 healthcare systems.

Materials and methods

We included patients 18 years and older who received care at 1 of 3 healthcare systems from 2016 through 2020 and had at least 1 free-text note in the EHR during this period. We conducted the study independently; the NLP algorithm logic and method of validity assessment were identical across sites. The approach to the development of the gold standard for assessment of validity differed across sites. Using the EntityRuler module of spaCy 2.3 Python toolkit, we created a rule-based NLP system made up of expert-developed patterns indicating residential instability at the lead site and enriched the NLP system using insight gained from its application at the other 2 sites. We adapted the algorithm at each site then validated the algorithm using a split-sample approach. We assessed the performance of the algorithm by measures of positive predictive value (precision), sensitivity (recall), and specificity.

Results

The NLP algorithm performed with moderate precision (0.45, 0.73, and 1.0) at 3 sites. The sensitivity and specificity of the NLP algorithm varied across 3 sites (sensitivity: 0.68, 0.85, and 0.96; specificity: 0.69, 0.89, and 1.0).

Discussion

The performance of this NLP algorithm to identify residential instability in 3 different healthcare systems suggests the algorithm is generally valid and applicable in other healthcare systems with similar EHRs.

Conclusion

The NLP approach developed in this project is adaptable and can be modified to extract types of social needs other than residential instability from EHRs across different healthcare systems.

Ineligibility for and Refusal to Participate in Randomized Controlled Trials That Have Studied Impact on Suicide-Related Outcomes in the United States: A Meta-Analysis

Objective: Ineligibility for and refusal to participate in randomized controlled trials (RCTs) can potentially lead to unrepresentative study samples and limited generalizability of findings. We examined the rates of exclusion and refusal in RCTs that have studied impact on suicide-related outcomes in the US. Data Sources: PubMed, the Cochrane Library, the Campbell Collaboration Library of Systematic Reviews, CINAHL, PsycINFO, and Education Resources Information Center were searched from January 1990 to May 2020 using the terms (suicide prevention) AND (clinical trial). Study Selection: Of 8,403 studies retrieved, 36 RCTs assessing effectiveness on suicide-related outcomes in youth (≤ 25 years old) conducted in the US were included. Data Extraction: Study-level data were extracted by 2 independent investigators for a random-effects meta-analysis and meta-regression. Results: The study participants (N = 13,264) had a mean (SD) age of 14.87 (1.58) years and were 50% male, 23% African American, and 24% Hispanic. The exclusion rate was 36.4%, while the refusal rate was 25.5%. The exclusion rate was significantly higher in the studies excluding individuals not exceeding specified cutoff points of suicide screening tools (51.2%; adjusted linear coefficient [β] = 1.30, standard error [SE] = 0.15; P = .041) and individuals not meeting the age or school grade criterion (45.9%; β = 1.37, SE = 0.13; P = .005). Conclusions: The rates of exclusion and refusal in youth prevention interventions studying impact on suicide-related outcomes were not as high compared to the rates found in other mental and behavioral interventions. While there was strong racial/ethnic group representation in RCTs examining youth suicide-related outcomes, suicide severity and age limited eligibility.

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.

Assessment of structured data elements for social risk factors

OBJECTIVES

Computable social risk factor phenotypes derived from routinely collected structured electronic health record (EHR) or health information exchange (HIE) data may represent a feasible and robust approach to measuring social factors. This study convened an expert panel to identify and assess the quality of individual EHR and HIE structured data elements that could be used as components in future computable social risk factor phenotypes.

STUDY DESIGN

Technical expert panel.

METHODS

A 2-round Delphi technique included 17 experts with an in-depth knowledge of available EHR and/or HIE data. The first-round identification sessions followed a nominal group approach to generate candidate data elements that may relate to socioeconomics, cultural context, social relationships, and community context. In the second-round survey, panelists rated each data element according to overall data quality and likelihood of systematic differences in quality across populations (ie, bias).

RESULTS

Panelists identified a total of 89 structured data elements. About half of the data elements (n = 45) were related to socioeconomic characteristics. The panelists identified a diverse set of data elements. Elements used in reimbursement-related processes were generally rated as higher quality. Panelists noted that several data elements may be subject to implicit bias or reflect biased systems of care, which may limit their utility in measuring social factors.

CONCLUSIONS

Routinely collected structured data within EHR and HIE systems may reflect patient social risk factors. Identifying and assessing available data elements serves as a foundational step toward developing future computable social factor phenotypes.

Association of Implementation and Social Network Factors With Patient Safety Culture in Medical Homes: A Coincidence Analysis

OBJECTIVES

The patient-centered medical home (PCMH) may provide a key model for ambulatory patient safety. Our objective was to explore which PCMH and patient safety implementation and social network factors may be necessary or sufficient for higher patient safety culture.

METHODS

This was a cross-case analysis study in 25 diverse U.S. PCMHs. Data sources included interviews of a clinician and an administrator in each PCMH, surveys of clinicians and staff, and existing data on the PCMHs' characteristics. We used coincidence analysis, a novel method based on set theory and Boolean logic, to evaluate relationships between factors and the implementation outcome of patient safety culture.

RESULTS

The coincidence analysis identified 5 equally parsimonious solutions (4 factors), accounting for all practices with higher safety culture. Three solutions contained the same core minimally sufficient condition: the implementation factor leadership priority for patient safety and the social network factor reciprocity in advice-seeking network ties (advice-seeking relationships). This minimally sufficient condition had the highest coverage (5/7 practices scoring higher on the outcome) and best performance across solutions; all included leadership priority for patient safety. Other key factors included self-efficacy and job satisfaction and quality improvement climate. The most common factor whose absence was associated with the outcome was a well-functioning process for behavioral health.

CONCLUSIONS

Our findings suggest that PCMH safety culture is higher when clinicians and staff perceive that leadership prioritizes patient safety and when high reciprocity among staff exists. Interventions to improve patient safety should consider measuring and addressing these key factors.

OUP accepted manuscript

Objective

Health care providers increasingly rely upon predictive algorithms when making important treatment decisions, however, evidence indicates that these tools can lead to inequitable outcomes across racial and socio-economic groups. In this study, we introduce a bias evaluation checklist that allows model developers and health care providers a means to systematically appraise a model’s potential to introduce bias.

Materials and Methods

Our methods include developing a bias evaluation checklist, a scoping literature review to identify 30-day hospital readmission prediction models, and assessing the selected models using the checklist.

Results

We selected 4 models for evaluation: LACE, HOSPITAL, Johns Hopkins ACG, and HATRIX. Our assessment identified critical ways in which these algorithms can perpetuate health care inequalities. We found that LACE and HOSPITAL have the greatest potential for introducing bias, Johns Hopkins ACG has the most areas of uncertainty, and HATRIX has the fewest causes for concern.

Discussion

Our approach gives model developers and health care providers a practical and systematic method for evaluating bias in predictive models. Traditional bias identification methods do not elucidate sources of bias and are thus insufficient for mitigation efforts. With our checklist, bias can be addressed and eliminated before a model is fully developed or deployed.

Conclusion

The potential for algorithms to perpetuate biased outcomes is not isolated to readmission prediction models; rather, we believe our results have implications for predictive models across health care. We offer a systematic method for evaluating potential bias with sufficient flexibility to be utilized across models and applications.

A scoping review of knowledge authoring tools used for developing computerized clinical decision support systems

Objective

Clinical Knowledge Authoring Tools (CKATs) are integral to the computerized Clinical Decision Support (CDS) development life cycle. CKATs enable authors to generate accurate, complete, and reliable digital knowledge artifacts in a relatively efficient and affordable manner. This scoping review aims to compare knowledge authoring tools and derive the common features of CKATs.

Materials and Methods

We performed a keyword-based literature search, followed by a snowball search, to identify peer-reviewed publications describing the development or use of CKATs. We used PubMed and Embase search engines to perform the initial search (n = 1579). After removing duplicate articles, nonrelevant manuscripts, and not peer-reviewed publication, we identified 47 eligible studies describing 33 unique CKATs. The reviewed CKATs were further assessed, and salient characteristics were extracted and grouped as common CKAT features.

Results

Among the identified CKATs, 55% use an open source platform, 70% provide an application programming interface for CDS system integration, and 79% provide features to validate/test the knowledge. The majority of the reviewed CKATs describe the flow of information, offer a graphical user interface for knowledge authors, and provide intellisense coding features (94%, 97%, and 97%, respectively). The composed list of criteria for CKAT included topics such as simulating the clinical setting, validating the knowledge, standardized clinical models and vocabulary, and domain independence. None of the reviewed CKATs met all common criteria.

Conclusion

Our scoping review highlights the key specifications for a CKAT. The CKAT specification proposed in this review can guide CDS authors in developing more targeted CKATs.

Comparing the predictive value of screening to the use of electronic health record data for detecting future suicidal thoughts and behavior in an urban pediatric emergency department: A preliminary analysis

AIM

Brief screening and predictive modeling have garnered attention for utility at identifying individuals at risk of suicide. Although previous research has investigated these methods, little is known about how these methods compare against each other or work in combination in the pediatric population.

METHODS

Patients were aged 8-18 years old who presented from January 1, 2017, to June 30, 2019, to a Pediatric Emergency Department (PED). All patients were screened with the Ask Suicide Questionnaire (ASQ) as part of a universal screening approach. For all models, we used 5-fold cross-validation. We compared four models: Model 1 only included the ASQ; Model 2 included the ASQ and EHR data gathered at the time of ED visit (EHR data); Model 3 only included EHR data; and Model 4 included EHR data and a single item from the ASQ that asked about a lifetime history of suicide attempt. The main outcome was subsequent PED visit with suicide-related presenting problem within a 3-month follow-up period.

RESULTS

Of the N = 13,420 individuals, n = 141 had a subsequent suicide-related PED visit. Approximately 63% identified as Black. Results showed that a model based only on EHR data (Model 3) had an area under the curve (AUC) of 0.775 compared to the ASQ alone (Model 1), which had an AUC of 0.754. Combining screening and EHR data (Model 4) resulted in a 17.4% (absolute difference = 3.6%) improvement in sensitivity and 13.4% increase in AUC (absolute difference = 6.6%) compared to screening alone (Model 1).

CONCLUSION

Our findings show that predictive modeling based on EHR data is helpful either in the absence or as an addition to brief suicide screening. This is the first study to compare brief suicide screening to EHR-based predictive modeling and adds to our understanding of how best to identify youth at risk of suicidal thoughts and behaviors in clinical care settings.

Assessing the Added Value of Blood Pressure Information Derived from Electronic Health Records in Predicting Health Care Cost and Utilization

Health care providers are increasingly using clinical measures derived from electronic health records (EHRs) for risk stratification and predictive modeling. EHR-specific data elements such as prescriptions, laboratory results, and vital signs have been shown to improve risk prediction models. In this study, the value of EHR-based blood pressure (BP) values was assessed in predicting health care costs (ie, total, medical, and pharmacy) and key utilization end points (ie, hospitalization, emergency department use, and being among the highest utilizers). The study population included 37,451 patients of a large integrated delivery system in the mid-western United States with complete EHR data files, who were 18-64 years old, had continuous insurance at an affiliated health plan, and had eligible BP records. Both EHRs and insurance claims of the study population were used to extract the predictors (ie, demographics, diagnosis, and BP values) and outcomes (ie, costs and utilizations). Predictors were extracted from 2012 data, whereas concurrent and prospective outcomes were extracted from 2012 to 2013 data. Three base models (BMs) were constructed to predict each of the outcomes. The first BM no. 1 used demographics. The second BM no. 2 added the Charlson comorbidity index to BM no. 1, whereas the third BM no. 3 added the Adjusted Clinical Group Dx-PM case-mix score to BM no. 1. BP was specified as means, ranges, and classes. Adding BP ranges to BM no. 1 and BM no. 2 showed the greatest improvements when predicting costs and utilization. More specifically, adjusted R² and area under the curve of BM no. 2 improved by 32.9% and 14.1% when BP ranges were added to predict concurrent total cost and hospitalization, respectively. The effect of BP measures on improving the risk stratification models was diminished when predicting prospective outcomes after adding the measures to BM no. 3 (ie, the more comprehensive diagnostic model), specifically when represented as BP means. Given the increasing availability of BP information, this research suggests that these data should be integrated into provider-based population health analytic activities. Future research should focus on subpopulations that benefit the most from incorporating vital signs such as BP measures in risk stratification models.

Assessing the Value of Unsupervised Clustering in Predicting Persistent High Health Care Utilizers: Retrospective Analysis of Insurance Claims Data

BACKGROUND

A high proportion of health care services are persistently utilized by a small subpopulation of patients. To improve clinical outcomes while reducing costs and utilization, population health management programs often provide targeted interventions to patients who may become persistent high users/utilizers (PHUs). Enhanced prediction and management of PHUs can improve health care system efficiencies and improve the overall quality of patient care.

OBJECTIVE

The aim of this study was to detect key classes of diseases and medications among the study population and to assess the predictive value of these classes in identifying PHUs.

METHODS

This study was a retrospective analysis of insurance claims data of patients from the Johns Hopkins Health Care system. We defined a PHU as a patient incurring health care costs in the top 20% of all patients' costs for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in 2014-2015. We applied latent class analysis (LCA), an unsupervised clustering approach, to identify patient subgroups with similar diagnostic and medication patterns to differentiate variations in health care utilization across PHUs. Logistic regression models were then built to predict PHUs in the full population and in select subpopulations. Predictors included LCA membership probabilities, demographic covariates, and health utilization covariates. Predictive powers of the regression models were assessed and compared using standard metrics.

RESULTS

We identified 164,221 patients with continuous enrollment between 2013 and 2015. The mean study population age was 19.7 years, 55.9% were women, 3.3% had ≥1 hospitalization, and 19.1% had 10+ outpatient visits in 2013. A total of 8359 (5.09%) patients were identified as PHUs in both 2014 and 2015. The LCA performed optimally when assigning patients to four probability disease/medication classes. Given the feedback provided by clinical experts, we further divided the population into four diagnostic groups for sensitivity analysis: acute upper respiratory infection (URI) (n=53,232; 4.6% PHUs), mental health (n=34,456; 12.8% PHUs), otitis media (n=24,992; 4.5% PHUs), and musculoskeletal (n=24,799; 15.5% PHUs). For the regression models predicting PHUs in the full population, the F1-score classification metric was lower using a parsimonious model that included LCA categories (F1=38.62%) compared to that of a complex risk stratification model with a full set of predictors (F1=48.20%). However, the LCA-enabled simple models were comparable to the complex model when predicting PHUs in the mental health and musculoskeletal subpopulations (F1-scores of 48.69% and 48.15%, respectively). F1-scores were lower than that of the complex model when the LCA-enabled models were limited to the otitis media and acute URI subpopulations (45.77% and 43.05%, respectively).

CONCLUSIONS

Our study illustrates the value of LCA in identifying subgroups of patients with similar patterns of diagnoses and medications. Our results show that LCA-derived classes can simplify predictive models of PHUs without compromising predictive accuracy. Future studies should investigate the value of LCA-derived classes for predicting PHUs in other health care settings.

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.

Measuring the Value of a Practical Text Mining Approach to Identify Patients With Housing Issues in the Free-Text Notes in Electronic Health Record: Findings of a Retrospective Cohort Study

Introduction: Despite the growing efforts to standardize coding for social determinants of health (SDOH), they are infrequently captured in electronic health records (EHRs). Most SDOH variables are still captured in the unstructured fields (i.e., free-text) of EHRs. In this study we attempt to evaluate a practical text mining approach (i.e., advanced pattern matching techniques) in identifying phrases referring to housing issues, an important SDOH domain affecting value-based healthcare providers, using EHR of a large multispecialty medical group in the New England region, United States. To present how this approach would help the health systems to address the SDOH challenges of their patients we assess the demographic and clinical characteristics of patients with and without housing issues and briefly look into the patterns of healthcare utilization among the study population and for those with and without housing challenges.

Methods: We identified five categories of housing issues [i.e., homelessness current (HC), homelessness history (HH), homelessness addressed (HA), housing instability (HI), and building quality (BQ)] and developed several phrases addressing each one through collaboration with SDOH experts, consulting the literature, and reviewing existing coding standards. We developed pattern-matching algorithms (i.e., advanced regular expressions), and then applied them in the selected EHR. We assessed the text mining approach for recall (sensitivity) and precision (positive predictive value) after comparing the identified phrases with manually annotated free-text for different housing issues.

Results: The study dataset included EHR structured data for a total of 20,342 patients and 2,564,344 free-text clinical notes. The mean (SD) age in the study population was 75.96 (7.51). Additionally, 58.78% of the cohort were female. BQ and HI were the most frequent housing issues documented in EHR free-text notes and HH was the least frequent one. The regular expression methodology, when compared to manual annotation, had a high level of precision (positive predictive value) at phrase, note, and patient levels (96.36, 95.00, and 94.44%, respectively) across different categories of housing issues, but the recall (sensitivity) rate was relatively low (30.11, 32.20, and 41.46%, respectively).

Conclusion: Results of this study can be used to advance the research in this domain, to assess the potential value of EHR's free-text in identifying patients with a high risk of housing issues, to improve patient care and outcomes, and to eventually mitigate socioeconomic disparities across individuals and communities.

An exploratory data quality analysis of time series physiologic signals using a large-scale intensive care unit database

Physiological data, such as heart rate and blood pressure, are critical to clinical decision-making in the intensive care unit (ICU). Vital signs data, which are available from electronic health records, can be used to diagnose and predict important clinical outcomes; While there have been some reports on the data quality of nurse-verified vital sign data, little has been reported on the data quality of higher frequency time-series vital signs acquired in ICUs, that would enable such predictive modeling. In this study, we assessed the data quality issues, defined as the completeness, accuracy, and timeliness, of minute-by-minute time series vital signs data within the MIMIC-III data set, captured from 16009 patient-ICU stays and corresponding to 9410 unique adult patients. We measured data quality of four time-series vital signs data streams in the MIMIC-III data set: heart rate (HR), respiratory rate (RR), blood oxygen saturation (SpO2), and arterial blood pressure (ABP). Approximately, 30% of patient-ICU stays did not have at least 1 min of data during the time-frame of the ICU stay for HR, RR, and SpO2. The percentage of patient-ICU stays that did not have at least 1 min of ABP data was ∼56%. We observed ∼80% coverage of the total duration of the ICU stay for HR, RR, and SpO2. Finally, only 12.5%%, 9.9%, 7.5%, and 4.4% of ICU lengths of stay had ≥ 99% data available for HR, RR, SpO2, and ABP, respectively, that would meet the three data quality requirements we looked into in this study. Our findings on data completeness, accuracy, and timeliness have important implications for data scientists and informatics researchers who use time series vital signs data to develop predictive models of ICU outcomes.

Development of measurable criteria to identify and prioritize patients for inclusion in comprehensive medication management programs within primary care settings

BACKGROUND: Pharmacists optimize medication use and ensure the safe and effective delivery of pharmacotherapy to patients using comprehensive medication management (CMM). Identifying and prioritizing individual patients who will most likely benefit from CMM can be challenging. Health systems have far more candidates for CMM than there are clinical pharmacists to provide this service. Furthermore, current evidence lacks widely accepted standards or automated mechanisms for identifying patients who would likely benefit from a pharmacist consultation. Existing tools to prioritize patients for pharmacist review often require manual chart review by a pharmacist or other clinicians or data collection by patient survey. OBJECTIVES: To (1) create new medication risk markers for identifying and prioritizing patients within a population and (2) identify patients who met these new markers, assess their clinical characteristics, and compare them with criteria that are widely used for medication therapy management (MTM). METHODS: Along with published literature, a panel of subject matter experts informed the development of 3 medication risk markers. To assess the prevalence of markers developed, we used Multum, a medication database, for medication-level characteristics, and for patient-level characteristics, we used QuintilesIMS, an administrative claims database derived from health plans across the United States, with data for 1,541,873 eligible individuals from 2014-2015. We compared the health care costs, utilization, and medication gap among patients identified through MTM criteria (both broad and narrow, as these are provided as ranges) and our new medication management score markers. RESULTS: We developed 3 claims-derivable markers: (1) instances when a patient filled a medication with high complexity that could affect adherence, (2) instances where a patient filled a medication defined as costly within a therapeutic category that could affect access, and (3) instances when a patient filled a medication defined as risky that could increase incidence of adverse drug events. In the QuintilesIMS database, individuals with 2 new medication risk markers plus at least 3 conditions and more than $3,017 in medication costs when compared with individuals meeting narrow MTM eligibility criteria (≥ 8 medications, ≥ 3 conditions, and > $3,017 medication costs) had increased costs ($36,000 vs $26,100 total; $24,800 vs 21,400 medical; $11,300 vs $4,800 pharmacy); acute care utilization (0.328 vs 0.256 inpatient admissions and 0.627 vs 0.579 emergency department visits); and 1 or more gaps in medication adherence(41.5% vs 34.7%). CONCLUSIONS: We identified novel markers of medication use risk that can be determined using insurance claims and can be useful to identify patients for CMM programs and prioritize patients who would benefit from clinical pharmacist intervention. These markers were associated with higher costs, acute care utilization, and gaps in medication use compared with the overall population and within certain subgroups. Providing CMM to these patients may improve health system performance in relevant quality measures. Evaluation of CMM services delivered by a pharmacist using these markers requires further investigation. DISCLOSURES: No outside funding supported this study. All authors are Johns Hopkins employees. The Johns Hopkins University receives royalties for nonacademic use of software based on the Johns Hopkins Adjusted Clinical Group (ACG) methodology. Chang, Kitchen, Weiner, and Kharrazi receive a portion of their salary support from this revenue. The authors have no conflicts of interests relevant to this study.

Assessing the association between area deprivation index on COVID-19 prevalence: a contrast between rural and urban U.S. jurisdictions

BACKGROUND

The COVID-19 pandemic has impacted communities differentially, with poorer and minority populations being more adversely affected. Prior rural health research suggests such disparities may be exacerbated during the pandemic and in remote parts of the U.S.

OBJECTIVES

To understand the spread and impact of COVID-19 across the U.S., county level data for confirmed cases of COVID-19 were examined by Area Deprivation Index (ADI) and Metropolitan vs. Nonmetropolitan designations from the National Center for Health Statistics (NCHS). These designations were the basis for making comparisons between Urban and Rural jurisdictions.

METHOD

Kendall's Tau-B was used to compare effect sizes between jurisdictions on select ADI composites and well researched social determinants of health (SDH). Spearman coefficients and stratified Poisson modeling was used to explore the association between ADI and COVID-19 prevalence in the context of county designation.

RESULTS

Results show that the relationship between area deprivation and COVID-19 prevalence was positive and higher for rural counties, when compared to urban ones. Family income, property value and educational attainment were among the ADI component measures most correlated with prevalence, but this too differed between county type.

CONCLUSIONS

Though most Americans live in Metropolitan Areas, rural communities were found to be associated with a stronger relationship between deprivation and COVID-19 prevalence. Models predicting COVID-19 prevalence by ADI and county type reinforced this observation and may inform health policy decisions.

Play and Learn for Surgeons: A Serious Game to Educate Medical Residents in Uterine Artery Ligation Surgery

Objective: Postpartum hemorrhage (PPH) is a leading cause of maternal mortality. Surgical interventions, such as uterine artery ligation and utero-ovarian arteries ligation (UAL and UOAL), are considered as effective methods to control PPH. Owing to PPH's severe outcomes, various educational tools have been developed to train surgical residents. A potential educational medium for this purpose could be serious digital games. In this pilot study, we assessed the usability and effectiveness of a serious game to promote the surgical skills of UAL/UOAL among obstetrics and gynecology (OB/GYN) residents. Methods: We designed and developed the Play and Learn for Surgeons (PLS) game to train OB/GYN residents. We assessed and compared the usability challenges of PLS before and after revising the game. To assess the effectiveness of PLS, residents were allocated randomly in control and intervention groups. Surgical skills of the residents were assessed pre- and post-test using the Objective Structured Assessment of Technical Skills checklist. Setting: This pilot study took place at the OB/GYN wards of Omolbanin Hospital (Mashhad University of Medical Sciences) and Imam Ali Hospital (Zahedan University of Medical Sciences) in Iran. Participants: Thirteen subject matter experts (nine OB/GYN experts and four senior clinical assistants) participated in the user interface design and usability assessment of PLS. Total of 46 OB/GYN residents participated in the educational effectiveness analysis of PLS. All participants were female with mean ages of 40.6, 29.9 and 28.0 years for OB/GYN experts, assistants, and residents, accordingly. Results: All participants completed the study. PLS significantly improved the skills of residents for UAL (P-value = 0.018) and UOAL (P-value <0.001) procedures. Conclusion: Serious games can be an effective and affordable approach in training OB/GYN residents for UAL and UOAL procedures. Approval number: (# IR.MUMS.fm.REC.1396.345) Trial registration number: (# IRCT2017092436366N1).

Social and Behavioral Variables in the Electronic Health Record: A Path Forward to Increase Data Quality and Utility

PURPOSE

Social and behavioral determinants of health (SBDH) are important factors that affect the health of individuals but are not routinely captured in a structured and systematic manner in electronic health records (EHRs). The purpose of this study is to generate recommendations for systematic implementation of SBDH data collection in EHRs through (1) reviewing SBDH conceptual and theoretical frameworks and (2) eliciting stakeholder perspectives on barriers to and facilitators of using SBDH information in the EHR and priorities for data collection.

METHOD

The authors reviewed SBDH frameworks to identify key social and behavioral variables and conducted focus groups and interviews with 17 clinicians and researchers at Johns Hopkins Health System between March and May 2018. Transcripts were coded and common themes were extracted to understand the barriers to and facilitators of accessing SBDH information.

RESULTS

The authors found that although the frameworks agreed that SBDH affect health outcomes, the lack of model consensus complicates the development of specific recommendations for the prioritization of SBDH data collection. Study participants recognized the importance of SBDH information and individual health and agreed that patient-reported information should be captured, but clinicians and researchers cited different priorities for which variables are most important. For the few SBDH variables that are captured, participants reported that data were often incomplete, unclear, or inconsistent, affecting both researcher and clinician responses to SBDH barriers to health.

CONCLUSIONS

Health systems need to identify and prioritize the systematic implementation of collection of a high-impact but limited list of SBDH variables in the EHR. These variables should affect care and be amenable to change and collection should be integrated into clinical workflows. Improved data collection of SBDH variables can lead to a better understanding of how SBDH affect health outcomes and ways to better address underlying health disparities that need urgent action.

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.

Analysis of Social Media Discussions on (#)Diet by Blue, Red, and Swing States in the U.S

The relationship between political affiliations and diet-related discussions on social media has not been studied on a population level. This study used a cost- and -time effective framework to leverage, aggregate, and analyze data from social media. This paper enhances our understanding of diet-related discussions with respect to political orientations in U.S. states. This mixed methods study used computational methods to collect tweets containing "diet" or "#diet" shared in a year, identified tweets posted by U.S. Twitter users, disclosed topics of tweets, and compared democratic, republican, and swing states based on the weight of topics. A qualitative method was employed to code topics. We found 32 unique topics extracted from more than 800,000 tweets, including a wide range of themes, such as diet types and chronic conditions. Based on the comparative analysis of the topic weights, our results revealed a significant difference between democratic, republican, and swing states. The largest difference was detected between swing and democratic states, and the smallest difference was identified between swing and republican states. Our study provides initial insight on the association of potential political leanings with health (e.g., dietary behaviors). Our results show diet discussions differ depending on the political orientation of the state in which Twitter users reside. Understanding the correlation of dietary preferences based on political orientation can help develop targeted and effective health promotion, communication, and policymaking strategies.

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.

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.

Comparing the Predictive Effects of Patient Medication Adherence Indices in Electronic Health Record and Claims-Based Risk Stratification Models

Multiple indices are available to measure medication adherence behaviors. Medication adherence measures, however, have rarely been extracted from electronic health records (EHRs) for population-level risk predictions. This study assessed the value of medication adherence indices in improving predictive models of cost and hospitalization. This study included a 2-year retrospective cohort of patients younger than age 65 years with linked EHR and insurance claims data. Three medication adherence measures were calculated: medication regimen complexity index (MRCI), medication possession ratio (MPR), and prescription fill rate (PFR). The authors examined the effects of adding these measures to 3 predictive models of utilization: a demographics model, a conventional model (Charlson index), and an advanced diagnosis-based model. Models were trained using EHR and claims data. The study population had an overall MRCI, MPR, and PFR of 14.6 ± 17.8, .624 ± .310, and .810 ± .270, respectively. Adding MRCI and MPR to the demographic and the morbidity models using claims data improved forecasting of next-year hospitalization substantially (eg, AUC of the demographic model increased from .605 to .656 using MRCI). Nonetheless, such boosting effects were attenuated for the advanced diagnosis-based models. Although EHR models performed inferior to claims models, adding adherence indices improved EHR model performances at a larger scale (eg, adding MRCI increased AUC by 4.4% for the Charlson model using EHR data compared to 3.8% using claims). This study shows that medication adherence measures can modestly improve EHR- and claims-derived predictive models of cost and hospitalization in non-elderly patients; however, the improvements are minimal for advanced diagnosis-based models.

Identifying vulnerable older adult populations by contextualizing geriatric syndrome information in clinical notes of electronic health records

OBJECTIVE

Geriatric syndromes such as functional disability and lack of social support are often not encoded in electronic health records (EHRs), thus obscuring the identification of vulnerable older adults in need of additional medical and social services. In this study, we automatically identify vulnerable older adult patients with geriatric syndrome based on clinical notes extracted from an EHR system, and demonstrate how contextual information can improve the process.

MATERIALS AND METHODS

We propose a novel end-to-end neural architecture to identify sentences that contain geriatric syndromes. Our model learns a representation of the sentence and augments it with contextual information: surrounding sentences, the entire clinical document, and the diagnosis codes associated with the document. We trained our system on annotated notes from 85 patients, tuned the model on another 50 patients, and evaluated its performance on the rest, 50 patients.

RESULTS

Contextual information improved classification, with the most effective context coming from the surrounding sentences. At sentence level, our best performing model achieved a micro-F1 of 0.605, significantly outperforming context-free baselines. At patient level, our best model achieved a micro-F1 of 0.843.

DISCUSSION

Our solution can be used to expand the identification of vulnerable older adults with geriatric syndromes. Since functional and social factors are often not captured by diagnosis codes in EHRs, the automatic identification of the geriatric syndrome can reduce disparities by ensuring consistent care across the older adult population.

CONCLUSION

EHR free-text can be used to identify vulnerable older adults with a range of geriatric syndromes.

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.

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.