BACKGROUND:Pulmonary ventilation imaging enables functional avoidance radiotherapy treatment plans by quantifying regional lung function. However, current clinical standards, such as 99𝑚Tc-based single-photon emission computed tomography (SPECT), rely on radioactive tracers, which can introduce imaging deposition artifacts. CT ventilation imaging (CTVI) methods based on both physical models and deep learning approaches currently require multiple CT images as input, such as the inhale/exhale phases of a 4DCT. While the theoretical foundation of physics-based CTVI is built on multi-phase information, the feasibility of single-phase deep learning CTV models has not been determined. PURPOSE:While deep learning methods have predicted SPECT ventilation from multi-phase 4DCT, the benefit of including more than one respiratory phase remains unclear. Predicting ventilation using only single-phase CTs reduces computational expense, potentially simplifies the image acquisition process, and avoids artifacts introduced by image registration, thereby making deep learning-based CTV approaches more feasible for clinical applications outside of radiotherapy. This study (1) develops a deep learning model to predict SPECT ventilation using only the inhale phase of non-contrast 4DCT and (2) evaluates the impact of adding the exhale phase. METHODS:We developed a SwinUNETR-based architecture using the maximum inhale 4DCT phase to predict pulmonary ventilation. A total of 44 cases with paired inhale CT and SPECT scans were used in the training. To assess multi-phase benefits, we compared: (1) InhaleCT-Swin Model-trained on inhale CT only; (2) ExhaleCT-Swin Model-trained on exhale CT only; (3) Hybrid Models IECT-Swin-FTD, IECT-Swin-FTDE, IECT-Swin-FTDES, fine-tuned on inhale/exhale CT pairs (IECT) with varying network components updated. A standard U-Net was also trained on inhale CT (InhaleCT-UNet), exhale CT (ExhaleCT-UNet), and IECT (IECT-UNet) for cross-architecture evaluation. RESULTS:The SwinUNETR-based Hybrid Model, IECT-Swin-FTD, achieved mean voxel-wise Spearman correlation of 0.762 ± 0.035, outperforming the current state-of-the-art methods. Our transformer-based model trained on inhale CT slightly outperformed exhale CT with no significant differences ( p = 0.098 $p = 0.098$ ). U-Net achieved lower overall accuracy, though its highest performance occurred with IECT. No significant difference was found between InhaleCT-Swin Model and the best-performing hybrid UNet Model, IECT-UNet ( p = 0.556 $p = 0.556$ ). CONCLUSIONS:A transformer-based model with its decoder fine-tuned on IECT (IECT-Swin-FTD) achieved state-of-the-art accuracy for SPECT ventilation prediction. Moreover, our InhaleCT-Swin Model achieved comparable results with widely used UNet-based models that require multi-phase CT, showing that single CT may be sufficient for accurate ventilation prediction and may improve clinical workflow by reducing acquisition requirements and registration-related artifacts.

Objective.Accurate lung function assessment is essential for diagnosing and managing diseases like chronic obstructive pulmonary disorder, pulmonary emboli, and lung cancer. Single-photon emission computed tomography (SPECT) provides valuable 3D functional imaging of ventilation and perfusion, but is limited by low spatial resolution, availability, additional radiation, and cost. Alternative methods, including CT-based perfusion (CT-P) and deep learning models, require large datasets to validate results that are often scarce. Pulmonary function tests (PFTs) offer rapid and noninvasive global lung function measures and are clinically widely used. While ventilation correlates well with PFTs, perfusion imaging presents challenges due to complex blood flow and difficulty summarizing 3D data into one value. Additionally, commonly employed percentile scaling removes absolute quantitative information, complicating interpretation.Approach.We propose a framework leveraging lung discretizations based on Voronoi diagrams to capture local spatial information from raw-valued and percentile-scaled perfusion maps (SPECT and CT-P). We compute hierarchical descriptive statistics at 3 levels (intra-subvolume, inter-subvolume, left-right lungs) to derive one global value per patient.Main results.Across PFT measures of diffusing capacity of lungs for carbon monoxide, forced expiratory volume after one second (FEV1), and FEV1/forced vital capacity, we find that discretizing perfusion maps into Voronoi subvolumes always yields stronger Spearman correlations than not discretizing. Specifically, our approach demonstrates strong correlations of0.636⩽ρ⩽0.843(P < 0.005) for raw-valued (SPECT and CT-P) maps,0.590⩽ρ⩽0.789(P < 0.005) for percentile-scaled maps, and reliably distinguishes normal from abnormal lung function via logistic regression analysis (0.865⩽AUC⩽0.937for raw-valued maps,0.877⩽AUC⩽0.933for percentile-scaled maps).Significance.This framework bridges regional perfusion imaging and global pulmonary function assessment, enabling meaningful quantitative comparisons between SPECT and CT-P maps. By preserving local spatial variability, the method offers a noninvasive tool for integrating imaging and physiological data, paving the way toward broader clinical and AI-driven applications in lung function evaluation.

This quality improvement study investigates the association of an electronic health record-integrated artificial intelligence note summarization tool with emergency physician medical record review time and user experience.

Objectives: Extracorporeal cardiopulmonary resuscitation (ECPR) has seen increasing use globally as a life-saving intervention for patients with refractory cardiac arrest, including those suffering out-of-hospital cardiac arrests (OHCA) transported to the Emergency Department (ED). ECPR requires extensive resource commitment and outcome data for OHCA patients transported to ECPR capable EDs remain limited. The objective of this study was to evaluate the association of implementing an ED ECPR program on OHCA ambulance arrivals to an academic medical center ED. Methods: We conducted a before-after study at an urban, academic, level 1 trauma, and STEMI-receiving center ED (annual census approximately 50,000). The regional county Emergency Medical Services (EMS) agency (population 3.1 million) initiated an ECPR pilot program to direct Advanced Life Support (ALS) 911 transports of refractory OHCA patients to a limited number of designated as ECPR receiving centers (i.e., ECPR-capable EDs). We analyzed ECPR, OHCA, and total ALS 911 EMS ED transports in the 6 months before (July-Oct 2024, pre-ECPR) and 6 months following (Dec 2024-May 2025, ECPR) county EMS agency designation as an ECPR receiving center. The implementation month, November, was excluded from all analyses. In addition, we compared these 6-month periods with the 6-month period 1 year prior to the implementation (July-Oct 2023, pre1y-ECPR). The number of OHCA per 1,000 ALS transports was compared for each of the three time periods using descriptive statistics and Fisher's exact testing as indicated, with a p < 0.05 considered statistically significant. Results: After ECPR designation, there was an increase in OHCA transports compared with both the pre-ECPR and pre1y-ECPR periods (7.8 vs. 3.2 vs. 3.5 per 1,000 ALS transports, respectively, p < 0.05). Of note, only eight OHCA patients transported to the ED in the ECPR period met the County ECPR criteria, and only one was placed on veno-arterial extracorporeal membrane oxygenation. Conclusion: Inclusion into a county wide ED ECPR program for refractory OHCA resulted in a significant increase in the number of OHCA and ALS transports to an academic medical center ED, even though many of these patients did not actually meet pre-determined criteria for ECPR activation from the field.

This study evaluates the predictive power of CT-derived functional imaging (CTFI) combined with forced expiratory volume in 1 second (FEV1) for 10-year all-cause mortality in COPD patients. We analyzed 8583 participants from the COPDGene® cohort, focusing on 3550 participants with spirometric obstruction. CTFI metrics, including ventilation (CT-V) and perfusion (PBM), were computed from non-contrast CT scans at lobar resolution. Our findings show that regional and global CTFI scores decline with advancing GOLD stages. A Random Survival Forest model, adjusted for age, BMI, and scanner type, demonstrated significant improvement in mortality prediction when combining FEV1 with CTFI, compared to FEV1 alone, with an AUC increase from 0.71 to 0.76 over 10 years. The Net Reclassification Index further confirmed the added predictive value of CTFI. These results suggest that integrating CTFI with traditional lung function measures enhances mortality prediction in COPD, offering a promising tool for clinical risk assessment.

Pulmonary perfusion imaging is a key lung health indicator with clinical utility as a diagnostic and treatment planning tool. However, current nuclear medicine modalities face challenges like low spatial resolution and long acquisition times which limit clinical utility to non-emergency settings and often placing extra financial burden on the patient. This study introduces a novel deep learning approach to predict perfusion imaging from non-contrast inhale and exhale computed tomography scans (IE-CT). We developed a U-Net Transformer architecture modified for Siamese IE-CT inputs, integrating insights from physical models and utilizing a self-supervised learning strategy tailored for lung function prediction. We aggregated 523 IE-CT images from nine different 4DCT imaging datasets for self-supervised training, aiming to learn a low-dimensional IE-CT feature space by reconstructing image volumes from random data augmentations. Supervised training for perfusion prediction used this feature space and transfer learning on a cohort of 44 patients who had both IE-CT and single-photon emission CT (SPECT/CT) perfusion scans. Testing with random bootstrapping, we estimated the mean and standard deviation of the spatial Spearman correlation between our predictions and the ground truth (SPECT perfusion) to be 0.742 ± 0.037, with a mean median correlation of 0.792 ± 0.036. These results represent a new state-of-the-art accuracy for predicting perfusion imaging from non-contrast CT. Our approach combines low-dimensional feature representations of both inhale and exhale images into a deep learning model, aligning with previous physical modeling methods for characterizing perfusion from IE-CT. This likely contributes to the high spatial correlation with ground truth. With further development, our method could provide faster and more accurate lung function imaging, potentially expanding its clinical applications beyond what is currently possible with nuclear medicine.

BACKGROUND:Emergency departments (EDs) often care for patients with acute mental health issues, especially patients with severe mental illness (SMI). This study assessed trends in ED utilization for patients with schizophrenia and bipolar disorder over a 4-year period in California, including during the COVID-19 pandemic. OBJECTIVE:This study aimed to assess changes in ED visit rates, demographic characteristics, and admission proportions for SMI-related visits before, during, and after COVID-19 pandemic. METHODS:A multicenter retrospective analysis of ED utilization among patients 18 years or older with SMI was conducted from 2018 to 2021, using California's Department of Health Care Access and Information ED and inpatient discharged databases. SMI-related visits were identified using International Classification of Diseases, 10th Revision codes. Demographic variables included age, sex, race and ethnicity, expected payer, and geographic region. RESULTS:Total ED visits increased from 2018 to 2019, then decreased in 2020 and 2021. SMI-related ED visits per 100,000 visits increased from 2019 to 2020 and remained elevated in 2021. Patients aged 25-44 years, non-Hispanic Black individuals, and Medicaid beneficiaries demonstrated the highest SMI-related ED utilization rates. Los Angeles County consistently had the highest rates among geographic regions. CONCLUSIONS:Despite an overall reduction in ED visits during the COVID-19 pandemic, SMI-related visits increased, demonstrating the need for mental health resources in EDs, specifically for vulnerable populations, such as non-Hispanic Black individuals and those with lower socioeconomic status.

PURPOSE Novel methods generate functional images using image processing techniques combined with four-dimensional computed tomography (4DCT) data (4DCT-ventilation). 4DCT-ventilation was implemented in a phase II, multicenter functional avoidance clinical trial. The work compares functional avoidance patient-reported outcomes (PROs) against historical standards. METHODS Patients with locally advanced lung cancer undergoing curative-intent chemoradiation were accrued. 4DCT-ventilation imaging was generated and functional avoidance treatment plans created reduced dose to functional lung. PRO instruments included Functional Assessment of Cancer Therapy Lung questionnaire and accompanying subscales (including the Trial Outcome Index [TOI]), EuroQol-5 Dimension (EQ-5D), and EQ-Visual Analog Scale (EQ-VAS). The average change from baseline and percentage of clinically meaningful declines were calculated. We compared results against PROs from RTOG 0617 and PACIFIC trial data using Student t-tests and chi-square tests. RESULTS Fifty-nine patients completed baseline PRO surveys. The median age was 65 (44-86) years, non–small cell lung cancer comprised 83%, and median dose was 60 Gy in 30 fractions. The percent of patients with clinically meaningful decline in FACT-TOI at 12 months was 47.8% for RTOG 0617% and 26.8% for functional avoidance ( P = .03). The functional avoidance cohort demonstrated a significantly ( P = .012) higher change in EQ-VAS score at 12 months (9.9 ± 3.3; average ± SE) compared with the PACIFIC cohort (1.6 ± 0.6). CONCLUSION The current work demonstrates improved PROs from a phase II functional avoidance trial in certain subscales (FACT-TOI and EQ-VAS) compared with PROs from seminal studies (RTOG 0617 and PACIFIC). The presented data support investigation of 4DCT functional avoidance in a phase III setting.

INTRODUCTION:Despite sepsis having growing awareness nationally, efforts to reduce the public health impact of sepsis have lagged. Although there are known pathophysiologic mechanisms and preventive strategies, sepsis is rarely approached as a predictable or preventable condition. Predicting who will develop sepsis in patients with infection still remains a challenge. This study examined modifiable and nonmodifiable risk factors associated with patients initially discharged home with an infection and had future sepsis-related admissions within 7 days of the index Emergency Department (ED) visit. METHODS:We conducted a multi-center retrospective cohort analysis of adults presenting to two university hospital EDs. The inclusion criteria encompassed adult patients who were discharged from the ED at their index visit with discharge diagnosis (ICD 10-CM code) of pneumonia, urinary tract infection (UTI), and/or cellulitis and who returned for hospital admission within 7 days of the index visit due to sepsis, severe sepsis without septic shock, and/or septic shock. Using multivariate regression, risk factors that predict return sepsis admission within 7 days of ED index visit were evaluated, and a 7-day return sepsis admission model was constructed. The predictive power of the model was measured by c-statistic. RESULTS:Among 10,179 unique ED patients, return sepsis admissions within 7 days occurred in 113 visits (1.11 % of discharged patients). Statistically significant risk factors among patients with infection associated with subsequent sepsis admission in the chosen model were Cardiovascular Disease (OR 2.07 95 % CI 1.26-3.42), Hypertension (OR 2.21 95 % CI 1.37-3.56), Chronic Kidney Disease (OR 1.80 95 % CI 1.11-2.91), Cancer (OR 2.22 95 % CI 1.43-3.45), Male (OR 1.67 95 % CI 1.13-2.45), arriving in an ambulance (vs. walk in OR 2.55 95 % CI 1.46-4.44), higher heart rate (OR 1.29 95 % CI 1.16-1.45), and higher temperature (OR 1.23 95 % CI 1.05-1.45), Hyperlipidemia was protective (OR 0.56 95 %CI 0.34-0.91). The c-statistic of our chosen model was 0.77 (95 % CI 0.73-0.81). The Hosmer-Lemeshow test for our logistic regression model resulted in a chi-square value of 7.23 with 8 degrees of freedom with a p-value of 0.51. This suggests that our model fits the data well. CONCLUSION:Our findings may be used to risk stratify and guide outpatient disposition decisions for ED patients with infection and to determine which patients need to be more closely monitored in the outpatient setting following ED discharge.

BACKGROUND:E-cigarette use and its health impacts remain understudied in medicine and public health. OBJECTIVES:This study aimed to investigate the prevalence, demographics, and self-reported health effects of e-cigarette use among emergency department (ED) patients. METHODS:This is a cross-sectional survey study of patients age ≥18 years from 2 urban academic EDs between February 2018 and November 2023. The primary outcome was frequent e-cigarette use (defined as ≥3 times/wk); secondary outcomes included self-reported symptoms, perceptions of health risks, and persistence of use despite adverse symptoms. Predictors of frequent use were examined with multivariable logistic regression, including variables with univariate p < 0.20 or clinical relevance. Results are reported as odds ratios (95% CI) with α = 0.05. Analyses were performed in SPSS. RESULTS:Among 3,656 respondents, 147 (4.0%) met our definition of frequent vaping. Of these frequent users, 84 (57%) were male and the greatest proportion fell in the 18-24-year age group. In multivariable analysis, male sex, and younger age independently predicted frequent use: females had roughly half the odds of frequent vaping (OR: 0.50, 95% CI: 0.35-0.72), while odds declined with increasing age (25-34 years OR: 0.46; 35-44 years OR: 0.40; ≥45 years OR: 0.10; p < 0.001). Among frequent users, 48% worried about additive safety and 54% reported coughing. CONCLUSIONS:Frequent vaping was most common among younger males in this study. Many of these users report continued vaping despite concerns about potential health risks. EDs are strategically positioned to screen adult patients for frequent e-cigarette use and deliver brief, targeted cessation counseling.

BACKGROUND:Older adults discharged from the Emergency Department (ED) experience an increased risk of adverse health outcomes. Telehealth video visits (TVVs) show promise as a method to facilitate timely post-ED care. This study evaluates the association between TVV utilization and ED revisit rates among older adults enrolled in an ED transition of care (TOC) program. METHODS:This retrospective cohort study analyzed 5006 TVVs from 1203 patients aged 55 and older who received follow-up care within 30 days of ED discharge at two academic EDs over a 20-month period. Data was collected on patient demographics, comorbidities, and ED revisit rate. TVV implementation was assessed through comparative analysis to a randomly matched cohort of eligible patients, who did not receive TVV after discharge. Univariate analyses were conducted to identify associations between TVV utilization and ED revisit rates. RESULTS:TVV follow-up was associated with reduced ED revisit rates at 7-days (-3.1 %) among patients aged 65-74 years and at 30-days (-5.0 %) among patients aged 75-84 years. Among patients with a Charlson Comorbidity Index (CCI) of 0, TVV implementation was associated with a reduction in ED revisit rates at 7-, 14-, and 30-days post-discharge. Subgroup analysis indicated patients with lower ED revisit rates following TVV implementation were predominantly male, non-Latinx, and had a CCI of 0. CONCLUSION:We found that the telehealth video visit intervention was associated with a reduction in 7-day and 30-day ED revisit rates among older adults. ED revisit rates also varied by patient demographics and comorbidity burden.

PURPOSE:Methods have been developed that apply image processing to 4-Dimension computed tomography (4DCT) to generate lung ventilation (4DCT-ventilation). Traditional methods for 4DCT-ventilation rely on density-change methods and lack reproducibility and do not provide 4DCT-perfusion data. Novel 4DCT-ventilation/perfusion methods have been developed that are robust and provide 4DCT-perfusion information. The purpose of this study was to use prospective clinical trial data to evaluate the ability of novel 4DCT-based lung function imaging methods to predict pneumonitis. MATERIALS AND METHODS:Sixty-three advanced-stage lung cancer patients enrolled in a multi-institutional, phase 2 clinical trial on 4DCT-based functional avoidance radiation therapy were used. 4DCTs were used to generate four lung function images: (1) 4DCT-ventilation using the traditional HU approach ('4DCT-vent-HU'), and 3 methods using the novel statistically robust methods: (2) 4DCT-ventilation based on the Mass Conserving Volume Change ('4DCT-vent-MCVC'), (3) 4DCT-ventilation using the Integrated Jacobian Formulation ('4DCT-vent-IJF') and 4) 4DCT-perfusion. Dose-function metrics including mean functional lung dose (fMLD), and percentage of functional lung receiving ≥5 Gy (fV5), and ≥20 Gy (fV20) were calculated using various structure-based thresholds. The ability of dose-function metrics to predict for ≥grade 2 RP was assessed using logistic regression and machine learning. Model performance was evaluated using the area under the curve (AUC) and validated through 10-fold cross-validation. RESULTS:10/63 (15.9 %) patients developed grade ≥2 RP. Logistic regression yielded mean AUCs of 0.70 ± 0.02 (p = 0.04), 0.64 ± 0.04 (p = 0.13), 0.60 ± 0.03 (p = 0.27), and 0.63 ± 0.03 (p = 0.20) for 4DCT-vent-MCVC, 4DCT-perfusion, 4DCT-vent-IJF, and 4DCT-vent-HU, respectively, compared to 0.65 ± 0.10 (p > 0.05) for standard lung metrics. Machine learning modeling resulted in AUCs 0.83 ± 0.04, 0.82 ± 0.05, 0.76 ± 0.05, 0.74 ± 0.06, and 0.75 ± 0.02 for 4DCT-vent-MCVC, 4DCT-perfusion, 4DCT-vent-IJF, and 4DCT-vent-HU, and standard lung metrics respectively, with an accuracy of 75-85 %. CONCLUSIONS:This is the first study to comprehensively evaluate 4DCT-perfusion and robust 4DCT-ventilation in predicting clinical outcomes. The data showed that on the presented 63-patient study and using classis logistic regression and ML methods, 4DCT-vent-MCVC was the best predictors of RP.

Background and purpose:Functional avoidance radiotherapy has emerged as a promising technique using functional imaging to minimize pulmonary toxicity by reducing doses to functional lung. This study aims to investigate the potential dose-volume advantages of a novel spot-scanning proton arc (SPArc) therapy for functional avoidance radiotherapy with four-dimensional computed tomography (4DCT)-based ventilation imaging. Material and methods:Twenty-five patients from a prospective functional avoidance clinical trial treated with intensity-modulated photon radiotherapy were included. Robustly optimized intensity modulated proton therapy (IMPT) and SPArc plans were generated in RayStation. Functional lung contour was derived from the 4DCT-based ventilation imaging and utilized as an optimization structure in photon as well as IMPT and SPArc functional planning. The dose distributions were compared, and normal tissue complication probability (NTCP) models were applied to estimate the probability of pulmonary toxicity. Results:Using clinical photon plans as the baseline for comparison, both proton plans achieved equivalent target coverage and reduced dose to organs at risk. Compared with photon plans, the median absolute reduction of fV20Gy (the volume of functional lung receiving ≥ 20 Gy) was 3.7 percentage points (pp) with IMPT and 13.0 pp with SPArc. Using fV20Gy for NTCP estimation, the median reduction of probability of grade ≥ 2 pneumonitis was 5.0 pp with IMPT and was 14.9 pp with SPArc. Conclusions:Our study highlighted the potential of SPArc to spare dose to functional lung. NTCP results further indicated that the risk of pulmonary complications can be reduced with SPArc compared to photon or IMPT for functional avoidance radiotherapy.

PURPOSE:Methods have been developed that apply image processing to 4DCTs to generate 4DCT-ventilation/perfusion lung imaging. Traditional methods for 4DCT-ventilation rely on Hounsfield-Unit (HU) density-change methods and suffer from poor numerical robustness while not providing 4DCT-perfusion data. The purpose of this work was to evaluate the clinical differences between classic HU-based 4DCT-ventilation approaches and novel 4DCT-ventilation/perfusion approaches. METHODS:Data from 63 lung cancer patients enrolled in a functional avoidance clinical trial were analyzed. 4DCT-data were used to generate four lung-function images: (1) classical HU-based 4DCT-ventilation ("4DCT-vent-HU"), and three novel, statistically robust methods: (2) 4DCT-ventilation based on the Mass Conserving Volume Change ("4DCT-vent-MCVC"), (3) 4DCT-ventilation using the Integrated Jacobian Formulation, and (4) 4DCT-perfusion. A radiologist reviewed all images for ventilation/perfusion defects (scored as yes/no) and the scores for the novel approaches were compared to those of 4DCT-vent-HU using receiver operating characteristic (ROC) analysis. Functional contours were generated using thresholding methods, and the contours from the three novel 4DCT-ventilation methods were compared against that from 4DCT-vent-HU (Dice similarity coefficients [DSC]). Functional mean lung dose (fMLD) and dose-function metrics were compared against dose-function metrics using 4DCT-vent-HU. RESULTS:ROC analysis revealed accuracy in the range of 0.55 to 0.73 comparing radiologist interpretations of 4DCT-vent-HU against the three novel approaches. Average DSC values were 0.41 ± 0.19, 0.44 ± 0.16, and 0.42 ± 0.17 comparing 4DCT-vent-HU to 4DCT-vent-IJF, 4DCT-vent-MCVC, and 4DCT-perf, respectively. All novel imaging methods showed significant differences (p < 0.01) in dose-function metrics compared to those of 4DCT-vent-HU. 4DCT-vent-MCVC and 4DCT-Perf depicted the smallest and largest differences from 4DCT-vent-HU in fMLD (3.51 ± 3.20 Gy and 5.90 ± 5.29 Gy, respectively). CONCLUSION:This is the first work to comprehensively compare novel 4DCT-ventilation/perfusion methods against classical formulations. Our data show that significant differences between the 4DCT-based functional imaging methods exist, suggesting that studies are needed to evaluate which methods provide the most robust clinical results.

BackgroundHospital readmissions pose a significant burden on patients, health care providers, and systems, with an estimated annual cost of $17 billion. Timely follow-up within 7 days postdischarge is known to reduce readmissions but is often limited by access constraints. While transitions of care clinics have demonstrated benefits in reducing unplanned readmissions, physical space requirements can be logistically and financially challenging. ObjectiveThis study aimed to evaluate the effectiveness of a virtual transitions of care (VToC) clinic in reducing 30-day hospital readmissions and improving postdischarge care coordination. MethodsUniversity of California, San Diego Health implemented a hospitalist-led VToC clinic designed to support clinical management, medication reconciliation, primary care provider repatriation, and specialty care navigation. The study included 2314 patients seen in the VToC clinic between September 2021 and September 2024. Outcomes were compared to a benchmark group using regression analysis to assess the impact on 30-day readmission rates. ResultsThe 30-day readmission rate for VToC patients was 14.9% (344/2314), significantly lower than the 20.1% (4659/23,129) observed in the benchmark group (P<.001). Regression analysis indicated that patients not participating in the VToC clinic had a higher likelihood of readmission (odds ratio=1.37; 95% CI=1.21-1.54; P<.001). The most substantial reduction in readmissions was observed among patients with moderate readmission risk (LACE+ score of 50-75). ConclusionsVToC clinics are a feasible and effective strategy for enhancing postdischarge care, reducing hospital readmissions, and improving care coordination. This model supports the quadruple aim by promoting better health outcomes, improved patient experience, cost-efficiency, and care equity.

PurposeFunctional radiotherapy avoids the delivery of high-radiation dosages to high-ventilated lung areas. Methods to determine CT-ventilation imaging (CTVI) typically rely on deformable image registration (DIR) to calculate volume changes within inhale/exhale CT image pairs. Since DIR is a non-trivial task that can bias CTVI, we hypothesize that lung volume changes needed to calculate CTVI can be computed from AI-driven lobe segmentations in inhale/exhale phases, without DIR. We utilize a novel lobe segmentation pipeline (TriSwinUNETR), and the resulting inhale/exhale lobe volumes are used to calculate CTVI.MethodsOur pipeline involves three SwinUNETR networks, each trained on 6,501 CT image pairs from the COPDGene study. An initial network provides right/left lung segmentations used to define bounding boxes for each lung. Bounding boxes are resized to focus on lung volumes and then lobes are segmented with dedicated right and left SwinUNETR networks. Fine-tuning was conducted on CTs from 11 patients treated with radiotherapy for non-small cell lung cancer. Five-fold cross-validation was then performed on 51 LUNA16 cases with manually delineated ground truth. Breathing-induced volume change was calculated for each lobe using AI-defined lobe volumes from inhale/exhale phases, without DIR. Resulting lobar CTVI values were validated with 4DCT and positron emission tomography (PET)-Galligas ventilation imaging for 19 lung cancer patients. Spatial Spearman correlation between TriSwinUNETR lobe ventilation and ground-truth PET-Galligas ventilation was calculated for each patient.ResultsTriSwinUNETR achieved a state-of-the-art mean Dice score of 93.72% (RUL: 93.49%, RML: 85.78%, RLL: 95.65%, LUL: 97.12%, LLL: 96.58%), outperforming best-reported accuracy of 92.81% for the lobe segmentation task. CTVI calculations yielded a median Spearman correlation coefficient of 0.9 across 19 cases, with 13 cases exhibiting correlations of at least 0.5, indicating strong agreement with PET-Galligas ventilation.ConclusionOur TriSwinUNETR pipeline demonstrated superior performance in the lobe segmentation task, while our segmentation-based CTVI exhibited strong agreement with PET-Galligas ventilation. Moreover, as our approach leverages deep-learning for segmentation, it provides interpretable ventilation results and facilitates quality assurance, thereby reducing reliance on DIR.

Background Stimulants are becoming increasingly prevalent among overdoses, yet little is understood about how stimulant use impacts emergency department (ED) utilization. Methods Using data from California's Department of Healthcare Access and Information, we conducted a five-year trend analysis of stimulant-related ED visits from acute care hospitals in California from 2017 to 2021. For each year, we determined the stimulant-related ED visit rate per 100,000 ED visits for adults aged ≥18 utilizing ICD-10 diagnosis codes. We estimated the percent changes in overall stimulant-related visit rates during the study period and by subgroup, including by demographic characteristics, Charlson comorbidity index score (CCIS), and cardiovascular (CV) diagnoses. We used chi-squared analyses to examine changes in trends over time. Results The rate of stimulant-related ED visits increased from 2064.4 per 100,000 ED visits in 2017 to 2586.1 per 100,000 ED visits in 2021, a 25.3 % increase (P < 0.001). By race/ethnicity, people identified as Native American/Alaska Natives had the highest ED visit rate in 2021 (4713.5 per 100,000 ED visits) and the largest increase of 60.8 % (P < 0.001). The proportion of stimulant-related ED visits with CV disease diagnoses increased from 13.8 % in 2017 to 18.0 % in 2021, a relative increase of 30.8 % (P < 0.001). Conclusions Stimulant-related ED visits are increasing among adults in California, especially among non-white populations and those with higher comorbidity. This sharp rise highlights the critical need for targeted interventions and harm reduction strategies that consider the unique effects of stimulant use on ED rates and CV outcomes.

Abstract Objective We sought to study the impact of the Centers for Medicare & Medicaid services (CMS) waiver of the 3‐day hospitalization requirement for skilled nursing facility (SNF) care implemented as part of the Federal COVID‐19 response on emergency department (ED) and inpatient hospital SNF discharges. Methods We conducted a multicenter retrospective cohort study of hospital ED and inpatient visits in California during 18 months before (prewaiver, September 2018–February 2020) and 18 months after (waiver, March 2020–August 2021) waiver implementation. Data were collected from all adult ED and admitted patients utilizing California Department of Health Care Access and Information datasets from all acute care hospitals licensed in the state. Prewaiver and waiver periods were compared for SNF discharge/disposition rates stratified by patient demographic and hospital data with differences in the proportion and 95% confidence interval [CI] reported (SPSS). Results SNF discharges decreased from the prewaiver to waiver periods from the ED (−7.4% [CI −8.1%, −6.6%]), along with larger declines occurring from the inpatient hospital setting (−18.1% [CI −18.4%, −17.9%]). For Medicare beneficiaries, there was a smaller decrease in ED SNF rates (−3.8% [CI −4.7%, −2.9%]), and there was no significant change for SNF discharge rates for inpatient admissions with a length of stay (LOS) <3 days (+1.0% [CI 0.0%, 2.1%]). Conclusion In California, the CMS waiver did not result in an increase, but an actual decrease rate of SNF discharges from the ED and inpatient setting, though with smaller declines for the ED, Medicare patients, and those with a LOS <3 days.

Purpose/Objective(s) CT-ventilation methods typically rely on deformable image registration (DIR) to calculate the apparent volume changes within an inhale/exhale computed tomography (CT) image pair. However, DIR is itself a non-trivial task that can potentially bias the resulting CT-ventilation. We hypothesize that the breathing-induced lung volume changes needed to calculate CT ventilation can be accurately computed directly from AI driven lobe segmentations, without a DIR. We utilize a novel transformer-based lobe segmentation pipeline that is comprised of three Swin UNETR networks. The resulting inhale/exhale lobe volumes are then used to calculate CT-ventilation. Materials/Methods Our segmentation model is based on the Swin UNETR network. Our segmentation pipeline involves the application of three Swin UNETR networks. Each network was trained on 6,501 unlabeled inhale/exhale CT image pairs from the COPDgene imaging study. First, an initial network provides right and left lung segmentations that are used to define bounding boxes for each lung. The bounding boxes are resized to focus on the lung volumes and then lobes are segmented with dedicated right and left lung Swin UNETR networks. Fine-tuning was conducted on manual lobe segmentations from diverse clinical datasets; 40 lung nodule cases from the LUNA16 challenge and CT from 11 patients treated with radiotherapy for non-small cell lung cancer. Segmentation accuracy was assessed on 10 LUNA16 test cases with manually delineated ground truth. Breathing-induced volume change (exhale volume/inhale volume) was calculated for each lobe using the Swin UNETR-defined lobe volumes delineated on the inhale/exhale phases, without the use of DIR. The resulting lobar CT-ventilation values were validated using publicly available 4DCT and PET-Galligas ventilation imaging for 19 lung cancer patients. The spatial Spearman correlation between our Swin UNETR lobe ventilation and the ground-truth PET Galligas images was calculated for each patient. Results The segmentation pipeline achieved a mean Dice score of 0.9538 (LUL = 0.9725, LLL = 0.9700, RUL = 0.9574, RML = 0.9063, and RLL = 0.9626) on the LUNA16 test cases, surpassing the mean Dice accuracies reported by current state-of-the-art models. CT-ventilation calculations yielded a median Spearman correlation coefficient of 0.8 across 19 cases, with 14 cases exhibiting correlations of at least 0.5, indicating strong agreement with PET Galligas ventilation. Upon visual inspection, lower correlations were associated with low 4DCT image quality. Conclusion Our Swin UNETR lobe segmentation pipeline demonstrated superior performance over prior methods, while our segmentation-based CT ventilation method exhibits strong agreement with PET Galligas ventilation. Moreover, as our approach leverages deep learning for segmentation, it provides interpretable ventilation results and facilitates straightforward quality assurance processes, thereby reducing reliance on DIR-dependent algorithms.