Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models.

OBJECTIVE: The timely stratification of trauma injury severity can enhance the quality of trauma care but it requires intense manual annotation from certified trauma coders. The objective of this study is to develop machine learning models for the stratification of trauma injury severity across various body regions using clinical text and structured electronic health records (EHRs) data. MATERIALS AND METHODS: Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create 2 machine learning models with different approaches to representing text. The first one fuses concept unique identifiers (CUIs) extracted from free text with structured EHR variables, while the second one integrates free text with structured EHR variables. Temporal validation was undertaken to ensure the models' temporal generalizability. Additionally, analyses to assess the variable importance were conducted. RESULTS: Both models demonstrated impressive performance in categorizing leg injuries, achieving high accuracy with macro-F1 scores of over 0.8. Additionally, they showed considerable accuracy, with macro-F1 scores exceeding or near 0.7, in assessing injuries in the areas of the chest and head. We showed in our variable importance analysis that the most important features in the model have strong face validity in determining clinically relevant trauma injuries. DISCUSSION: The CUI-based model achieves comparable performance, if not higher, compared to the free-text-based model, with reduced complexity. Furthermore, integrating structured EHR data improves performance, particularly when the text modalities are insufficiently indicative. CONCLUSIONS: Our multi-modal, multiclass models can provide accurate stratification of trauma injury severity and clinically relevant interpretations.

Causes, Diagnostic Testing, and Treatments Related to Clinical Deterioration Events among High-Risk Ward Patients.

OBJECTIVE: Timely intervention for clinically deteriorating ward patients requires that care teams accurately diagnose and treat their underlying medical conditions. However, the most common diagnoses leading to deterioration and the relevant therapies provided are poorly characterized. Therefore, we aimed to determine the diagnoses responsible for clinical deterioration, the relevant diagnostic tests ordered, and the treatments administered among high-risk ward patients using manual chart review. DESIGN: Multicenter retrospective observational study. SETTING: Inpatient medical-surgical wards at four health systems from 2006-2020 PATIENTS: Randomly selected patients (1,000 from each health system) with clinical deterioration, defined by reaching the 95th percentile of a validated early warning score, electronic Cardiac Arrest Risk Triage (eCART), were included. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Clinical deterioration was confirmed by a trained reviewer or marked as a false alarm if no deterioration occurred for each patient. For true deterioration events, the condition causing deterioration, relevant diagnostic tests ordered, and treatments provided were collected. Of the 4,000 included patients, 2,484 (62%) had clinical deterioration confirmed by chart review. Sepsis was the most common cause of deterioration (41%; n=1,021), followed by arrhythmia (19%; n=473), while liver failure had the highest in-hospital mortality (41%). The most common diagnostic tests ordered were complete blood counts (47% of events), followed by chest x-rays (42%), and cultures (40%), while the most common medication orders were antimicrobials (46%), followed by fluid boluses (34%), and antiarrhythmics (19%). CONCLUSIONS: We found that sepsis was the most common cause of deterioration, while liver failure had the highest mortality. Complete blood counts and chest x-rays were the most common diagnostic tests ordered, and antimicrobials and fluid boluses were the most common medication interventions. These results provide important insights for clinical decision-making at the bedside, training of rapid response teams, and the development of institutional treatment pathways for clinical deterioration. KEY POINTS: Question: What are the most common diagnoses, diagnostic test orders, and treatments for ward patients experiencing clinical deterioration? Findings: In manual chart review of 2,484 encounters with deterioration across four health systems, we found that sepsis was the most common cause of clinical deterioration, followed by arrythmias, while liver failure had the highest mortality. Complete blood counts and chest x-rays were the most common diagnostic test orders, while antimicrobials and fluid boluses were the most common treatments. Meaning: Our results provide new insights into clinical deterioration events, which can inform institutional treatment pathways, rapid response team training, and patient care.

Creation of a data commons for substance misuse related health research through privacy-preserving patient record linkage between hospitals and state agencies.

Objectives: Substance misuse is a complex and heterogeneous set of conditions associated with high mortality and regional/demographic variations. Existing data systems are siloed and have been ineffective in curtailing the substance misuse epidemic. Therefore, we aimed to build a novel informatics platform, the Substance Misuse Data Commons (SMDC), by integrating multiple data modalities to provide a unified record of information crucial to improving outcomes in substance misuse patients. Materials and Methods: The SMDC was created by linking electronic health record (EHR) data from adult cases of substance (alcohol, opioid, nonopioid drug) misuse at the University of Wisconsin hospitals to socioeconomic and state agency data. To ensure private and secure data exchange, Privacy-Preserving Record Linkage (PPRL) and Honest Broker services were utilized. The overlap in mortality reporting among the EHR, state Vital Statistics, and a commercial national data source was assessed. Results: The SMDC included data from 36 522 patients experiencing 62 594 healthcare encounters. Over half of patients were linked to the statewide ambulance database and prescription drug monitoring program. Chronic diseases accounted for most underlying causes of death, while drug-related overdoses constituted 8%. Our analysis of mortality revealed a 49.1% overlap across the 3 data sources. Nonoverlapping deaths were associated with poor socioeconomic indicators. Discussion: Through PPRL, the SMDC enabled the longitudinal integration of multimodal data. Combining death data from local, state, and national sources enhanced mortality tracking and exposed disparities. Conclusion: The SMDC provides a comprehensive resource for clinical providers and policymakers to inform interventions targeting substance misuse-related hospitalizations, overdoses, and death.

Development and multimodal validation of a substance misuse algorithm for referral to treatment using artificial intelligence (SMART-AI): a retrospective deep learning study.

BACKGROUND: Substance misuse is a heterogeneous and complex set of behavioural conditions that are highly prevalent in hospital settings and frequently co-occur. Few hospital-wide solutions exist to comprehensively and reliably identify these conditions to prioritise care and guide treatment. The aim of this study was to apply natural language processing (NLP) to clinical notes collected in the electronic health record (EHR) to accurately screen for substance misuse. METHODS: The model was trained and developed on a reference dataset derived from a hospital-wide programme at Rush University Medical Center (RUMC), Chicago, IL, USA, that used structured diagnostic interviews to manually screen admitted patients over 27 months (between Oct 1, 2017, and Dec 31, 2019; n=54 915). The Alcohol Use Disorder Identification Test and Drug Abuse Screening Tool served as reference standards. The first 24 h of notes in the EHR were mapped to standardised medical vocabulary and fed into single-label, multilabel, and multilabel with auxillary-task neural network models. Temporal validation of the model was done using data from the subsequent 12 months on a subset of RUMC patients (n=16 917). External validation was done using data from Loyola University Medical Center, Chicago, IL, USA between Jan 1, 2007, and Sept 30, 2017 (n=1991 adult patients). The primary outcome was discrimination for alcohol misuse, opioid misuse, or non-opioid drug misuse. Discrimination was assessed by the area under the receiver operating characteristic curve (AUROC). Calibration slope and intercept were measured with the unreliability index. Bias assessments were performed across demographic subgroups. FINDINGS: The model was trained on a cohort that had 3·5% misuse (n=1 921) with any type of substance. 220 (11%) of 1921 patients with substance misuse had more than one type of misuse. The multilabel convolutional neural network classifier had a mean AUROC of 0·97 (95% CI 0·96-0·98) during temporal validation for all types of substance misuse. The model was well calibrated and showed good face validity with model features containing explicit mentions of aberrant drug-taking behaviour. A false-negative rate of 0·18-0·19 and a false-positive rate of 0·03 between non-Hispanic Black and non-Hispanic White groups occurred. In external validation, the AUROCs for alcohol and opioid misuse were 0·88 (95% CI 0·86-0·90) and 0·94 (0·92-0·95), respectively. INTERPRETATION: We developed a novel and accurate approach to leveraging the first 24 h of EHR notes for screening multiple types of substance misuse. FUNDING: National Institute On Drug Abuse, National Institutes of Health.

Identifying COVID-19 Outbreaks From Contact-Tracing Interview Forms for Public Health Departments: Development of a Natural Language Processing Pipeline.

BACKGROUND: In Wisconsin, COVID-19 case interview forms contain free-text fields that need to be mined to identify potential outbreaks for targeted policy making. We developed an automated pipeline to ingest the free text into a pretrained neural language model to identify businesses and facilities as outbreaks. OBJECTIVE: We aimed to examine the precision and recall of our natural language processing pipeline against existing outbreaks and potentially new clusters. METHODS: Data on cases of COVID-19 were extracted from the Wisconsin Electronic Disease Surveillance System (WEDSS) for Dane County between July 1, 2020, and June 30, 2021. Features from the case interview forms were fed into a Bidirectional Encoder Representations from Transformers (BERT) model that was fine-tuned for named entity recognition (NER). We also developed a novel location-mapping tool to provide addresses for relevant NER. Precision and recall were measured against manually verified outbreaks and valid addresses in WEDSS. RESULTS: There were 46,798 cases of COVID-19, with 4,183,273 total BERT tokens and 15,051 unique tokens. The recall and precision of the NER tool were 0.67 (95% CI 0.66-0.68) and 0.55 (95% CI 0.54-0.57), respectively. For the location-mapping tool, the recall and precision were 0.93 (95% CI 0.92-0.95) and 0.93 (95% CI 0.92-0.95), respectively. Across monthly intervals, the NER tool identified more potential clusters than were verified in WEDSS. CONCLUSIONS: We developed a novel pipeline of tools that identified existing outbreaks and novel clusters with associated addresses. Our pipeline ingests data from a statewide database and may be deployed to assist local health departments for targeted interventions.

Correction: Identifying COVID-19 Outbreaks From Contact-Tracing Interview Forms for Public Health Departments: Development of a Natural Language Processing Pipeline.

[This corrects the article DOI: 10.2196/36119.].

The Evaluation of a Clinical Decision Support Tool Using Natural Language Processing to Screen Hospitalized Adults for Unhealthy Substance Use: Protocol for a Quasi-Experimental Design.

BACKGROUND: Automated and data-driven methods for screening using natural language processing (NLP) and machine learning may replace resource-intensive manual approaches in the usual care of patients hospitalized with conditions related to unhealthy substance use. The rigorous evaluation of tools that use artificial intelligence (AI) is necessary to demonstrate effectiveness before system-wide implementation. An NLP tool to use routinely collected data in the electronic health record was previously validated for diagnostic accuracy in a retrospective study for screening unhealthy substance use. Our next step is a noninferiority design incorporated into a research protocol for clinical implementation with prospective evaluation of clinical effectiveness in a large health system. OBJECTIVE: This study aims to provide a study protocol to evaluate health outcomes and the costs and benefits of an AI-driven automated screener compared to manual human screening for unhealthy substance use. METHODS: A pre-post design is proposed to evaluate 12 months of manual screening followed by 12 months of automated screening across surgical and medical wards at a single medical center. The preintervention period consists of usual care with manual screening by nurses and social workers and referrals to a multidisciplinary Substance Use Intervention Team (SUIT). Facilitated by a NLP pipeline in the postintervention period, clinical notes from the first 24 hours of hospitalization will be processed and scored by a machine learning model, and the SUIT will be similarly alerted to patients who flagged positive for substance misuse. Flowsheets within the electronic health record have been updated to capture rates of interventions for the primary outcome (brief intervention/motivational interviewing, medication-assisted treatment, naloxone dispensing, and referral to outpatient care). Effectiveness in terms of patient outcomes will be determined by noninferior rates of interventions (primary outcome), as well as rates of readmission within 6 months, average time to consult, and discharge rates against medical advice (secondary outcomes) in the postintervention period by a SUIT compared to the preintervention period. A separate analysis will be performed to assess the costs and benefits to the health system by using automated screening. Changes from the pre- to postintervention period will be assessed in covariate-adjusted generalized linear mixed-effects models. RESULTS: The study will begin in September 2022. Monthly data monitoring and Data Safety Monitoring Board reporting are scheduled every 6 months throughout the study period. We anticipate reporting final results by June 2025. CONCLUSIONS: The use of augmented intelligence for clinical decision support is growing with an increasing number of AI tools. We provide a research protocol for prospective evaluation of an automated NLP system for screening unhealthy substance use using a noninferiority design to demonstrate comprehensive screening that may be as effective as manual screening but less costly via automated solutions. TRIAL REGISTRATION: ClinicalTrials.gov NCT03833804; https://clinicaltrials.gov/ct2/show/NCT03833804. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/42971.

Occupational respiratory health: a survey of Wisconsin workers who wear respirators.

CONTEXT: Little is known about Wisconsin workers who wear respirators and the prevalence of work-related asthma (WRA) in that population. To understand this problem, we questioned workers who wear respirators. OBJECTIVES: The primary objective was to learn more about the health experiences of workers who wear respirators. A secondary objective was to evaluate the utility of the survey in WRA surveillance. DESIGN: A survey was mailed to an opportunistic sample of workers who received medical evaluation for respirator fit testing. PARTICIPANTS: Surveys were sent to 1356 workers medically evaluated to wear a respirator; 192 surveys were completed and returned. RESULTS: The majority of respondents were men who have been medically evaluated for respirator wear an average of 3 times during their career. Every time, most respirator medical evaluations used 3 evaluation tools: questionnaire, physical exam and breathing test. Thirty-two percent of survey respondents had some asthma symptoms while at work in the last 30 days, and half reported discussing these symptoms with a physician. Lifetime prevalence of asthma as determined by this survey was 18%. Lifetime prevalence for WRA amongthis population was 3% (18% among those with asthma). CONCLUSIONS: This survey was an efficient and effective way to learn more about workers' respirator experiences and to determine the prevalence of asthma in this population. Few differences existed between those with asthma and those without. However, some differences were noted between those with asthma and those with WRA. Data also suggest that the respirator medical evaluation process provides an opportunity for health practitioners to discuss asthma and asthma prevention with workers.

Effects of Smoking and Smoking Cessation on the Intestinal Microbiota.

We evaluated associations of smoking heaviness markers and the effects of smoking cessation on the intestinal microbiota and cardiovascular disease risk factors in current smokers undertaking a quit attempt. Participants were current smokers enrolled in a prospective randomized clinical trial of smoking cessation therapies with visits at baseline, 2, and 12 weeks. Genomic DNA was extracted from fecal samples followed by 16S rRNA gene sequencing and analysis using the QIIME2 software workflow. Relative abundances of bacterial taxa and alpha- and beta-diversity measures were used for comparisons. The 36 smokers were (mean (standard deviation)) 51.5 (11.1) years old (42% male) and smoked 15.1 (6.4) cigarettes per day for 22.7 (11.9) pack-years. Relative abundances of the phylum Actinobacteria correlated with pack-years (rho = -0.44, p = 0.008) and Cyanobacteria correlated with CO levels (rho = 0.39, p = 0.021). After 12 weeks, relative abundances of the phylum Bacteroidetes increased (pANCOVA = 0.048) and Firmicutes decreased (pANCOVA = 0.036) among abstainers compared to continuing smokers. Increases in alpha-diversity were associated with heart rates (rho = -0.59, p = 0.037), systolic blood pressures (rho = -0.58, p = 0.043), and C-reactive protein (rho = -0.60, p = 0.034). Smoking cessation led to minor changes in the intestinal microbiota. It is unclear if the proven health benefits of smoking cessation lead to salutary changes in the intestinal microbiota.

Recruiting and engaging smokers in treatment in a primary care setting: developing a chronic care model implemented through a modified electronic health record.

Almost 35 million U.S. smokers visit primary care clinics annually, creating a need and opportunity to identify such smokers and engage them in evidence-based smoking treatment. The purpose of this study is to examine the feasibility and effectiveness of a chronic care model of treating tobacco dependence when it is integrated into primary care systems using electronic health records (EHRs). The EHR prompted primary care clinic staff to invite patients who smoked to participate in a tobacco treatment program. Patients who accepted and were eligible were offered smoking reduction or cessation treatment. More than 65 % of smokers were invited to participate, and 12.4 % of all smokers enrolled in treatment-30 % in smoking reduction and 70 % in cessation treatment. The chronic care model developed for treating tobacco dependence, integrated into the primary care system through the EHR, has the potential to engage up to 4.3 million smokers in treatment a year.