Dataset Information

Validation of an alcohol misuse classifier in hospitalized patients.

ABSTRACT:

Background

Current modes of identifying alcohol misuse in hospitalized patients rely on self-report questionnaires and diagnostic codes that have limitations, including low sensitivity. Information in the clinical notes of the electronic health record (EHR) may further augment the identification of alcohol misuse. Natural language processing (NLP) with supervised machine learning has been successful at analyzing clinical notes and identifying cases of alcohol misuse in trauma patients.

Methods

An alcohol misuse NLP classifier, previously developed on trauma patients who completed the Alcohol Use Disorders Identification Test, was validated in a cohort of 1000 hospitalized patients at a large, tertiary health system between January 1, 2007 and September 1, 2017. The clinical notes were processed using the clinical Text Analysis and Knowledge Extraction System. The National Institute on Alcohol Abuse and Alcoholism (NIAAA) guidelines for alcohol misuse were used during annotation of the medical records in our validation dataset.

Results

The alcohol misuse classifier had an area under the receiver operating characteristic curve of 0.91 (95% CI 0.90-0.93) in the cohort of hospitalized patients. The sensitivity, specificity, positive predictive value, and negative predictive value were 0.88 (95% CI 0.85-0.90), 0.78 (95% CI 0.74-0.82), 0.85 (95% CI 0.82-0.87), and 0.82 (95% CI 0.78-0.86), respectively. The Hosmer-Lemeshow Test (p = 0.13) demonstrates good model fit. Additionally, there was a dose-dependent response in alcohol consumption behaviors across increasing strata of predicted probabilities for alcohol misuse.

Conclusion

The alcohol misuse NLP classifier had good discrimination and test characteristics in hospitalized patients. An approach using the clinical notes with NLP and supervised machine learning may better identify alcohol misuse cases than conventional methods solely relying on billing diagnostic codes.

SUBMITTER: To D

PROVIDER: S-EPMC7101259 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background Opioid misuse screening in hospitals is resource-intensive and rarely done. Many hospitalized patients are never offered opioid treatment. An automated approach leveraging routinely captured electronic health record (EHR) data may be easier for hospitals to institute. We previously derived and internally validated an opioid classifier in a separate hospital setting. The aim is to externally validate our previously published and open-source machine-learning classifier at a different hospital for identifying cases of opioid misuse. Methods An observational cohort of 56,227 adult hospitalizations was examined between October 2017 and December 2019 during a hospital-wide substance use screening program with manual screening. Manually completed Drug Abuse Screening Test served as the reference standard to validate a convolutional neural network (CNN) classifier with coded word embedding features from the clinical notes of the EHR. The opioid classifier utilized all notes in the EHR and sensitivity analysis was also performed on the first 24 h of notes. Calibration was performed to account for the lower prevalence than in the original cohort. Results Manual screening for substance misuse was completed in 67.8% (n?=?56,227) with 1.1% (n?=?628) identified with opioid misuse. The data for external validation included 2,482,900 notes with 67,969 unique clinical concept features. The opioid classifier had an AUC of 0.99 (95% CI 0.99–0.99) across the encounter and 0.98 (95% CI 0.98–0.99) using only the first 24 h of notes. In the calibrated classifier, the sensitivity and positive predictive value were 0.81 (95% CI 0.77–0.84) and 0.72 (95% CI 0.68–0.75). For the first 24 h, they were 0.75 (95% CI 0.71–0.78) and 0.61 (95% CI 0.57–0.64). Conclusions Our opioid misuse classifier had good discrimination during external validation. Our model may provide a comprehensive and automated approach to opioid misuse identification that augments current workflows and overcomes manual screening barriers. Supplementary Information The online version contains supplementary material available at 10.1186/s13722-021-00229-7.

Project description:The objective was to assess the relationship between alcohol use and misuse and patient sex among emergency department (ED) patients by comparing self-reported estimates of quantity and frequency of alcohol use, estimated blood alcohol concentrations (eBACs) when typically drinking and during heavy episodic drinking (binging), and alcohol misuse severity, to understand sex differences in alcohol use and misuse for this population.The authors surveyed a random sample of nonintoxicated, subcritically ill or injured, 18- to 64-year-old English- or Spanish-speaking patients on randomly selected dates and times at two EDs during July 2009 and August 2009. Participants self-administered a questionnaire about their self-reported alcohol use during a typical month within the past 12 months and the Alcohol Use Disorders Identification Test (AUDIT). Using the formulae by Matthews and Miller, sex-specific eBACs were calculated for participants according to their reported weight and the number of reported alcoholic drinks consumed on days when typically drinking and on days of heavy episodic (binge) drinking (five or more drinks/occasion for men, four or more drinks for women). Sex-specific alcohol misuse severity levels (low-risk, harmful, hazardous, and dependence) were calculated using AUDIT scores. Wilcoxon rank-sum and Pearson's chi-square tests were used to compare outcomes by sex. Negative binomial regression was used to assess the relationship between sex and the number of drinks consumed on a typical day, the number of days spent drinking and binging, and estimated AUDIT scores. Logistic regression was used to assess the outcome of the presence of binging according to sex. Multinomial logistic regression was used to compare by sex the percentage of days spent drinking and binging in 1 month, eBACs when typically drinking and when binging, and AUDIT at-risk drinking levels. Incidence rate ratios (IRRs) and adjusted odds ratios (AORs) with 95% confidence intervals (CIs) were estimated. All models were adjusted for patient demographic characteristics.Of the 513 participants, 52.1% were women, 55.8% were white non-Hispanic, and their median age was 34 years (interquartile range [IQR] = 25 to 46 years). Men reported greater mean alcohol consumption than women when typically drinking (4.3 vs. 3.3 drinks/day; p < 0.001) and during heavy episodic drinking (8.6 vs. 5.3 drinks/occasion; p < 0.001). Men spent more days drinking (IRR = 1.41, 95% CI = 1.19 to 1.65) and engaging in heavy episodic drinking (IRR = 1.68, 95% CI = 1.31 to 2.17) than women. Additionally, men were more likely to engage in heavy episodic drinking (AOR = 1.72, 95% CI = 1.16 to 2.56) than women. However, the mean eBACs for men and women were similar when typically drinking (0.05 vs. 0.06; p < 0.13) and during heavy episodic drinking (0.13 vs. 0.12; p < 0.13). Mean AUDIT scores were greater for men than women (7.5 vs. 5.3; p < 0.001), although alcohol misuse severity levels were similar between men and women (24.4% vs. 26.6% for hazardous, 2.8% vs. 2.2% for harmful, and 6.5% vs. 3.4% for dependence; p < 0.38).Although men drink more than women, women have similar eBACs with comparable levels of alcohol misuse. Women may benefit from recognizing that they are reaching similar levels of intoxication compared to men. Addressing these differences and possible health implications in future ED brief interventions may induce changes in problematic alcohol use among women.

Project description:BackgroundApproaches are needed to better delineate the continuum of opioid misuse that occurs in hospitalized patients. A prognostic enrichment strategy with latent class analysis (LCA) may facilitate treatment strategies in subtypes of opioid misuse. We aim to identify subtypes of patients with opioid misuse and examine the distinctions between the subtypes by examining patient characteristics, topic models from clinical notes, and clinical outcomes.MethodsThis was an observational study of inpatient hospitalizations at a tertiary care center between 2007 and 2017. Patients with opioid misuse were identified using an operational definition applied to all inpatient encounters. LCA with eight class-defining variables from the electronic health record (EHR) was applied to identify subtypes in the cohort of patients with opioid misuse. Comparisons between subtypes were made using the following approaches: (1) descriptive statistics on patient characteristics and healthcare utilization using EHR data and census-level data; (2) topic models with natural language processing (NLP) from clinical notes; (3) association with hospital outcomes.FindingsThe analysis cohort was 6,224 (2.7% of all hospitalizations) patient encounters with opioid misuse with a data corpus of 422,147 clinical notes. LCA identified four subtypes with differing patient characteristics, topics from the clinical notes, and hospital outcomes. Class 1 was categorized by high hospital utilization with known opioid-related conditions (36.5%); Class 2 included patients with illicit use, low socioeconomic status, and psychoses (12.8%); Class 3 contained patients with alcohol use disorders with complications (39.2%); and class 4 consisted of those with low hospital utilization and incidental opioid misuse (11.5%). The following hospital outcomes were the highest for each subtype when compared against the other subtypes: readmission for class 1 (13.9% vs. 10.5%, p<0.01); discharge against medical advice for class 2 (12.3% vs. 5.3%, p<0.01); and in-hospital death for classes 3 and 4 (3.2% vs. 1.9%, p<0.01).ConclusionsA 4-class latent model was the most parsimonious model that defined clinically interpretable and relevant subtypes for opioid misuse. Distinct subtypes were delineated after examining multiple domains of EHR data and applying methods in artificial intelligence. The approach with LCA and readily available class-defining substance use variables from the EHR may be applied as a prognostic enrichment strategy for targeted interventions.

Project description:RationaleAlcohol misuse is common in patients admitted to the intensive care unit (ICU), but there is currently no evidence-based approach to address drinking in ICU survivors.ObjectivesWe sought to describe the experience of ICU survivors with alcohol misuse during their hospitalization and the 3 months after hospital discharge to inform an alcohol-specific intervention for this unique population.MethodsWe conducted a descriptive qualitative study of ICU survivors from medical ICUs in three separate hospitals with a positive screening result on the Alcohol Use Disorders Identification Test. Semistructured interviews were conducted 3 months after hospital discharge of patients. Patients were also allowed to nominate up to two friends or family members for enrollment to provide additional perspective on the patient's experience.ResultsWe enrolled 50 patients and 22 of their friends and/or family members. The average APACHE II score was 23, 80% of patients were male, and the average age was 50 years; 70% of patients and 77% of friends/family members completed the semistructured interview 3 months after hospital discharge. We identified three domains that could inform an alcohol-specific intervention, each with multiple themes: motivation with complications (anxiety and depression, critical illness as a catalyst, delirium and cognitive impairment); therapeutic alliance (autonomy, failure and opportunities to build a therapeutic alliance); and the return to the home milieu (lack of screening for depression and anxiety, social network support for drinking, social isolation, social network support for abstinence, lack of available and affordable treatment, and negative experiences with Alcoholics Anonymous).ConclusionsAn alcohol intervention for ICU survivors would account for the context in which patients are making a decision about their drinking and optimize the patient-provider interaction. Contrary to current paradigms that focus on addressing alcohol consumption only during a hospitalization, an intervention for ICU survivors should continue as patients transition from the hospital to home.