Using technology to promote gastrointestinal outcomes research: a case for electronic health records

Multisite learning of high-dimensional heterogeneous data with applications to opioid use disorder study of 15,000 patients across 5 clinical sites

Integrating data across institutions can improve learning efficiency. To integrate data efficiently while protecting privacy, we propose A one-shot, summary-statistics-based, Distributed Algorithm for fitting Penalized (ADAP) regression models across multiple datasets. ADAP utilizes patient-level data from a lead site and incorporates the first-order (ADAP1) and second-order gradients (ADAP2) of the objective function from collaborating sites to construct a surrogate objective function at the lead site, where model fitting is then completed with proper regularizations applied. We evaluate the performance of the proposed method using both simulation and a real-world application to study risk factors for opioid use disorder (OUD) using 15,000 patient data from the OneFlorida Clinical Research Consortium. Our results show that ADAP performs nearly the same as the pooled estimator but achieves higher estimation accuracy and better variable selection than the local and average estimators. Moreover, ADAP2 successfully handles heterogeneity in covariate distributions.

SAT: a Surrogate-Assisted Two-wave case boosting sampling method, with application to EHR-based association studies

OBJECTIVES

Electronic health records (EHRs) enable investigation of the association between phenotypes and risk factors. However, studies solely relying on potentially error-prone EHR-derived phenotypes (ie, surrogates) are subject to bias. Analyses of low prevalence phenotypes may also suffer from poor efficiency. Existing methods typically focus on one of these issues but seldom address both. This study aims to simultaneously address both issues by developing new sampling methods to select an optimal subsample to collect gold standard phenotypes for improving the accuracy of association estimation.

MATERIALS AND METHODS

We develop a surrogate-assisted two-wave (SAT) sampling method, where a surrogate-guided sampling (SGS) procedure and a modified optimal subsampling procedure motivated from A-optimality criterion (OSMAC) are employed sequentially, to select a subsample for outcome validation through manual chart review subject to budget constraints. A model is then fitted based on the subsample with the true phenotypes. Simulation studies and an application to an EHR dataset of breast cancer survivors are conducted to demonstrate the effectiveness of SAT.

RESULTS

We found that the subsample selected with the proposed method contains informative observations that effectively reduce the mean squared error of the resultant estimator of the association.

CONCLUSIONS

The proposed approach can handle the problem brought by the rarity of cases and misclassification of the surrogate in phenotype-absent EHR-based association studies. With a well-behaved surrogate, SAT successfully boosts the case prevalence in the subsample and improves the efficiency of estimation.

A Methodology to Generate Longitudinally Updated Acute-On-Chronic Liver Failure Prognostication Scores From Electronic Health Record Data

Queries of electronic health record (EHR) data repositories allow for automated data collection. These techniques have not been used in hepatology due to the inability to capture hepatic encephalopathy (HE) grades, which are inputs for acute-on-chronic liver failure (ACLF) models. Here, we describe a methodology to use EHR data to calculate rolling ACLF scores. We examined 239 patient admissions with end-stage liver disease from July 2014 to June 2019. We mapped EHR flowsheet data to determine HE grades and calculated two longitudinally updated ACLF scores. We validated HE grades and ACLF diagnoses by chart review and calculated sensitivity, specificity, and Cohen's kappa. Of 239 patient admissions analyzed, 37% were women, 46% were non-Hispanic white, median age was 60 years, and the median Model for End-Stage Liver Disease-Na score at admission was 25. Of the 239, 7% were diagnosed with ACLF as defined by the North American Consortium for the Study of End-Stage Liver Disease (NACSELD) diagnostic criteria at admission, 27% during the hospitalization, and 9% at discharge. Forty percent were diagnosed with ACLF by the European Association for the Study of the Liver- Chronic Liver Failure Consortium (CLIF-C) diagnostic criteria at admission, 51% during the hospitalization, and 34% at discharge. From the chart review of 51 admissions, we found sensitivities and specificities for any HE (grades 1-4) were 92%-97% and 76%-95%, respectively; for severe HE (grades 3-4), sensitivities and specificities were 100% and 78%-98%, respectively. Cohen's kappa between flowsheet and chart review of HE grades ranged from 0.55 to 0.72. Sensitivities and specificities for NACSELD-ACLF diagnoses were 75%-100% and 96%-100%, respectively; for CLIF-C-ACLF diagnoses, these were 91%-100% and 96-100%, respectively. We generated approximately 28 unique ACLF scores per patient per admission day. Conclusion: We developed an informatics-based methodology to calculate longitudinally updated ACLF scores. This opens new analytic potentials, such as big data methods, to develop electronic phenotypes for patients with ACLF.

Development of an Inflammatory Bowel Disease Research Registry Derived from Observational Electronic Health Record Data for Comprehensive Clinical Phenotyping

BACKGROUND

Inflammatory bowel disease (IBD) is a heterogeneous collection of chronic inflammatory disorders of the digestive tract. Clinical, genetic, and pathological heterogeneity makes it increasingly difficult to translate efficacy studies into real-world practice. Our objective was to develop a comprehensive natural history registry derived from multi-year observational data to facilitate effectiveness and clinical phenotypic research in IBD.

METHODS

A longitudinal, consented registry with prospectively collected data was developed at UPMC. All adult IBD patients receiving care at the tertiary care center of UPMC are eligible for enrollment. Detailed data in the electronic health record are accessible for registry research purposes. Data are exported directly from the electronic health record and temporally organized for research.

RESULTS

To date, there are over 2565 patients participating in the IBD research registry. All patients have demographic data, clinical disease characteristics, and disease course data including healthcare utilization, laboratory values, health-related questionnaires quantifying disease activity and quality of life, and analytical information on treatment, temporally organized for 6 years (2009-2015). The data have resulted in a detailed definition of clinical phenotypes suitable for association studies with parameters of disease outcomes and treatment response. We have established the infrastructure required to examine the effectiveness of treatment and disease course in the real-world setting of IBD.

CONCLUSIONS

The IBD research registry offers a unique opportunity to investigate clinical research questions regarding the natural course of the disease, phenotype association studies, effectiveness of treatment, and quality of care research.

Predictors of Increased Risk of Hepatocellular Carcinoma in Patients with Type 2 Diabetes

Epidemiological data indicate that type 2 diabetes is associated with increased risk of hepatocellular carcinoma (HCC). However, risk stratification for HCC has not been fully elucidated in diabetic population. The aim of this study was to identify potential predictors of HCC in diabetic patients without chronic viral hepatitis. A cohort of 3,544 diabetic patients without chronic viral hepatitis or alcoholic cirrhosis was established and subjects were randomly allocated into a derivation and a validation set. A scoring system was developed by using potential predictors of increased risk of HCC from the Cox proportional hazards model. The performance of the scoring system was tested for validation by using receiver operating characteristics analysis. During median follow-up of 55 months, 36 cases of HCC developed (190 per 100,000 person-years). The 5- and 10-year cumulative incidences of HCC were 1.0%, and 2.2%, respectively. Multivariate Cox regression analysis showed that age > 65 years, low triglyceride levels and high gamma-glutamyl transferase levels were independently associated with an increased risk of HCC. DM-HCC risk score, a weighted sum of scores from these 3 parameters, predicted 10-year development of HCC with area under the receiver operating characteristics curve of 0.86, and discriminated different risk categories for HCC in the derivation and validation cohort. In conclusion, old age, low triglyceride level and high gamma-glutamyl transferase level may help to identify individuals at high risk of developing HCC in diabetic patients without chronic viral hepatitis or alcoholic cirrhosis.

Challenges in designing a national surveillance program for inflammatory bowel disease in the United States

This review describes the history of U.S. government funding for surveillance programs in inflammatory bowel diseases (IBD), provides current estimates of the incidence and prevalence of IBD in the United States, and enumerates a number of challenges faced by current and future IBD surveillance programs. A rationale for expanding the focus of IBD surveillance beyond counts of incidence and prevalence, to provide a greater understanding of the burden of IBD, disease etiology, and pathogenesis, is provided. Lessons learned from other countries are summarized, in addition to potential resources that may be used to optimize a new form of IBD surveillance in the United States. A consensus recommendation on the goals and available resources for a new model for disease surveillance are provided. This new model should focus on "surveillance of the burden of disease," including (1) natural history of disease and (2) outcomes and complications of the disease and/or treatments.

Optimising the use of electronic health records to estimate the incidence of rheumatoid arthritis in primary care: what information is hidden in free text?

Background

Primary care databases are a major source of data for epidemiological and health services research. However, most studies are based on coded information, ignoring information stored in free text. Using the early presentation of rheumatoid arthritis (RA) as an exemplar, our objective was to estimate the extent of data hidden within free text, using a keyword search.

Methods

We examined the electronic health records (EHRs) of 6,387 patients from the UK, aged 30 years and older, with a first coded diagnosis of RA between 2005 and 2008. We listed indicators for RA which were present in coded format and ran keyword searches for similar information held in free text. The frequency of indicator code groups and keywords from one year before to 14 days after RA diagnosis were compared, and temporal relationships examined.

Results

One or more keyword for RA was found in the free text in 29% of patients prior to the RA diagnostic code. Keywords for inflammatory arthritis diagnoses were present for 14% of patients whereas only 11% had a diagnostic code. Codes for synovitis were found in 3% of patients, but keywords were identified in an additional 17%. In 13% of patients there was evidence of a positive rheumatoid factor test in text only, uncoded. No gender differences were found. Keywords generally occurred close in time to the coded diagnosis of rheumatoid arthritis. They were often found under codes indicating letters and communications.

Conclusions

Potential cases may be missed or wrongly dated when coded data alone are used to identify patients with RA, as diagnostic suspicions are frequently confined to text. The use of EHRs to create disease registers or assess quality of care will be misleading if free text information is not taken into account. Methods to facilitate the automated processing of text need to be developed and implemented.

Electronic health records: a new tool to combat chronic kidney disease?

Electronic health records (EHRs) were first developed in the 1960s as clinical information systems for document storage and retrieval. Adoption of EHRs has increased in the developed world and is increasing in developing countries. Studies have shown that quality of patient care is improved among health centers with EHRs. In this article, we review the structure and function of EHRs along with an examination of its potential application in CKD care and research. Well-designed patient registries using EHRs data allow for improved aggregation of patient data for quality improvement and to facilitate clinical research. Preliminary data from the United States and other countries have demonstrated that CKD care might improve with use of EHRs-based programs. We recently developed a CKD registry derived from EHRs data at our institution and complimented the registry with other patient details from the United States Renal Data System and the Social Security Death Index. This registry allows us to conduct a EHRs-based clinical trial that examines whether empowering patients with a personal health record or patient navigators improves CKD care, along with identifying participants for other clinical trials and conducting health services research. EHRs use have shown promising results in some settings, but not in others, perhaps attributed to the differences in EHRs adoption rates and varying functionality. Thus, future studies should explore the optimal methods of using EHRs to improve CKD care and research at the individual patient level, health system and population levels.

Patient survival and healthcare utilization costs after diagnosis of triple-negative breast cancer in a United States managed care cancer registry

BACKGROUND

Triple-negative breast cancer (TNBC) makes up 10-17% of all breast cancers and, due to lack of receptor expression, is unresponsive to therapies that target hormonal receptors or HER2. Unique in its tumor aggression and high rates of recurrence, TNBC is less likely to be detected by mammogram and has a poorer prognosis than other breast cancer subtypes (non-TNBC).

OBJECTIVES

To examine the survival, healthcare utilization, and healthcare cost for women with TNBC compared with non-TNBC breast cancer.

METHODS

The study population was derived from a US managed care cancer registry linked to health insurance claims and social security mortality data. Based on initial type and stage at diagnosis, patients were divided into two cohorts: patients with TNBC and those with non-TNBC. Records were analyzed from initial diagnosis until death, disenrollment, or end of observation period. Survival and annual healthcare utilization and costs were estimated and compared between cohorts after adjusting for baseline demographic characteristics, comorbidities, and prior resource use. Subgroup analyses were performed in patients diagnosed with stage I-III and IV breast cancer.

RESULTS

The study included women diagnosed with TNBC (n = 450) and non-TNBC (n = 1807). Median follow-up time for all patients was 716 days (688.5 and 733 days for TNBC and non-TNBC patients, respectively). After initial diagnosis, overall mortality risk for the TNBC cohort was twice as high as the non-TNBC cohort (HR = 2.02, p < 0.0001). Patients with TNBC had more annual hospitalizations, hospitalized days, and number of emergency room visits relative to non-TNBC. Despite similar annual total healthcare costs, adjusted inpatient costs for patients with non-TNBC averaged 77% higher ($8395 vs. $4745, p < 0.0001). Furthermore, payer reimbursements were higher for TNBC than non-TNBC patients ($8213 vs. $4486, p < 0.0001).

CONCLUSIONS

While it does not control for race or socioeconomic status, this study found that in a US managed care setting, patients with TNBC compared with non-TNBC have significantly shorter survival, accompanied by higher inpatient utilization and healthcare costs.

A primer on endoscopic electronic medical records

Endoscopic electronic medical record systems (EEMRs) are now increasingly utilized in many endoscopy centers. Modern EEMRs not only support endoscopy report generation, but often include features such as practice management tools, image and video clip management, inventory management, e-faxes to referring physicians, and database support to measure quality and patient outcomes. There are many existing software vendors offering EEMRs, and choosing a software vendor can be time consuming and confusing. The goal of this article is inform the readers about current functionalities available in modern EEMR and provide them with a framework necessary to find an EEMR that is best fit for their practice.

Health technology assessment in the era of personalized health care

OBJECTIVES

This article examines the challenges for health technology assessment (HTA) in the light of new developments of personalized health care, focusing on European HTA perspectives.

METHODS

Using the example of the Integrated Genome Research Network - Mutanom (IG Mutanom) project, with focus on personalized cancer diagnostics and treatment, we assess the scope of current HTA and examine it prospectively in the context of the translation of basic and clinical research into public health genomics and personalized health care.

RESULTS

The approaches developed within the IG-Mutanom project are based on innovative technology potentially providing targeted therapies for cancer; making translation into clinical practice requires a novel course of action, however. New models of HTA are needed that can account for the unique types of evidence inherent to individualized targeted therapies. Using constructive health technology assessment (CTA) models is an option, but further suitable models should be developed.

CONCLUSIONS

Integrative, systems biology-based approaches toward personalized medicine call for novel assessment methods. The translation of their highly innovative technologies into the practice of health care requires the development of new HTA concepts.

The use of databases and registries to enhance colonoscopy quality

Administrative databases, registries, and clinical databases are designed for different purposes and therefore have different advantages and disadvantages in providing data for enhancing quality. Administrative databases provide the advantages of size, availability, and generalizability, but are subject to constraints inherent in the coding systems used and from data collection methods optimized for billing. Registries are designed for research and quality reporting but require significant investment from participants for secondary data collection and quality control. Electronic health records contain all of the data needed for quality research and measurement, but that data is too often locked in narrative text and unavailable for analysis. National mandates for electronic health record implementation and functionality will likely change this landscape in the near future.