Negative Screening AI in Ankle Stress Radiography to Reduce Workload.

RATIONALE AND OBJECTIVES: Interpreting ankle stress radiographs is subjective and time-consuming. We aimed to train an AI model that efficiently screens negative cases, assess the agreement with expert with and without AI-assistance, and compare the workload reduction. MATERIAL AND METHODS: We collected anterior draw test (ADT) and talar tilt test (TTT) ankle stress radiographs from Seoul St. Mary's Hospital and St. Vincent's Hospital. Patients with prior surgery, severe joint fusion, or incomplete images were excluded. Expert measurements of tibio-talar distance (TTD) and tibio-talar angle (TTA) served as reference, defining positive labels as TTD ≥ 8.3 mm or TTA ≥ 6.2°. We trained a VGG16 model on data from hospital A and tested it on three separate test sets (testset1, 2 from St. Mary's Hospital, and testset3 from St. Vincent's Hospital). Three readers (expert, reader2, and the collective reading reports) evaluated the test sets, with and without AI-assistance (focusing only on AI-predicted positive cases). We measured agreement with the expert using Cohen's weighted Kappa and assessed the hypothetical workload reduction. RESULTS: AI-assistance did not significantly affect agreement with the expert for any reader in all test sets. Reader2 showed moderate-substantial agreement for all test sets, while collective reports reached fair agreement. The AI alone demonstrated fair to moderate agreement with the expert. AI-assistance reduced the hypothetical workload by 68.8-89.2% for ADT and 58.3-70.4% for TTT. CONCLUSION: We successfully trained an AI model for ankle stress radiography, achieving an average of 70% workload reduction while maintaining agreement with expert radiologists.

A Novel Method for Tracking Neck Motions Using a Skin-Conformable Wireless Accelerometer: A Pilot Study.

Introduction: Cervical spine disease is a leading cause of pain and disability. Degenerative conditions of the spine can result in neurologic compression of the cervical spinal cord or nerve roots and may be surgically treated with an anterior cervical discectomy and fusion (ACDF) in up to 137,000 people per year in the United States. A common sequelae of ACDF is reduced cervical range of motion (CROM) with patient-based complaints of stiffness and neck pain. Currently, tools for assessment of CROM are manual, subjective, and only intermittently utilized during doctor or physical therapy visits. We propose a skin-mountable acousto-mechanic sensor (ADvanced Acousto-Mechanic sensor; ADAM) as a tool for continuous neck motion monitoring in postoperative ACDF patients. We have developed and validated a machine learning neck motion classification algorithm to differentiate between eight neck motions (right/left rotation, right/left lateral bending, flexion, extension, retraction, protraction) in healthy normal subjects and patients. Methods: Sensor data from 12 healthy normal subjects and 5 patients were used to develop and validate a Convolutional Neural Network (CNN). Results: An average algorithm accuracy of 80.0 ± 3.8% was obtained for healthy normal subjects (94% for right rotation, 98% for left rotation, 65% for right lateral bending, 87% for left lateral bending, 89% for flexion, 77% for extension, 50% for retraction, 84% for protraction). An average accuracy of 67.5 ± 5.8% was obtained for patients. Discussion: ADAM, with our algorithm, may serve as a rehabilitation tool for neck motion monitoring in postoperative ACDF patients. Sensor-captured vital signs and other events (extubation, vocalization, physical therapy, walking) are potential metrics to be incorporated into our algorithm to offer more holistic monitoring of patients after cervical spine surgery.

A battery-less wireless implant for the continuous monitoring of vascular pressure, flow rate and temperature.

Devices for monitoring blood haemodynamics can guide the perioperative management of patients with cardiovascular disease. Current technologies for this purpose are constrained by wired connections to external electronics, and wireless alternatives are restricted to monitoring of either blood pressure or blood flow. Here we report the design aspects and performance parameters of an integrated wireless sensor capable of implantation in the heart or in a blood vessel for simultaneous measurements of pressure, flow rate and temperature in real time. The sensor is controlled via long-range communication through a subcutaneously implanted and wirelessly powered Bluetooth Low Energy system-on-a-chip. The device can be delivered via a minimally invasive transcatheter procedure or it can be mounted on a passive medical device such as a stent, as we show for the case of the pulmonary artery in a pig model and the aorta and left ventricle in a sheep model, where the device performs comparably to clinical tools for monitoring of blood flow and pressure. Battery-less and wireless devices such as these that integrate capabilities for flow, pressure and temperature sensing offer the potential for continuous monitoring of blood haemodynamics in patients.

Utilizing Deep Learning on Limited Mobile Speech Recordings for Detection of Obstructive Pulmonary Disease.

Passive assessment of obstructive pulmonary disease has gained substantial interest over the past few years in the mobile and wearable computing communities. One of the promising approaches is speech-based pulmonary assessment wherein spontaneous or scripted speech is used to evaluate an individual's pulmonary condition. Recent approaches in this regard heavily rely on accurate speech activity segmentation and specific, hand-crafted features. In this paper, we present an end-to-end deep learning approach for detecting obstructive pulmonary disease. We leveraged transfer learning using a network pre-trained for a different audio-based task, and employed our own additional shallow network on top as a binary classifier to indicate if a given speech recording belongs to an asthma or COPD patient. The additional network was a fully connected neural net with 2 hidden layers, and this was evaluated on two real-world datasets. We demonstrated that the system can identify subjects with obtructive pulmonary disease using their speech with 88.3 % precision, 88.8 % recall and 88.3% F-1 score using 10-fold cross-validation. The system showed improved performance in identifying the most severely affected subgroup of patients in the dataset, with an average 93.6 % accuracy.

Use of technology for the objective evaluation of scratching behavior: A systematic review.

INTRODUCTION: Pruritus is a common symptom across various dermatologic conditions, with a negative impact on quality of life. Devices to quantify itch objectively primarily use scratch as a proxy. This review compares and evaluates the performance of technologies aimed at objectively measuring scratch behavior. METHODS: Articles identified from literature searches performed in October 2020 were reviewed and those that did not report a primary statistical performance measure (eg, sensitivity, specificity) were excluded. The articles were independently reviewed by 2 authors. RESULTS: The literature search resulted in 6231 articles, of which 24 met eligibility criteria. Studies were categorized by technology, with actigraphy being the most studied (n = 21). Wrist actigraphy's performance is poorer in pruritic patients and inherently limited in finger-dominant scratch detection. It has moderate correlations with objective measures (Eczema and Area Severity Index/Investigator's Global Assessment: rs(ρ) = 0.70-0.76), but correlations with subjective measures are poor (r2 = 0.06, rs(ρ) = 0.18-0.40 for itch measured using a visual analog scale). This may be due to varied subjective perception of itch or actigraphy's underestimation of scratch. CONCLUSION: Actigraphy's large variability in performance and limited understanding of its specificity for scratch merits larger studies looking at validation of data analysis algorithms and device performance, particularly within target patient populations.

Differential cardiopulmonary monitoring system for artifact-canceled physiological tracking of athletes, workers, and COVID-19 patients.

Soft, skin-integrated electronic sensors can provide continuous measurements of diverse physiological parameters, with broad relevance to the future of human health care. Motion artifacts can, however, corrupt the recorded signals, particularly those associated with mechanical signatures of cardiopulmonary processes. Design strategies introduced here address this limitation through differential operation of a matched, time-synchronized pair of high-bandwidth accelerometers located on parts of the anatomy that exhibit strong spatial gradients in motion characteristics. When mounted at a location that spans the suprasternal notch and the sternal manubrium, these dual-sensing devices allow measurements of heart rate and sounds, respiratory activities, body temperature, body orientation, and activity level, along with swallowing, coughing, talking, and related processes, without sensitivity to ambient conditions during routine daily activities, vigorous exercises, intense manual labor, and even swimming. Deployments on patients with COVID-19 allow clinical-grade ambulatory monitoring of the key symptoms of the disease even during rehabilitation protocols.

A skin-conformable wireless sensor to objectively quantify symptoms of pruritus.

Itch is a common clinical symptom and major driver of disease-related morbidity across a wide range of medical conditions. A substantial unmet need is for objective, accurate measurements of itch. In this article, we present a noninvasive technology to objectively quantify scratching behavior via a soft, flexible, and wireless sensor that captures the acousto-mechanic signatures of scratching from the dorsum of the hand. A machine learning algorithm validated on data collected from healthy subjects (n = 10) indicates excellent performance relative to smartwatch-based approaches. Clinical validation in a cohort of predominately pediatric patients (n = 11) with moderate to severe atopic dermatitis included 46 sleep-nights totaling 378.4 hours. The data indicate an accuracy of 99.0% (84.3% sensitivity, 99.3% specificity) against visual observation. This work suggests broad capabilities relevant to applications ranging from assessing the efficacy of drugs for conditions that cause itch to monitoring disease severity and treatment response.

Wireless, soft electronics for rapid, multisensor measurements of hydration levels in healthy and diseased skin.

Precise, quantitative measurements of the hydration status of skin can yield important insights into dermatological health and skin structure and function, with additional relevance to essential processes of thermoregulation and other features of basic physiology. Existing tools for determining skin water content exploit surrogate electrical assessments performed with bulky, rigid, and expensive instruments that are difficult to use in a repeatable manner. Recent alternatives exploit thermal measurements using soft wireless devices that adhere gently and noninvasively to the surface of the skin, but with limited operating range (∼1 cm) and high sensitivity to subtle environmental fluctuations. This paper introduces a set of ideas and technologies that overcome these drawbacks to enable high-speed, robust, long-range automated measurements of thermal transport properties via a miniaturized, multisensor module controlled by a long-range (∼10 m) Bluetooth Low Energy system on a chip, with a graphical user interface to standard smartphones. Soft contact to the surface of the skin, with almost zero user burden, yields recordings that can be quantitatively connected to hydration levels of both the epidermis and dermis, using computational modeling techniques, with high levels of repeatability and insensitivity to ambient fluctuations in temperature. Systematic studies of polymers in layered configurations similar to those of human skin, of porcine skin with known levels of hydration, and of human subjects with benchmarks against clinical devices validate the measurement approach and associated sensor hardware. The results support capabilities in characterizing skin barrier function, assessing severity of skin diseases, and evaluating cosmetic and medication efficacy, for use in the clinic or in the home.

Wireless, skin-interfaced sensors for compression therapy.

Therapeutic compression garments (TCGs) are key tools for the management of a wide range of vascular lower extremity conditions. Proper use of TCGs involves application of a minimum and consistent pressure across the lower extremities for extended periods of time. Slight changes in the characteristics of the fabric and the mechanical properties of the tissues lead to requirements for frequent measurements and corresponding adjustments of the applied pressure. Existing sensors are not sufficiently small, thin, or flexible for practical use in this context, and they also demand cumbersome, hard-wired interfaces for data acquisition. Here, we introduce a flexible, wireless monitoring system for tracking both temperature and pressure at the interface between the skin and the TCGs. Detailed studies of the materials and engineering aspects of these devices, together with clinical pilot trials on a range of patients with different pathologies, establish the technical foundations and measurement capabilities.

Eating Episode Detection with Jawbone-Mounted Inertial Sensing.

Recent work in Automated Dietary Monitoring (ADM) has shown promising results in eating detection by tracking jawbone movements with a proximity sensor mounted on a necklace. A significant challenge with this approach, however, is that motion artifacts introduced by natural body movements cause the necklace to move freely and the sensor to become misaligned. In this paper, we propose a different but related approach: we developed a small wireless inertial sensing platform and perform eating detection by mounting the sensor directly on the underside of the jawbone. We implemented a data analysis pipeline to recognize eating episodes from the inertial sensor data, and evaluated our approach in two different conditions: in the laboratory and in naturalistic settings. We demonstrated that in the lab (n=9), the system can detect eating with 91.7% precision and 91.3% recall using the leave-one-participant-out cross-validation (LOPO-CV) performance metric. In naturalistic settings, we obtained an average precision of 92.3% and a recall of 89.0% (n=14). These results represent a significant improvement (>10% in F1 score) over state-of-the-art necklace-based approaches. Additionally, this work presents a wearable device that is more inconspicuous and thus more likely to be adopted in clinical applications.

Towards a Generalizable Method for Detecting Fluid Intake with Wrist-Mounted Sensors and Adaptive Segmentation.

Over the last decade, advances in mobile technologies have enabled the development of intelligent systems that attempt to recognize and model a variety of health-related human behaviors. While automated dietary monitoring based on passive sensors has been an area of increasing research activity for many years, much less attention has been given to tracking fluid intake. In this work, we apply an adaptive segmentation technique on a continuous stream of inertial data captured with a practical, off-the-shelf wrist-mounted device to detect fluid intake gestures passively. We evaluated our approach in a study with 30 participants where 561 drinking instances were recorded. Using a leave-one-participant-out (LOPO), we were able to detect drinking episodes with 90.3% precision and 91.0% recall, demonstrating the generalizability of our approach. In addition to our proposed method, we also contribute an anonymized and labeled dataset of drinking and non-drinking gestures to encourage further work in the field.

Reducing thumb extensor risk in laboratory rat gavage.

Gavage is a common technique for orally administering compounds to small laboratory animals using a syringe. It involves highly repetitive thumb extensor exertions for filling the syringe, a risk factor for DeQuervain's tenosynovitis. As an intervention, a series of bench tests were performed varying fluid viscosity, syringe size and needle size to determine the forces required for drawing fluid. Forces up to 28 N were observed for a viscosity of 0.29 Pa s. A guide is presented to minimize thumb forces for a particular combination of syringe (3 mL, 5 mL and 10 mL), fluid viscosity (0.001 Pa s, 0.065 Pa s, 0.21 and 0.29 Pa s), and needle length (52 mm, 78 mm and 100 mm) based on maximum acceptable exertion levels. In general, a small syringe and large needle size had a greater number of acceptable rat gavages per day due to the lower forces experienced as compared to all other syringe and needle combinations.