A Comparison of Veterans with Problematic Opioid Use Identified through Natural Language Processing of Clinical Notes versus Using Diagnostic Codes.

Opioid use disorder is known to be under-coded as a diagnosis, yet problematic opioid use can be documented in clinical notes, which are included in electronic health records. We sought to identify problematic opioid use from a full range of clinical notes and compare the demographic and clinical characteristics of patients identified as having problematic opioid use exclusively in clinical notes to patients documented through ICD opioid use disorder diagnostic codes. We developed and applied a natural language processing (NLP) tool that combines rule-based pattern analysis and a trained support vector machine to the clinical notes of a patient cohort (n = 222,371) from two Veteran Affairs service regions to identify patients with problematic opioid use. We also used a set of ICD diagnostic codes to identify patients with opioid use disorder from the same cohort. The NLP tool achieved 96.6% specificity, 90.4% precision/PPV, 88.4% sensitivity/recall, and 94.4% accuracy on unseen test data. NLP exclusively identified 57,331 patients; 6997 patients had positive ICD code identifications. Patients exclusively identified through NLP were more likely to be women. Those identified through ICD codes were more likely to be male, younger, have concurrent benzodiazepine prescriptions, more comorbidities, and more care encounters, and were less likely to be married. Patients in both these groups had substantially elevated comorbidity levels compared with patients not documented through either method as experiencing problematic opioid use. Clinicians may be reluctant to code for opioid use disorder. It is therefore incumbent on the healthcare team to search for documentation of opioid concerns within clinical notes.

Identifying suicide documentation in clinical notes through zero-shot learning.

Background and Aims: In deep learning, a major difficulty in identifying suicidality and its risk factors in clinical notes is the lack of training samples given the small number of true positive instances among the number of patients screened. This paper describes a novel methodology that identifies suicidality in clinical notes by addressing this data sparsity issue through zero-shot learning. Our general aim was to develop a tool that leveraged zero-shot learning to effectively identify suicidality documentation in all types of clinical notes. Methods: US Veterans Affairs clinical notes served as data. The training data set label was determined using diagnostic codes of suicide attempt and self-harm. We used a base string associated with the target label of suicidality to provide auxiliary information by narrowing the positive training cases to those containing the base string. We trained a deep neural network by mapping the training documents' contents to a semantic space. For comparison, we trained another deep neural network using the identical training data set labels, and bag-of-words features. Results: The zero-shot learning model outperformed the baseline model in terms of area under the curve, sensitivity, specificity, and positive predictive value at multiple probability thresholds. In applying a 0.90 probability threshold, the methodology identified notes documenting suicidality but not associated with a relevant ICD-10-CM code, with 94% accuracy. Conclusion: This method can effectively identify suicidality without manual annotation.

Patient Dietary Supplements Use: Do Results from Natural Language Processing of Clinical Notes Agree with Survey Data?

There is widespread use of dietary supplements, some prescribed but many taken without a physician's guidance. There are many potential interactions between supplements and both over-the-counter and prescription medications in ways that are unknown to patients. Structured medical records do not adequately document supplement use; however, unstructured clinical notes often contain extra information on supplements. We studied a group of 377 patients from three healthcare facilities and developed a natural language processing (NLP) tool to detect supplement use. Using surveys of these patients, we investigated the correlation between self-reported supplement use and NLP extractions from the clinical notes. Our model achieved an F1 score of 0.914 for detecting all supplements. Individual supplement detection had a variable correlation with survey responses, ranging from an F1 of 0.83 for calcium to an F1 of 0.39 for folic acid. Our study demonstrated good NLP performance while also finding that self-reported supplement use is not always consistent with the documented use in clinical records.

Opioid use and opioid use disorder in mono and dual-system users of veteran affairs medical centers.

Introduction: Efforts to achieve opioid guideline concordant care may be undermined when patients access multiple opioid prescription sources. Limited data are available on the impact of dual-system sources of care on receipt of opioid medications. Objective: We examined whether dual-system use was associated with increased rates of new opioid prescriptions, continued opioid prescriptions and diagnoses of opioid use disorder (OUD). We hypothesized that dual-system use would be associated with increased odds for each outcome. Methods: This retrospective cohort study was conducted using Veterans Administration (VA) data from two facilities from 2015 to 2019, and included active patients, defined as Veterans who had at least one encounter in a calendar year (2015-2019). Dual-system use was defined as receipt of VA care as well as VA payment for community care (non-VA) services. Mono users were defined as those who only received VA services. There were 77,225 dual-system users, and 442,824 mono users. Outcomes were three binary measures: new opioid prescription, continued opioid prescription (i.e., received an additional opioid prescription), and OUD diagnosis (during the calendar year). We conducted a multivariate logistic regression accounting for the repeated observations on patient and intra-class correlations within patients. Results: Dual-system users were significantly younger than mono users, more likely to be women, and less likely to report white race. In adjusted models, dual-system users were significantly more likely to receive a new opioid prescription during the observation period [Odds ratio (OR) = 1.85, 95% confidence interval (CI) 1.76-1.93], continue prescriptions (OR = 1.24, CI 1.22-1.27), and to receive an OUD diagnosis (OR = 1.20, CI 1.14-1.27). Discussion: The prevalence of opioid prescriptions has been declining in the US healthcare systems including VA, yet the prevalence of OUD has not been declining at the same rate. One potential problem is that detailed notes from non-VA visits are not immediately available to VA clinicians, and information about VA care is not readily available to non-VA sources. One implication of our findings is that better health system coordination is needed. Even though care was paid for by the VA and presumably closely monitored, dual-system users were more likely to have new and continued opioid prescriptions.