Search

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. [ABSTRACT FROM AUTHOR]

This document is a copyright notice from the American College of Sports Medicine, stating that unauthorized reproduction of the article is prohibited. [Extracted from the article]

As patients continue to live longer from diseases that predispose them to right ventricular (RV) dysfunction or failure, many more patients will require surgery for acute or chronic health issues. Because RV dysfunction results in significant perioperative morbidity if not adequately assessed or managed, understanding appropriate assessment and treatments is important in preventing subsequent morbidity and mortality in the perioperative period. In light of the epidemiology of right heart disease, a working knowledge of right heart anatomy and physiology and an understanding of the implications of right-sided heart function for perioperative care are essential for perioperative practitioners. However, a significant knowledge gap exists concerning this topic. This manuscript is one part of a collection of papers from the PeriOperative Quality Initiative (POQI) IX Conference focusing on "Current Perspectives on the Right Heart in the Perioperative Period." This review aims to provide perioperative clinicians with an essential understanding of right heart physiology by answering five key questions on this topic and providing an explanation of seven fundamental concepts concerning right heart physiology. [ABSTRACT FROM AUTHOR]

Background Large vessel recanalization (LVR) before endovascular therapy (EVT) for acute large vessel ischemic strokes is a poorly understood phenomenon. Better understanding of predictors for LVR is important for optimizing stroke triage and patient selection for bridging thrombolysis. Methods In this retrospective cohort study, consecutive patients presenting to a comprehensive stroke center for EVT treatment were identified from 2018 to 2022. Demographic information, clinical characteristics, intravenous thrombolysis (IVT) use, and LVR before EVT were recorded. Factors independently associated with different rates of LVR were identified, and a prediction model for LVR was constructed. Results 640 patients were identified. 57 (8.9%) patients had LVR before EVT. A minority (36.4%) of LVR patients had significant improvements in National Institutes of Health Stroke Scale. Independent predictors for LVR were identified and used to construct the 8-point HALT score: hyperlipidemia (1 point), atrial fibrillation (1 point), location of vascular occlusion (internal carotid: 0 points, M1: 1 point, M2: 2 points, vertebral/basilar: 3 points), and thrombolysis at least 1.5 hours before angiography (3 points). The HALT score had an area under the receiver-operating curve (AUC) of 0.85 (95% CI 0.81 to 0.90, P<0.001) for predicting LVR. LVR before EVT occurred in only 1 of 302 patients (0.3%) with low (0-2) HALT scores. Conclusions IVT at least 1.5 hours before angiography, site of vascular occlusion, atrial fibrillation, and hyperlipidemia are independent predictors for LVR. The 8-point HALT score proposed in this study may be a valuable tool for predicting LVR before EVT. [ABSTRACT FROM AUTHOR]

Objective The classification of clinical note sections is a critical step before doing more fine-grained natural language processing tasks such as social determinants of health extraction and temporal information extraction. Often, clinical note section classification models that achieve high accuracy for 1 institution experience a large drop of accuracy when transferred to another institution. The objective of this study is to develop methods that classify clinical note sections under the SOAP ("Subjective," "Object," "Assessment," and "Plan") framework with improved transferability. Materials and methods We trained the baseline models by fine-tuning BERT-based models, and enhanced their transferability with continued pretraining, including domain-adaptive pretraining and task-adaptive pretraining. We added in-domain annotated samples during fine-tuning and observed model performance over a varying number of annotated sample size. Finally, we quantified the impact of continued pretraining in equivalence of the number of in-domain annotated samples added. Results We found continued pretraining improved models only when combined with in-domain annotated samples, improving the F 1 score from 0.756 to 0.808, averaged across 3 datasets. This improvement was equivalent to adding 35 in-domain annotated samples. Discussion Although considered a straightforward task when performing in-domain, section classification is still a considerably difficult task when performing cross-domain, even using highly sophisticated neural network-based methods. Conclusion Continued pretraining improved model transferability for cross-domain clinical note section classification in the presence of a small amount of in-domain labeled samples. [ABSTRACT FROM AUTHOR]

AbstractObjective: To examine the relationship between body mass index (BMI) and genotype among pre-symptomatic carriers of different pathogenic variants associated with amyotrophic lateral sclerosis. Methods: C9orf72+ carriers, SOD1+ carriers, and pathogenic variant negative controls (Gene-Negatives) were included from 3 largely independent cohorts: ALS Families Project (ALS-Families); Dominantly inherited ALS (DIALS); and Pre-symptomatic Familial ALS (Pre-fALS). First reported (ALS-Families) or measured (DIALS and Pre-fALS) weight and height were used to calculate BMI. Age at weight measurement, self-reported sex (male vs. female), and highest education (high school or below vs. college education vs. graduate school or above) were extracted. The associations between BMI and genotype in each cohort were examined with multivariable linear regression models, adjusted for age, sex, and education. Results: A total of 223 C9orf72+ carriers, 135 SOD1+ carriers, and 191 Gene-Negatives were included, deriving from ALS-Families (n = 114, median age 46, 37% male), DIALS (n = 221, median age 46, 30% male), and Pre-fALS (n = 214, median age 44, 39% male). Adjusting for age, sex, and education, the mean BMI of C9orf72+ carriers was lower than Gene-Negatives by 2.4 units (95% confidence interval [CI] = 0.3–4.6, p = 0.02) in ALS-Families; 2.7 units (95% CI = 0.9–4.4, p = 0.003) in DIALS; and 1.9 units (95% CI = 0.5–4.2, p = 0.12) in Pre-fALS. There were no significant differences in BMI between SOD1+ carriers and Gene-Negatives in any of the 3 cohorts. Conclusions: Compared to Gene-Negatives, average BMI is lower in asymptomatic C9orf72+ carriers across 3 cohorts while no significant difference was found between Gene-Negatives and SOD1+ carriers. [ABSTRACT FROM AUTHOR]