Hojjat Salmasian

Combing signals from spontaneous reports and electronic health records for detection of adverse drug reactions.

OBJECTIVE Data-mining algorithms that can produce accurate signals of potentially novel adverse drug reactions (ADRs) are a central component of pharmacovigilance. We propose a signal-detection strategy that combines the adverse event reporting system (AERS) of the Food and Drug Administration and electronic health records (EHRs) by requiring signaling in both sources. We claim that this approach leads to improved accuracy of signal detection when the goal is to produce a highly selective ranked set of candidate ADRs. MATERIALS AND METHODS Our investigation was based on over 4 million AERS reports and information extracted from 1.2 million EHR narratives. Well-established methodologies were used to generate signals from each source. The study focused on ADRs related to three high-profile serious adverse reactions. A reference standard of over 600 established and plausible ADRs was created and used to evaluate the proposed approach against a comparator. RESULTS The combined signaling system achieved a statistically significant large improvement over AERS (baseline) in the precision of top ranked signals. The average improvement ranged from 31% to almost threefold for different evaluation categories. Using this system, we identified a new association between the agent, rasburicase, and the adverse event, acute pancreatitis, which was supported by clinical review. CONCLUSIONS The results provide promising initial evidence that combining AERS with EHRs via the framework of replicated signaling can improve the accuracy of signal detection for certain operating scenarios. The use of additional EHR data is required to further evaluate the capacity and limits of this system and to extend the generalizability of these results.

Proton Pump Inhibitors and Risk for Recurrent Clostridium difficile Infection Among Inpatients

OBJECTIVES:Observational studies suggest that proton pump inhibitors (PPIs) are a risk factor for incident Clostridium difficile infection (CDI). Data also suggest an association between PPIs and recurrent CDI, although large-scale studies focusing solely on hospitalized patients are lacking. We therefore performed a retrospective cohort analysis of inpatients with incident CDI to assess receipt of PPIs as a risk factor for CDI recurrence in this population.METHODS:Using electronic medical records, we identified hospitalized adult patients between 1 December 2009 and 30 June 2012 with incident CDI, defined as a first positive stool test for C. difficile toxin B and who received appropriate treatment. Electronic records were parsed for clinical factors including receipt of PPIs, other acid suppression, non-CDI antibiotics, and comorbidities. The primary exposure was in-hospital PPIs given concurrently with C. difficile treatment. Recurrence was defined as a second positive stool test 15–90 days after the initial positive test. C. difficile recurrence rates in the PPI exposed and unexposed groups were compared with the log-rank test. Multivariable Cox proportional hazards modeling was performed to control for demographics, comorbidities, and other clinical factors.RESULTS:We identified 894 inpatients with incident CDI. The cumulative incidence of CDI recurrence in the cohort was 23%. Receipt of PPIs concurrent with CDI treatment was not associated with C. difficile recurrence (hazard ratio (HR)=0.82; 95% confidence interval (CI)=0.58–1.16). Black race (HR=1.66, 95% CI=1.05–2.63), increased age (HR=1.02, 95% CI=1.01–1.03), and increased comorbidities (HR=1.09, 95% CI=1.04–1.14) were associated with CDI recurrence. In light of a higher 90-day mortality seen among those who received PPIs (log-rank P=0.02), we also analyzed the subset of patients who survived to 90 days of follow-up. Again, there was no association between PPIs and CDI recurrence (HR=0.87; 95% CI=0.60–1.28). Finally, there was no association between recurrent CDI and increased duration or dose of PPIs.CONCLUSIONS:Among hospitalized adults with C. difficile, receipt of PPIs concurrent with C. difficile treatment was not associated with CDI recurrence. Black race, increased age, and increased comorbidities significantly predicted recurrence. Future studies should test interventions to prevent CDI recurrence among high-risk inpatients.

Proton Pump Inhibitors Do Not Increase Risk for Clostridium difficile Infection in the Intensive Care Unit.

Objectives:Patients in the intensive care unit (ICU) frequently receive proton pump inhibitors (PPIs) and have high rates of Clostridium difficile infection (CDI). PPIs have been associated with CDI in hospitalized patients, but ICU patients differ fundamentally from non-ICU patients and few studies have focused on PPI use exclusively in the critical care setting. We performed a retrospective cohort study to determine the associations between PPIs and health-care facility-onset CDI in the ICU.Methods:We analyzed data from all adult ICU patients at three affiliated hospitals (14 ICUs) between 2010 and 2013. Patients were excluded if they had recent CDI or an ICU stay of <3 days. We parsed electronic medical records for ICU exposures, focusing on PPIs and other potentially modifiable exposures that occurred during ICU stays. Health-care facility-onset CDI in the ICU was defined as a newly positive PCR for the C. difficile toxin B gene from an unformed stool, with subsequent receipt of anti-CDI therapy. We analyzed PPIs and other exposures as time-varying covariates and used Cox proportional hazards models to adjust for demographics, comorbidities, and other clinical factors.Results:Of 18,134 patients who met the criteria for inclusion, 271 (1.5%) developed health-care facility-onset CDI in the ICU. Receipt of antibiotics was the strongest risk factor for CDI (adjusted HR (aHR) 2.79; 95% confidence interval (CI), 1.50–5.19). There was no significant increase in risk for CDI associated with PPIs in those who did not receive antibiotics (aHR 1.56; 95% CI, 0.72–3.35), and PPIs were actually associated with a decreased risk for CDI in those who received antibiotics (aHR 0.64; 95% CI, 0.48–0.83). There was also no evidence of increased risk for CDI in those who received higher doses of PPIs.Conclusions:Exposure to antibiotics was the most important risk factor for health-care facility-onset CDI in the ICU. PPIs did not increase risk for CDI in the ICU regardless of use of antibiotics.

A method for controlling complex confounding effects in the detection of adverse drug reactions using electronic health records.

OBJECTIVE Electronic health records (EHRs) contain information to detect adverse drug reactions (ADRs), as they contain comprehensive clinical information. A major challenge of using comprehensive information involves confounding. We propose a novel data-driven method to identify ADR signals accurately by adjusting for confounders. MATERIALS AND METHODS We focused on two serious ADRs, rhabdomyolysis and pancreatitis, and used information in 264,155 unique patient records. We identified an ADR using established criteria, selected potential confounders, and then used penalized logistic regressions to estimate confounder-adjusted ADR associations. A reference standard was created to evaluate and compare the precision of the proposed method and four others. RESULTS Precision was 83.3% for rhabdomyolysis and 60.8% for pancreatitis when using the proposed method, and we identified several drug safety signals that are interesting for further clinical review. DISCUSSION The proposed method effectively estimated ADR associations after adjusting for confounders. A main cause of error was probably due to the nature of the dataset in that a substantial number of patients had a single visit only and, therefore, it was not possible to determine correctly the appropriate sequence of events for them. It is likely that performance will be improved with use of EHR data that contain more longitudinal records. CONCLUSIONS This data-driven method is effective in controlling for confounding, resulting in either a higher or similar precision when compared with four comparators, has the unique ability to provide insight into confounders for each specific medication-ADR pair, and can be easily adapted to other EHR systems.

Deriving comorbidities from medical records using natural language processing

Extracting comorbidity information is crucial for phenotypic studies because of the confounding effect of comorbidities. We developed an automated method that accurately determines comorbidities from electronic medical records. Using a modified version of the Charlson comorbidity index (CCI), two physicians created a reference standard of comorbidities by manual review of 100 admission notes. We processed the notes using the MedLEE natural language processing system, and wrote queries to extract comorbidities automatically from its structured output. Interrater agreement for the reference set was very high (97.7%). Our method yielded an F1 score of 0.761 and the summed CCI score was not different from the reference standard (p=0.329, power 80.4%). In comparison, obtaining comorbidities from claims data yielded an F1 score of 0.741, due to lower sensitivity (66.1%). Because CCI has previously been validated as a predictor of mortality and readmission, our method could allow automated prediction of these outcomes.

Intercepting Wrong-Patient Orders in a Computerized Provider Order Entry System

STUDY OBJECTIVE We evaluate the short- and long-term effect of a computerized provider order entry-based patient verification intervention to reduce wrong-patient orders in 5 emergency departments. METHODS A patient verification dialog appeared at the beginning of each ordering session, requiring providers to confirm the patients identity after a mandatory 2.5-second delay. Using the retract-and-reorder technique, we estimated the rate of wrong-patient orders before and after the implementation of the intervention to intercept these errors. We conducted a short- and long-term quasi-experimental study with both historical and parallel controls. We also measured the amount of time providers spent addressing the verification system, and reasons for discontinuing ordering sessions as a result of the intervention. RESULTS Wrong-patient orders were reduced by 30% immediately after implementation of the intervention. This reduction persisted when inpatients were used as a parallel control. After 2 years, the rate of wrong-patient orders remained 24.8% less than before intervention. The mean viewing time of the patient verification dialog was 4.2 seconds (SD=4.0 seconds) and was longer when providers indicated they placed the order for the wrong patient (4.9 versus 4.1 seconds). Although the display of each dialog took only seconds, the large number of display episodes triggered meant that the physician time to prevent each retract-and-reorder event was 1.5 hours. CONCLUSION A computerized provider order entry-based patient verification system led to a moderate reduction in wrong-patient orders that was sustained over time. Interception of wrong-patient orders at data entry is an important step in reducing these errors.

An automated tool for detecting medication overuse based on the electronic health records

Medication overuse is a serious concern in healthcare as it leads to increased expenditures, side effects, and morbidities. Identifying overuse is only possible through excluding appropriate indications that are primarily mentioned in unstructured notes. We developed a framework for automatic identification of medication overuse and applied it to proton pump inhibitors (PPIs).

Medication-indication knowledge bases: a systematic review and critical appraisal.

OBJECTIVE Medication-indication information is a key part of the information needed for providing decision support for and promoting appropriate use of medications. However, this information is not readily available to end users, and a lot of the resources only contain this information in unstructured form (free text). A number of public knowledge bases (KBs) containing structured medication-indication information have been developed over the years, but a direct comparison of these resources has not yet been conducted. MATERIAL AND METHODS We conducted a systematic review of the literature to identify all medication-indication KBs and critically appraised these resources in terms of their scope as well as their support for complex indication information. RESULTS We identified 7 KBs containing medication-indication data. They notably differed from each other in terms of their scope, coverage for on- or off-label indications, source of information, and choice of terminologies for representing the knowledge. The majority of KBs had issues with granularity of the indications as well as with representing duration of therapy, primary choice of treatment, and comedications or comorbidities. DISCUSSION AND CONCLUSION This is the first study directly comparing public KBs of medication indications. We identified several gaps in the existing resources, which can motivate future research.

Disease Heritability Inferred from Familial Relationships Reported in Medical Records

Heritability is essential for understanding the biological causes of disease but requires laborious patient recruitment and phenotype ascertainment. Electronic health records (EHRs) passively capture a wide range of clinically relevant data and provide a resource for studying the heritability of traits that are not typically accessible. EHRs contain next-of-kin information collected via patient emergency contact forms, but until now, these data have gone unused in research. We mined emergency contact data at three academic medical centers and identified 7.4 million familial relationships while maintaining patient privacy. Identified relationships were consistent with genetically derived relatedness. We used EHR data to compute heritability estimates for 500 disease phenotypes. Overall, estimates were consistent with the literature and between sites. Inconsistencies were indicative of limitations and opportunities unique to EHR research. These analyses provide a validation of the use of EHRs for genetics and disease research.

Clinical Application of Screening for GJB2 Mutations before Cochlear Implantation in a Heterogeneous Population with High Rate of Autosomal Recessive Nonsyndromic Hearing Loss

Clinical application of mutation screening and its effect on the outcome of cochlear implantation is widely debated. We investigated the effect of mutations in GJB2 gene on the outcome of cochlear implantation in a population with a high rate of consanguineous marriage and autosomal recessive nonsyndromic hearing loss. Two hundred and one children with profound prelingual sensorineural hearing loss were included. Forty-six patients had 35delG in GJB2. Speech awareness thresholds (SATs) and speech recognition thresholds (SRTs) improved following implantation, but there was no difference in performance between patients with GJB2-related deafness versus control (all P > 0.10). Both groups had produced their first comprehensible words within the same period of time following implantation (2.27 months in GJB2-related deaf versus 2.62 months in controls, P = 0.22). Although our findings demonstrate the need to uncover unidentified genetic causes of hereditary deafness, they do not support the current policy for genetic screening before cochlear implantation, nor prove a prognostic value.