TBscreen: A passive cough classifier for tuberculosis screening with a controlled dataset.

Recent respiratory disease screening studies suggest promising performance of cough classifiers, but potential biases in model training and dataset quality preclude robust conclusions. To examine tuberculosis (TB) cough diagnostic features, we enrolled subjects with pulmonary TB (N = 149) and controls with other respiratory illnesses (N = 46) in Nairobi. We collected a dataset with 33,000 passive coughs and 1600 forced coughs in a controlled setting with similar demographics. We trained a ResNet18-based cough classifier using images of passive cough scalogram as input and obtained a fivefold cross-validation sensitivity of 0.70 (±0.11 SD). The smartphone-based model had better performance in subjects with higher bacterial load {receiver operating characteristic-area under the curve (ROC-AUC): 0.87 [95% confidence interval (CI): 0.87 to 0.88], P < 0.001} or lung cavities [ROC-AUC: 0.89 (95% CI: 0.88 to 0.89), P < 0.001]. Overall, our data suggest that passive cough features distinguish TB from non-TB subjects and are associated with bacterial burden and disease severity.

MMPD: Multi-Domain Mobile Video Physiology Dataset.

Remote photoplethysmography (rPPG) is an attractive method for noninvasive, convenient and concomitant measurement of physiological vital signals. Public benchmark datasets have served a valuable role in the development of this technology and improvements in accuracy over recent years. However, there remain gaps in the public datasets. First, despite the ubiquity of cameras on mobile devices, there are few datasets recorded specifically with mobile phone cameras. Second, most datasets are relatively small and therefore are limited in diversity, both in appearance (e.g., skin tone), behaviors (e.g., motion) and environment (e.g., lighting conditions). In an effort to help the field advance, we present the Multi-domain Mobile Video Physiology Dataset (MMPD), comprising 11 hours of recordings from mobile phones of 33 subjects. The dataset is designed to capture videos with greater representation across skin tone, body motion, and lighting conditions. MMPD is comprehensive with eight descriptive labels and can be used in conjunction with the rPPG-toolbox [1]. The reliability of the dataset is verified by mainstream unsupervised methods and neural methods. The GitHub repository of our dataset: https://github.com/THU-CS-PI/MMPD_rPPG_dataset.

Soli-enabled noncontact heart rate detection for sleep and meditation tracking.

Heart rate (HR) is a crucial physiological signal that can be used to monitor health and fitness. Traditional methods for measuring HR require wearable devices, which can be inconvenient or uncomfortable, especially during sleep and meditation. Noncontact HR detection methods employing microwave radar can be a promising alternative. However, the existing approaches in the literature usually use high-gain antennas and require the sensor to face the user's chest or back, making them difficult to integrate into a portable device and unsuitable for sleep and meditation tracking applications. This study presents a novel approach for noncontact HR detection using a miniaturized Soli radar chip embedded in a portable device (Google Nest Hub). The chip has a [Formula: see text] dimension and can be easily integrated into various devices. The proposed approach utilizes advanced signal processing and machine learning techniques to extract HRs from radar signals. The approach is validated on a sleep dataset (62 users, 498 h) and a meditation dataset (114 users, 1131 min). The approach achieves a mean absolute error (MAE) of 1.69 bpm and a mean absolute percentage error (MAPE) of [Formula: see text] on the sleep dataset. On the meditation dataset, the approach achieves an MAE of 1.05 bpm and a MAPE of [Formula: see text]. The recall rates for the two datasets are [Formula: see text] and [Formula: see text], respectively. This study represents the first application of the noncontact HR detection technology to sleep and meditation tracking, offering a promising alternative to wearable devices for HR monitoring during sleep and meditation.

Blood glucose variance measured by continuous glucose monitors across the menstrual cycle.

Past studies on how blood glucose levels vary across the menstrual cycle have largely shown inconsistent results based on limited blood draws. In this study, 49 individuals wore a Dexcom G6 continuous glucose monitor and a Fitbit Sense smartwatch while measuring their menstrual hormones and self-reporting characteristics of their menstrual cycles daily. The average duration of participation was 79.3 ± 21.2 days, leading to a total of 149 cycles and 554 phases in our dataset. We use periodic restricted cubic splines to evaluate the relationship between blood glucose and the menstrual cycle, after which we assess phase-based changes in daily median glucose level and associated physiological parameters using mixed-effects models. Results indicate that daily median glucose levels increase and decrease in a biphasic pattern, with maximum levels occurring during the luteal phase and minimum levels occurring during the late-follicular phase. These trends are robust to adjustments for participant characteristics (e.g., age, BMI, weight) and self-reported menstrual experiences (e.g., food cravings, bloating, fatigue). We identify negative associations between each of daily estrogen level, step count, and low degrees of fatigue with higher median glucose levels. Conversely, we find positive associations between higher food cravings and higher median glucose levels. This study suggests that blood glucose could be an important parameter for understanding menstrual health, prompting further investigation into how the menstrual cycle influences glucose fluctuation.

Identifying long-term effects of SARS-CoV-2 and their association with social determinants of health in a cohort of over one million COVID-19 survivors.

BACKGROUND: Despite an abundance of information on the risk factors of SARS-CoV-2, there have been few US-wide studies of long-term effects. In this paper we analyzed a large medical claims database of US based individuals to identify common long-term effects as well as their associations with various social and medical risk factors. METHODS: The medical claims database was obtained from a prominent US based claims data processing company, namely Change Healthcare. In addition to the claims data, the dataset also consisted of various social determinants of health such as race, income, education level and veteran status of the individuals. A self-controlled cohort design (SCCD) observational study was performed to identify ICD-10 codes whose proportion was significantly increased in the outcome period compared to the control period to identify significant long-term effects. A logistic regression-based association analysis was then performed between identified long-term effects and social determinants of health. RESULTS: Among the over 1.37 million COVID patients in our datasets we found 36 out of 1724 3-digit ICD-10 codes to be statistically significantly increased in the post-COVID period (p-value < 0.05). We also found one combination of ICD-10 codes, corresponding to 'other anemias' and 'hypertension', that was statistically significantly increased in the post-COVID period (p-value < 0.05). Our logistic regression-based association analysis with social determinants of health variables, after adjusting for comorbidities and prior conditions, showed that age and gender were significantly associated with the multiple long-term effects. Race was only associated with 'other sepsis', income was only associated with 'Alopecia areata' (autoimmune disease causing hair loss), while education level was only associated with 'Maternal infectious and parasitic diseases' (p-value < 0.05). CONCLUSION: We identified several long-term effects of SARS-CoV-2 through a self-controlled study on a cohort of over one million patients. Furthermore, we found that while age and gender are commonly associated with the long-term effects, other social determinants of health such as race, income and education levels have rare or no significant associations.

Automatic Classification of Audio Uroflowmetry with a Smartwatch.

Prior work has shown the classification of voiding dysfunctions from uroflowmeter data using machine learning. We present the use of smartwatch audio, collected through the UroSound platform, in order to automatically classify voiding signals as normal or abnormal, using classical machine learning techniques. We train several classification models using classical machine learning and report a maximal test accuracy of 86.16% using an ensemble method classifier. Clinical relevance- This classification task has the potential to be part of an essential toolkit for urology telemedicine. It is especially useful in areas that lack proper medical infrastructure but still host ubiquitous audio capture devices such as smartphones and smartwatches.

Smartphone camera oximetry in an induced hypoxemia study.

Hypoxemia, a medical condition that occurs when the blood is not carrying enough oxygen to adequately supply the tissues, is a leading indicator for dangerous complications of respiratory diseases like asthma, COPD, and COVID-19. While purpose-built pulse oximeters can provide accurate blood-oxygen saturation (SpO2) readings that allow for diagnosis of hypoxemia, enabling this capability in unmodified smartphone cameras via a software update could give more people access to important information about their health. Towards this goal, we performed the first clinical development validation on a smartphone camera-based SpO2 sensing system using a varied fraction of inspired oxygen (FiO2) protocol, creating a clinically relevant validation dataset for solely smartphone-based contact PPG methods on a wider range of SpO2 values (70-100%) than prior studies (85-100%). We built a deep learning model using this data to demonstrate an overall MAE = 5.00% SpO2 while identifying positive cases of low SpO2 < 90% with 81% sensitivity and 79% specificity. We also provide the data in open-source format, so that others may build on this work.

Prospective validation of smartphone-based heart rate and respiratory rate measurement algorithms.

Background: Measuring vital signs plays a key role in both patient care and wellness, but can be challenging outside of medical settings due to the lack of specialized equipment. Methods: In this study, we prospectively evaluated smartphone camera-based techniques for measuring heart rate (HR) and respiratory rate (RR) for consumer wellness use. HR was measured by placing the finger over the rear-facing camera, while RR was measured via a video of the participants sitting still in front of the front-facing camera. Results: In the HR study of 95 participants (with a protocol that included both measurements at rest and post exercise), the mean absolute percent error (MAPE) ± standard deviation of the measurement was 1.6% ± 4.3%, which was significantly lower than the pre-specified goal of 5%. No significant differences in the MAPE were present across colorimeter-measured skin-tone subgroups: 1.8% ± 4.5% for very light to intermediate, 1.3% ± 3.3% for tan and brown, and 1.8% ± 4.9% for dark. In the RR study of 50 participants, the mean absolute error (MAE) was 0.78 ± 0.61 breaths/min, which was significantly lower than the pre-specified goal of 3 breaths/min. The MAE was low in both healthy participants (0.70 ± 0.67 breaths/min), and participants with chronic respiratory conditions (0.80 ± 0.60 breaths/min). Conclusions: These results validate the accuracy of our smartphone camera-based techniques to measure HR and RR across a range of pre-defined subgroups.

HearCough: Enabling continuous cough event detection on edge computing hearables.

Cough event detection is the foundation of any measurement associated with cough, one of the primary symptoms of pulmonary illnesses. This paper proposes HearCough, which enables continuous cough event detection on edge computing hearables, by leveraging always-on active noise cancellation (ANC) microphones in commodity hearables. Specifically, we proposed a lightweight end-to-end neural network model - Tiny-COUNET and its transfer learning based traning method. When evaluated on our acted cough event dataset, Tiny-COUNET achieved equivalent detection performance but required significantly less computational resources and storage space than cutting-edge cough event detection methods. Then we implemented HearCough by quantifying and deploying the pre-trained Tiny-COUNET to a popular micro-controller in consumer hearables. Lastly, we evaluated that HearCough is effective and reliable for continuous cough event detection through a field study with 8 patients. HearCough achieved 2 Hz cough event detection with an accuracy of 90.0% and an F1-score of 89.5% by consuming an additional 5.2 mW power. We envision HearCough as a low-cost add-on for future hearables to enable continuous cough detection and pulmonary health monitoring.

O-pH: Optical pH Monitor to Measure Dental Biofilm Acidity and Assist in Enamel Health Monitoring.

OBJECTIVE: Bacteria in the dental biofilm produceacid after consumption of carbohydrates which if left unmonitored leads to caries formation. We present O-pH, a device that can measure dental biofilm acidity and provide quantitative feedback to assist in oral health monitoring. METHOD: O-pH utilizes a ratiometric pH sensing method by capturing fluorescence of Sodium Fluorescein, an FDA approved chemical dye. The device was calibrated to a lab pH meter using buffered fluorescein solution with a correlation coefficient of 0.97. The calibration was further verified in vitro on additional buffered solution, artificial, and extracted teeth. An in vivo study on 30 pediatric subjects was performed to measure pH before (rest pH) and after (drop pH) a sugar rinse, and the resultant difference in pH (diff pH) was calculated. The study enrolled subjects with low (Post-Cleaning) and heavy (Pre-Cleaning) biofilm load, having both unhealthy/healthy surfaces. Further, we modified point-based O-pH to an image-based device using a multimode-scanning fiber endoscope (mm-SFE) and tested in vivo on one subject. RESULTS AND CONCLUSION: We found significant difference between Post-Cleaning and Pre-Cleaning group using drop pH and diff pH. Additionally, in Pre-Cleaning group, the rest and drop pH is lower at the caries surfaces compared to healthy surfaces. Similar trend was not noticed in the Post-Cleaning group. mm-SFE pH scope recorded image-based pH heatmap of a subject with an average diff pH of 1.5. SIGNIFICANCE: This work builds an optical pH prototype and presents a pioneering study for non-invasively measuring pH of dental biofilm clinically.

Passively sensing SARS-CoV-2 RNA in public transit buses.

Affordably tracking the transmission of respiratory infectious diseases in urban transport infrastructures can inform individuals about potential exposure to diseases and guide public policymakers to prepare timely responses based on geographical transmission in different areas in the city. Towards that end, we designed and tested a method to detect SARS-CoV-2 RNA in the air filters of public buses, revealing that air filters could be used as passive fabric sensors for the detection of viral presence. We placed and retrieved filters in the existing HVAC systems of public buses to test for the presence of trapped SARS-CoV-2 RNA using phenol-chloroform extraction and RT-qPCR. SARS-CoV-2 RNA was detected in 14% (5/37) of public bus filters tested in Seattle, Washington, from August 2020 to March 2021. These results indicate that this sensing system is feasible and that, if scaled, this method could provide a unique lens into the geographically relevant transmission of SARS-CoV-2 through public transit rider vectors, pooling samples of riders over time in a passive manner without installing any additional systems on transit vehicles.

Using Health Concept Surveying to Elicit Usable Evidence: Case Studies of a Novel Evaluation Methodology.

BACKGROUND: Developers, designers, and researchers use rapid prototyping methods to project the adoption and acceptability of their health intervention technology (HIT) before the technology becomes mature enough to be deployed. Although these methods are useful for gathering feedback that advances the development of HITs, they rarely provide usable evidence that can contribute to our broader understanding of HITs. OBJECTIVE: In this research, we aim to develop and demonstrate a variation of vignette testing that supports developers and designers in evaluating early-stage HIT designs while generating usable evidence for the broader research community. METHODS: We proposed a method called health concept surveying for untangling the causal relationships that people develop around conceptual HITs. In health concept surveying, investigators gather reactions to design concepts through a scenario-based survey instrument. As the investigator manipulates characteristics related to their HIT, the survey instrument also measures proximal cognitive factors according to a health behavior change model to project how HIT design decisions may affect the adoption and acceptability of an HIT. Responses to the survey instrument were analyzed using path analysis to untangle the causal effects of these factors on the outcome variables. RESULTS: We demonstrated health concept surveying in 3 case studies of sensor-based health-screening apps. Our first study (N=54) showed that a wait time incentive could influence more people to go see a dermatologist after a positive test for skin cancer. Our second study (N=54), evaluating a similar application design, showed that although visual explanations of algorithmic decisions could increase participant trust in negative test results, the trust would not have been enough to affect people's decision-making. Our third study (N=263) showed that people might prioritize test specificity or sensitivity depending on the nature of the medical condition. CONCLUSIONS: Beyond the findings from our 3 case studies, our research uses the framing of the Health Belief Model to elicit and understand the intrinsic and extrinsic factors that may affect the adoption and acceptability of an HIT without having to build a working prototype. We have made our survey instrument publicly available so that others can leverage it for their own investigations.

Enabling Real-Time On-Chip Audio Super Resolution for Bone-Conduction Microphones.

Voice communication using an air-conduction microphone in noisy environments suffers from the degradation of speech audibility. Bone-conduction microphones (BCM) are robust against ambient noises but suffer from limited effective bandwidth due to their sensing mechanism. Although existing audio super-resolution algorithms can recover the high-frequency loss to achieve high-fidelity audio, they require considerably more computational resources than is available in low-power hearable devices. This paper proposes the first-ever real-time on-chip speech audio super-resolution system for BCM. To accomplish this, we built and compared a series of lightweight audio super-resolution deep-learning models. Among all these models, ATS-UNet was the most cost-efficient because the proposed novel Audio Temporal Shift Module (ATSM) reduces the network's dimensionality while maintaining sufficient temporal features from speech audio. Then, we quantized and deployed the ATS-UNet to low-end ARM micro-controller units for a real-time embedded prototype. The evaluation results show that our system achieved real-time inference speed on Cortex-M7 and higher quality compared with the baseline audio super-resolution method. Finally, we conducted a user study with ten experts and ten amateur listeners to evaluate our method's effectiveness to human ears. Both groups perceived a significantly higher speech quality with our method when compared to the solutions with the original BCM or air-conduction microphone with cutting-edge noise-reduction algorithms.

Optical pH measurement system using a single fluorescent dye for assessing susceptibility to dental caries (Erratum).

The erratum corrects a grant number listed in Acknowledgments section of the original article.

Multi-Channel Facial Photoplethysmography Sensing.

Motivated by the need for continuous cardiovascular monitoring, we present a system for performing photoplethysmography sensing at multiple facial locations. As a proof-of-concept, our system incorporates an optical sensor array into a wearable face mask form factor for application in a surgical hemodynamic monitoring use case. Here we demonstrate that our design can accurately detect pulse timing by validating estimated heart rate against ground truth electrocardiogram recordings. In an experiment across 10 experimental subjects, our system achieves an error standard deviation of 2.84 beats per minute. This system shows promise for performing non-invasive, continuous pulse waveform recording from multiple locations on the face.

Diagnostic accuracy of an app-guided, self-administered test for influenza among individuals presenting to general practice with influenza-like illness: study protocol.

INTRODUCTION: Diagnostic tests for influenza in Australia are currently only authorised for use in clinical settings. At-home diagnostic testing for influenza could reduce the need for patient contact with healthcare services, which potentially could contribute to symptomatic improvement and reduced spread of influenza. We aim to determine the accuracy of an app-guided nasal self-swab combined with a lateral flow immunoassay for influenza conducted by individuals with influenza-like illness (ILI). METHODS AND ANALYSIS: Adults (≥18 years) presenting with ILI will be recruited by general practitioners (GP) participating in Australian Sentinel Practices Research Network. Eligible participants will have a nasal swab obtained by their GP for verification of influenza A/B status using reverse transcription polymerase chain reaction (RT-PCR) test at an accredited laboratory. Participants will receive an influenza test kit and will download an app that collects self-reported symptoms and influenza risk factors, then instructs them in obtaining a low-nasal self-swab, running a QuickVue influenza A+B lateral flow immunoassay (Quidel Corporation) and interpreting the results. Participants will also interpret an enhanced image of the test strip in the app. The primary outcome will be the accuracy of participants' test interpretation compared with the laboratory RT-PCR reference standard. Secondary analyses will include accuracy of the enhanced test strip image, accuracy of an automatic test strip reader algorithm and validation of prediction rules for influenza based on self-reported symptoms. A post-test survey will be used to obtain participant feedback on self-test procedures. ETHICS AND DISSEMINATION: The study was approved by the Human Research and Ethic Committee (HREC) at the University of Adelaide (H-2019-116). Protocol details and any amendments will be reported to https://www.tga.gov.au/. Results will be published in the peer-reviewed literature, and shared with stakeholders in the primary care and diagnostics communities. TRIAL REGISTRATION NUMBER: Australia New Zealand Clinical Trial Registry (U1111-1237-0688).

Optical pH measurement system using a single fluorescent dye for assessing susceptibility to dental caries.

Sugar-rich diets and poor dental hygiene promote the formation of a biofilm (plaque) that strongly adheres to the dental enamel surface and fosters the evolution of aciduric bacteria. The acid contributes to demineralization of the exterior tooth enamel, which accelerates after the pH drops below a critical value (∼5.5) for extended time periods resulting in the need for restorative procedures. Preventative techniques to alert the dentist and caries-susceptible patients regarding vulnerability to dental decay require a clinical measure of plaque activity. Therefore, there is a need to evaluate the acid production capability of plaque deposits in the pits and fissures of occlusal and interproximal regions. A ratiometric fluorescence pH-sensing device has been developed using an FDA-approved dye and LED excitation. Fluorescein spectral profiles were collected using a spectrometer and analyzed with a spectral unmixing algorithm for calibration over the pH range of 4.5 to 7. An in vivo pilot study on human subjects was performed using a sucrose rinse to accelerate bacterial metabolism and to measure the time-dependent drop in pH. The optical system is relatively immune to confounding factors such as photobleaching, dye concentration, and variation in excitation intensity associated with earlier dye-based pH measurement techniques.

Dental pH Opti-Wand (DpOW): measuring oral acidity to guide enamel preservation.

Undetected caries can lead to painful cavities and surgical restorations. Lack of proper detection tools makes caries prevention dependent on dentist's expertise and presents obstacles in oral health monitoring. To overcome this problem, we have developed a new approach to predict early stages of enamel demineralization caused by oral bacteria. These bacteria metabolize sugars in our food and produce organic acids that lead to cavities. Measuring the acidity level can help predict early stages of tooth decay. pH paper or pH electrodes can be used to monitor acidity, but neither are able to track pH levels in all dental locations. Our device, DpOW, is a noncontact optics-based pH device that uses changes in the spectral fluorescence of FDA allowed fluorescein dye to measure acidity levels in difficult to access dental locations such as occlusal fissures. A prototype has been tested over a wide pH range (7.12 to 3.89) and shown to track the change in pH with 0.94 correlation coefficient.

SpiroConfidence: Determining the Validity of Smartphone Based Spirometry Using Machine Learning.

Prior work has shown that smartphone spirometry can effectively measure lung function using the phone's built-in microphone and could one day play a critical role in making spirometry more usable, accessible, and cost-effective. Although traditional spirometry is performed with the guidance of a medical expert, smartphone spirometry lacks the ability to provide the patient feedback or guarantee the quality of a patient's spirometry efforts. Smartphone spirometry is particularly susceptible to poorly performed efforts because any sounds in the environment (e.g., a person's voice) or mistakes in the effort (e.g., coughs or short breaths) can invalidate the results. We introduce two approaches to analyze and estimate the quality of smartphone spirometry efforts. A gradient boosting model achieves 98.2% precision and 86.6% recall identifying invalid efforts when given expert tuned audio features, while a Gated-Convolutional Recurrent Neural Network achieves 98.3% precision and 88.0% recall and automatically develops patterns from a Mel-spectrogram, a more general audio feature.

Noninvasive hemoglobin measurement using unmodified smartphone camera and white flash.

We show that a mobile phone can measure hemoglobin levels using the built-in RGB camera and white LED without modification. Prior work has demonstrated that a smartphone using the built-in RGB camera with the aid of visible and IR lights can achieve a Pearson correlation results between 0.69-0.82 and an RMSE value between 1.26-1.56 g/dL. Our system builds upon the prior work and demonstrates that with only the built-in white LED, the estimation of hemoglobin level has a Pearson correlation of 0.62 with an RMSE of 1.27 g/dL. This extension work demonstrates that it is feasible to measure hemoglobin without using an IR source.