Citations

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.

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.

Abstract Hereditary hemorrhagic telangiectasia (HHT), an autosomal dominant vasculopathy affecting 1 in 5000 individuals, is the second most common inherited bleeding disorder worldwide. Despite this prevalence, comprehensive data on disease manifestations and complications remain limited. To address this gap, the US Congress allocated funding leading to the Comprehensive HHT Outcomes Registry of the United States (CHORUS), a prospective, 15-center longitudinal registry enrolling unselected patients with confirmed HHT. In this initial report, we describe findings from the first 600 participants, with a median age of 53 (range, 0-88) years and 60% female. Despite most participants developing typical HHT manifestations by age 13 years, the majority (63%) were not diagnosed until mid-to-late adulthood. Recurrent spontaneous epistaxis occurred in 95% of participants, chronic gastrointestinal bleeding in 30%, and heavy menstrual bleeding in 35% of postmenarche females, together resulting in moderate-to-severe mucosal bleeding in 76%. Iron deficiency and/or anemia were diagnosed in 68%, with 41% requiring IV iron and 25% requiring red cell transfusions. Serious complications of solid-organ arteriovenous malformations were frequent, including intracranial hemorrhage (3%), pulmonary hemorrhage (2%), venous thromboembolism (7%), arterial thromboembolism (11%), heart failure (7%), and pulmonary hypertension (7%). These data from CHORUS, the first national US registry of its kind, provide reliable, real-world estimates of the incidence, prevalence, and severity of numerous HHT manifestations and complications. HHT has a high burden of moderate-to-severe bleeding, anemia, thrombosis, and major neurologic and cardiopulmonary complications. There is a mean interval between first symptoms and diagnosis of >2 decades, during which substantial, serious, and preventable HHT morbidity, including early intracranial hemorrhage, may occur. This trial was registered at clinicaltrials.gov as NCT06259292.

Abstract Hereditary hemorrhagic telangiectasia (HHT) results in recurrent severe epistaxis, chronic gastrointestinal bleeding, and other morbid manifestations. Pomalidomide was recently demonstrated to be efficacious for bleeding in HHT in the landmark PATH-HHT trial. Given that the vascular remodeling that results in bleeding improvement may require several months, characteristics associated with treatment response would be invaluable to plan treatment. Using data from PATH-HHT (NCT03910244), we identified characteristics associated with change from baseline in Epistaxis Severity Score (ESS; a well-validated 10-point HHT bleeding scale and the trial’s primary end point) using multivariable-adjusted repeated-measures models. Characteristics associated with a better response to pomalidomide at weeks 16 to 24 of the trial included a higher (more severe) baseline ESS (change from baseline, −0.76 [95% confidence interval (CI), −0.99 to −0.54] points per 1-point higher baseline score, P< .001) and concomitant antifibrinolytic therapy (−0.73 [95% CI, −1.48 to 0.01] vs no therapy, P = .05). Characteristics associated with a less robust response were older age (0.29 [95% CI, 0.05-0.53] per 10 years older, P = .02) and underlying ACVRL1 germ line mutation (0.62 [95% CI, −0.04 to 1.27] vs ENG, SMAD4, or mutation not known, P = .06]. Characteristics notably associated with placebo response (placebo effect) were patient-reported outcome measures, such that those experiencing more severe disease at baseline had less placebo effect. In conclusion, several baseline patient and disease characteristics were associated with pomalidomide response, findings that may help guide patient selection for the use of pomalidomide in HHT. This trial was registered at www.Clinicaltrials.gov as NCT03910244.

Hypertension has been traditionally known to be highlighted by mean blood pressure; however, emerging evidence exhibits that blood pressure variability (BPV), including short-term, day-to-day, and visit-to-visit fluctuations can have an implication across multiple body systems. Elevated BPV reflects repetitive hemodynamic stress, affecting the physiologic hemostasis contributing to vascular injury and end organ damage. This narrative review is a compilation of recent evidence on the prognostic value of BPV, explained by pathophysiology, various devices with its measurement approaches, and, essentially, the clinical implication of BPV and the use of such devices utilizing artificial intelligence. A comprehensive literature search across PubMed, Cochrane Library, Scopus, and Web of Science were conducted, focusing on observational studies, cohorts, randomized trials, and meta-analyses. Higher BPV has been associated with an increased risk of cardiovascular mortality, stroke, coronary events, and heart failure, the progression of chronic kidney disease, cognitive decline, and preeclampsia, among other end organ damage, despite mean blood pressure. The various pathophysiologic mechanisms include autonomic dysregulation, arterial stiffness, endothelial dysfunction, circadian rhythm alteration, and systemic inflammation, which result in vascular remodeling and multisystem damage. Antihypertensive medications such as calcium channel blockers and renin–angiotensin–aldosterone system inhibitors seem to reduce BPV; randomized trials have not specifically investigated their BPV-reducing effects. The aim of this review is to highlight that BPV is a dynamic marker of multisystem risk, and question how various AI-based devices can aid continuous BPV monitoring and patient specific risk stratification.

Purpose of review Indoor water parks, with over 1100 facilities in the United States, are popular recreational venues with an estimated 1.5 million visitors per year in North America. While generally well tolerated, they can be associated with significant respiratory and nonrespiratory health risks. This review focuses exclusively on the infectious and noninfectious respiratory health issues associated with indoor water park usage and is timely due to increasing popularity, evolving water-treatment practices, and the unique vulnerability of specific populations. Recent findings This review synthesizes peer-reviewed studies and institutional data from 2014 to 2024, detailing exposure mechanisms, health effects, mitigation strategies, and impacts on vulnerable populations such as children, asthmatic individuals, cystic fibrosis patients, immunocompromised individuals, and workers. Topics covered include disinfection by-products (DBPs), chloramine inhalation effects, asthma risks, hypersensitivity pneumonitis from nontuberculous mycobacteria, and occupational exposures. Emerging technologies in air and water quality management, alongside recent policy and facility-design developments, are also examined. Summary While indoor water parks remain a valued recreational resource, they pose significant and often under-recognized respiratory risks. Through better facility ventilation, hygiene education, disinfection innovation, and regulatory reform, these risks can be mitigated to protect both patrons and staff, particularly in vulnerable subpopulations.

Abstract Hereditary hemorrhagic telangiectasia (HHT) causes severe recurrent epistaxis, chronic gastrointestinal bleeding, solid organ arteriovenous malformations, and significant anemia. Although it is the second most common inherited bleeding disorder worldwide, no approved therapies exist. The multicenter, US randomized, controlled PATH-HHT trial demonstrated efficacy of short-term pomalidomide treatment of epistaxis in HHT. However, questions regarding long-term safety, effectiveness, and utility for HHT-associated gastrointestinal bleeding remain. The PATH-HHT ATLAS (after trial longitudinal assessment study) was a multicenter US longitudinal observational study evaluating patients enrolled in PATH-HHT who continued pomalidomide after PATH-HHT through a poststudy drug access program, with ongoing close monitoring per PATH-HHT protocol and as mandated by the US Food and Drug Administration. Sixty-two patients treated with pomalidomide for HHT for up to 4.4 years were included. Significant, durable improvements in mean epistaxis severity score (5.55 points [baseline] to 2.80 points [month 12]; P< .0001) and mean hematologic support score (9.11 red cell unit equivalents [RUEs] during 6 months pretreatment to 5.73 RUEs [months 7-12]; P = .0056) were observed. Pomalidomide was less effective for gastrointestinal bleeding than for epistaxis, particularly in patients with high red blood cell transfusion requirements. Thirty-one patients (50%) underwent dose reduction from 4 mg daily, primarily due to neutropenia, but most maintained effectiveness at 2 or 3 mg daily. Over 105.2 patient-years of pomalidomide treatment, 0 patients developed peripheral neuropathy, 1 developed venous thromboembolism, and 5 developed serious infections. In conclusion, pomalidomide was effective for HHT-associated epistaxis over extended durations, albeit with nontrivial potential toxicities, and may be considered for certain patients with HHT. This trial was registered at www.clinicaltrials.gov as NCT07018401.

Background: Interstitial lung disease (ILD) involves numerous chronic pulmonary conditions that damage the lung parenchyma and alveolar interstitium. ILD has overlapping clinical and radiological features with other commonly seen cardiac and respiratory conditions. If not identified and treated in a timely manner, it may lead to irreversible fibrosis and a poor prognosis in the patient. The current diagnostic methods are either invasive or reliant on imaging or specialist interpretation, which can lead to diagnostic delay, increased radiation exposure, and healthcare costs. Lung crackles, often under-recognized as a non-specific feature of ILD, may serve as an important diagnostic clue in identifying not only the early stages of ILD but also its subtypes. This review explores the potential of analyzing the lung sounds in ILD through AI-based auscultation. Objective: To provide a comprehensive analysis of the pathophysiological stages of lung injury in ILD, the specific acoustic features, and the location associated with each ILD subtype and to evaluate the current state-of-the-art non-AI and AI methodologies that are used to diagnose ILD. This review aims to analyze the limitations associated with the current modalities and to envision AI-integrated auscultation as a powerful, cost-effective, non-invasive, radiation-free screening tool for early detection of ILD and its subtypes. Content Overview: The review begins with a detailed analysis of the lung sound pathophysiology, exploring the two-stage mechanism of alveolar epithelial injury and fibrosis formation. Existing hypotheses explaining the mechanism behind crackle production and the role of structural anatomy and surface tension in the generation of pathological lung sounds are examined. A tabulated summary of common ILD subtypes is provided, including their inciting events, pathogenesis, anatomical auscultation locations, and prognostic implications. Current diagnostic modalities for ILD, both non-AI and AI-based, are summarized along with their limitations, emphasizing the need for improved diagnostic tools. Discussion: Existing studies suggest that AI-based auscultation can match or exceed the current modalities in its sensitivity and specificity for detecting ILD-related crackles. Clinicians can identify the specific sound pattern and then correlate it with the ILD subtype and understand the prognosis in real time, thereby providing timely intervention to the patient. Additionally, AI-based auscultation can be used in resource-limited settings and can potentially reduce dependence on pulmonology expertise and radiation-based imaging for monitoring the condition. Conclusions: This literature review highlights the clinical potential of AI-based auscultation for early and accurate diagnoses of ILD. Understanding the associated pathological sounds, biomarkers, and genetic mutations linked to different subtypes opens avenues for future development of non-invasive diagnostic panels for ILD in clinical practice.