Arunachalam, Shivaram P.

Introduction: Heart failure with preserved ejection fraction (HFpEF) is an increasingly common clinical syndrome with diagnostic challenges and no effective treatment. The high heterogeneity of HFpEF clinical syndrome demands novel technologies to distinguish from heart failure with reduced ejection Fraction (HFrEF). Currently, invasive hemodynamic exercise testing is performed to evaluate for HFpEF with right heart catheterization. Hypothesis: We hypothesize that a deep learning model can noninvasively detect patients with HFpEF using phonocardiogram (PCG). Methods: Eligible patients undergoing right heart catheterization were recruited after IRB approval. Eko duo stethoscope was used to record simultaneous ECG & PCG at the mitral area on the patients prior to right heart catheterization at baseline. Each recording was 30 seconds in length with a frequency range between 250 - 5000 Hz. R-wave peak detection was performed & beat to beat PCG annotations were performed. The annotated PCG signals were converted into Mel-frequency cepstral coefficients (MFCC) and padded to account for the difference in lengths. Deep Learning model was developed using a Sequential Neural Network with 80% data to train and validate the model and 20% hold out data was used for testing accuracy of the model. Receiver operating curve (ROC) was obtained to estimate area under the curve (AUC) for performance analysis. Results: 42 patients were enrolled with 25 patients diagnosed as HFpEF by right heart catheterization and 17 were reported as controls. 2544 & 1771 individual PCG annotations for HFpEF and controls were used for model training/validation and testing. The model performed reasonably well with accuracy of 0.89, F1 score of 0.88, precision of 0.80 and recall of 0.97 on the test data. ROC was obtained with AUC of 0.94. Conclusions: The results demonstrate the ability of the deep learning model to noninvasively detect HFpEF using PCG. Larger study is needed to validate these findings.

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.

Abstract Bowel sounds have been previously used to study intestinal motility and overall digestive health in various clinical settings. However, the blurred definition of bowel sounds and their subtypes, limited resources for interpretation, poor sensitivity, and low positive predictive value led to their restricted utility. Recent advances in artificial intelligence and machine learning have steered interest in developing unique tools using the phonoenterogram to analyze diverse bowel sounds. In our study, bowel sounds were recorded from eight healthy volunteers using the Eko Duo stethoscope. A novel deep-learning algorithm was designed to classify the recordings into baseline or prominent bowel sounds. A total of 11,210 data points (5,605 balanced sounds) were used to train and test the model to yield an accuracy of 0.895, a precision of 0.890, and a recall of 0.854 reflecting successful segregation of these sounds into respective groups. More extensive studies enrolling healthy and diseased subjects with a device specifically tailored to record bowel sounds are needed to generalize these results and determine their application in the patient population.

Abstract Blood pressure measurement in current medical practice relies on manual methods with the most widely used modality being sphygmomanometers. Utilizing the principle of Photoplethysmography, it is possible to provide an accurate reading of one’s blood pressure through light signals and photodetector devices. This research paper introduces a new Artificial Intelligence driven approach to predict Blood pressure levels and classify them according to the updated ACC (American College of Cardiology) criteria as Normal, Elevated, Stage I, and II Hypertension from the given PPG signal values using Machine Learning Models. This research paper aims to accurately read the Systolic and Diastolic Blood Pressure using Artificial Intelligence, place them into the correct value bins and further prove that the blood pressure values differ based on different skin tones in different light wavelengths such as red, infrared, and green. Machine Learning models such as the Support Vector Machine have shown an accuracy of 70.58% for Systolic Blood Pressure and Decision Tree with an accuracy of 74.4% for Diastolic Blood Pressure classification. The models used in this research are Support Vector Machine, Decision Tree and K-Nearest Neighbor. This research study has future applications and extensions to predict blood pressure levels for patients with different skin tones under different light radiations and PPG signal readings. Neural Network models will be developed to compare the blood predictions from this work.

Abstract Majority of hospitals still utilize manual methods for patient scheduling and predicting future appointments, resulting in longer wait times, hospital burnout and inadequate use of resources. A variety of avenues have been explored, including priority patient routing, tele-health, neural networks for improving ER efficiency, predicting no-shows, consultation duration variations, and optimizing operating room utilization. Addressing this issue, a study was conducted using 700 pre-visit notes of pancreatic patients to determine the requirement of endoscopic or biliary procedure. Through natural language processing and traditional or transfer learning algorithms, data could directly be sent to EPIC for nurses to assess in further decision making. Performance of the models was above average with the transfer learning method outperforming the traditional method. Although limited by less dataset and fewer circumstances to test the models on, the results exposed potential for future development with the possibility of patients reporting their chief concerns, in turn analyzed by algorithms, ultimately creating a smooth and effective patient itinerary.

Abstract Designing an effective antenna is very important to utilize microwave imaging. A high gain antipodal antenna designed with ultra-wideband frequency range is presented here. The simulated results are validated with measured data. The antenna can operate within the Ultra band frequency range of 3 to 8 GHz. The maximum gain of 2.96 dBi is obtained at 4 GHz. An experiment with biological tissues is also done to show the effectiveness of the antenna using as a resonator.

Abstract Chronic cough is not only one of the leading causes of seeking healthcare all over the world but also a huge emotional drain on the affected patient population. In this study, we used 24-hour cough recordings to analyze the intervening conversations for sentiment analyses to better diagnose, guide, and manage treatment in such patients. We surveyed a cough clinic and selected four subjects with active cough complaints using relevant ICD-10 codes. Subjects were given and instructed to wear a device to record cough for 24 hours and the recordings were collected at weeks 0, 4, 8, and 12 of the treatment. The collected data was preprocessed to eliminate sections with no data (sleep, silence) and the number of coughs was counted. Google search API calls were used to transcribe the audio files and NLTK’s VADER analyzer was used to classify sentiments on a scale of 0 to 1. Finally, average scores were calculated and plotted over a graph to interpret any trends. 12 weeks of cough treatment had varied results on the four subjects. We categorized the exhibited sentiments into negative, neutral, positive, and compound and noted that they also showed no general trends. Among these, the compound sentiment displayed the most erratic patterns, and the obtained results could not generate a steady trend. Further studies are required with a large cohort to collect data over a longer duration to accurately analyze the sentiments associated with chronic cough.

Abstract Optical coherence tomography (OCT) is an advanced imaging modality to detect Barrett’s esophagus (BE) dysplasia, providing widefield, cross-sectional imaging and microscopic resolution. BE dysplasia is characterized under OCT by the presence and number of glandular structures with atypical morphology. Accurate detection and interpretation of BE glands under OCT is essential to detect dysplastic lesions. Object Detection using deep learning has the potential to identify glands from OCT images. We developed a YOLO model to identify the presence of glands in BE tissue. The YOLOv4 object detector was trained on a custom BE dataset of 30 patients with confirmed BE who underwent OCT imaging, of which 222 OCT images included at least one gland. Our model identified glands with a high average precision of 88.79% on the test dataset. We showed that the developed model is robust to rotation, brightness, and blur in images. We have implemented an object detection model to identify glands from OCT images with promising results accurately. This model has the potential to improve the diagnosis and surveillance of BE by eliminating human error and missed dysplastic lesions adaptable for capsule endoscopy applications.