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.

Integrating E-Prescribing and Pharmacy Claims Data for Predictive Modeling: Comparing Costs and Utilization of Health Plan Members Who Fill Their Initial Medications with Those Who Do Not.

BACKGROUND: Nonfilling of prescribed medications is a worldwide problem of serious concern. Studies of health care costs and utilization associated with medication nonadherence frequently rely on claims data and usually focus on patients with specific conditions. Past studies also have little agreement on whether higher medication costs associated with higher adherence can reduce downstream health care consumption. OBJECTIVES: To (a) compare the characteristics between people with and without complete medication initiations from a general population and (b) quantify the effect of medication initiation on health care utilization and expenditures with propensity score weighting. METHODS: We conducted a retrospective cohort study using 2012 and 2013 electronic health records (EHR) and insurance claims data from an integrated health care delivery network. We included 43,097 eligible primary care patients in the study. Annual medication fill rates of initial prescriptions in 2012 were defined as the number of filled prescriptions from claims divided by the number of e-prescriptions from EHRs, while excluding all refills. A claim was considered filled if (a) EHR and claims records were from the same drug class; (b) claims occurred between the date of a current EHR order and that of the next EHR order of the same class; and (c) the maximum fill rate was 100%. The 6 annual outcomes included total costs, medical costs, pharmacy costs, being a high-cost "outlier" (in top 5%), having 1 or more hospitalizations, and having 1 or more emergency department (ED) visits. Individuals were classified as either having completed all medication initiations (100% annual filling rate for initiations) or not. We used propensity score weighting to control for baseline differences between complete and incomplete initial fillers. We adopted linear and logistic regressions to model costs and binary utilization indicators for the same year (concurrently) and next year (prospectively). RESULTS: Approximately 42% of the study sample had complete medication initiations (100% filling rate), while the remaining 58% had incomplete initiations. Individuals who fully filled initial prescriptions had lower comorbidity burden and consumed fewer health care resources. After applying propensity score weighting and controlling for variables such as the number of prescription orders, patients with complete medication initiations had lower overall and medical costs, concurrently and prospectively (e.g., $751 and $252 less for annual total costs). Complete medication initiation fillers were also less likely to have concurrent health care utilization (OR = 0.78, 95% CI = 0.68-0.90 for hospitalization; OR = 0.77, 95% CI = 0.72-0.82 for ED admissions) but no difference in prospective utilization other than for ED visits (OR = 0.93, 95% CI = 0.87-0.99). CONCLUSIONS: Identifying the subpopulation of patients with incomplete medication initiations (i.e., filling less than 100% of initial prescriptions) is a pragmatic approach for population health management programs to align resources and potentially contain cost and utilization. DISCLOSURES: No outside funding supported this study. This study applied the Adjusted Clinical Group (ACG) case-mix/risk adjustment methodology, developed at Johns Hopkins Bloomberg School of Public Health. Although ACGs are an important aspect of this study, the goal of the study was not to directly assess or evaluate the methodology. The Johns Hopkins University receives royalties for nonacademic use of software based on the ACG methodology. Chang, Kharrazi, and Weiner receive a portion of their salary support from this revenue. Chang is also a part-time consultant for Monument Analytics, a health care consultancy whose clients include the life sciences industry, as well as plaintiffs in opioid litigation. Alexander is past Chair of FDA's Peripheral and Central Nervous System Advisory Committee; has served as a paid advisor to IQVIA; is a co-founding Principal and equity holder in Monument Analytics; and is a member of OptumRx's National P&T Committee. These arrangements have been reviewed and approved by Johns Hopkins University in accordance with its conflict of interest policies. The other authors have nothing to disclose.

Integrating social and behavioral determinants of health into patient care and population health at Veterans Health Administration: a conceptual framework and an assessment of available individual and population level data sources and evidence-based measurements.

The premise of this project was that social and behavioral determinants of health (SBDH) affect the use of healthcare services and outcomes for patients in an integrated healthcare system such as the Veterans Health Administration (VHA), and thus individual patient level socio-behavioral factors in addition to the neighborhood characteristics and geographically linked factors could add information beyond medical factors mostly considered in clinical decision making, patient care, and population health. To help VHA better address SBDH risk factors for the veterans it cares for within its primary care clinics, we proposed a conceptual and analytic framework, a set of evidence-based measures, and their data source. The framework and recommended SBDH metrics can provide a road map for other primary care-centric healthcare organizations wishing to use health analytic tools to better understand how SBDH affect health outcomes.

Assessing the Impact of Body Mass Index Information on the Performance of Risk Adjustment Models in Predicting Health Care Costs and Utilization.

BACKGROUND: Using electronic health records (EHRs) for population risk stratification has gained attention in recent years. Compared with insurance claims, EHRs offer novel data types (eg, vital signs) that can potentially improve population-based predictive models of cost and utilization. OBJECTIVE: To evaluate whether EHR-extracted body mass index (BMI) improves the performance of diagnosis-based models to predict concurrent and prospective health care costs and utilization. METHODS: We used claims and EHR data over a 2-year period from a cohort of continuously insured patients (aged 20-64 y) within an integrated health system. We examined the addition of BMI to 3 diagnosis-based models of increasing comprehensiveness (ie, demographics, Charlson, and Dx-PM model of the Adjusted Clinical Group system) to predict concurrent and prospective costs and utilization, and compared the performance of models with and without BMI. RESULTS: The study population included 59,849 patients, 57% female, with BMI class I, II, and III comprising 19%, 9%, and 6% of the population. Among demographic models, R improvement from adding BMI ranged from 61% (ie, R increased from 0.56 to 0.90) for prospective pharmacy cost to 29% (1.24-1.60) for concurrent medical cost. Adding BMI to demographic models improved the prediction of all binary service-linked outcomes (ie, hospitalization, emergency department admission, and being in top 5% total costs) with area under the curve increasing from 2% (0.602-0.617) to 7% (0.516-0.554). Adding BMI to Charlson models only improved total and medical cost predictions prospectively (13% and 15%; 4.23-4.79 and 3.30-3.79), and also improved predicting all prospective outcomes with area under the curve increasing from 3% (0.649-0.668) to 4% (0.639-0.665; and, 0.556-0.576). No improvements in prediction were seen in the most comprehensive model (ie, Dx-PM). DISCUSSION: EHR-extracted BMI levels can be used to enhance predictive models of utilization especially if comprehensive diagnostic data are missing.

Assessing markers from ambulatory laboratory tests for predicting high-risk patients.

OBJECTIVES: This exploratory study used outpatient laboratory test results from electronic health records (EHRs) for patient risk assessment and evaluated whether risk markers based on laboratory results improve the performance of diagnosis- and pharmacy-based predictive models for healthcare outcomes. STUDY DESIGN: Observational study of a patient cohort over 2 years. METHODS: We used administrative claims and EHR data over a 2-year period for a population of continuously insured patients in an integrated health system who had at least 1 ambulatory visit during the first year. We performed regression tree analyses to develop risk markers from frequently ordered outpatient laboratory tests. We added these risk markers to demographic and Charlson Comorbidity Index models and 3 models from the Johns Hopkins Adjusted Clinical Groups system to predict individual cost, inpatient admission, and high-cost patients. We evaluated the predictive and discriminatory performance of 5 lab-enhanced models. RESULTS: Our study population included 120,844 patients. Adding laboratory markers to base models improved R2 predictions of costs by 0.1% to 3.7%, identification of high-cost patients by 3.4% to 121%, and identification of patients with inpatient admissions by 1.0% to 188% for the demographic model. The addition of laboratory risk markers to comprehensive risk models, compared with simpler models, resulted in smaller improvements in predictive power. CONCLUSIONS: The addition of laboratory risk markers can significantly improve the identification of high-risk patients using models that include age, gender, and a limited number of morbidities; however, models that use comprehensive risk measures may be only marginally improved.

Patient sharing among physicians and costs of care: a network analytic approach to care coordination using claims data.

BACKGROUND: Improving care coordination is a national priority and a key focus of health care reforms. However, its measurement and ultimate achievement is challenging. OBJECTIVE: To test whether patients whose providers frequently share patients with one another-what we term 'care density'-tend to have lower costs of care and likelihood of hospitalization. DESIGN: Cohort study PARTICIPANTS: 9,596 patients with congestive heart failure (CHF) and 52,688 with diabetes who received care during 2009. Patients were enrolled in five large, private insurance plans across the US covering employer-sponsored and Medicare Advantage enrollees MAIN MEASURES: Costs of care, rates of hospitalizations KEY RESULTS: The average total annual health care cost for patients with CHF was $29,456, and $14,921 for those with diabetes. In risk adjusted analyses, patients with the highest tertile of care density, indicating the highest level of overlap among a patient's providers, had lower total costs compared to patients in the lowest tertile ($3,310 lower for CHF and $1,502 lower for diabetes, p < 0.001). Lower inpatient costs and rates of hospitalization were found for patients with CHF and diabetes with the highest care density. Additionally, lower outpatient costs and higher pharmacy costs were found for patients with diabetes with the highest care density. CONCLUSION: Patients treated by sets of physicians who share high numbers of patients tend to have lower costs. Future work is necessary to validate care density as a tool to evaluate care coordination and track the performance of health care systems.

Applying diagnosis and pharmacy-based risk models to predict pharmacy use in Aragon, Spain: the impact of a local calibration.

BACKGROUND: In the financing of a national health system, where pharmaceutical spending is one of the main cost containment targets, predicting pharmacy costs for individuals and populations is essential for budget planning and care management. Although most efforts have focused on risk adjustment applying diagnostic data, the reliability of this information source has been questioned in the primary care setting. We sought to assess the usefulness of incorporating pharmacy data into claims-based predictive models (PMs). Developed primarily for the U.S. health care setting, a secondary objective was to evaluate the benefit of a local calibration in order to adapt the PMs to the Spanish health care system. METHODS: The population was drawn from patients within the primary care setting of Aragon, Spain (n = 84,152). Diagnostic, medication and prior cost data were used to develop PMs based on the Johns Hopkins ACG methodology. Model performance was assessed through r-squared statistics and predictive ratios. The capacity to identify future high-cost patients was examined through c-statistic, sensitivity and specificity parameters. RESULTS: The PMs based on pharmacy data had a higher capacity to predict future pharmacy expenses and to identify potential high-cost patients than the models based on diagnostic data alone and a capacity almost as high as that of the combined diagnosis-pharmacy-based PM. PMs provided considerably better predictions when calibrated to Spanish data. CONCLUSION: Understandably, pharmacy spending is more predictable using pharmacy-based risk markers compared with diagnosis-based risk markers. Pharmacy-based PMs can assist plan administrators and medical directors in planning the health budget and identifying high-cost-risk patients amenable to care management programs.

Is quality free? The relationship between cost and quality across 18 provider groups.

OBJECTIVE: To learn whether the healthcare costs for patients of various care delivery systems are associated with the quality of ambulatory care received. Despite intense interest in the cost and quality of healthcare delivery in the United States, there have been relatively few studies of the relationship between those measures, and none have addressed the relationship for integrated care delivery systems. STUDY DESIGN: Results of a retrospective analysis of claims records for overall costs of care for enrollees of 18 care delivery systems were compared with a variety of quality measures for each system. PATIENTS AND METHODS: We analyzed the yearly (1996-1998) claims records of 110,000 to 150,000 employees and dependents of member companies of an employer coalition in Minnesota that received all of their medical services from 18 care systems that had at least 1,000 employees and dependents. Overall case-mix and inflation-adjusted costs of care for enrollees of each care system were compared with 21 ambulatory care process-oriented quality indicators covering 3 chronic diseases and 5 preventive services. RESULTS: Regardless of whether the unit of analysis was the care system or the individual enrollee, there was no evidence of a consistent relationship between overall cost of care and quality on any measures. The little association there was tended to suggest that higher quality was provided by the lowest-cost care systems. CONCLUSION: Although additional confirmatory research is needed, this analysis of the quality-cost relationship provides some reassurance for those who question whether selecting lower-cost sources of medical care might have a negative effect on quality of care.