A randomized study on the usefulness of an electronic outpatient hypoglycemia risk calculator for clinicians of patients with diabetes in a safety-net institution.

Objective: Hypoglycemia (HG) occurs in up to 60% of patients with diabetes mellitus (DM) each year. We assessed a HG alert tool in an electronic health record system, and determined its effect on clinical practice and outcomes.Methods: The tool applied a statistical model, yielding patient-specific information about HG risk. We randomized outpatient primary-care providers (PCPs) to see or not see the alerts. Patients were assigned to study group according to the first PCP seen during four months. We assessed prescriptions, testing, and HG. Variables were compared by multinomial, logistic, or linear model. ClinicalTrials.gov ID: NCT04177147 (registered on 22 November 2019).Results: Patients (N = 3350) visited 123 intervention PCPs; 3395 patients visited 220 control PCPs. Intervention PCPs were shown 18,645 alerts (mean of 152 per PCP). Patients' mean age was 55 years, with 61% female, 49% black, and 49% Medicaid recipients. Mean baseline A1c and body mass index were similar between groups. During follow-up, the number of A1c and glucose tests, and number of new, refilled, changed, or discontinued insulin prescriptions, were highest for patients with highest risk. Per 100 patients on average, the intervention group had fewer sulfonylurea refills (6 vs. 8; p < .05) and outpatient encounters (470 vs. 502; p < .05), though the change in encounters was not significant. Frequency of HG events was unchanged.Conclusions: Informing PCPs about risk of HG led to fewer sulfonylurea refills and visits. Longer-term studies are needed to assess potential for long-term benefits.

Predictive modeling of hypoglycemia for clinical decision support in evaluating outpatients with diabetes mellitus.

Objective: Hypoglycemia occurs in 20-60% of patients with diabetes mellitus. Identifying at-risk patients can facilitate interventions to lower risk. We sought to develop a hypoglycemia prediction model. Methods: In this retrospective cohort study, urban adults prescribed a diabetes drug between 2004 and 2013 were identified. Demographic and clinical data were extracted from an electronic medical record (EMR). Laboratory tests, diagnostic codes and natural language processing (NLP) identified hypoglycemia. We compared multiple logistic regression, classification and regression trees (CART), and random forest. Models were evaluated on an independent test set or through cross-validation. Results: The 38,780 patients had mean age 57 years; 56% were female, 40% African-American and 39% uninsured. Hypoglycemia occurred in 8128 (539 identified only by NLP). In logistic regression, factors positively associated with hypoglycemia included infection, non-long-acting insulin, dementia and recent hypoglycemia. Negatively associated factors included long-acting insulin plus sulfonylurea, and age 75 or older. The models' area under curve was similar (logistic regression, 89%; CART, 88%; random forest, 90%, with ten-fold cross-validation). Conclusions: NLP improved identification of hypoglycemia. Non-long-acting insulin was an important risk factor. Decreased risk with age may reflect treatment or diminished awareness of hypoglycemia. More complex models did not improve prediction.

Phenome-wide association studies across large population cohorts support drug target validation.

Phenome-wide association studies (PheWAS) have been proposed as a possible aid in drug development through elucidating mechanisms of action, identifying alternative indications, or predicting adverse drug events (ADEs). Here, we select 25 single nucleotide polymorphisms (SNPs) linked through genome-wide association studies (GWAS) to 19 candidate drug targets for common disease indications. We interrogate these SNPs by PheWAS in four large cohorts with extensive health information (23andMe, UK Biobank, FINRISK, CHOP) for association with 1683 binary endpoints in up to 697,815 individuals and conduct meta-analyses for 145 mapped disease endpoints. Our analyses replicate 75% of known GWAS associations (P < 0.05) and identify nine study-wide significant novel associations (of 71 with FDR < 0.1). We describe associations that may predict ADEs, e.g., acne, high cholesterol, gout, and gallstones with rs738409 (p.I148M) in PNPLA3 and asthma with rs1990760 (p.T946A) in IFIH1. Our results demonstrate PheWAS as a powerful addition to the toolkit for drug discovery.

Development of an Algorithm to Identify Patients with Physician-Documented Insomnia.

We developed an insomnia classification algorithm by interrogating an electronic medical records (EMR) database of 314,292 patients. The patients received care at Massachusetts General Hospital (MGH), Brigham and Women's Hospital (BWH), or both, between 1992 and 2010. Our algorithm combined structured variables (such as International Classification of Diseases 9th Revision [ICD-9] codes, prescriptions, laboratory observations) and unstructured variables (such as text mentions of sleep and psychiatric disorders in clinical narrative notes). The highest classification performance of our algorithm was achieved when it included a combination of structured variables (billing codes for insomnia, common psychiatric conditions, and joint disorders) and unstructured variables (sleep disorders and psychiatric disorders). Our algorithm had superior performance in identifying insomnia patients compared to billing codes alone (area under the receiver operating characteristic curve [AUROC] = 0.83 vs. 0.55 with 95% confidence intervals [CI] of 0.76-0.90 and 0.51-0.58, respectively). When applied to the 314,292-patient population, our algorithm classified 36,810 of the patients with insomnia, of which less than 17% had a billing code for insomnia. In conclusion, an insomnia classification algorithm that incorporates clinical notes is superior to one based solely on billing codes. Compared to traditional methods, our study demonstrates that a classification algorithm that incorporates physician notes can more accurately, comprehensively, and quickly identify large cohorts of insomnia patients.

Predictive Modeling of Physician-Patient Dynamics That Influence Sleep Medication Prescriptions and Clinical Decision-Making.

Insomnia remains under-diagnosed and poorly treated despite its high economic and social costs. Though previous work has examined how patient characteristics affect sleep medication prescriptions, the role of physician characteristics that influence this clinical decision remains unclear. We sought to understand patient and physician factors that influence sleep medication prescribing patterns by analyzing Electronic Medical Records (EMRs) including the narrative clinical notes as well as codified data. Zolpidem and trazodone were the most widely prescribed initial sleep medication in a cohort of 1,105 patients. Some providers showed a historical preference for one medication, which was highly predictive of their future prescribing behavior. Using a predictive model (AUC = 0.77), physician preference largely determined which medication a patient received (OR = 3.13; p = 3 × 10-37). In addition to the dominant effect of empirically determined physician preference, discussion of depression in a patient's note was found to have a statistically significant association with receiving a prescription for trazodone (OR = 1.38, p = 0.04). EMR data can yield insights into physician prescribing behavior based on real-world physician-patient interactions.

Characterizing Sleep Issues Using Twitter.

BACKGROUND: Sleep issues such as insomnia affect over 50 million Americans and can lead to serious health problems, including depression and obesity, and can increase risk of injury. Social media platforms such as Twitter offer exciting potential for their use in studying and identifying both diseases and social phenomenon. OBJECTIVE: Our aim was to determine whether social media can be used as a method to conduct research focusing on sleep issues. METHODS: Twitter posts were collected and curated to determine whether a user exhibited signs of sleep issues based on the presence of several keywords in tweets such as insomnia, "can't sleep", Ambien, and others. Users whose tweets contain any of the keywords were designated as having self-identified sleep issues (sleep group). Users who did not have self-identified sleep issues (non-sleep group) were selected from tweets that did not contain pre-defined words or phrases used as a proxy for sleep issues. RESULTS: User data such as number of tweets, friends, followers, and location were collected, as well as the time and date of tweets. Additionally, the sentiment of each tweet and average sentiment of each user were determined to investigate differences between non-sleep and sleep groups. It was found that sleep group users were significantly less active on Twitter (P=.04), had fewer friends (P<.001), and fewer followers (P<.001) compared to others, after adjusting for the length of time each user's account has been active. Sleep group users were more active during typical sleeping hours than others, which may suggest they were having difficulty sleeping. Sleep group users also had significantly lower sentiment in their tweets (P<.001), indicating a possible relationship between sleep and pyschosocial issues. CONCLUSIONS: We have demonstrated a novel method for studying sleep issues that allows for fast, cost-effective, and customizable data to be gathered.