We developed ML models with close to moderate predictive performance for SSRI-associated bleeding using data from the NIH AoU Research Program as part of what will be a larger precision medicine endeavor. The AoU database allows us to create models incorporating not only clinical information from the EHR but also sociodemographic characteristics through survey data including income, health literacy, and education level. More importantly, we created our models with the goal of eventually implementing them in clinical practice. Thus, most of our features were selected to ensure that they can be feasibly obtained in clinical settings.
Multiple meta-analyses have demonstrated an augmented risk of gastrointestinal (GI) bleeding with SSRIs, especially when taken concurrently with a non-steroidal anti-inflammatory drug (NSAID).33–35 Another meta-analysis demonstrated an increased risk of intracerebral and intracranial hemorrhage (ICH) with SSRIs, albeit these bleeding events were rare.36 There was an estimated a 36% increase in non-specific, global bleeding risk from SSRI treatment.10 Despite the literature establishing SSRI bleeding risk, studies have not extensively examined actionable risk factors to prevent bleeding ADEs. To our knowledge, this is the first ML prediction model developed specifically for bleeding events associated with SSRIs.
Prior bleeding history was identified as clinically significant in almost all drug cohorts, except escitalopram, although bleeding history remains arguably important as significant changes in AUC was found in two out of its four ML escitalopram models. This is unsurprising as bleeding history is a component of bleeding risk stratification tools for other clinical settings such as HAS-BLED, RIETE, and VTE-BLEED.29,37 Further, this evidenced the importance of evaluating predisposing risk factors to bleeding prior to SSRI prescribing. Socioeconomic status was identified as a clinically important feature cluster in the fluoxetine cohort and the combined SSRI cohort. This is an important finding as hospital admissions due to antidepressant-related ADE were also identified to be higher in patients from low-income areas38 and the need for use of antidepressants may be higher in low-income populations.39 Interestingly, health literacy based on survey data was also deemed clinically significant in the escitalopram cohort. These support the need to examine sociodemographic factors for evaluation of ADE risk at the time of prescribing, as well as interventions to improve patient understanding of their medications. Surprisingly, use of concurrent antithrombotics was defined as clinically important only for the warfarin cohort and concurrent NSAID use was not noted to be clinically significant in our ML models which is inconsistent with previous studies evaluating bleeding risk with SSRIs.33–35, 40 This may be explained by our evaluation of global bleeding events rather than localized GI bleeding as our targeted ADE in this study. While the interpretation of feature importance with ML approaches does not inform the direction of risk (higher or lower risk of bleeding) for each clinically significant feature, our approach has established preliminary evidence of important associations which are to be verified in future pharmacoepidemiologic studies.
While the AUC scores and Youden’s index-optimized sensitivity and specificity for each drug cohort are modest, the performances of models established from this study are comparable to those of previously validated prediction models for clinically relevant bleeding. In the AMADEUS study, CHADS2, CHA2DS2-VASc and HAS-BLED scores were used to determine predictive value for bleeding for enrolled patients.41 The best performing model, and only one of the three recommended to perform bleeding risk assessment, was HAS-BLED, which demonstrated a modest performance in predicting clinically relevant bleeding, with an AUC of 0.60. Of note, prediction of bleeding events in this study was in patients with atrial fibrillation being treated with anticoagulants; thus, its findings are likely not directly comparable to ours. Nevertheless, this illustrates that our models demonstrate at least comparable performance to currently utilized prediction models in clinical settings.
This study does have some limitations. First, there are inherent limitations when using EHR databases retrospectively for ADE research. Selection of participants and identification of ADEs is challenging, as it is difficult to ascertain information necessary for thorough causality assessment. Poor quality data collected from EHR sources designed for non-research methods, or missing data, may lead to selection bias and information bias. Therefore, we applied recommended practices to address these inherent limitations, employing strategies such as defining the index date as the first drug exposure date to reduce the risk of immortal time bias.28 We also designed the follow-up period carefully and treated drug exposure as a time-varying feature, considering factors such gaps in medication records and initiation of other drugs, rather than assuming initial exposure remains the same throughout the follow-up period. Feature selection and clusters were determined a priori, which could have excluded important features identifiable with empirical methods, while the definition of clinically significant features requires optimization. Nonetheless, the rich data made available by the AoU program allow us to make robust predictions with reasonable sample sizes while performing hypothesis-generating research for further evaluation with prospective studies.