Developing a Framework to Infer Opioid Use Disorder Severity From Clinical Notes to Inform Natural Language Processing Methods: Characterization Study.

BACKGROUND: Information regarding opioid use disorder (OUD) status and severity is important for patient care. Clinical notes provide valuable information for detecting and characterizing problematic opioid use, necessitating development of natural language processing (NLP) tools, which in turn requires reliably labeled OUD-relevant text and understanding of documentation patterns. OBJECTIVE: To inform automated NLP methods, we aimed to develop and evaluate an annotation schema for characterizing OUD and its severity, and to document patterns of OUD-relevant information within clinical notes of heterogeneous patient cohorts. METHODS: We developed an annotation schema to characterize OUD severity based on criteria from the Diagnostic and Statistical Manual of Mental Disorders, 5th edition. In total, 2 annotators reviewed clinical notes from key encounters of 100 adult patients with varied evidence of OUD, including patients with and those without chronic pain, with and without medication treatment for OUD, and a control group. We completed annotations at the sentence level. We calculated severity scores based on annotation of note text with 18 classes aligned with criteria for OUD severity and determined positive predictive values for OUD severity. RESULTS: The annotation schema contained 27 classes. We annotated 1436 sentences from 82 patients; notes of 18 patients (11 of whom were controls) contained no relevant information. Interannotator agreement was above 70% for 11 of 15 batches of reviewed notes. Severity scores for control group patients were all 0. Among noncontrol patients, the mean severity score was 5.1 (SD 3.2), indicating moderate OUD, and the positive predictive value for detecting moderate or severe OUD was 0.71. Progress notes and notes from emergency department and outpatient settings contained the most and greatest diversity of information. Substance misuse and psychiatric classes were most prevalent and highly correlated across note types with high co-occurrence across patients. CONCLUSIONS: Implementation of the annotation schema demonstrated strong potential for inferring OUD severity based on key information in a small set of clinical notes and highlighting where such information is documented. These advancements will facilitate NLP tool development to improve OUD prevention, diagnosis, and treatment.

Identification of opioid use disorder using electronic health records: Beyond diagnostic codes.

BACKGROUND: We used structured and unstructured electronic health record (EHR) data to develop and validate an approach to identify moderate/severe opioid use disorder (OUD) that includes individuals without prescription opioid use or chronic pain, an underrepresented population. METHODS: Using electronic diagnosis grouper text from EHRs of ~1 million patients (2012-2020), we created indicators of OUD-with "tiers" indicating OUD likelihood-combined with OUD medication (MOUD) orders. We developed six sub-algorithms with varying criteria (multiple vs single MOUD orders, multiple vs single tier 1 indicators, tier 2 indicators, tier 3 and 4 indicators). Positive predictive values (PPVs) were calculated based on chart review to determine OUD status and severity. We compared demographic and clinical characteristics of cases identified by the sub-algorithms. RESULTS: In total, 14,852 patients met criteria for one of the sub-algorithms. Five sub-algorithms had PPVs ≥0.90 for any severity OUD; four had PPVs ≥0.90 for moderate/severe OUD. Demographic and clinical characteristics differed substantially between groups. Of identified OUD cases, 31.3% had no past opioid analgesic orders, 79.7% lacked evidence of chronic prescription opioid use, and 43.5% lacked a chronic pain diagnosis. DISCUSSION: Incorporating unstructured data with MOUD orders yielded an approach that adequately identified moderate/severe OUD, identified unique demographic and clinical sub-groups, and included individuals without prescription opioid use or chronic pain, whose OUD may stem from illicit opioids. Findings show that incorporating unstructured data strengthens EHR algorithms for identifying OUD and suggests approaches limited to populations with prescription opioid use or chronic pain exclude many individuals with OUD.

Identifying High-Risk Comorbidities Associated with Opioid Use Patterns Using Electronic Health Record Prescription Data.

Introduction: Opioid use disorders (OUDs) constitute a major public health issue, and we urgently need alternative methods for characterizing risk for OUD. Electronic health records (EHRs) are useful tools for understanding complex medical phenotypes but have been underutilized for OUD because of challenges related to underdiagnosis, binary diagnostic frameworks, and minimally characterized reference groups. As a first step in addressing these challenges, a new paradigm is warranted that characterizes risk for opioid prescription misuse on a continuous scale of severity, i.e., as a continuum. Methods: Across sites within the PsycheMERGE network, we extracted prescription opioid data and diagnoses that co-occur with OUD (including psychiatric and substance use disorders, pain-related diagnoses, HIV, and hepatitis C) for over 2.6 million patients across three health registries (Vanderbilt University Medical Center, Mass General Brigham, Geisinger) between 2005 and 2018. We defined three groups based on levels of opioid exposure: no prescriptions, minimal exposure, and chronic exposure and then compared the comorbidity profiles of these groups to the full registries and to those with OUD diagnostic codes. Results: Our results confirm that EHR data reflects known higher prevalence of substance use disorders, psychiatric disorders, medical, and pain diagnoses in patients with OUD diagnoses and chronic opioid use. Comorbidity profiles that distinguish opioid exposure are strikingly consistent across large health systems, indicating the phenotypes described in this new quantitative framework are robust to health systems differences. Conclusion: This work indicates that EHR prescription opioid data can serve as a platform to characterize complex risk markers for OUD using existing data.

Higher scores on autonomic symptom scales in pediatric patients with neurodevelopmental disorders of known genetic etiology.

INTRODUCTION: Features of underlying autonomic dysfunction, including sleep disturbances, gastrointestinal problems, and atypical heart rate, have been reported in neurodevelopmental conditions, including autism spectrum disorder (ASD). The current cross-sectional, between-groups study aimed to quantify symptoms of autonomic dysfunction in a neurodevelopmental pediatric cohort characterized by clinical diagnoses as well as genetic etiology. METHOD: The Pediatric Autonomic Symptom Scales (PASS) questionnaire was used to assess autonomic features across a group of patients with clinical neurodevelopmental diagnoses (NPD; N = 90) and genetic etiologies. Patients were subdivided based on either having a clinical ASD diagnosis (NPD-ASD; n = 37) or other non-ASD neurodevelopmental diagnoses, such as intellectual disability without ASD, speech and language disorders, and/or attention deficit hyperactivity disorder (NPD-OTHER; n = 53). Analyses focused on characterizing differences between the NPD group compared to previously published reference samples, as well as differences between the two NPD subgroups (NPD-ASD and NPD-OTHER). RESULTS: Our results indicate higher PASS scores in our NPD cohort relative to children with and without ASD from a previously published cohort. However, we did not identify significant group differences between our NPD-ASD and NPD-OTHER subgroups. Furthermore, we find a significant relationship between quantitative ASD traits and symptoms of autonomic function. CONCLUSION: This work demonstrates the utility of capturing quantitative estimates of autonomic trait dimensions that may be significantly linked with psychosocial impairments and other core clinical features of ASD.

Classifying Characteristics of Opioid Use Disorder From Hospital Discharge Summaries Using Natural Language Processing.

Background: Opioid use disorder (OUD) is underdiagnosed in health system settings, limiting research on OUD using electronic health records (EHRs). Medical encounter notes can enrich structured EHR data with documented signs and symptoms of OUD and social risks and behaviors. To capture this information at scale, natural language processing (NLP) tools must be developed and evaluated. We developed and applied an annotation schema to deeply characterize OUD and related clinical, behavioral, and environmental factors, and automated the annotation schema using machine learning and deep learning-based approaches. Methods: Using the MIMIC-III Critical Care Database, we queried hospital discharge summaries of patients with International Classification of Diseases (ICD-9) OUD diagnostic codes. We developed an annotation schema to characterize problematic opioid use, identify individuals with potential OUD, and provide psychosocial context. Two annotators reviewed discharge summaries from 100 patients. We randomly sampled patients with their associated annotated sentences and divided them into training (66 patients; 2,127 annotated sentences) and testing (29 patients; 1,149 annotated sentences) sets. We used the training set to generate features, employing three NLP algorithms/knowledge sources. We trained and tested prediction models for classification with a traditional machine learner (logistic regression) and deep learning approach (Autogluon based on ELECTRA's replaced token detection model). We applied a five-fold cross-validation approach to reduce bias in performance estimates. Results: The resulting annotation schema contained 32 classes. We achieved moderate inter-annotator agreement, with F1-scores across all classes increasing from 48 to 66%. Five classes had a sufficient number of annotations for automation; of these, we observed consistently high performance (F1-scores) across training and testing sets for drug screening (training: 91-96; testing: 91-94) and opioid type (training: 86-96; testing: 86-99). Performance dropped from training and to testing sets for other drug use (training: 52-65; testing: 40-48), pain management (training: 72-78; testing: 61-78) and psychiatric (training: 73-80; testing: 72). Autogluon achieved the highest performance. Conclusion: This pilot study demonstrated that rich information regarding problematic opioid use can be manually identified by annotators. However, more training samples and features would improve our ability to reliably identify less common classes from clinical text, including text from outpatient settings.

Variability and concordance of sulcal patterns in the orbitofrontal cortex: A twin study.

Sulcogyral patterns have been identified in the orbitofrontal cortex (OFC) based on the continuity of the medial and lateral orbital sulci. Pattern types are named according to their frequency in the population, with Type I present in ∼60%, Type II in ∼25%, Type III in ∼10%, and Type IV in ∼5%. Previous work has demonstrated that psychiatric conditions with high estimated heritability (e.g. schizophrenia, bipolar disorder) are associated with reduced frequency of Type I patterns, but the general heritability of the OFC sulcogyral patterns is unknown. We examined concordance of OFC patterns in 304 monozygotic (MZ) twins relative to 172 dizygotic (DZ) twins using structural magnetic resonance imaging data. We find that the frequency of pattern types within MZ and DZ twins are similar and bilateral concordance rates across all pattern types in DZ twins were 14% and 21% for MZ twins. Results from follow-up analyses confirm that continuity in the rostral-caudal direction is an important source of variability within the OFC, and subtype analyses indicate that variability is present in other sulci that are not represented by overall OFC pattern type. Overall, these results suggest that OFC sulcogyral patterns may reflect important variance that is not genetic in origin.

Positive associations between cannabis and alcohol use polygenic risk scores and phenotypic opioid misuse among African-Americans.

BACKGROUND: This study examined whether polygenic risk scores (PRS) for lifetime cannabis and alcohol use were associated with misusing opioids, and whether sex differences existed in these relations in an urban, African-American sample. METHODS: Data were drawn from three cohorts of participants (N = 1,103; 45% male) who were recruited in first grade as part of a series of elementary school-based, universal preventive intervention trials conducted in a Mid-Atlantic region of the U.S. In young adulthood, participants provided a DNA sample and reported on whether they had used heroin or misused prescription opioids in their lifetime. Three substance use PRS were computed based on prior GWAS: lifetime cannabis use from Pasman et al. (2018), heavy drinking indexed via maximum number of drinks from Gelernter et al. (2019), and alcohol consumption from Kranzler et al. (2019). RESULTS: Higher PRS for lifetime cannabis use, greater heavy drinking, and greater alcohol consumption were associated with heightened risk for misusing opioids among the whole sample. Significant sex by PRS interactions were also observed such that higher PRS for heavy drinking and alcohol consumption were associated with a greater likelihood of opioid misuse among males, but not females. CONCLUSION: Our findings further elucidate the genetic contributions to misusing opioids by showing that the genetics of cannabis and alcohol consumption are associated with lifetime opioid misuse among young adults, though replication of our findings is needed.

Genetics and prescription opioid use (GaPO): study design for consenting a cohort from an existing biobank to identify clinical and genetic factors influencing prescription opioid use and abuse.

BACKGROUND: Prescription opioids (POs) are commonly used to treat moderate to severe chronic pain in the health system setting. Although they improve quality of life for many patients, more work is needed to identify both the clinical and genetic factors that put certain individuals at high risk for developing opioid use disorder (OUD) following use of POs for pain relief. With a greater understanding of important risk factors, physicians will be better able to identify patients at highest risk for developing OUD for whom non-opioid alternative therapies and treatments should be considered. METHODS: We are conducting a prospective observational study that aims to identify the clinical and genetic factors most stongly associated with OUD. The study design leverages an existing biobank that includes whole exome sequencing and array genotyping. The biobank is maintained within an integrated health system, allowing for the large-scale capture and integration of genetic and non-genetic data. Participants are enrolled into the health system biobank via informed consent and then into a second study that focuses on opioid medication use. Data capture includes validated self-report surveys measuring addiction severity, depression, anxiety, and nicotine use, as well as additional clinical, prescription, and brain imaging data extracted from electronic health records. DISCUSSION: We will harness this multimodal data capture to establish meaningful patient phenotypes in order to understand the genetic and non-genetic contributions to OUD.

Co-Occurring Opioid Use and Depressive Disorders: Patient Characteristics and Co-Occurring Health Conditions.

OBJECTIVE: Among persons with opioid use disorder (OUD), co-occurring depression is linked to a greater risk of opioid misuse, overdose and suicide. Less is known about characteristics and other comorbid health conditions of persons with co-occurring opioid use and depressive disorders. METHODS: This study used electronic health record (EHR) encounters from the Geisinger Health System prior to the fall of 2019. Adult patients were recruited from a medication-based treatment clinic and had an OUD diagnosis (N = 692). Co-occurring depression was defined by a depression diagnosis in the EHR. Multivariable logistic regression was performed to assess differences in characteristics, behavioral health and medical diagnoses, as well as opioid overdose and suicide attempt or ideation between individuals with and without comorbid depression. RESULTS: Forty-seven percent of patients with OUD had a lifetime depression diagnosis. Individuals with co-occurring depression were more likely to be female and have comorbid chronic pain or other medical conditions. Co-occurring depression was associated with an increased likelihood of other mental health and substance use disorders, as well as opioid overdose and/or suicide attempt or ideation. CONCLUSIONS: While it is established that co-occurring depression is associated with increased risk of overdose and suicide, this study adds that other health conditions, including chronic pain and common medical conditions, are more prevalent among persons with co-occurring depressive disorders. Results highlight the need to consider these complex health needs when developing treatment plans and services.

Comprehensive Assessment of Visual Perceptual Skills in Autism Spectrum Disorder.

The purpose of the current study was to assess meaningful variability in visual-perceptual skills using a standardized assessment of visual perception, the Test of Visual Perceptual Skills (TVPS), across children with and without autism spectrum disorder (ASD). In addition to assessing overall accuracy across subtests of the TVPS, we also assessed response variability at the item-level, and the linear relationship between quantitative measures of ASD symptoms, task performance, and item-level variance. We report a significant linear relationship between ASD features and performance on the TVPS Figure Ground subtest. Additionally, results of an item-level analysis point to a significant relationship between within-task variability on the Figure Ground subtest and quantitative ASD traits, with a less variable response pattern being associated with increased ASD symptoms. Findings presented here suggest variability in perceptual processing across ASD may be influenced by individual differences in trait distribution.

Resting and Functional Pupil Response Metrics Indicate Features of Reward Sensitivity and ASD in Children.

The current study examined the relationship between quantitative measures of reward and punishment sensitivity, features of autism spectrum disorder (ASD), and resting and functional pupil response metrics across a clinically heterogeneous sample. Scores on a parent-report measure of punishment and reward sensitivity were correlated with ASD features. We also assessed whether pupil measurements could be used as a physiologic correlate of reward sensitivity and predictor of ASD diagnosis. In a logistic regression model, pupil dilation metrics, sex, and IQ, correctly classified 86.3% of participants as having an ASD diagnosis versus not. This research highlights individual differences of reward sensitivity associated with ASD features. Results support the use of pupil metrics and other patient-level variables as predictors of ASD diagnostic status.

The stability flexibility tradeoff and the dark side of detail.

Learning in dynamic environments requires integrating over stable fluctuations to minimize the impact of noise (stability) but rapidly responding in the face of fundamental changes (flexibility). Achieving one of these goals often requires sacrificing the other to some degree, producing a stability-flexibility tradeoff. Individuals navigate this tradeoff in different ways; some people learn rapidly (emphasizing flexibility) and others rely more heavily on historical information (emphasizing stability). Despite the prominence of such individual differences in learning tasks, the degree to which they relate to broader characteristics of real-world behavior or pathologies has not been well explored. We relate individual differences in learning behavior to self-report measures thought to capture collectively the characteristics of the Autism spectrum. We show that young adults who learn most slowly tend to integrate more effective samples into their beliefs about the world making them more robust to noise (more stability) but are more likely to integrate information from previous contexts (less flexibility). We show that individuals who report paying more attention to detail tend to use high flexibility and low stability information processing strategies. We demonstrate the robustness of this inverse relationship between attention to detail and formation of stable beliefs in a heterogeneous population of children that includes a high proportion of Autism diagnoses. Together, our results highlight that attention to detail reflects an information processing policy that comes with a substantial downside, namely the ability to integrate data to overcome environmental noise.

Orbitofrontal sulcogyral morphology in patients with cocaine use disorder.

Orbitofrontal cortex (OFC) is thought to be involved in appropriate processing of rewarding stimuli, and abnormal OFC structure and function has been found in patients with substance use disorders. Atypical patterns of the H-sulcus in the OFC have been primarily identified with schizophrenia, but also with bipolar disorder, both of which are associated with comorbid substance use. Given the high rates of substance use within Axis I psychiatric disorders, it is reasonable to consider how frequencies of OFC patterns in populations with only substance use compare to controls. This information is crucial to disentangle whether atypical frequencies of H-sulcus sulcogyral patterns within psychopathology are associated with the psychiatric or substance use phenotype. Here, we present the first analysis of H-sulcus sulcogyral patterns in a population of adult black men with (n = 84) and without (n = 24) cocaine use disorder (CUD). We find that OFC sulcogyral patterns are not significantly different from the control group, indicating that OFC sulcogyral patterns are not disrupted in patients with CUD. As exploratory analyses, we describe OFC sulcogyral pattern subtypes in this cohort as well as an additional control group (n = 52), in order to add to the growing body of literature on OFC sulcogyral pattern characterization.

Assessment of Probable Opioid Use Disorder Using Electronic Health Record Documentation.

Importance: Electronic health records are a potentially valuable source of information for identifying patients with opioid use disorder (OUD). Objective: To evaluate whether proxy measures from electronic health record data can be used reliably to identify patients with probable OUD based on Diagnostic and Statistical Manual of Mental Disorders (Fifth Edition) (DSM-5) criteria. Design, Setting, and Participants: This retrospective cross-sectional study analyzed individuals within the Geisinger health system who were prescribed opioids between December 31, 2000, and May 31, 2017, using a mixed-methods approach. The cohort was identified from 16 253 patients enrolled in a contract-based, Geisinger-specific medication monitoring program (GMMP) for opioid use, including patients who maintained or violated contract terms, as well as a demographically matched control group of 16 253 patients who were prescribed opioids but not enrolled in the GMMP. Substance use diagnoses and psychiatric comorbidities were assessed using automated electronic health record summaries. A manual medical record review procedure using DSM-5 criteria for OUD was completed for a subset of patients. The analysis was conducted beginning from June 5, 2017, until May 29, 2020. Main Outcomes and Measures: The primary outcome was the prevalence of OUD as defined by proxy measures for DSM-5 criteria for OUD as well as the prevalence of comorbidities among patients prescribed opioids within an integrated health system. Results: Among the 16 253 patients enrolled in the GMMP (9309 women [57%]; mean [SD] age, 52 [14] years), OUD diagnoses as defined by diagnostic codes were present at a much lower rate than expected (291 [2%]), indicating the necessity for alternative diagnostic strategies. The DSM-5 criteria for OUD can be assessed using manual medical record review; a manual review of 200 patients in the GMMP and 200 control patients identifed a larger percentage of patients with probable moderate to severe OUD (GMMP, 145 of 200 [73%]; and control, 27 of 200 [14%]) compared with the prevalence of OUD assessed using diagnostic codes. Conclusions and Relevance: These results suggest that patients with OUD may be identified using information available in the electronic health record, even when diagnostic codes do not reflect this diagnosis. Furthermore, the study demonstrates the utility of coding for DSM-5 criteria from medical records to generate a quantitative DSM-5 score that is associated with OUD severity.

Behavioural profiling of autism connectivity abnormalities.

BACKGROUND: Brain regions are functionally diverse, and a given region may engage in a variety of tasks. This functional diversity of brain regions may be one factor that has prevented the finding of consistent biomarkers for brain disorders such as autism spectrum disorder (ASD). Thus, methods to characterise brain regions would help to determine how functional abnormalities contribute to affected behaviours. AIMS: As the first illustration of the meta-analytic behavioural profiling procedure, we evaluated how the regions with disrupted connectivity in ASD contributed to various behaviours. METHOD: Connectivity abnormalities were determined from a published degree centrality group comparison based on functional magnetic resonance imaging data from the Autism Brain Imaging Data Exchange. Using BrainMap's database of task-based neuroimaging studies, behavioural profiles were created for abnormally connected regions by relating these regions to tasks activating them. RESULTS: Hyperconnectivity in ASD brains was significantly related to memory, attention, reasoning, social, execution and speech behaviours. Hypoconnectivity was related to vision, execution and speech behaviours. CONCLUSIONS: The procedure outlines the first clinical neuroimaging application of a behavioural profiling method that estimates the functional diversity of brain regions, allowing for the relation of abnormal functional connectivity to diagnostic criteria. Behavioural profiling and the computational insights it provides can facilitate better understanding of the functional manifestations of various disorders, including ASD.

The use of the orbitofrontal H-sulcus as a reference frame for value signals.

Understanding the factors that drive organization and function of the brain is an enduring question in neuroscience. Using functional magnetic resonance imaging (fMRI), structure and function have been mapped in primary sensory cortices based on knowledge of the organizational principles that likely drive a given region (e.g., aspects of visual form in primary visual cortex and sound frequency in primary auditory cortex) and knowledge of underlying cytoarchitecture. The organizing principles of higher-order brain areas that encode more complex signals, such as the orbitofrontal cortex (OFC), are less well understood. One fundamental component that underlies the many functions of the OFC is the ability to compute the reward or value of a given object. There is evidence of variability in the spatial location of responses to specific categories of objects (or value of said objects) within the OFC, and several reference frames have been proposed to explain this variability, including topographic spatial gradients that correspond to axes of primary versus secondary rewards and positive versus negative reinforcers. One potentially useful structural morphometric reference frame in the OFC is the "H-sulcus," a pattern formed by medial orbital, lateral orbital and transverse orbital sulci. In 48 human subjects, we use a structural morphometric tracing procedure to localize functional activation along the H-sulcus for face and food stimuli. We report the novel finding that food-selective responses are consistently found within the caudal portion of the medial orbital sulcus, but no consistency within the H-sulcus for response to face stimuli. These results suggest that sulcogyral anatomy of the H-sulcus may be an important morphological metric that contributes to the organizing principles of the OFC response to certain stimulus categories, including food.