Wheezing is a critical indicator of various respiratory conditions, including asthma and chronic obstructive pulmonary disease (COPD). Current diagnosis relies on subjective lung auscultation by physicians. Enabling this capability via a low-profile, objective wearable device for remote patient monitoring (RPM) could offer pre-emptive, accurate respiratory data to patients. With this goal as our aim, we used a low-profile accelerometer-based wearable system that utilizes deep learning to objectively detect wheezing along with respiration rate using a single sensor. The miniature patch consists of a sensitive wideband MEMS accelerometer and low-noise CMOS interface electronics on a small board, which was then placed on nine conventional lung auscultation sites on the patient’s chest walls to capture the pulmonary-induced vibrations (PIVs). A deep learning model was developed and compared with a deterministic time–frequency method to objectively detect wheezing in the PIV signals using data captured from 52 diverse patients with respiratory diseases. The wearable accelerometer patch, paired with the deep learning model, demonstrated high fidelity in capturing and detecting respiratory wheezes and patterns across diverse and pertinent settings. It achieved accuracy, sensitivity, and specificity of 95%, 96%, and 93%, respectively, with an AUC of 0.99 on the test set—outperforming the deterministic time–frequency approach. Furthermore, the accelerometer patch outperforms the digital stethoscopes in sound analysis while offering immunity to ambient sounds, which not only enhances data quality and performance for computational wheeze detection by a significant margin but also provides a robust sensor solution that can quantify respiration patterns simultaneously.

Second heart sound (S2) splitting can be used as an indicator for diagnosis of cardiovascular diseases; specifically, paradoxical S2 splitting is an indicator of aortic stenosis. We present that S2 acoustic signatures can be captured accurately from the seismocardiogram (SCG) signals of a sensitive wearable accelerometer contact microphone (ACM) and validated by comparing with digital stethoscope phonocardiogram (PCG) signals. The ACM was placed on the pulmonic region of 18 subjects, 10 with no known heart disease and 8 with known heart disease, for 60 seconds of SCG data collection. Smoothed Pseudo Wigner-Ville distribution is used to extract S2 time split and to identify S2 paradoxical splitting. Healthy subjects had SCG S2 time splits range agreeing with S2 time splits from past literature from PCG signals. The ACM SCG signal was al-so used to identify and capture paradoxical splitting from subjects with known valvular heart diseases such as aortic stenosis, from subjects with mild to severe diagnosis. In conclusion, a wearable ACM can be used to detect paradoxical splitting in subjects suspected with aortic valvular heart disease and shows high fidelity of capturing S2 time split through SCG signals.

Physicians evaluate a patient’s respiratory health during a physical examination by visual assessment of the work of breathing (WoB) to determine respiratory stability, and by detecting abnormal lung sounds via lung auscultation using a stethoscope to identify common pathological lung diseases, such as chronic obstructive pulmonary disease (COPD) and pneumonia. Since these assessment methods are subjective, a low-profile device used for an accurate and quantitative monitoring approach could provide valuable preemptive insights into respiratory health, proving to be clinically beneficial. To achieve this goal, we have developed a miniature patch consisting of a sensitive wideband multi-axis seismometer that can be placed on the anatomical areas of a patient’s lungs to enable an effective quantification of a patient’s WoB and lung sounds. When used on a patch, the seismometer captures chest wall vibrations due to respiratory muscle effort, known as high-frequency mechanomyogram (MMG), during tidal breathing as well as seismic pulmonary-induced vibrations (PIVs) during deep breathing due to normal and/or adventitious lung sounds like crackles, while simultaneously recording respiration rate and phase. A system comprised of multiple patches was evaluated on 124 patients in the hospital setting and shown to accurately assess and quantify a patent’s physical signs of WoB by measuring the average respiratory effort extracted from high-frequency MMG signals, demonstrating statistical significance of this method in comparison to clinical bedside observation of WoB and respiration rate. A data fusion deep learning model was developed which combined the inputs of PIVs lung sounds and the corresponding respiration phase to detect crackle, wheeze and normal breath sound features. The model exhibited high accuracy, sensitivity, specificity, precision and F1 score of 93%, 93%, 97%, 93% and 93% respectively, with area under the curve (AUC) of precision recall (PR) of 0.97 on the test set. Additionally, the PIVs with corresponding respiration phase captured from each auscultation point generated an acoustic map of the patient’s lung, which correlated with traditional lung radiographic findings.

Carotid artery disease, including atherosclerotic stenosis and non-atherosclerotic abnormalities, substantially increases ischemic stroke risk and motivates accessible tools for early screening. Current diagnostic pathways rely on clinic-based imaging and skilled operators, creating barriers to frequent monitoring and scalable deployment. We present a non-invasive diagnostic approach using a wearable MEMS accelerometer patch to capture mechano-acoustic vibrations generated by carotid blood flow at the neck. The miniature device integrates a hermetically sealed wideband accelerometer with out-of-plane sensitivity and micro-g resolution to detect subtle flow-induced vibrations. We validated the approach in a carotid flow phantom and a clinical study of 74 patients. Time–frequency representations were computed using the continuous wavelet transform (CWT), from which interpretable spectral and scalogram-derived candidate biomarkers were extracted. Six non-redundant features were then selected for multivariate classification, distinguishing pathology, defined as 50% or greater stenosis or a non-atherosclerotic abnormality, from non-pathology, defined as less than 50% stenosis. Finally, model interpretability was assessed using SHapley Additive exPlanations (SHAP) to quantify the contribution of each biomarker to predicted disease probability. These findings resulted in an AUROC of 0.97 and AUPR of 0.947, with 81.7% sensitivity and 93.6% specificity at the prespecified threshold (precision 85.4%, F1 83.5%, accuracy 89.8%), highlighting the potential of wearable seismic sensing combined with interpretable machine learning for fast screening and longitudinal monitoring of the right and left carotid arteries.

We present a hermetically sealed capacitive microelectromechanical system (MEMS) strain sensor designed for arterial pulse waveform extraction using the strain plethysmography (SPG) modality. The MEMS strain sensor features a small form factor of 3.3 mm × 3.3 mm × 1 mm, leverages a nano-gap fabrication process to improve the sensitivity, and uses a differential sensing mechanism to improve the linearity and remove the common mode drift. The MEMS strain sensor is interfaced with an application-specific integrated circuit (ASIC) to form a compact strain sensing system. This system exhibits a high strain sensitivity of 316 aF/µε, a gauge factor (GF) of 35, and a strain sensing resolution of 1.26 µε, while maintaining a linear range exceeding 700 µε. SPG signals have been reliably captured at both the fingertip and wrist using the MEMS strain sensor with high signal quality, preserving various photoplethysmography (PPG) features. Experimental results demonstrate that heart rate (HR) and heart rate variability (HRV) can be estimated from the SPG signal collected at the fingertip and wrist using the sensor with an accuracy of over 99%. Pulse arrival time (PAT) and pulse transit time (PTT) have been successfully extracted using the sensor together with a MEMS seismometer, showcasing its potential for ambulatory BP monitoring (ABPM) application.