In recent years, cardiovascular diseases are on the rise, and they entail enormous health burdens on global economies. Cardiac vibrations yield a wide and rich spectrum of essential information regarding the functioning of the heart, and thus it is necessary to take advantage of this data to better monitor cardiac health by way of prevention in early stages. Specifically, seismocardiography (SCG) is a noninvasive technique that can record cardiac vibrations by using new cutting-edge devices as accelerometers. Therefore, providing new and reliable data regarding advancements in the field of SCG, i.e., new devices and tools, is necessary to outperform the current understanding of the State-of-the-Art (SoTA). This paper reviews the SoTA on SCG and concentrates on three critical aspects of the SCG approach, i.e., on the acquisition, annotation, and its current applications. Moreover, this comprehensive overview also presents a detailed summary of recent advancements in SCG, such as the adoption of new techniques based on the artificial intelligence field, e.g., machine learning, deep learning, artificial neural networks, and fuzzy logic. Finally, a discussion on the open issues and future investigations regarding the topic is included.

A Comprehensive Review on Seismocardiogram: Current Advancements on Acquisition, Annotation, and Applications

Early identification of atypical infant movement behaviors consistent with underlying neuromotor pathologies can expedite timely enrollment in therapeutic interventions that exploit inherent neuroplasticity to promote recovery. Traditional neuromotor assessments rely on qualitative evaluations performed by specially trained personnel, mostly available in tertiary medical centers or specialized facilities. Such approaches are high in cost, require geographic proximity to advanced healthcare resources, and yield mostly qualitative insight. This paper introduces a simple, low-cost alternative in the form of a technology customized for quantitatively capturing continuous, full-body kinematics of infants during free living conditions at home or in clinical settings while simultaneously recording essential vital signs data. The system consists of a wireless network of small, flexible inertial sensors placed at strategic locations across the body and operated in a wide-bandwidth and time-synchronized fashion. The data serve as the basis for reconstructing three-dimensional motions in avatar form without the need for video recordings and associated privacy concerns, for remote visual assessments by experts. These quantitative measurements can also be presented in graphical format and analyzed with machine-learning techniques, with potential to automate and systematize traditional motor assessments. Clinical implementations with infants at low and at elevated risks for atypical neuromotor development illustrates application of this system in quantitative and semiquantitative assessments of patterns of gross motor skills, along with body temperature, heart rate, and respiratory rate, from long-term and follow-up measurements over a 3-mo period following birth. The engineering aspects are compatible for scaled deployment, with the potential to improve health outcomes for children worldwide via early, pragmatic detection methods.

https://www.pnas.org/content/pnas/118/43/e2104925118.full.pdf

Miniaturized wireless, skin-integrated sensor networks for quantifying full-body movement behaviors and vital signs in infants

Early diagnosis can be crucial to limit both the mortality and economic burden of cardiovascular diseases. Recent developments have focused on the continuous monitoring of cardiac activity for a prompt diagnosis. Nowadays, wearable devices are gaining broad interest for a continuous monitoring of the heart rate (HR). One of the most promising methods to estimate HR is the seismocardiography (SCG) which allows to record the thoracic vibrations with high non-invasiveness in out-of-laboratory settings. Despite significant progress on SCG, the current state-of-the-art lacks both information on standardized sensor positioning and optimization of wearables design. Here, we introduce a soft wearable system (SWS), whose novel design, based on a soft polymer matrix embedding an array of fiber Bragg gratings, provides a good adhesion to the body and enables the simultaneous recording of SCG signals from multiple measuring sites. The feasibility assessment on healthy volunteers revealed that the SWS is a suitable wearable solution for HR monitoring and its performance in HR estimation is strongly influenced by sensor positioning and improved by a multi-sensor configuration. These promising characteristics open the possibility of using the SWS in monitoring patients with cardiac pathologies in clinical (e.g., during cardiac magnetic resonance procedures) and everyday life settings.

/pdf/a-multi-point-heart-rate-monitoring-using-a-soft-wearable-ev43n751s4.pdf

A multi-point heart rate monitoring using a soft wearable system based on fiber optic technology

Background Developing deep learning models for radiology requires large data sets and substantial computational resources. Data set size limitations can be further exacerbated by distribution shifts, such as rapid changes in patient populations and standard of care during the COVID-19 pandemic. A common partial mitigation is transfer learning by pretraining a "generic network" on a large nonmedical data set and then fine-tuning on a task-specific radiology data set. Purpose To reduce data set size requirements for chest radiography deep learning models by using an advanced machine learning approach (supervised contrastive [SupCon] learning) to generate chest radiography networks. Materials and Methods SupCon helped generate chest radiography networks from 821 544 chest radiographs from India and the United States. The chest radiography networks were used as a starting point for further machine learning model development for 10 prediction tasks (eg, airspace opacity, fracture, tuberculosis, and COVID-19 outcomes) by using five data sets comprising 684 955 chest radiographs from India, the United States, and China. Three model development setups were tested (linear classifier, nonlinear classifier, and fine-tuning the full network) with different data set sizes from eight to 85. Results Across a majority of tasks, compared with transfer learning from a nonmedical data set, SupCon reduced label requirements up to 688-fold and improved the area under the receiver operating characteristic curve (AUC) at matching data set sizes. At the extreme low-data regimen, training small nonlinear models by using only 45 chest radiographs yielded an AUC of 0.95 (noninferior to radiologist performance) in classifying microbiology-confirmed tuberculosis in external validation. At a more moderate data regimen, training small nonlinear models by using only 528 chest radiographs yielded an AUC of 0.75 in predicting severe COVID-19 outcomes. Conclusion Supervised contrastive learning enabled performance comparable to state-of-the-art deep learning models in multiple clinical tasks by using as few as 45 images and is a promising method for predictive modeling with use of small data sets and for predicting outcomes in shifting patient populations. © RSNA, 2022 Online supplemental material is available for this article.

Simplified Transfer Learning for Chest Radiography Models Using Less Data.

Background The World Health Organization (WHO) recommends chest radiography to facilitate tuberculosis (TB) screening. However, chest radiograph interpretation expertise remains limited in many regions. Purpose To develop a deep learning system (DLS) to detect active pulmonary TB on chest radiographs and compare its performance to that of radiologists. Materials and Methods A DLS was trained and tested using retrospective chest radiographs (acquired between 1996 and 2020) from 10 countries. To improve generalization, large-scale chest radiograph pretraining, attention pooling, and semisupervised learning ("noisy-student") were incorporated. The DLS was evaluated in a four-country test set (China, India, the United States, and Zambia) and in a mining population in South Africa, with positive TB confirmed with microbiological tests or nucleic acid amplification testing (NAAT). The performance of the DLS was compared with that of 14 radiologists. The authors studied the efficacy of the DLS compared with that of nine radiologists using the Obuchowski-Rockette-Hillis procedure. Given WHO targets of 90% sensitivity and 70% specificity, the operating point of the DLS (0.45) was prespecified to favor sensitivity. Results A total of 165 754 images in 22 284 subjects (mean age, 45 years; 21% female) were used for model development and testing. In the four-country test set (1236 subjects, 17% with active TB), the receiver operating characteristic (ROC) curve of the DLS was higher than those for all nine India-based radiologists, with an area under the ROC curve of 0.89 (95% CI: 0.87, 0.91). Compared with these radiologists, at the prespecified operating point, the DLS sensitivity was higher (88% vs 75%, P < .001) and specificity was noninferior (79% vs 84%, P = .004). Trends were similar within other patient subgroups, in the South Africa data set, and across various TB-specific chest radiograph findings. In simulations, the use of the DLS to identify likely TB-positive chest radiographs for NAAT confirmation reduced the cost by 40%-80% per TB-positive patient detected. Conclusion A deep learning method was found to be noninferior to radiologists for the determination of active tuberculosis on digital chest radiographs. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by van Ginneken in this issue.

Deep Learning Detection of Active Pulmonary Tuberculosis at Chest Radiography Matched the Clinical Performance of Radiologists.

Objective: Optimizing peri-operative fluid management has been shown to improve patient outcomes and the use of stroke volume (SV) measurement has become an accepted tool to guide fluid therapy. The Transesophageal Doppler (TED) is a validated, minimally invasive device that allows clinical assessment of SV. Unfortunately, the use of the TED is restricted to the intra-operative setting in anesthetized patients and requires constant supervision and periodic adjustment for accurate signal quality. However, post-operative fluid management is also vital for improved outcomes. Currently, there is no device regularly used in clinics that can track patient's SV continuously and non-invasively both during and after surgery. Methods: In this paper, we propose the use of a wearable patch mounted on the mid-sternum, which captures the seismocardiogram (SCG) and electrocardiogram (ECG) signals continuously to predict SV in patients undergoing major surgery. In a study of 12 patients, hemodynamic data was recorded simultaneously using the TED and wearable patch. Signal processing and regression techniques were used to derive SV from the signals (SCG and ECG) captured by the wearable patch and compare it to values obtained by the TED. Results: The results showed that the combination of SCG and ECG contains substantial information regarding SV, resulting in a correlation and median absolute error between the predicted and reference SV values of 0.81 and 7.56 mL, respectively. Significance: This work shows promise for the proposed wearable-based methodology to be used as an alternative to TED for continuous patient monitoring and guiding peri-operative fluid management.

Non-Invasive Wearable Patch Utilizing Seismocardiography for Peri-Operative Use in Surgical Patients

Chest radiography (CXR) is the most widely-used thoracic clinical imaging modality and is crucial for guiding the management of cardiothoracic conditions. The detection of specific CXR findings has been the main focus of several artificial intelligence (AI) systems. However, the wide range of possible CXR abnormalities makes it impractical to build specific systems to detect every possible condition. In this work, we developed and evaluated an AI system to classify CXRs as normal or abnormal. For development, we used a de-identified dataset of 248,445 patients from a multi-city hospital network in India. To assess generalizability, we evaluated our system using 6 international datasets from India, China, and the United States. Of these datasets, 4 focused on diseases that the AI was not trained to detect: 2 datasets with tuberculosis and 2 datasets with coronavirus disease 2019. Our results suggest that the AI system generalizes to new patient populations and abnormalities. In a simulated workflow where the AI system prioritized abnormal cases, the turnaround time for abnormal cases reduced by 7-28%. These results represent an important step towards evaluating whether AI can be safely used to flag cases in a general setting where previously unseen abnormalities exist.

Deep Learning for Distinguishing Normal versus Abnormal Chest Radiographs and Generalization to Unseen Diseases.

Cardiac MRI (CMR) techniques offer non-invasive visualizations of cardiac morphology and function. However, imaging can be time-consuming and complex. Seismocardiography (SCG) measures physical vibrations transmitted through the chest from the beating heart and pulsatile blood flow. SCG signals can be acquired quickly and easily, with inexpensive electronics. This study investigates relationships between CMR metrics of function and SCG signal features. Same-day CMR and SCG data were collected from 28 healthy adults and 6 subjects with aortic valve disease history. Correlation testing and statistical median/decile calculations were performed with data from the healthy cohort. MR-quantified flow and function parameters in the healthy cohort correlated with particular SCG energy levels, such as peak aortic velocity with low-frequency SCG (coefficient 0.43, significance 0.02) and peak flow with high-frequency SCG (coefficient 0.40, significance 0.03). Valve disease-induced flow abnormalities in patients were visualized with MRI, and corresponding abnormalities in SCG signals were identified. This investigation found significant cross-modality correlations in cardiac function metrics and SCG signals features from healthy subjects. Additionally, through comparison to normative ranges from healthy subjects, it observed correspondences between pathological flow and abnormal SCG. This may support development of an easy clinical test used to identify potential aortic flow abnormalities.

Detecting Aortic Valve-Induced Abnormal Flow with Seismocardiography and Cardiac MRI.

Background and study aims Storage of full-length endoscopic procedures is becoming increasingly popular. To facilitate large-scale machine learning (ML) focused on clinical outcomes, these videos must be merged with the patient-level data in the electronic health record (EHR). Our aim was to present a method of accurately linking patient-level EHR data with cloud stored colonoscopy videos. Methods This study was conducted at a single academic medical center. Most procedure videos are automatically uploaded to the cloud server but are identified only by procedure time and procedure room. We developed and then tested an algorithm to match recorded videos with corresponding exams in the EHR based upon procedure time and room and subsequently extract frames of interest. Results Among 28,611 total colonoscopies performed over the study period, 21,170 colonoscopy videos in 20,420 unique patients (54.2 % male, median age 58) were matched to EHR data. Of 100 randomly sampled videos, appropriate matching was manually confirmed in all. In total, these videos represented 489,721 minutes of colonoscopy performed by 50 endoscopists (median 214 colonoscopies per endoscopist). The most common procedure indications were polyp screening (47.3 %), surveillance (28.9 %) and inflammatory bowel disease (9.4 %). From these videos, we extracted procedure highlights (identified by image capture; mean 8.5 per colonoscopy) and surrounding frames. Conclusions We report the successful merging of a large database of endoscopy videos stored with limited identifiers to rich patient-level data in a highly accurate manner. This technique facilitates the development of ML algorithms based upon relevant patient outcomes.

/pdf/amalgamation-of-cloud-based-colonoscopy-videos-with-patient-5vg480m95t.pdf

Florencia Garcia Vicente

Papers

Non-Invasive Wearable Patch Utilizing Seismocardiography for Peri-Operative Use in Surgical Patients

Deep Learning for Distinguishing Normal versus Abnormal Chest Radiographs and Generalization to Unseen Diseases.

Detecting Aortic Valve-Induced Abnormal Flow with Seismocardiography and Cardiac MRI.

Amalgamation of cloud-based colonoscopy videos with patient-level metadata to facilitate large-scale machine learning.