Iyer, Vivek

Background: Lung cancer remains the leading cause of cancer-related mortality globally, largely due to delayed diagnosis in its early stages. While conventional diagnostic tools like low-dose CT and tissue biopsy are routinely used, they suffer from limitations including invasiveness, radiation exposure, cost, and limited sensitivity for early-stage detection. Liquid biopsy, a minimally invasive alternative that captures circulating tumor-derived biomarkers such as ctDNA, cfRNA, and exosomes from body fluids, offers promising diagnostic potential—yet its sensitivity in early disease remains suboptimal. Recent advances in Artificial Intelligence (AI) and radiomics are poised to bridge this gap. Objective: This review aims to explore how AI, in combination with radiomics, enhances the diagnostic capabilities of liquid biopsy for early detection of lung cancer and facilitates personalized monitoring strategies. Content Overview: We begin by outlining the molecular heterogeneity of lung cancer, emphasizing the need for earlier, more accurate detection strategies. The discussion then transitions into liquid biopsy and its key analytes, followed by an in-depth overview of AI techniques—including machine learning (e.g., SVMs, Random Forest) and deep learning models (e.g., CNNs, RNNs, GANs)—that enable robust pattern recognition across multi-omics datasets. The role of radiomics, which quantitatively extracts spatial and morphological features from imaging modalities such as CT and PET, is explored in conjunction with AI to provide an integrative, multimodal approach. This convergence supports the broader vision of precision medicine by integrating omics data, imaging, and electronic health records. Discussion: The synergy between AI, liquid biopsy, and radiomics signifies a shift from traditional diagnostics toward dynamic, patient-specific decision-making. Radiomics contributes spatial information, while AI improves pattern detection and predictive modeling. Despite these advancements, challenges remain—including data standardization, limited annotated datasets, the interpretability of deep learning models, and ethical considerations. A push toward rigorous validation and multimodal AI frameworks is necessary to facilitate clinical adoption. Conclusion: The integration of AI with liquid biopsy and radiomics holds transformative potential for early lung cancer detection. This non-invasive, scalable, and individualized diagnostic paradigm could significantly reduce lung cancer mortality through timely and targeted interventions. As technology and regulatory pathways mature, collaborative research is crucial to standardize methodologies and translate this innovation into routine clinical practice.

ABSTRACT Hereditary hemorrhagic telangiectasia (HHT, Osler‐Weber‐Rendu disease) is the second most common inherited bleeding disorder worldwide, affecting approximately 1 in 5000 people. Development of disease‐modifying and efficacious hemostatic agents to treat HHT has finally begun after decades without such medical therapies. However, the lack of consensus on standardized severity definitions, outcome criteria, and terminology remains a major obstacle to clinical investigation and therapeutic development in HHT. Additionally, with the ongoing repurposing of antiangiogenic agents and emerging development of novel HHT‐specific therapies, comparative clinical trials are expected in the future. Therefore, to end the problematic heterogeneity hindering these efforts, the Global Research and Medical Advisory Board (GRMAB) of the Cure HHT Foundation, an international group of recognized HHT experts, convened a conference of expert HHT clinician‐investigators from within GRMAB as well as invited external experts in HHT and bleeding disorders generally, patients with HHT, and patient advocates to define standard terminology and definitions for outcomes and severity classification for bleeding and anemia in HHT. These criteria and definitions should be adopted by regulators, investigators, and the pharmaceutical industry in the development and performance of interventional clinical trials and cohort studies to allow improved comparability between clinical trials, facilitate communication between clinicians and investigators, improve therapeutic guideline development, and provide a standardized framework for regulatory agencies. Search Strategy and Selection Criteria Evidence for this report was systematically identified and evaluated utilizing two search strategies in Ovid MEDLINE, described in full detail in the Appendix, pp.4–13. The searches were conducted on January 7, 2025. The titles and abstracts of each record were reviewed, and the inclusion criteria were applied to all search results to identify full text articles to be retrieved for further review. All retrieved full texts were then reviewed to reach a final determination if a study met the inclusion criteria. Included references were then compiled into evidence tables, which were then utilized by the International Consensus Report Working Group throughout the development of report recommendations.

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 Introduction: Cystic fibrosis (CF) is a genetic disorder characterized by defective chloride ion transport, leading to thick mucus production, chronic respiratory infections, and other multisystem involvement. Although CF is often diagnosed in childhood, the condition can be missed or misdiagnosed in adults. Description of Case: We present the case of a 60-year-old male from India who was diagnosed with CF after a prolonged period of sinopulmonary symptoms. He initially presented in 2014. His medical history was pertinent for asthma, and multiple episodes of clinically and radiographically confirmed pneumonia and polypoid sinusitis requiring IV antibiotics and sinus surgery. He carried a prior diagnosis of allergic bronchopulmonary aspergillosis treated with itraconazole and steroids, as well as elevated IgE levels. His CT chest was notable for extensive bronchiectasis, bronchial wall thickening, and mucus plugging of both lungs. He had no known family history of CF. Sweat chloride testing was in the intermediate range (44, 47 mmol/L; normal <30 mmol/L, intermediate 30 to 59 mmol/L, abnormal >59 mmol/L). Given high suspicion for CF, cystic fibrosis transmembrane conductance regulator (CFTR) full gene analysis was pursued. Sequence analysis and multiplex ligation-dependent probe amplification of the CFTR gene detected heterozygous sequence changes c.1717-2A>T, classified as likely deleterious, and c.1367T>C (p.V456A), variant of uncertain significance. He was thus initially diagnosed as a CF carrier. He re-presented in 2024 with decline in pulmonary function testing and continued sinopulmonary infections. Genetic testing results from 2014 were re-analyzed. Between initial presentation and present, his V456A variant was upgraded to pathogenic. He met diagnostic criteria for CF with two pathogenic CFTR variants, a repeated intermediate sweat chloride (47 mmol/L) suggestive of CFTR protein dysfunction, and disease that could be attributed to CFTR dysfunction. He subsequently started TRIKAFTA® (elexacaftor/tezacaftor/ivacaftor and ivacaftor) and airway clearance therapy. Discussion: The diagnosis of CF in adults can be challenging, particularly in individuals without a known family history, intermediate sweat chloride testing, and with inconclusive genetic testing. Our understanding of CF in Asian populations is limited. CF is suspected to be underreported in patients with Southeast Asian ancestry in part due to genetic heterogeneity. The interpretation of certain genetic variants can evolve over time. A variant of unknown significance may later be reclassified as pathogenic, revealing its true role in disease development. This highlights the critical importance of regularly re-evaluating genetic test results.