An electronic health record driven algorithm to identify incident antidepressant medication users

Poor Neonatal Adaptation After Antidepressant Exposure During the Third Trimester in a Geographically Defined Cohort

Objective

To examine the associations between antidepressant exposure during the third trimester of pregnancy, including individual drugs, drug doses, and antidepressant combinations, and the risk of poor neonatal adaptation (PNA).

Patients and Methods

The Rochester Epidemiology Project medical records-linkage system was used to study infants exposed to selective serotonin reuptake inhibitors (SSRIs; n=1014), bupropion, (n=118), serotonin-norepinephrine reuptake inhibitors (n=80), antidepressant combinations (n=20), or other antidepressants (n=22) during the third trimester (April 11, 2000-December 31, 2013). Poor neonatal adaptation was defined based on a review of medical records. Poisson regression was used to examine the risk of PNA with serotonergic antidepressant and drug combinations compared with that with bupropion monotherapy as well as with high- vs standard-dose antidepressants. When possible, analyses were performed using propensity score (PS) weighting.

Results

Forty-four infants were confirmed cases of PNA. Serotonin-norepinephrine reuptake inhibitor monotherapy, antidepressant combinations, and paroxetine monotherapy were associated with a significantly higher risk of PNA than bupropion monotherapy in unweighted analyses. High-dose SSRI exposure was associated with a significantly increased risk of PNA in unadjusted (relative risk, 2.61; 95% confidence interval, 1.35-5.04) and PS-weighted models (relative risk, 2.29; 95% confidence interval, 1.17-4.48) compared with standard-dose SSRI exposure. The risk of PNA was significantly higher with high-dose paroxetine and sertraline than with standard doses in the PS-weighted analyses. The other risk factors for PNA included maternal anxiety disorders.

Conclusion

Although the frequency of PNA in this cohort was low (3%-4%), the risk of PNA was increased in infants exposed to serotonergic antidepressants, particularly with SSRIs at higher doses, during the third trimester of pregnancy compared with that in infants exposed to standard doses. Potential risk factors for PNA also included third-trimester use of paroxetine (especially at higher doses) and maternal anxiety.

Unsupervised characterization of Major Depressive Disorder medication treatment pathways

Learning health systems have the ability to systematically evaluate treatments and treatment pathways. Characterization of treatment pathways can enhance a health system's ability to perform systematic evaluation to improve care quality. In this study we use a Long-Short Term Memory (LSTM) autoencoder model to systematically characterize treatment pathways in a prevalent phenotype-Major Depressive Disorder (MDD). LSTM autoencoder models generate representations of medication treatment pathways that account for temporality and complex interactions. Patients with similar pathways are grouped with K-means clustering. Clusters are characterized by analysis of medication utilization sequences and trends, as well as clinical features, such as demographics, outcomes and comorbidities. Cluster characterization identifies endotypes of MDD including acute MDD, moderate-chronic MDD and severe-chronic, but managed MDD.

A Review of Automatic Phenotyping Approaches using Electronic Health Records

Electronic Health Records (EHR) are a rich repository of valuable clinical information that exist in primary and secondary care databases. In order to utilize EHRs for medical observational research a range of algorithms for automatically identifying individuals with a specific phenotype have been developed. This review summarizes and offers a critical evaluation of the literature relating to studies conducted into the development of EHR phenotyping systems. This review describes phenotyping systems and techniques based on structured and unstructured EHR data. Articles published on PubMed and Google scholar between 2013 and 2017 have been reviewed, using search terms derived from Medical Subject Headings (MeSH). The popularity of using Natural Language Processing (NLP) techniques in extracting features from narrative text has increased. This increased attention is due to the availability of open source NLP algorithms, combined with accuracy improvement. In this review, Concept extraction is the most popular NLP technique since it has been used by more than 50% of the reviewed papers to extract features from EHR. High-throughput phenotyping systems using unsupervised machine learning techniques have gained more popularity due to their ability to efficiently and automatically extract a phenotype with minimal human effort.

Detecting moderate or complex congenital heart defects in adults from an electronic health records system

Background

The prevalence of moderate or complex (moderate-complex) congenital heart defects (CHDs) among adults is increasing due to improved survival, but many patients experience lapses in specialty care or their CHDs are undocumented in the medical system. There is, to date, no efficient approach to identify this population.

Objective

To develop and assess the performance of a risk score to identify adults aged 20-60 years with undocumented specific moderate-complex CHDs from electronic health records (EHR).

Methods

We used a case-control study (596 adults with specific moderate-complex CHDs and 2384 controls). We extracted age, race/ethnicity, electrocardiogram (EKG), and blood tests from routine outpatient visits (1/2009 through 12/2012). We used multivariable logistic regression models and a split-sample (4: 1 ratio) approach to develop and internally validate the risk score, respectively. We generated receiver operating characteristic (ROC) c-statistics and Brier scores to assess the ability of models to predict the presence of specific moderate-complex CHDs.

Results

Out of six models, the non-blood biomarker model that included age, sex, and EKG parameters offered a high ROC c-statistic of 0.96 [95% confidence interval: 0.95, 0.97] and low Brier score (0.05) relative to the other models. The adult moderate-complex congenital heart defect risk score demonstrated good accuracy with 96.4% sensitivity and 80.0% specificity at a threshold score of 10.

Conclusions

A simple risk score based on age, sex, and EKG parameters offers early proof of concept and may help accurately identify adults with specific moderate-complex CHDs from routine EHR systems who may benefit from specialty care.

Clinical Informatics Researcher's Desiderata for the Data Content of the Next Generation Electronic Health Record

OBJECTIVE

Clinical informatics researchers depend on the availability of high-quality data from the electronic health record (EHR) to design and implement new methods and systems for clinical practice and research. However, these data are frequently unavailable or present in a format that requires substantial revision. This article reports the results of a review of informatics literature published from 2010 to 2016 that addresses these issues by identifying categories of data content that might be included or revised in the EHR.

MATERIALS AND METHODS

We used an iterative review process on 1,215 biomedical informatics research articles. We placed them into generic categories, reviewed and refined the categories, and then assigned additional articles, for a total of three iterations.

RESULTS

Our process identified eight categories of data content issues: Adverse Events, Clinician Cognitive Processes, Data Standards Creation and Data Communication, Genomics, Medication List Data Capture, Patient Preferences, Patient-reported Data, and Phenotyping.

DISCUSSION

These categories summarize discussions in biomedical informatics literature that concern data content issues restricting clinical informatics research. These barriers to research result from data that are either absent from the EHR or are inadequate (e.g., in narrative text form) for the downstream applications of the data. In light of these categories, we discuss changes to EHR data storage that should be considered in the redesign of EHRs, to promote continued innovation in clinical informatics.

CONCLUSION

Based on published literature of clinical informaticians' reuse of EHR data, we characterize eight types of data content that, if included in the next generation of EHRs, would find immediate application in advanced informatics tools and techniques.

Improving risk prediction for depression via Elastic Net regression - Results from Korea National Health Insurance Services Data

Depression, despite its high prevalence, remains severely under-diagnosed across the healthcare system. This demands the development of data-driven approaches that can help screen patients who are at a high risk of depression. In this work, we develop depression risk prediction models that incorporate disease co-morbidities using logistic regression with Elastic Net. Using data from the one million twelve-year longitudinal cohort from Korean National Health Insurance Services (KNHIS), our model achieved an Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) of 0.7818, compared to a traditional logistic regression model without co-morbidity analysis (AUC of 0.6992). We also showed co-morbidity adjusted Odds Ratios (ORs), which may be more accurate independent estimate of each predictor variable. In conclusion, inclusion of co-morbidity analysis improved the performance of depression risk prediction models.

Trends in biomedical informatics: automated topic analysis of JAMIA articles

Biomedical Informatics is a growing interdisciplinary field in which research topics and citation trends have been evolving rapidly in recent years. To analyze these data in a fast, reproducible manner, automation of certain processes is needed. JAMIA is a "generalist" journal for biomedical informatics. Its articles reflect the wide range of topics in informatics. In this study, we retrieved Medical Subject Headings (MeSH) terms and citations of JAMIA articles published between 2009 and 2014. We use tensors (i.e., multidimensional arrays) to represent the interaction among topics, time and citations, and applied tensor decomposition to automate the analysis. The trends represented by tensors were then carefully interpreted and the results were compared with previous findings based on manual topic analysis. A list of most cited JAMIA articles, their topics, and publication trends over recent years is presented. The analyses confirmed previous studies and showed that, from 2012 to 2014, the number of articles related to MeSH terms Methods, Organization & Administration, and Algorithms increased significantly both in number of publications and citations. Citation trends varied widely by topic, with Natural Language Processing having a large number of citations in particular years, and Medical Record Systems, Computerized remaining a very popular topic in all years.