Enhancing post-traumatic stress disorder patient assessment: leveraging natural language processing for research of domain criteria identification using electronic medical records.

BACKGROUND: Extracting research of domain criteria (RDoC) from high-risk populations like those with post-traumatic stress disorder (PTSD) is crucial for positive mental health improvements and policy enhancements. The intricacies of collecting, integrating, and effectively leveraging clinical notes for this purpose introduce complexities. METHODS: In our study, we created a natural language processing (NLP) workflow to analyze electronic medical record (EMR) data and identify and extract research of domain criteria using a pre-trained transformer-based natural language model, all-mpnet-base-v2. We subsequently built dictionaries from 100,000 clinical notes and analyzed 5.67 million clinical notes from 38,807 PTSD patients from the University of Pittsburgh Medical Center. Subsequently, we showcased the significance of our approach by extracting and visualizing RDoC information in two use cases: (i) across multiple patient populations and (ii) throughout various disease trajectories. RESULTS: The sentence transformer model demonstrated high F1 macro scores across all RDoC domains, achieving the highest performance with a cosine similarity threshold value of 0.3. This ensured an F1 score of at least 80% across all RDoC domains. The study revealed consistent reductions in all six RDoC domains among PTSD patients after psychotherapy. We found that 60.6% of PTSD women have at least one abnormal instance of the six RDoC domains as compared to PTSD men (51.3%), with 45.1% of PTSD women with higher levels of sensorimotor disturbances compared to men (41.3%). We also found that 57.3% of PTSD patients have at least one abnormal instance of the six RDoC domains based on our records. Also, veterans had the higher abnormalities of negative and positive valence systems (60% and 51.9% of veterans respectively) compared to non-veterans (59.1% and 49.2% respectively). The domains following first diagnoses of PTSD were associated with heightened cue reactivity to trauma, suicide, alcohol, and substance consumption. CONCLUSIONS: The findings provide initial insights into RDoC functioning in different populations and disease trajectories. Natural language processing proves valuable for capturing real-time, context dependent RDoC instances from extensive clinical notes.

Long-Term Outcomes Associated With ß-Lactam Allergies.

Importance: ß-lactam (BL) allergies are the most common drug allergy worldwide, but most are reported in error. BL allergies are also well-established risk factors for adverse drug events and antibiotic-resistant infections during inpatient health care encounters, but the understanding of the long-term outcomes of patients with BL allergies remains limited. Objective: To evaluate the long-term clinical outcomes of patients with BL allergies. Design, Setting, and Participants: This longitudinal retrospective cohort study was conducted at a single regional health care system in western Pennsylvania. Electronic health records were analyzed for patients who had an index encounter with a diagnosis of sepsis, pneumonia, or urinary tract infection between 2007 and 2008. Patients were followed-up until death or the end of 2018. Data analysis was performed from January 2022 to January 2024. Exposure: The presence of any BL class antibiotic in the allergy section of a patient's electronic health record, evaluated at the earliest occurring observed health care encounter. Main Outcomes and Measures: The primary outcome was all-cause mortality, derived from the Social Security Death Index. Secondary outcomes were defined using laboratory and microbiology results and included infection with methicillin-resistant Staphylococcus aureus (MRSA), Clostridium difficile, or vancomycin-resistant Enterococcus (VRE) and severity and occurrence of acute kidney injury (AKI). Generalized estimating equations with a patient-level panel variable and time exposure offset were used to evaluate the odds of occurrence of each outcome between allergy groups. Results: A total of 20 092 patients (mean [SD] age, 62.9 [19.7] years; 12 231 female [60.9%]), of whom 4211 (21.0%) had BL documented allergy and 15 881 (79.0%) did not, met the inclusion criteria. A total of 3513 patients (17.5%) were Black, 15 358 (76.4%) were White, and 1221 (6.0%) were another race. Using generalized estimating equations, documented BL allergies were not significantly associated with the odds of mortality (odds ratio [OR], 1.02; 95% CI, 0.96-1.09). BL allergies were associated with increased odds of MRSA infection (OR, 1.44; 95% CI, 1.36-1.53), VRE infection (OR, 1.18; 95% CI, 1.05-1.32), and the pooled rate of the 3 evaluated antibiotic-resistant infections (OR, 1.33; 95% CI, 1.30-1.36) but were not associated with C difficile infection (OR, 1.04; 95% CI, 0.94-1.16), stage 2 and 3 AKI (OR, 1.02; 95% CI, 0.96-1.10), or stage 3 AKI (OR, 1.06; 95% CI, 0.98-1.14). Conclusions and Relevance: Documented BL allergies were not associated with the long-term odds of mortality but were associated with antibiotic-resistant infections. Health systems should emphasize accurate allergy documentation and reduce unnecessary BL avoidance.

Enhancing post-traumatic stress disorder patient assessment: Leveraging Natural Language Processing for Research of Domain Criteria Identification using electronic medical records.

Background: Extracting research of domain criteria (RDoC) from high-risk populations like those with post-traumatic stress disorder (PTSD) is crucial for positive mental health improvements and policy enhancements. The intricacies of collecting, integrating, and effectively leveraging clinical notes for this purpose introduce complexities. Methods: In our study, we created an NLP workflow to analyze electronic medical record (EMR) data, and identify and extract research of domain criteria using a pre-trained transformer-based natural language model, allmpnet-base-v2. We subsequently built dictionaries from 100,000 clinical notes and analyzed 5.67 million clinical notes from 38,807 PTSD patients from the University of Pittsburgh Medical Center. Subsequently, we showcased the significance of our approach by extracting and visualizing RDoC information in two use cases: (i) across multiple patient populations and (ii) throughout various disease trajectories. Results: The sentence transformer model demonstrated superior F1 macro scores across all RDoC domains, achieving the highest performance with a cosine similarity threshold value of 0.3. This ensured an F1 score of at least 80% across all RDoC domains. The study revealed consistent reductions in all six RDoC domains among PTSD patients after psychotherapy. Women had the highest abnormalities of sensorimotor systems, while veterans had the highest abnormalities of negative and positive valence systems. The domains following first diagnoses of PTSD were associated with heightened cue reactivity to trauma, suicide, alcohol, and substance consumption. Conclusions: The findings provide initial insights into RDoC functioning in different populations and disease trajectories. Natural language processing proves valuable for capturing real-time, context dependent RDoC instances from extensive clinical notes.

DeepBiomarker2: Prediction of Alcohol and Substance Use Disorder Risk in Post-Traumatic Stress Disorder Patients Using Electronic Medical Records and Multiple Social Determinants of Health.

Prediction of high-risk events amongst patients with mental disorders is critical for personalized interventions. We developed DeepBiomarker2 by leveraging deep learning and natural language processing to analyze lab tests, medication use, diagnosis, social determinants of health (SDoH) parameters, and psychotherapy for outcome prediction. To increase the model's interpretability, we further refined our contribution analysis to identify key features by scaling with a factor from a reference feature. We applied DeepBiomarker2 to analyze the EMR data of 38,807 patients from the University of Pittsburgh Medical Center diagnosed with post-traumatic stress disorder (PTSD) to determine their risk of developing alcohol and substance use disorder (ASUD). DeepBiomarker2 predicted whether a PTSD patient would have a diagnosis of ASUD within the following 3 months with an average c-statistic (receiver operating characteristic AUC) of 0.93 and average F1 score, precision, and recall of 0.880, 0.895, and 0.866 in the test sets, respectively. Our study found that the medications clindamycin, enalapril, penicillin, valacyclovir, Xarelto/rivaroxaban, moxifloxacin, and atropine and the SDoH parameters access to psychotherapy, living in zip codes with a high normalized vegetative index, Gini index, and low-income segregation may have potential to reduce the risk of ASUDs in PTSD. In conclusion, the integration of SDoH information, coupled with the refined feature contribution analysis, empowers DeepBiomarker2 to accurately predict ASUD risk. Moreover, the model can further identify potential indicators of increased risk along with medications with beneficial effects.

Prediction of Adverse Events Risk in Patients with Comorbid Post- Traumatic Stress Disorder and Alcohol Use Disorder Using Electronic Medical Records by Deep Learning Models.

Background: Prediction of high-risk events in mental disorder patients is crucial. In our previous study, we developed a deep learning model: DeepBiomarker by using electronic medical records (EMR) to predict suicide related event (SRE) risk in post-traumatic stress disorder (PTSD) patients. Methods: We applied DeepBiomarker2 through data integration of multimodal information: lab test, medication, co-morbidities, and social determinants of health. We analyzed EMRs of 5,565 patients from University of Pittsburgh Medical Center with a diagnosis of PTSD and alcohol use disorder (AUD) on risk of developing an adverse event (opioid use disorder, SREs, depression and death). Results: DeepBiomarker2 predicted whether a PTSD + AUD patient will have a diagnosis of any adverse events (SREs, opioid use disorder, depression, death) within 3 months with area under the receiver operator curve (AUROC) of 0.94. We found piroxicam, vilazodone, dronabinol, tenofovir, suvorexant, empagliflozin, famciclovir, veramyst, amantadine, sulfasalazine, and lamivudine to have potential to reduce risk. Conclusions: DeepBiomarker2 can predict multiple adverse event risk with high accuracy and identify potential risk and beneficial factors. Our results offer suggestions for personalized interventions in a variety of clinical and diverse populations.

DeepBiomarker2: Prediction of alcohol and substance use disorder risk in post-traumatic stress disorder patients using electronic medical records and multiple social determinants of health.

Introduction: Prediction of high-risk events amongst patients with mental disorders is critical for personalized interventions. In our previous study, we developed a deep learning-based model, DeepBiomarker by utilizing electronic medical records (EMR) to predict the outcomes of patients with suicide-related events in post-traumatic stress disorder (PTSD) patients. Methods: We improved our deep learning model to develop DeepBiomarker2 through data integration of multimodal information: lab tests, medication use, diagnosis, and social determinants of health (SDoH) parameters (both individual and neighborhood level) from EMR data for outcome prediction. We further refined our contribution analysis for identifying key factors. We applied DeepBiomarker2 to analyze EMR data of 38,807 patients from University of Pittsburgh Medical Center diagnosed with PTSD to determine their risk of developing alcohol and substance use disorder (ASUD). Results: DeepBiomarker2 predicted whether a PTSD patient will have a diagnosis of ASUD within the following 3 months with a c-statistic (receiver operating characteristic AUC) of 0·93. We used contribution analysis technology to identify key lab tests, medication use and diagnosis for ASUD prediction. These identified factors imply that the regulation of the energy metabolism, blood circulation, inflammation, and microbiome is involved in shaping the pathophysiological pathways promoting ASUD risks in PTSD patients. Our study found protective medications such as oxybutynin, magnesium oxide, clindamycin, cetirizine, montelukast and venlafaxine all have a potential to reduce risk of ASUDs. Discussion: DeepBiomarker2 can predict ASUD risk with high accuracy and can further identify potential risk factors along with medications with beneficial effects. We believe that our approach will help in personalized interventions of PTSD for a variety of clinical scenarios.

Derivation and assessment of the opioid use disorder severity scale: prediction of health, psychological and social adjustment problems.

Background: Severity of substance use disorder (SUD) is typically evaluated by tabulating the number of symptoms. The resulting estimate of disorder severity is, however, biased due to intercorrelations among symptoms and their unequal salience. Objective. Employing item response theory (IRT) methodology, opioid use disorder symptoms were calibrated to derive the Opioid Use Disorder Severity Scale (OUDSS) and assess its predictive ability in men and women separately. Methods: A two-parameter IRT model was utilized to derive the OUDSS from DSM-IV symptoms recorded on the Structured Clinical Interview for DSM-IV (SCID) in 438 men and 429 women who reported at least one lifetime opioid consumption event. The predictive ability of the OUDSS was evaluated using the 10 health, psychological, and social adjustment domains of the revised Drug Use Screening Inventory (DUSI-R) assessed 2 years later. Results: The OUDSS score predicted the severity of problems in all 10 DUSI-R domains in men and women. The OUDSS also predicted the DUSI-R diagnostic cutoff score of overall problem density score in men and women (OR = 2.21 and OR = 4.83, respectively). Withdrawal was the most frequently endorsed symptom in this sample of opioid users. The other symptoms' frequencies, while somewhat lower than withdrawal's, did not differ from it substantially, indicating a similar severity threshold. Conclusions: OUDSS enables dimensional measurement of opioid use severity on an interval scale. The OUDSS and DUSI-R together can identify problem areas requiring prevention or treatment.

Could a continuous measure of individual transmissible risk be useful in clinical assessment of substance use disorder? Findings from the National Epidemiological Survey on Alcohol and Related Conditions.

OBJECTIVE: Toward meeting the need for a measure of individual differences in substance use disorder (SUD) liability that is grounded in the multifactorial model of SUD transmission, this investigation tested to what degree transmissible SUD risk is better measured using the continuous Transmissible Liability Index (TLI) (young adult version) compared to alternative contemporary clinical methods. METHOD: Data from 9535 18- to 30-year-olds in the 2001-2002 National Epidemiologic Survey on Alcohol and Related Conditions, a U.S. representative sample, were used to compute TLI scores and test hypotheses. Other variables were SUDs of each DSM-IV drug class, clinical predictors of SUD treatment outcomes, treatment seeking and usage, age of onset of SUDs and substance use (SU), and eligibility for SUD clinical trials. RESULTS: TLI scores account for variation in SUD risk over and above parental lifetime SUD, conduct and antisocial personality disorder criteria and frequency of SU. SUD risk increases two- to four-fold per standard deviation increment in TLI scores. The TLI is associated with SUD treatment seeking and usage, younger age of onset of SU and SUD, and exclusion from traditional clinical trials of SUD treatment. CONCLUSIONS: The TLI can identify persons with high versus low transmissible SUD risk, worse prognosis of SUD recovery and to whom extant SUD clinical trials results may not generalize. Recreating TLI scores in extant datasets facilitates etiology and applied research on the full range of transmissible SUD risk in development, treatment and recovery without obtaining new samples.

Screening current and future diagnosis of psychiatric disorders using the Revised Drug Use Screening Inventory.

The revised Drug Use Screening Inventory (DUSI-R) is a valid and reliable self-report questionnaire used for quantifying problems that frequently precede and co-occur with substance abuse. The present investigation determined whether the DUSI-R's items can be aggregated into scales that implicate current and future psychiatric disorders. Scales were derived to screen for attention deficit, conduct, antisocial, anxiety, depression, and substance use disorders in a longitudinally tracked cohort of 328 boys. Evaluations were conducted when the boys were 12-14, 16, 19, and 22 years of age. All of the scales identified youths qualifying for current DSM-IV diagnosis with excellent accuracy. Predictive validity of the scales ranged from good to excellent. Accordingly cut-off scores were determined for each scale for use in practical settings to identify youths who require comprehensive diagnostic evaluation. Thus in addition to its utility for detecting problems that precede and correlate with substance abuse, the DUSI-R is cost-efficient for screening youths for mental disorders.

Assessment of risk for substance use disorder consequent to consumption of illegal drugs: psychometric validation of the neurobehavior disinhibition trait.

Previous research has shown that the trait neurobehavior disinhibition (ND), which consists of affect, behavior, and cognitive indicators of self-regulation, is a significant predictor of substance use disorder (SUD) between childhood and young adulthood. The authors evaluated the psychometric properties of the ND trait in 278 boys evaluated at ages 10-12 and 16 years. ND score significantly predicted SUD and outcomes that commonly manifest in tandem with SUD by age 19, such as violence, arrests, committing crime while intoxicated, and concussion injury. In addition to predictive validity, the ND trait was found to have good construct, discriminative, and concurrent validity, as well as good test-retest and internal reliability. The ND trait may be useful for detecting youths at high risk for developing SUD and related outcomes.

Outcomes and costs of abciximab versus eptifibatide for percutaneous coronary intervention.

BACKGROUND: Patients undergoing percutaneous coronary intervention (PCI) with stent placement are often prescribed glycoprotein IIb/IIIa inhibitors. However, drug selection is often based on clinicians' preference and cost because few studies have directly compared abciximab and eptifibatide. OBJECTIVE: To compare clinical outcomes and total hospital costs of abciximab and eptifibatide in patients undergoing stent placement during PCI in a real-world setting. METHODS: A retrospective cohort analysis was conducted of 960 patients administered abciximab or eptifibatide for intracoronary stent placement between 1999 and 2001 at a tertiary care hospital. The primary outcome was bleeding, defined as major, moderate, or minor according to published criteria. Secondary outcomes included in-hospital death, myocardial infarction, revascularization, and the triple composite endpoint of those outcomes, thrombocytopenia, length-of-stay, and total hospital costs. Pearson's chi(2) analysis, Fisher's exact test, and ANOVA were used for statistical analysis. RESULTS: The frequency of bleeding complications based on severity was similar between abciximab and eptifibatide: major (2.4% vs 2.8%), moderate (12.4% vs 10.5%), and minor (4.0% vs 3.9%), respectively (p = 0.86). Secondary clinical outcomes were also similar between groups (p > 0.05). Total costs for hospitalization were significantly greater for abciximab compared with eptifibatide ($16,383 +/- 6799 vs $14,115 +/- 6285; p < 0.001). Drug acquisition costs were also significantly greater for abciximab compared with eptifibatide ($508 +/- 159 vs $465 +/- 263; p = 0.003). CONCLUSIONS: In patients undergoing stent placement during PCI, abciximab and eptifibatide are comparable in terms of safety and effectiveness despite significant differences in hospitalization and acquisition costs.

Characteristics of men with substance use disorder consequent to illicit drug use: comparison of a random sample and volunteers.

OBJECTIVE: Men qualifying for substance use disorder (SUD) consequent to consumption of an illicit drug were compared according to recruitment method. It was hypothesized that volunteers would be more self-disclosing and exhibit more severe disturbances compared to randomly recruited subjects. METHODS: Personal, demographic, family, social, substance use, psychiatric, and SUD characteristics of volunteers (N = 146) were compared to randomly recruited (N = 102) subjects. RESULTS: Volunteers had lower socioceconomic status, were more likely to be African American, and had lower IQ than randomly recruited subjects. Volunteers also evidenced greater social and family maladjustment and more frequently had received treatment for substance abuse. In addition, lower social desirability response bias was observed in the volunteers. SUD was not more severe in the volunteers; however, they reported a higher lifetime rate of opiate, diet, depressant, and analgesic drug use. CONCLUSIONS: Volunteers and randomly recruited subjects qualifying for SUD consequent to illicit drug use are similar in SUD severity but differ in terms of severity of psychosocial disturbance and history of drug involvement. The factors discriminating volunteers and randomly recruited subjects are well known to impact on outcome, hence they need to be considered in research design, especially when selecting a sampling strategy in treatment research.

Dental abnormalities in children of fathers with substance use disorders.

Very little is known about whether parental substance-use disorders (SUDs) affect the prevalence of dental abnormalities among their offspring. This study examined the prevalence of various dental abnormalities in sons of fathers with SUDs (the high average risk, or HAR, group) versus the prevalence of these abnormalities among sons of fathers without SUDs (the low average risk, or LAR, group). A total of 385 sons and their families were comprehensively assessed at five different ages, 10-12, 12-14, 16, 19, and 22. All of these participants were participating in an ongoing longitudinal NIDA-funded center study (CEDAR) evaluating the etiology of SUDs, in collaboration with the University of Pittsburgh Dental School. The data from this study provide evidence that paternal SUDs (HAR vs. LAR status) is associated with poor dental condition, poor oral hygiene, a greater need for dental treatment, and inadequate levels of dental treatment utilization.

Liability to substance use disorders: 2. A measurement approach.

Liabilities to complex disorders, discussed in the accompanying paper, present difficulties in measurement related to the arbitrariness of diagnostic threshold definitions and problems with discrimination between trait values, especially within the 'normal' individuals. The inability to quantitatively estimate the risk for a disorder, such as substance use disorders (SUD), is an obstacle for studying etiological (e.g. genetic) mechanisms and developing efficient prevention and treatment measures. Based on the concept of common liability to SUD, this paper delineates an application of the longitudinal family/high-risk design and item response theory to the development of a continuous index of liability. The method has been tested in both simulation study and empirical data. The approach described affords the opportunity to quantitatively estimate the risk for SUD at an early age and before any drug exposure. This method is also applicable to measuring liabilities to other complex disorders, especially those with relatively late onset.