Assessing the health and healthcare of the nation’s children depends critically on data that are timely, relevant, and accurate. Currently, surveillance and policy decisions rely heavily on labor-intensive periodic and ad hoc surveys using cross-sectional designs [1]. However, electronic health records (EHRs) are rapidly coming into wider use as the medium in which information about care of patients is recorded [2]; in the United States, the ‘Meaningful Use’ initiative for EHR systems [3] [4] is providing a significant stimulus for this process. The shift of health information into electronic forms more amenable to analysis and exchange creates opportunities to improve healthcare quality, develop new methods for clinical research, and follow the health of patient populations using EHR-derived data [5]. Several policy analysts have suggested that multi-institutional sharing of EHR data presents a new paradigm for advancing population health [6] [7] [8]. In particular, greater facility with EHR data is critical to achieving a learning health system [9] [10], in which information derived from clinical care continuously supports advances in medical understanding and delivery of health care. These advances will be of particular value to child health research, much of which relies on longitudinal changes in growth, health, and development.

Realizing the potential of EHR-derived data requires addressing important questions, including differences in representation of information, variability in data capture, and governance issues [11]. Early efforts include the eMERGE Consortium, which used site-specific combinations of discrete data and natural language processing to identify patients with particular diagnoses that could be pooled for genotype-phenotype studies [12]. The HMO Research Network [13] has piloted a system that allows queries against member sites’ records; the Shared Health Research Information Network’s (SHRINE) query framework operates across sites that have implemented compatible infrastructure using i2b2 [14]. These tools provide for addressing aspects of heterogeneity between EHRs to support federated case ascertainment for research, but require significant resources to implement the required infrastructure. In parallel, mechanisms for patient-centered health information exchange supporting clinical operations and continuity of care are rapidly evolving [15], with significant involvement in the United States from the Office of the National Coordinator for Health IT [16]. Processes that benefit from frequent iteration, such as quality improvement and public health surveillance, may benefit from hybrid strategies that incorporate limited start-up cost and well-defined data models.

Groups of institutions having unified EHRs, such as the Kaiser Permanente system [17], the Harvard Vanguard Medical Associates [18], and the Nemours foundation [19] have demonstrated the utility of aggregating data to examine larger populations of patients in pediatric as well as adult health care, and analyses based on data from a single EHR are becoming more common. At the same time, we are better defining potential limitations of EHR-derived data [20] and developing ways to address them [21] [22]. Sharing of data from disparate EHR systems to enable population-based research [9] is a logical and widely anticipated extension. As we evolve toward this goal, it will be important to study not only the mechanisms for data sharing, but also the ability of data aggregated through various means to support valid and meaningful conclusions about population health.

America’s children, like the population as a whole, are experiencing alarming levels of obesity, although rates appear to have stabilized at 17–19% of children and adolescents [23] [18]. National estimates of childhood obesity are generated by the National Health and Nutrition Examination Survey (NHANES) [24]. Data are combined over two-year intervals to accrue sufficient subjects to generate precise estimates. Sharing of EHR-derived anthropometrics can achieve very large sample sizes to generate interval assessments more rapidly, provide multiple assessments per child to permit longitudinal assessment, and link with other relevant clinical data. In these ways, it can serve as a valuable complement to more in-depth but resource-intensive structured population surveys such as NHANES. This sort of population health surveillance is a key goal of the Meaningful Use initiative, and early efforts to examine feasibility are underway [15], but there are few examples to date in pediatrics.

We report here a study testing the feasibility, validity, and utility of multi-institutional EHR data sharing for monitoring and investigating childhood obesity. The study was expressly designed to minimize resources required by contributing institutions, using processes similar to those used for quality improvement, or for the health information exchange envisioned in the Meaningful Use initiative as a part of routine EHR interoperation. Six pediatric academic health systems from different regions of the United States participated, sharing data from 2007–2008, to examine both the logistical requirements for data sharing and the characteristics of EHR-derived data. The interval matches a data-reporting period for NHANES, to better compare the two approaches. To further assess the utility of EHR-derived data, we examined the association of measured obesity with other clinical data, including the diagnosis of obesity, detection of co-morbidities, and assessment of healthcare utilization. Our goal was to explore the unique potential of EHR-derived data to provide an integrated clinical picture over time.

This study demonstrates the feasibility and validity of sharing EHR-derived data for assessing obesity in large populations of children. The effort required to retrieve the data was nominal, and largely for query development and validation, a one-time cost that would not apply to refreshing data for ongoing surveillance. The scale of EHR-derived data is significant: this sample from six pediatric centers produced 6,000 BMI assessments per month of age for most of childhood.

Aggregation of data across sites and EHR types represents an important test of principle. This study was designed with the intent to isolate technical and procedural factors that might affect the feasibility of data exchange. To that end, we focused on data types, such as anthropometric measurements, where the meaning of a value, as distinct from the method used to obtain it, was unambiguous. For clinical diagnoses, we used the International Classification of Disease, 9^th Edition, Clinical Modification (ICD9-CM) [36], the current standard diagnostic terminology in use in the United States. This provided a common vocabulary, though as noted below, usage of specific codes differed across institutions. In the general case, the problem of semantic interoperability [37], or accounting for the ways in which a common concept is represented in different contexts, remains a barrier to sharing of clinical information. Addressing this problem will require additional work in a number of areas, including development of more robust terminologies and standards for data interchange [37] [38], better understanding of ways in which clinicians interact with the EHR [39] and data are captured [40], and further studies of the operating characteristics of EHR-derived data.

Because most data in the EHR are obtained as part of routine clinical care, their structure will also reflect practice patterns that must be accounted for in secondary analyses. In our case, consistent with expected outpatient practice, patient heights were measured less often than patient weights. Where no height or weight data were available for a child, we considered them inevaluable for obesity, as it would be error-prone, and risk circularity, to impute these directly from a population distribution to an individual. However, unlike weight, for a given individual height velocity is a relatively stable physiologic quantity over the interval considered in this study. Therefore, when at least two measured heights were available, we used a conservative imputation strategy to derive height, and hence BMI, values for visits where it was not directly measured. Although this added no subjects to the dataset, it increased by 21% the number of evaluable visits available for longitudinal and practice type analyses with low risk to validity of data. It also reflects an anticipated, if not yet widely realized, benefit of EHR adoption: information from one site becomes more widely available for use at other sites sharing the EHR.

Secondary use of clinical data for research has also generated concern about the potential consequences of increased variability across measurements. Although the carefully controlled NHANES methodology likely does produce more precise individual measurements, the survey yields an average sample of 16 subjects per month of age. In the EHR data, the potential effects of individual measurement error are damped by the size of the sample and repeated measurement, resulting in highly stable population estimates of BMI and obesity prevalence compatible with NHANES results. This difference was particularly apparent in adolescents, where the EHR-derived data did not display the increased variance seen in NHANES measurements, which was likely due to the differences between individual children in timing of pubertal growth. Furthermore, at the individual level, we found high reliability for BMI assessments over time, suggesting that any error introduced by variation in assessment technique is small.

The cohort size achievable with EHR-derived data permits detection of clinically relevant associations not possible with survey data, such as the known association between acute lymphoblastic leukemia and secondary obesity [41]. EHRs also facilitate construction of cohorts with linked clinical data, to assess the impact of obesity on children with rare primary disorders. In these ways, EHR-based population surveillance can provide an important complement to in-depth but resource-intensive surveys such as NHANES.

It is important to note potential limitations of our EHR-based study. First, data are derived from six centers, leaving gaps in national geographic coverage and underrepresentation of rural areas. In particular, this may contribute to the difference from NHANES in prevalence of obesity in younger children; the higher proportion of measurements from children aged 2–10 in the EHR-derived data than in the NHANES sample is also in keeping with expected patterns of clinical utilization. In most respects, however, our estimates closely match the results of the NHANES stratified sampling model. A fortuitous combination of contributing sites is possible, though participating centers were not selected based on obesity prevalence. The means of 2.6 evaluable visits/child and 1.9 diagnoses/visit also indicate that our results were not likely to have been heavily biased by a subpopulation of children with complex medical conditions affecting their growth. Moreover, the low cost of EHR queries suggests that as the nation’s healthcare system becomes increasingly digitized, it will become possible to readily combine data from additional geographic areas and clinical settings, and increase the generalizability of results based on data sharing.

Second, the high data quality observed in the EHR dataset may in part reflect the selection of anthropometric and demographic data, which are semantically unambiguous and directly measured as a matter of routine in pediatrics, as the source of the primary outcome measured. Our results do provide significant reassurance against the concern that clinical data are generally too unreliable for use in research. However, the quality of other types of information, particularly subjective findings or clinical decisions, will depend on different sets of semantic and pragmatic considerations. Further study will be required to assess the fitness of these and other types of EHR-derived data for population-level analyses [42] [43].

Third, rates of obesity diagnosis in the EHR were remarkably low, even in primary care settings. Although unsurprising [44] [45] [46], this is a significant problem, since growth monitoring is a core function of pediatrics. We considered the possibility that our obesity-related ICD9-CM diagnosis cluster did not sufficiently comprise codes in common use. Examination of the most common diagnoses for obese children does not indicate that an alternative code(s), including those for overweight or specific BMI ranges, was used frequently (data not shown). Of note, the inclusion of 783.1 (“abnormal weight gain”) in our cluster is the result of this analysis demonstrating that it was the most common weight-related diagnosis given to obese children at one site. It is also possible that obesity is missing because multiple other diagnoses are recorded. However, obese children had on average 1.9 diagnoses/visit, a number unlikely to preclude adding a diagnosis of obesity. The low rates of diagnosis in primary care and well-child visits also argue that addressing more acute problems is not a major factor preventing diagnosis of obesity. We did observe stronger association between a diagnosis of obesity and many comorbid diagnoses than between measured obesity itself and these diagnoses (data not shown), suggesting that the presence of a comorbid condition such as hypertension or diabetes may “prompt” a diagnosis of obesity. Adding entries from the EHR’s problem list at the largest site increased the documentation rate by just 3%, showing that this is not a major alternative method of recording recognition of obesity. It is more likely that pediatricians are not recording obesity diagnoses for reasons other than lack of opportunity, such as a belief that obesity is best addressed by “non-medical” interventions, non-reimbursement of obesity diagnoses, or concern for stigmatization of patients. If we are to improve the quality of care for obese children, we will need to better document the problem in the medical record, where it serves not only as a cognitive marker, but as a trigger for additional decision support around appropriate screening and treatment.

EHRs provide access to primary clinical data, rather than specifically coded or prompted responses as on a case report form. This can bias ascertainment of a datum if it does not reflect a common element of clinical care. However, it can also be valuable, if it permits ascertainment of affected status directly, rather than relying on diagnoses or similar administrative data. As we demonstrate, using administrative data to identify obese children misses over 75% of affected individuals. It is possible that similar biases affect diagnoses of comorbid conditions used in our analyses. The strong associations seen between obesity and several known comorbidities are reassuring in this respect. However, further analyses using EHR-derived data can provide opportunities for direct assessment of other conditions, to more reliably establish association with obesity, and potentially to allow us to better identify subsets of children at higher risk for specific complications of obesity.

Using EHR data to monitor other aspects of population health will benefit increasingly from structured data in the EHR, such as diagnoses, vital signs, medications, and diagnostic results. Free text (e.g. clinical assessments and instructions) will require greater, though not necessarily prohibitive [21], effort to derive useful population-level information. In addition to data type, it will be important to understand operating characteristics of EHR-derived data, since the potential for selection and reporting biases will be different from other survey methods.

Using clinical information from the EHR, we demonstrate robust associations between measured obesity and diagnosed comorbidities such as diabetes and other endocrinopathies [47] [48] [49], hypertension [50] [51], dyslipidemia [52] [4], liver disease [53], and sleep apnea [54]. Obese children had increased overall healthcare utilization as well, about half of which is explained by excess diagnosed comorbidities. Both findings highlight public health implications of the high prevalence of obesity for children today and adults tomorrow. Further study to identify appropriate markers in the medical record of screening for and treatment of obesity-associated morbidity will help to define strategies for addressing these problems.

This study also suggests several opportunities for quality improvement. Overall, 44% of visits did not include sufficient data to assess BMI and 24% of subjects had no assessments over the two-year study period, which is recommended at least annually by the American Academy of Pediatrics as a universal practice [55], and is a core objective of the stage 1 meaningful use measures [56]. Only one in five obese children have the diagnosis recorded, an important step in the medical management of any condition. Moreover, the low opportunity cost of EHR-derived monitoring, potentially coupled with geocoding or other public health data, makes it possible to assess the impact of medical and community-based interventions on obesity in a variety of geographic and demographic settings. Methods validated using EHR-derived data can also provide direct input into design of decision support systems to improve quality at the point of care.