Search

Antidepressant selection is largely a trial-and-error process. We used electronic health record (EHR) data and artificial intelligence (AI) to predict response to four antidepressants classes (SSRI, SNRI, bupropion, and mirtazapine) 4 to 12 weeks after antidepressant initiation. The final data set comprised 17,556 patients. Predictors were derived from both structured and unstructured EHR data and models accounted for features predictive of treatment selection to minimize confounding by indication. Outcome labels were derived through expert chart review and AI-automated imputation. Regularized generalized linear model (GLM), random forest, gradient boosting machine (GBM), and deep neural network (DNN) models were trained and their performance compared. Predictor importance scores were derived using SHapley Additive exPlanations (SHAP). All models demonstrated similarly good prediction performance (AUROCs ≥ 0.70, AUPRCs ≥ 0.68). The models can estimate differential treatment response probabilities both between patients and between antidepressant classes for the same patient. In addition, patient-specific factors driving response probabilities for each antidepressant class can be generated. We show that antidepressant response can be accurately predicted from real-world EHR data with AI modeling, and our approach could inform further development of clinical decision support systems for more effective treatment selection.

Bipolar disorder is a leading contributor to disability, premature mortality, and suicide. Early identification of risk for bipolar disorder using generalizable predictive models trained on diverse cohorts around the United States could improve targeted assessment of high risk individuals, reduce misdiagnosis, and improve the allocation of limited mental health resources.This observational case-control study intended to develop and validate generalizable predictive models of bipolar disorder as part of the multisite, multinational PsycheMERGE Consortium across diverse and large biobanks with linked electronic health records (EHRs) from three academic medical centers: in the Northeast (Massachusetts General Brigham), the Mid-Atlantic (Geisinger) and the Mid-South (Vanderbilt University Medical Center).Predictive models were developed and validated with multiple algorithms at each study site: random forests, gradient boosting machines, penalized regression, including stacked ensemble learning algorithms combining them. Predictors were limited to widely available EHR-based features agnostic to a common data model including demographics, diagnostic codes, and medications. The main study outcome was bipolar disorder diagnosis as defined by the International Cohort Collection for Bipolar Disorder, 2015.In total, the study included records for 3,529,569 patients including 12,533 cases (0.3%) of bipolar disorder. After internal and external validation, algorithms demonstrated optimal performance in their respective development sites. The stacked ensemble achieved the best combination of overall discrimination (AUC = 0.82 - 0.87) and calibration performance with positive predictive values above 5% in the highest risk quantiles at all three study sites.In conclusion, generalizable predictive models of risk for bipolar disorder can be feasibly developed across diverse sites to enable precision medicine. Comparison of a range of machine learning methods indicated that an ensemble approach provides the best performance overall but required local retraining. These models will be disseminated via the PsycheMERGE Consortium website.

Metformin, a diabetes drug with anti-aging cellular responses, has complex actions that may alter dementia onset. Mixed results are emerging from prior observational studies. To address this complexity, we deploy a causal inference approach accounting for the competing risk of death in emulated clinical trials using two distinct electronic health record systems. In intention-to-treat analyses, metformin use associates with lower hazard of all-cause mortality and lower cause-specific hazard of dementia onset, after accounting for prolonged survival, relative to sulfonylureas. In parallel systems pharmacology studies, the expression of two AD-related proteins, APOE and SPP1, was suppressed by pharmacologic concentrations of metformin in differentiated human neural cells, relative to a sulfonylurea. Together, our findings suggest that metformin might reduce the risk of dementia in diabetes patients through mechanisms beyond glycemic control, and that SPP1 is a candidate biomarker for metformin’s action in the brain.

Background Strong and consistent associations between access to firearms and suicide have been found in ecologic and individual-level observational studies. For adolescents, a seminal case–control study estimated that living in a home with (vs without) a firearm was associated with a fourfold increase in the risk of death by suicide. Methods We use data from a nationally representative study of 10 123 US adolescents aged 13–18 years to (1) measure how much adolescents who live in a home with a firearm differ from those who do not in ways related to their risk of suicide, and (2) incorporate these differences into an updated effect estimate of the risk of adolescent suicide attributable to living in a home with firearms. Results Almost one-third (30.7%) of adolescents reported living in a home with firearms. Relative to those who did not, adolescents reporting living in a home with a firearm were slightly more likely to be male, older and reside in the South and rural areas, but few differences were identified for mental health characteristics. The effect size found by Brent and colleagues appeared robust to sources of possible residual confounding: updated relative risks remained above 4.0 across most sensitivity analyses and at least 3.1 in even the most conservative estimates. Conclusions Although unmeasured confounding and other biases may nonetheless remain, our updated estimates reinforce the suggestion that adolescents’ risk of suicide was increased threefold to fourfold if they had lived in homes with a firearm compared with if they had not.

Metformin, an antidiabetic drug, triggers anti-aging cellular responses. Aging is the principal risk factor for dementia, but previous observational studies of the diabetes drugs metformin vs. sulfonylureas have been mixed. We tested the hypotheses that metformin improves survival and reduces the risk of dementia, relative to the sulfonylureas, by emulating target trials in electronic health records of diabetic patients at an academic-centered healthcare system in the US and a wide-ranging group of primary care practices in the UK. To address metformin’s potentially dual influences on dementia risk—that it might reduce the hazard of death and put more people at risk of developing dementia while reducing the hazard of dementia by slowing biological aging, we used a competing risks approach and carefully grounded that within a causal inference emulated trial framework. To identify candidate biomarkers of metformin’s actions in the brain that might mediate reduced dementia risk, we conducted an in-vitro systems pharmacology evaluation of metformin and glyburide on differentiated human neural cells through differential gene expression. We named our multi-dimensional approach DRIAD-EHR (Drug Repurposing in Alzheimer’s Disease-Electronic Health Records). In intention-to-treat analyses, metformin was associated with a lower hazard of all-cause mortality than sulfonylureas in both cohorts. In competing risks analyses, there was also a lower cause-specific hazard of dementia onset among metformin initiators. In in-vitro studies, metformin reduced human neural cell expression ofSPP1andAPOE, two secreted proteins that have been implicated in Alzheimer’s disease pathogenesis and whose levels can be quantified in the CSF. Together, our findings suggest that metformin might prevent dementia in patientswithouttype II diabetes. In addition, our results inform the design of clinical trials of metformin in non-diabetics and suggest a pharmacodynamic CSF biomarker, SPP1, for metformin’s action in the brain.

IntroductionPharmacological treatment of depression mostly occurs in non-psychiatric settings, but factors that determine the initial choice of antidepressant treatment in these settings are not well-understood. This study models how non-psychiatrists choose among four antidepressant classes at first prescription (selective serotonin reuptake inhibitors [SSRI], bupropion, mirtazapine, or serotonin-norepinephrine reuptake inhibitors [SNRI]), by analyzing electronic health record (EHR) data.MethodsEHR data were from the Mass General Brigham Healthcare System (Boston, Massachusetts, USA) for the period from 1990 to 2018. From a literature search and expert consultation, we selected 64 variables that may be associated with antidepressant choice. Patients who participated in the study were aged 18 to 65 at the time of first antidepressant prescription with a co-occurring International Classification of Diseases (ICD) code for a depressive disorder. Multinomial logistic regression with main effect terms for all 64 variables was used to model the choice of antidepressant. Using SSRI as the reference class, odds ratios, 95% confidence intervals (CI), and likelihood ratio-based p-values for each variable were reported. We used a false discovery rate (FDR) with the Benjamini–Hochberg procedure to correct for multiple comparisons.FindingsA total of 47,107 patients were included after application of inclusion/exclusion criteria. We observed significant associations for 36 of 64 variables after multiple comparison corrections. Many of these associations suggested that antidepressants’ known pharmacological properties/actions guided choice. For example, there was a decreased likelihood of bupropion prescription among patients with epilepsy (adjusted OR 0.41, 95% CI: 0.33–0.51, p < 0.001), an increased likelihood of mirtazapine prescription among patients with insomnia (adjusted OR 1.58, 95% CI: 1.39–1.80, p < 0.001), and an increased likelihood of SNRI prescription among patients with pain (adjusted OR 1.22, 95% CI: 1.11–1.34, p = 0.001).InterpretationNon-psychiatrists’ selection of antidepressant class appears to be guided by clinically relevant pharmacological properties, indications, and contraindications, suggesting that broadly speaking they choose antidepressants based on meaningful differences among medication classes.

Antidepressants may increase the risk of fractures by disrupting sensory-motor function, thereby increasing the risk of falls, and by decreasing bone mineral density and consequently increasing the fall- or impact-related risk of fracture. Selective serotonin reuptake inhibitor (SSRI) antidepressants appear to increase fracture risk relative to no treatment, while less is known about the effect of serotonin–norepinephrine reuptake inhibitor (SNRI) antidepressants, despite SNRIs being prescribed with increasing frequency. No prior study has directly examined how fracture risk differs among patients initiating SNRIs versus those initiating SSRIs. The objective of this study was to assess the effect of SNRI versus SSRI initiation on fracture rates. Data were derived from a PharMetrics claims database, 1998–2010, which is comprised of commercial health plan information obtained from managed care plans throughout the US. We constructed a cohort of patients aged 50 years or older initiating either of the two drug classes (SSRI, N = 335,146; SNRI, N = 61,612). Standardized mortality weighting and Cox proportional hazards regression were used to estimate hazard ratios (HRs) for fractures by antidepressant class. In weighted analyses, the fracture rates were approximately equal in SNRI and SSRI initiators: HRs for the first 1- and 5-year periods following initiation were 1.11 [95 % confidence interval (CI) 0.92–1.36] and 1.06 (95 % CI 0.90–1.26), respectively. For the subgroup of patients with depression who initiated on either SNRIs or SSRIs, those initiating SNRIs had a modestly, but not significantly, elevated fracture risk compared with those who initiated on SSRIs [HR 1.31 (95 % CI 0.95–1.79)]. We found no evidence that initiating SNRIs rather than SSRIs materially influenced fracture risk among a cohort of middle-aged and older adults.

Background/Purpose The USA Food and Drug Administration (FDA) issued warnings regarding the use of antipsychotics in patients with dementia in 2003 and 2005. We aimed to study the dose and duration of antipsychotic treatment in dementia, and to examine whether physicians' prescription behaviors changed after the FDA warnings. Methods Medical charts of outpatients who had Alzheimer's disease, vascular dementia, or mixed dementia were reviewed. Patients must have achieved a clinically stable state for at least 4 weeks after receiving antipsychotic treatment for agitation or psychosis. Demographics, clinical correlates, and duration of antipsychotic treatment were compared among different antipsychotic groups. Because the quetiapine group had the largest sample size, the optimal dose and duration of quetiapine treatment were compared among three time periods (before 2003, 2003–2005, after 2005). Results Stable state was achieved in 215 patients (80 had Alzheimer's disease, 117 vascular dementia, and 18 mixed dementia). Most patients (177) took quetiapine, 25 took risperidone, and 13 took sulpiride. The whole sample had a long total duration of antipsychotic treatment (median 525 days, mean 707 days). The median dose and total duration of antipsychotic treatment were 1.0 mg/day and 238 days for risperidone, 100 mg/day and 390 days for sulpiride, and 25 mg/day and 611 days for quetiapine, respectively. The optimal dose and total duration of quetiapine treatment decreased significantly after FDA warning in 2005, although the duration remained long. Conclusion The optimal doses of antipsychotics were not higher than those of western reports, but the total duration of antipsychotic treatment was quite long. Although our study suggests the prescription dosage and duration of antipsychotic treatment decreased significantly after FDA warning in 2005, the duration of treatment was still long. Given the serious safety concerns, more effort should be made to avoid unnecessary and prolonged prescription.

The feasible intervention strategy at the prodromal state of psychosis is under debate. We report nine subjects clinically in a putative prodromal state of psychosis who responded to low-dose aripiprazole within the first week of medication. We conjecture that the pathophysiological processes might be easier to modify by antipsychotics in the prodromal state and we believe a short-term low-dose trial of antipsychotic agents is a convenient option for subjects at ultra high risk of psychosis. We urge specific attention to monitor the dissolution of psychotic-like symptoms carefully in order to have a better understanding of the pathogenesis and pharmacotherapy in the inception of psychosis.

244 Background: Risk of suicide is increased after cancer diagnosis. Our study aims to investigate the racial differences on risk of suicide after cancer diagnosis in a nationwide cohort of U.S. patients. Methods: Patients ≥ 18 years and diagnosed with breast (n = 616,099; 26.4%), lung (n = 585,978; 25.0%), colorectal (n = 429,060; 18.4%), or prostate cancer (n = 705,812; 30.2%) from 1988-2010 in Surveillance, Epidemiology and End Results Program (SEER) were identified. A Cox-proportional hazard model was used to compare the suicide mortality of the races (Hispanic white, African American, Asian/Pacific Islander, American Indian/Alaska Native) to non-Hispanic white patients adjusting for age, sex, marital status, household income, education level and cancer sites. Results: A total of 2,336,949 patients were identified, and there were 3,406 suicide death events. Fifty percent of suicide deaths were within 32 months after cancer diagnosis (interquartile range: 66 months). After a median follow-up of 49 months, the suicide mortality was lower in African American (HR: 0.29, 95% CI: 0.25-0.35, p value

1590 Background: Surgery or radiation therapy (RT) remains the definitive treatment for early-stage (Stage I/II) non-small cell lung cancer (NSCLC). Early-stage NSCLC should be treated appropriatel...