Iyer, Vivek N

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.

Respiratory disorders, being one of the leading causes of disability worldwide, account for constant evolution in management technologies, resulting in the incorporation of artificial intelligence (AI) in the recording and analysis of lung sounds to aid diagnosis in clinical pulmonology practice. Although lung sound auscultation is a common clinical practice, its use in diagnosis is limited due to its high variability and subjectivity. We review the origin of lung sounds, various auscultation and processing methods over the years and their clinical applications to understand the potential for a lung sound auscultation and analysis device. Respiratory sounds result from the intra-pulmonary collision of molecules contained in the air, leading to turbulent flow and subsequent sound production. These sounds have been recorded via an electronic stethoscope and analyzed using back-propagation neural networks, wavelet transform models, Gaussian mixture models and recently with machine learning and deep learning models with possible use in asthma, COVID-19, asbestosis and interstitial lung disease. The purpose of this review was to summarize lung sound physiology, recording technologies and diagnostics methods using AI for digital pulmonology practice. Future research and development in recording and analyzing respiratory sounds in real time could revolutionize clinical practice for both the patients and the healthcare personnel.

Patients with hereditary hemorrhagic telangiectasia (HHT) have arteriovenous malformations (AVMs) with genetic mutations involving the activin-A receptor like type 1 ( ACVRL1 or ALK1 ) and endoglin ( ENG ). Recent studies have shown that Neuropilin-1 (NRP-1) inhibits ALK1. We investigated the expression of NRP-1 in livers of patients with HHT and found that there was a significant reduction in NRP-1 in perivascular smooth muscle cells (SMCs). We used Nrp1 SM22KO mice ( Nrp1 was ablated in SMCs) and found hemorrhage, increased immune cell infiltration with a decrease in SMCs, and pericyte lining in lungs and liver in adult mice. Histologic examination revealed lung arteriovenous fistulas (AVFs) with enlarged liver vessels. Evaluation of the retina vessels at P5 from Nrp1 SM22KO mice demonstrated dilated capillaries with a reduction of pericytes. In inflow artery of surgical AVFs from the Nrp1 SM22KO versus WT mice , there was a significant decrease in Tgfb1 , Eng , and Alk1 expression and phosphorylated SMAD1/5/8 (pSMAD1/5/8), with an increase in apoptosis. TGF-β1–stimulated aortic SMCs from Nrp1 SM22KO versus WT mice have decreased pSMAD1/5/8 and increased apoptosis. Coimmunoprecipitation experiments revealed that NRP-1 interacts with ALK1 and ENG in SMCs. In summary, NRP-1 deletion in SMCs leads to reduced ALK1, ENG, and pSMAD1/5/8 signaling and reduced cell death associated with AVM formation.

Abstract Introduction: Blastomycosis is an uncommon; potentially life threatening granulomatous fungal infection. The aim of this study is to report hospital and intensive care unit (ICU) outcomes of patients admitted with blastomycosis. Methods: All patients admitted for treatment of blastomycosis at the Mayo Clinic-Rochester, Minnesota between 01/01/2006 and 09/30/2019 were included. Demographics, comorbidities, clinical presentation, ICU admission, and outcomes were reviewed.Results: A total of 84 Patients were identified with 93 unique hospitalizations primarily for blastomycosis. The median age at diagnosis was 49 (IQR 28.1-65, range: 6-85) years and 56 (66.7%) were male. The most frequent comorbidities incl­uded hypertension (n=28, 33.3%); immunosuppressed state (n=25, 29.8%) and diabetes mellitus (n=21, 25%). The lungs were the only organ involved in 56 (66.7%) cases and the infection was disseminated in 19 (22.6%) cases. A total of 29 patients (34.5%) underwent ICU admission due to complications of blastomycosis. ICU related events included mechanical ventilation (n=21, 25%), acute respiratory distress syndrome (ARDS) (n=13, 15.5%), tracheostomy (n=9, 10.7%), renal replacement therapy (n=8, 9.5%), and extracorporeal membrane oxygenation (ECMO) (n=4, 4.8%). A total of 12 patients (14.3%) died in the hospital; all of whom had undergone ICU admission. In-hospital mortality was associated with renal replacement therapy (RRT) (P=0.0255).Conclusions: Blastomycosis is a serious, potentially life-threatening infection that results in significant morbidity and mortality with a 34.5% ICU admission rate. Renal replacement therapy was associated with in-hospital mortality.

Background. There is little published literature regarding the impact of age on outcomes amongst hospitalized HHT (hereditary hemorrhagic telangiectasia) patients. Methods. The Nationwide Inpatient Sample (NIS) was used to obtain data on all hospital discharges occurring in HHT patients from 2000 to 2012. The association between admission age and HHT-related complications and outcomes were studied. Results. 10293 hospitalizations in HHT patients from 2000 to 2012 were included. Patients > 50 accounted for 77% of all admissions with 30% of admissions occurring in the 51–65 age group. Bleeding related complications were the most frequent (62.7%, n=6455 hospitalizations), followed by cardiovascular (41%, n=4216), neurological (12.4%, n=1276), and hepatobiliary (6.4%, n=660) complications. Patients older than 50 accounted for 83% of bleeding events, 90% of cardiovascular events, 58% of neurologic events, and 81% of hepatobiliary events. The vast majority (83%) of medical and surgical procedures were performed in those older than 50 years of age. Older patients also experienced higher rates of death. Conclusion. Aging has significant adverse impacts on rates of hospitalization, complications, and outcomes amongst HHT patients in the United States. Except for neurologic complications, the vast majority of this disease burden is borne by patients older than 50 years.