Citations

Objective: Pulmonary air trapping is critical for diagnosing and prognostication of various lung diseases. Expiratory CT imaging serves as an accessible method to assess air trapping, which correlates with small airway disease outcomes. Air trapping manifests as mosaic attenuation on inspiratory chest CT that is difficult for visual estimation. The primary aim of this study was to develop an automated tool to quantify mosaic attenuation on inspiratory CT and air trapping on paired expiratory CT. Secondary aims included comparing CT-derived parameters with PFT measurements and dyspnea scores. Methods: This retrospective analysis of noncontrast chest CTs from 2 academic hospitals was conducted between January 1, 2018, and December 31, 2019. Patients with paired inspiratory and expiratory CT chest scans and PFTs performed on the same day were included. A chest radiologist manually annotated lung parenchyma in a reference cohort. Several histogram-based metrics were computed from lung parenchymal CT values, with the maximum peak position showing the strongest correlation with manually determined thresholds. This threshold, derived from the histogram peak, was applied in the adaptive thresholding process to quantify mosaic attenuation and air trapping. Results: We analyzed 267 patients (65.5% female, median age 68). Most exhibited normal physiological patterns (44.0%). Patients with elevated residual volume (RV) by PFTs (28.1%) had significantly higher inspiratory CT mosaic attenuation (1629.6 vs. 1311.5 mL, P <0.01) and expiratory CT air trapping volumes (1413.7 vs. 886.2 mL, P <0.01). Correlation analyses demonstrated strong relationships between CT-derived mosaic attenuation and air trapping measures and RV. The correlation with PFT parameters was even stronger in subgroup analyses in patients with obstructive PFT patterns. These models had good predictive ability for an abnormal RV (AUC of 0.92, sensitivity of 72.4%, and specificity of 92.0%) and clinical utility based on good correlation with the mMRC dyspnea score ( r =0.71; 95% CI: 0.65-0.77). Conclusions: This automated adaptive thresholding on inspiratory and expiratory chest CT scans showed a high correlation of lung volume and air trapping parameters with PFTs, revealing that measures of lung function have a complex interplay with air trapping.

Accurate diagnosis of gastrointestinal (GI) diseases typically requires invasive procedures or imaging studies that pose the risk of various post-procedural complications or involve radiation exposure. Bowel sounds (BSs), though typically described during a GI-focused physical exam, are highly inaccurate and variable, with low clinical value in diagnosis. Interpretation of the acoustic characteristics of BSs, i.e., using a phonoenterogram (PEG), may aid in diagnosing various GI conditions non-invasively. Use of artificial intelligence (AI) and improvements in computational analysis can enhance the use of PEGs in different GI diseases and lead to a non-invasive, cost-effective diagnostic modality that has not been explored before. The purpose of this work was to develop an automated AI model, You Only Listen Once (YOLO), to detect prominent bowel sounds that can enable real-time analysis for future GI disease detection and diagnosis. A total of 110 2-minute PEGs sampled at 44.1 kHz were recorded using the Eko DUO® stethoscope from eight healthy volunteers at two locations, namely, left upper quadrant (LUQ) and right lower quadrant (RLQ) after IRB approval. The datasets were annotated by trained physicians, categorizing BSs as prominent or obscure using version 1.7 of Label Studio Software®. Each BS recording was split up into 375 ms segments with 200 ms overlap for real-time BS detection. Each segment was binned based on whether it contained a prominent BS, resulting in a dataset of 36,149 non-prominent segments and 6435 prominent segments. Our dataset was divided into training, validation, and test sets (60/20/20% split). A 1D-CNN augmented transformer was trained to classify these segments via the input of Mel-frequency cepstral coefficients. The developed AI model achieved area under the receiver operating curve (ROC) of 0.92, accuracy of 86.6%, precision of 86.85%, and recall of 86.08%. This shows that the 1D-CNN augmented transformer with Mel-frequency cepstral coefficients achieved creditable performance metrics, signifying the YOLO model’s capability to classify prominent bowel sounds that can be further analyzed for various GI diseases. This proof-of-concept study in healthy volunteers demonstrates that automated BS detection can pave the way for developing more intuitive and efficient AI-PEG devices that can be trained and utilized to diagnose various GI conditions. To ensure the robustness and generalizability of these findings, further investigations encompassing a broader cohort, inclusive of both healthy and disease states are needed.

Abstract Background: Understanding of the diagnosis and treatment of adults with community-acquired pneumonia (CAP) has evolved thanks to new evidence, experience, and emerging technologies. This document updates evidence-based clinical practice guidelines on four key questions for the diagnosis and management of adult patients with CAP. Methods: A multidisciplinary panel integrated systematic reviews of comparative evidence with other relevant research and clinical experience, then applied Grading of Recommendations, Assessment, Development and Evaluation (GRADE) methodology to produce recommendations using the Evidence to Decision Framework. Results: The panel formulated clinical recommendations that address questions related to CAP, including lung ultrasound for diagnosis, empiric antibacterial therapy if a test for a respiratory virus is positive, antibiotic duration, and the use of systemic corticosteroids. Conclusions: The panel formulated and provided the rationale for recommendations on selected diagnostic and treatment strategies for adult patients with CAP.

Accurate analysis of medical videos remains a major challenge in deep learning (DL) due to the need for effective spatiotemporal feature mapping that captures both spatial detail and temporal dynamics. Despite advances in DL, most existing models in medical AI focus on static images, overlooking critical temporal cues present in video data. To bridge this gap, a novel DL-based framework is proposed for spatiotemporal feature extraction from medical video sequences. As a feasibility use case, this study focuses on gastrointestinal (GI) endoscopic video classification. A 3D convolutional neural network (CNN) is developed to classify upper and lower GI endoscopic videos using the hyperKvasir dataset, which contains 314 lower and 60 upper GI videos. To address data imbalance, 60 matched pairs of videos are randomly selected across 20 experimental runs. Videos are resized to 224 × 224, and the 3D CNN captures spatiotemporal information. A 3D version of the parallel spatial and channel squeeze-and-excitation (P-scSE) is implemented, and a new block called the residual with parallel attention (RPA) block is proposed by combining P-scSE3D with a residual block. To reduce computational complexity, a (2 + 1)D convolution is used in place of full 3D convolution. The model achieves an average accuracy of 0.933, precision of 0.932, recall of 0.944, F1-score of 0.935, and AUC of 0.933. It is also observed that the integration of P-scSE3D increased the F1-score by 7%. This preliminary work opens avenues for exploring various GI endoscopic video-based prospective studies.

The human voice is an important medium of communication and expression of feelings or thoughts. Disruption in the regulatory systems of the human voice can be analyzed and used as a diagnostic tool, labeling voice as a potential “biomarker”. Conversational artificial intelligence is at the core of voice-powered technologies, enabling intelligent interactions between machines. Due to its richness and availability, voice can be leveraged for predictive analytics and enhanced healthcare insights. Utilizing this idea, we reviewed artificial intelligence (AI) models that have executed vocal analysis and their outcomes. Recordings undergo extraction of useful vocal features to be analyzed by neural networks and machine learning models. Studies reveal machine learning models to be superior to spectral analysis in dynamically combining the huge amount of data of vocal features. Clinical applications of a vocal biomarker exist in neurological diseases such as Parkinson’s, Alzheimer’s, psychological disorders, DM, CHF, CAD, aspiration, GERD, and pulmonary diseases, including COVID-19. The primary ethical challenge when incorporating voice as a diagnostic tool is that of privacy and security. To eliminate this, encryption methods exist to convert patient-identifiable vocal data into a more secure, private nature. Advancements in AI have expanded the capabilities and future potential of voice as a digital health solution.

Abstract Rationale Pulmonary function tests (PFT) are interpreted in the context of reference values that were based on sex, age, height and previously race/ethnicity. The Global Lung Function Initiative (GLI) published spirometry references equations in 2012 and static lung volume reference equations in 2021. In 2023, the American Thoracic Society recommended removal of race from predictive equations for spirometry using the new race-neutral GLI-Global reference equations. Since the change of spirometry reference equations, we have noticed an increase in number of patients with normal spirometry but a low total lung capacity (TLC), where historically the incidence was less than 5 percent and normal spirometry was used to exclude restriction. The goal of this study was to further investigate this observation and characterize the population of patients with normal spirometry and reduced TLC, which we termed occult restriction. Methods We analyzed our existing PFT database which included 28,415 spirometry tests performed at Mayo Clinic Rochester and Mayo Clinic Florida between 2013 to 2016. 26,856 tests included lung volume measurements. The spirometry was interpreted using both GLI-2012 and GLI-Global reference equations and TLC was interpreted using GLI lung volume reference equations. Patients’ demographics including self-identified race were obtained. Patients with occult restriction were further characterized using descriptive statistics. All data analysis was done using BlueSky Statistics Version 10.3.1. Results Our study showed that 920 (3.4%) patients with normal spirometry using GLI-2012 reference equations had low TLC, while 1526 (5.7%) patients with normal spirometry using GLI-Global reference equations had low TLC. Among these patients, 697 patients had a change from abnormal to normal spirometry interpretation and 91 patients had a change from normal to abnormal spirometry interpretation when using GLI-Global reference equations. Comparing patients of different races and ethnicities, there is increased incidence of occult restriction in Caucasian patients with transition to GLI-Global, while the incidence of occult restriction decreased in African American patients. Patients who identify as African American or Southeast Asian are more likely to have occult restriction than others (Table 1). Conclusions With the change from GLI-2012 to GLI-Global spirometry reference equations, the frequency of occult restriction has increased from 3.4% to 5.7% with predominant effect on Caucasian patients. The clinical implication of this finding requires further study but clinicians need to be vigilant that a normal spirometry may not exclude restrictive lung disease using our current reference equations.

Background/Objectives: Peri-intubation hypotension is a known complication of endotracheal intubation. In the hospital setting, peri-intubation hypotension has been shown to increase hospital mortality and length of stay. The use of prophylactic vasopressors at the time of sedation induction to prevent peri-intubation hypotension has been raised. This systematic review and meta-analysis aims to review the safety and efficacy of this practice. Methods: The study was fully registered with PROSPERO on 13 October 2022, and screening for eligibility was initiated on 20 September 2024. Randomized controlled trials, along with retrospective or prospective cohort studies, were included in the search. The terms “peri-intubation hypotension”, “vasopressors”, “intubation”, and “anesthesia induced hypotension” were used to search the title/summary in PubMed, Cochrane Library, and Google Scholar databases. An assessment of bias for each study was conducted using the Newcastle-Ottawa Quality Assessment Scale. The primary outcome was the rate of hypotension peri-intubation. Any complications secondary to hypotension or vasopressors were the secondary outcome. Results: We identified 13 studies, which were all randomized controlled studies, to include in the final analysis. The risk ratio for preventing peri-intubation hypotension was 1.6 (95% CI, 1.2–2.14) with the use of prophylactic phenylephrine while giving propofol versus no prophylactic vasopressors and 1.28 (95% CI 1.03–1.60) with the use of ephedrine. Conclusions: These findings suggest that in patients undergoing intubation in the operating room with propofol, prophylactic vasopressors given with induction for intubation decrease the odds of hypotension.

Abstract Objectives We aimed to improve the operational efficiency of clinical staff, including physicians and allied health professionals, in the previsit review of patients by implementing a disease-focused dashboard within the electronic health record system. The dashboard was tailored to the unique requirements of the clinic and patient population. Methods A prospective quality improvement study was conducted at an accredited pulmonary hypertension (PH) clinic within a large academic center, staffed by two full time physicians and two allied health professionals. Physicians' review time before and after implementation of the PH dashboard was measured using activity log data derived from an EHR database. The review time for clinic staff was measured through direct observation, with review method—either conventional or newly implemented dashboard—randomly assigned. Results Over the study period, the median number of patients reviewed by physicians per day increased slightly from 5.50 (interquartile range [IQR]: 1.35) before to 5.95 (IQR: 0.85) after the implementation of the PH dashboard (p = 0.535). The median review time for the physicians decreased with the use of the dashboard, from 7.0 minutes (IQR: 1.55) to 4.95 minutes (IQR: 1.35; p < 0.001). Based on the observed timing of 70 patient encounters among allied clinical staff, no significant difference was found for experienced members (4.65 minutes [IQR: 2.02] vs. 4.43 minutes [IQR: 0.69], p = 0.752), while inexperienced staff saw a significant reduction in review time after familiarization with the dashboard (5.06 minutes [IQR: 1.51] vs. 4.12 minutes [IQR: 1.99], p = 0.034). Subjective feedback highlighted the need for further optimization of the dashboard to align with the workflow of allied health staff to achieve similar efficiency benefits. Conclusion A disease-focused dashboard significantly reduced physician previsit review time while that for clinic staff remained unchanged. Validation studies are necessary with our patient populations to explore further qualitative impacts on patient care efficiency and long-term benefits on workflow.