Citations

Objectives: Pulmonary function tests (PFTs) are essential for diagnosis, management, and follow-up of a wide range of respiratory conditions as they provide quantitative insights into various aspects of lung function. Precision in ordering and scheduling PFTs, like any test, is crucial as errors can lead to misdiagnoses, delayed treatments, unnecessary retesting, inflated healthcare costs, and potentially compromised patient care. Hence, the aim of this quality improvement initiative was to reduce the PFT ordering error rate to below 5% by redesigning the ordering workflow and implementing a standardized order set tailored to specific clinical scenarios. Methods: The quality improvement initiative was implemented from August 2023 to March 2024. Data was collected from the electronic medical record (EMR) using predefined operational definitions to identify incorrect PFT orders and scheduling errors. A redesigned orderset was created to align with specific clinical presentations, including symptoms, suspected diagnosis, confirmed diagnosis, and presurgical evaluation. Scheduling was also restructured to match the expected testing time for each category. Education sessions were conducted with ordering providers, and ongoing feedback loops were established. Results: Among 575 preintervention PFT orders, 130 (22.6%) contained errors. Following implementation, review of 607 postintervention orders showed a reduction in error rates to 4.1%, representing an ∼80% improvement ( P <0.01). There was no increase in unnecessary testing, supporting the effectiveness of the intervention without unintended negative consequences. Conclusions: Implementation of a knowledge-based CDSS with standardized order sets significantly reduced PFT ordering errors and variability, improving guideline adherence and care quality. Continued refinement and integration with evolving technologies are essential for broader applicability.

Photoplethysmography (PPG) is a non-invasive optical technique commonly used to measure heart rate and oxygen saturation, but its waveform contains additional physiological information that can be analyzed using artificial intelligence (AI). This narrative review summarizes the emerging applications of AI-based PPG in cardiovascular, respiratory, sleep, hemodynamic, pregnancy-related, and portal-hypertension assessment, with the aim of evaluating its potential beyond conventional monitoring and identifying barriers to clinical translation. The literature search was conducted using PubMed, Google Scholar, IEEE Xplore, ScienceDirect, and SpringerLink. Additional relevant studies were identified through screening the reference lists of included articles. Studies published between 2002 and 2026 were identified to capture the development of PPG from conventional monitoring to newer AI-based applications. Human studies were prioritized, while relevant computational, simulated, synthetic, ex vivo, and technical studies were also included. Studies unrelated to PPG, duplicates, and studies with limited relevance were excluded. A total of 96 references were included, covering AI approaches such as convolutional and deep neural networks, ensemble methods, transfer learning, U-Net, generative adversarial networks, and Transformer-based models. Overall, the reviewed evidence suggests that AI-based PPG may support blood pressure estimation, atrial fibrillation detection, sleep and respiratory monitoring, vascular aging assessment, pulmonary hypertension screening, preeclampsia assessment, volume-status and compensatory-reserve assessment, and exploratory assessment related to portal hypertension. However, clinical translation remains limited by motion artifacts, sensor and measurement-site variability, skin-pigmentation-related bias, physiological and environmental influences, heterogeneous methods, limited external validation, and inconsistent clinical and regulatory standards.

Introduction Post-intubation hypotension (PIH) is a frequent complication of emergency endotracheal intubation and is associated with increased mortality. Early identification of high-risk patients remains challenging, and existing prediction tools demonstrate moderate accuracy. Objective We aim to identify predictors of PIH and develop machine learning models for pre-intubation risk stratification. Methods We conducted a multicentre retrospective study across 3 Mayo Clinic hospitals, including 600 adults undergoing urgent intubation in the intensive care unit. PIH was defined by mean arterial pressure<65 mm Hg, systolic blood pressure (SBP)<80 mm Hg or ≥40% decline or vasopressor initiation/escalation within 30 min. Three model frameworks were developed: Shock Indices (SIs), Acute Physiology and Chronic Health Evaluation II (APACHE II) and Sequential Organ Failure Assessment (SOFA), incorporating demographic, haemodynamic, laboratory and sedation variables. Various machine learning algorithms were applied to analyse the three models. Results PIH occurred in 46% of patients included in the study. In the SIs model, stepwise logistic regression achieved an area under the curve (AUC) of 0.76. The APACHE II framework showed the strongest performance, with random forest achieving an ROC AUC of 0.82 and the ensemble model demonstrating the highest overall discrimination (Receiver operator Curve [ROC] AUC 0.83) with favourable accuracy and F1 metrics. The SOFA framework showed moderate performance, with an ensemble ROC AUC of 0.73. Key predictors included pre-intubation vasopressor use, SBP, platelet count and haematological parameters. Conclusions Machine learning models using routinely available pre-intubation data showed potential to predict PIH in this retrospective proof-of-concept study. These findings support further development of anticipatory artificial intelligence-driven risk stratification in critical care, but the models should not be considered ready for bedside implementation until they undergo prospective validation in larger, independent and more diverse cohorts.

Artificial intelligence (AI) is rapidly transforming healthcare through applications in clinical decision support, diagnostic imaging, population health management, and workflow optimization. Despite these advances, real-world deployment continues to expose critical challenges related to safety, bias, transparency, and integration into clinical workflows. Algorithmic bias can exacerbate health disparities, limited explainability may undermine clinician trust, and insufficient validation and post-deployment monitoring can compromise patient safety. Although the World Health Organization (WHO) has established six ethical principles for AI in health, including autonomy, well-being and safety, transparency, accountability, equity, and sustainability, translating these high-level principles into practical and enforceable governance mechanisms remains a persistent challenge. This narrative review synthesizes insights from bioethics, health policy, computer science, and clinical medicine to identify gaps in current AI governance approaches and proposes a lifecycle-aligned governance-by-design framework that operationalizes WHO ethical principles across key stages of the healthcare AI lifecycle, including data collection, model development, validation, deployment, and post-deployment monitoring. The framework integrates concrete governance mechanisms such as consent governance, fairness evaluation, external validation, explainability, clinician oversight, and continuous performance monitoring. Overall, this work advances a practical, lifecycle-integrated approach to AI governance and provides a structured foundation for developing safe, equitable, and trustworthy AI systems in healthcare.

Abstract Pain assessment plays a critical role in clinical decision-making, yet conventional methods rely heavily on subjective self-reports such as the Visual Analog Scale (VAS) or the Numeric Rating Scale (NRS). These approaches fail in scenarios involving infants, sedated patients, unconscious individuals, or those with cognitive or communication impairments. To address this gap, this research proposes PainNet, an AI-driven, real-time facial pain recognition system that integrates deep learning-based object detection with Action Unit (AU)–based pain intensity scoring. The system uses YOLOv8 for rapid facial expression detection and incorporates Py-Feat to extract pain-relevant AUs, enabling computation of the Prkachin and Solomon Pain Intensity (PSPI) score. A balanced dataset comprising 500 images sourced from Delaware, BioVid, and RaFD was curated, annotated, and preprocessed for training. The YOLOv8-based binary pain vs. no-pain classifier achieved a mean Average Precision (mAP) of 0.89 and an F1-score of 0.80 on the test dataset, demonstrating strong performance in diverse environments and facial variations. The design emphasizes computational efficiency by activating AU analysis only when YOLOv8 detects probable pain, making PainNet suitable for continuous monitoring in ICUs, elder-care facilities, and telemedicine systems. This study demonstrates that the fusion of real-time object detection and clinically validated AU scoring can significantly advance automated, objective, and scalable pain assessment.

Abstract Interstitial lung disease (ILD) is a chronic, irreversible condition that is challenging to diagnose due to subtle symptoms and limitations of conventional tools. Noninvasive lung sound analysis using phonopulmography offers a promising alternative. This study evaluated the feasibility of a deep learning model for distinguishing normal and pathological lung sounds in ILD. Lung sound recordings were collected from 12 subjects (6 healthy, 6 ILD) and segmented beat-to-beat using simultaneously acquired ECG and phonopulmography, yielding 2,280 segments. Mel-frequency cepstral coefficients (MFCCs; 13 per segment) were extracted, and a one-dimensional CNN-based You Only Listen Once (YOLO) model was trained for segment classification. Evaluation used Leave-One-Out Cross-Validation, with patient-level classification by aggregating segment predictions via majority vote. On the test set (190 segments per class), the model achieved an average segment-level accuracy of 0.738 ± 0.087 and mean AUC of 0.850 ± 0.062. Precision, recall, and F1-score were 0.775 ± 0.148, 0.755 ± 0.183, and 0.738 ± 0.089, respectively. These preliminary results suggest that beat-level MFCCs with a 1D CNN-based YOLO model enable accurate segment- and patient-level classification. This feasibility study highlights the potential of AI-assisted auscultation for noninvasive monitoring and clinical decision support in ILD management, pending further validation in larger cohorts.

Abstract Accurate assessment of left-ventricular ejection fraction (EF) is a critical metric in diagnosing and managing heart failure; however, methods of assessment remain resource intensive, not widely available in low-acuity or remote settings and are intermittent in nature. This study explores the potential of a novel framework, cardiac electromechanical fingerprinting (cEMF) using synchronized electrocardiography (ECG) and seismocardiography (SCG) collected from a wearable sensing patch as a low-cost, non-invasive, continuous estimate of EF that can be used for rapid point of care screening. A machine learning pipeline was developed to process raw ECG and SCG data to derive EF. Signals were cleaned using band-pass filtering, NeuroKit2-based ECG cleaning and fiducial detection of critical electromechanical events. We extracted an ECG-SCG feature space consisting of heart-rate variability metrics, ECG morphological characterization, SCG timing intervals, spectral and entropy-based features. The top thirty most important features for EF were used to train and evaluate several regressor models. The best performing model was the Gaussian Process Regressor with an MAE of 5.43. Our findings demonstrate the promise of producing clinically relevant cardiac function measures, such as EF, from wearable electromechanical signals. Future work using larger datasets and complementary physiological signals such as phonocardiogram (PCG) may significantly strengthen EF% estimation and other cardiac functions for clinical applicability.

Microplastics may pose health risks, particularly for chronic lung diseases. Clarifying the link between circulating microplastics and pulmonary disease is vital for shaping research and interventions. The objective of this study was to evaluate whether microplastics in peripheral blood are associated with COPD or IPF vs. no lung disease. In this pilot prospective case-control study, participants were grouped as control (n = 10), COPD (n = 9), or IPF (n = 10). Relevant comorbidities and exposures were obtained from records and questionnaires. All underwent standardized blood collection (PlasticTox©). Samples were analyzed for total microplastic concentration, stratified by size (<10 µm, 10–30 µm, 30–70 µm). The primary outcome was to show a difference in total microplastic burden between lung disease and controls. Secondary measures were to determine size-specific concentrations and associations with demographic variables and smoking history. Among 29 participants (median age 70 (IQR 64–80); 14 women (48.3%)), COPD/IPF groups had significantly higher total microplastic concentrations vs. controls (median 26.0 vs. 3.5 particles/100 µL; p < 0.01). Particle burdens <10 µm and 10–30 µm were particularly elevated (both p < 0.01). After adjusting for smoking, only the <10 µm fraction remained independently associated with lung disease (adjusted odds ratio 1.94 (95% CI, 1.23–7.04)). In this pilot exploratory study, individuals with COPD or IPF showed greater circulating microplastic levels than controls. These findings should be interpreted as hypothesis-generating, and larger analytically validated studies are needed to clarify directionality, causal mechanisms, contamination control, and the clinical relevance of circulating microplastic burden.