Feasibility of Tracking Human Kinematics with Simultaneous Localization and Mapping (SLAM).

We evaluated a new wearable technology that fuses inertial sensors and cameras for tracking human kinematics. These devices use on-board simultaneous localization and mapping (SLAM) algorithms to localize the camera within the environment. Significance of this technology is in its potential to overcome many of the limitations of the other dominant technologies. Our results demonstrate this system often attains an estimated orientation error of less than 1° and a position error of less than 4 cm as compared to a robotic arm. This demonstrates that SLAM's accuracy is adequate for many practical applications for tracking human kinematics.

A novel particle filtering method for estimation of pulse pressure variation during spontaneous breathing.

BACKGROUND: We describe the first automatic algorithm designed to estimate the pulse pressure variation ([Formula: see text]) from arterial blood pressure (ABP) signals under spontaneous breathing conditions. While currently there are a few publicly available algorithms to automatically estimate [Formula: see text] accurately and reliably in mechanically ventilated subjects, at the moment there is no automatic algorithm for estimating [Formula: see text] on spontaneously breathing subjects. The algorithm utilizes our recently developed sequential Monte Carlo method (SMCM), which is called a maximum a-posteriori adaptive marginalized particle filter (MAM-PF). We report the performance assessment results of the proposed algorithm on real ABP signals from spontaneously breathing subjects. RESULTS: Our assessment results indicate good agreement between the automatically estimated [Formula: see text] and the gold standard [Formula: see text] obtained with manual annotations. All of the automatically estimated [Formula: see text] index measurements ([Formula: see text]) were in agreement with manual gold standard measurements ([Formula: see text]) within ±4 % accuracy. CONCLUSION: The proposed automatic algorithm is able to give reliable estimations of [Formula: see text] given ABP signals alone during spontaneous breathing.

Beyond the 510(k): The regulation of novel moderate-risk medical devices, intellectual property considerations, and innovation incentives in the FDA's De Novo pathway.

Moderate-risk medical devices constitute 99% of those that have been regulated by the U.S. Food and Drug Administration (FDA) since it gained authority to regulate medical technology nearly five decades ago. This article presents an analysis of the interaction between the 510(k) process -the historically dominant path to market for most medical devices- and the De Novo pathway, a more recent alternative that targets more novel devices, including those involving new technologies, diagnostics, hardware, and software. The De Novo pathway holds significant potential for innovators seeking to define new categories of medical devices, as it represents a less burdensome approach than would have otherwise been needed historically. Moreover, it supports the FDA in its effort to modernize the long-established 510(k) pathway by promoting the availability of up-to-date device "predicates" upon which subsequent device applications can be based, reflecting positive spillovers that are likely to encourage manufacturers to adopt current state-of-the-art technologies and modern standards of safety and effectiveness. We analyze the of characteristics all the De Novo classification requests to date, including the submission type, trends, FDA review times, and device types. After characterizing how the De Novo process has been used over time, we discuss its unique challenges and opportunities with respect to medical device software and AI-enabled devices, including considerations for intellectual property, innovation, and competition economics.

New government drug repurposing programs: Opportunities and uncertainties.

Drug repurposing can be cheaper and faster than developing new compounds. Yet, it remains underused, partially because of regulatory and intellectual property challenges. Policy-makers in the United States and Europe have created seven drug development programs that aim to overcome these challenges using a variety of different strategies.

Pulse pressure variation: where are we today?

In the present review we will describe and discuss the physiological and technological background necessary in understanding the dynamic parameters of fluid responsiveness and how they relate to recent softwares and algorithms' applications. We will also discuss the potential clinical applications of these parameters in the management of patients under general anesthesia and mechanical ventilation along with the potential improvements in the computational algorithms.

Standard contractual clauses for cross-border transfers of health data after Schrems II.

Standard contractual clauses (SCCs) have long been considered the most accessible method to transfer personal data legally across borders. In July 2020, the Court of Justice of the European Union (CJEU) in Data Protection Commissioner v Facebook Ireland Limited, Maximillian Schrems (Schrems II) placed heavy conditions on their use. The Schrems II Court found that SCCs were valid as 'appropriate safeguards' for data transfers from EU entities to others outside the EU/EEA as long as unspecified 'supplementary measures' were in place to compensate for the lack of data protection in the third country. Data protection officers are under intense pressure to explain these measures and allow routine transfers to continue. Some authorities interpret the decision as preventing the use of SCCs to transfer personal data outside of the EU because private contracts cannot comprehensively redress gaps in national law. This article argues that these authorities are mistaken and that notwithstanding Schrems II SCCs can still be useful instruments for cross-border transfers. This is especially true in highly regulated contexts such as medical research. This paper traces the history of SCCs under the General Data Protection Regulation (GDPR) and shows how the CJEU in Schrems II misunderstood the purpose of SCCs and other Article 46 GDPR 'appropriate safeguards'. The CJEU mistakenly approached Article 46 safeguards such as SCCs as being similar to country-specific adequacy rulings under Article 45 GDPR. But unlike Article 45 adequacy rulings, SCCs were not intended to provide a stand-alone mechanism for transfer reliant on the law of the importing country. Rather SCCs provide an alternative, multi-layered standard for data protection that encompasses law, technology and organizational commitments. Their purpose is to be used in situations where legislation alone is insufficient to protect data subject rights. The European Commission's new draft SCCs support this analysis.

International transfers of health data between the EU and USA: a sector-specific approach for the USA to ensure an 'adequate' level of protection.

International health research increasingly depends on collaboration and combination using medical data to advance treatment and drug discovery. The European Union (EU), through its General Data Protection Regulation, has tightened the rules for sharing data across borders to protect individual privacy. These new rules threaten cooperation between the EU and the USA, the two largest public funders of biomedical research. This article analyzes the primary pathway for sharing research data with the USA, the US-EU Privacy Shield, and argues that the Shield is ill-suited to support complex health studies. Its legitimacy is in question under both EU and US law, and its terms are too restrictive for the variety of exchanges underlying research, treatment, and care. As an alternative, we propose that the USA seek an additional sector-based adequacy determination based on the existing US health privacy law, the Health Insurance Portability and Accountability Act. A sector-specific approach to adequacy for health would avoid many of the most contentious issues that divide the USA and EU on data protection. It could also serve as a model for other third-party jurisdictions and facilitate international harmonization of health research practices.

COVID-19 contact tracing apps: a stress test for privacy, the GDPR, and data protection regimes.

Digital surveillance has played a key role in containing the COVID-19 outbreak in China, Singapore, Israel, and South Korea. Google and Apple recently announced the intention to build interfaces to allow Bluetooth contact tracking using Android and iPhone devices. In this article, we look at the compatibility of the proposed Apple/Google Bluetooth exposure notification system with Western privacy and data protection regimes and principles, including the General Data Protection Regulation (GDPR). Somewhat counter-intuitively, the GDPR's expansive scope is not a hindrance, but rather an advantage in conditions of uncertainty such as a pandemic. Its principle-based approach offers a functional blueprint for system design that is compatible with fundamental rights. By contrast, narrower, sector-specific rules such as the US Health Insurance Portability and Accountability Act (HIPAA), and even the new California Consumer Privacy Act (CCPA), leave gaps that may prove difficult to bridge in the middle of an emergency.

Regulatory responses to medical machine learning.

Companies and healthcare providers are developing and implementing new applications of medical artificial intelligence, including the artificial intelligence sub-type of medical machine learning (MML). MML is based on the application of machine learning (ML) algorithms to automatically identify patterns and act on medical data to guide clinical decisions. MML poses challenges and raises important questions, including (1) How will regulators evaluate MML-based medical devices to ensure their safety and effectiveness? and (2) What additional MML considerations should be taken into account in the international context? To address these questions, we analyze the current regulatory approaches to MML in the USA and Europe. We then examine international perspectives and broader implications, discussing considerations such as data privacy, exportation, explanation, training set bias, contextual bias, and trade secrecy.

Description of a portable wireless device for high-frequency body temperature acquisition and analysis.

We describe a device for dual channel body temperature monitoring. The device can operate as a real time monitor or as a data logger, and has Bluetooth capabilities to enable for wireless data download to the computer used for data analysis. The proposed device is capable of sampling temperature at a rate of 1 sample per minute with a resolution of 0.01 °C . The internal memory allows for stand-alone data logging of up to 10 days. The device has a battery life of 50 hours in continuous real-time mode. In addition to describing the proposed device in detail, we report the results of a statistical analysis conducted to assess its accuracy and reproducibility.

Continental drift? Do European clinical genetic testing laboratories have a patent problem?

Recent US Supreme Court decisions have invalidated patent claims on isolated genomic DNA, and testing methods that applied medical correlations using conventional techniques. As a consequence, US genetic testing laboratories have a relatively low risk of infringing patents on naturally occurring DNA or methods for detecting genomic variants. In Europe, however, such claims remain patentable, and European laboratories risk infringing them. We report the results from a survey that collected data on the impact of patents on European genetic testing laboratories. The results indicate that the proportion of European laboratories that have refrained from providing associated testing services owing to patent protection has increased over the last decade (up from 7% in 2008 to 15% in 2017), and that the non-profit sector was particularly strongly affected (up from 4% in 2008 to 14% in 2017). We renew calls for more readily available legal support to help public sector laboratories deal with patent issues, but we do not recommend aligning European law with US law at present. Watchful monitoring is also recommended to ensure that patents do not become a greater hindrance for clinical genetic testing laboratories.

A Two-Stage Tremor Detection Algorithm for Wearable Inertial Sensors During Normal Daily Activities.

Continuous monitoring of tremor with wearable wrist sensors during normal daily activities is more difficult than in a clinical setting when subjects perform prescribed activities because some normal daily activities resemble tremor, many normal movements contain frequency content that overlaps with the tremor frequency, and the tremor amplitude has a large dynamic range during normal daily activities. We describe a novel two-stage algorithm that offers improvement at discriminating tremor from other activities. Some of this improvement is attained by using prior domain knowledge that tremor occurs over a narrow range of frequencies for an individual, but the mean tremor frequency may vary significantly between individuals in a study population. We validated the algorithm in continuous recordings from people with Parkinson's disease and matched control subjects. The algorithm has good face validity, a low rate of false positives on recordings from control subjects (<; 1.1%), and good correspondence with the constancy of rest tremor as measured by this question on the MDS-UPDRS (ρ = 0.54).

Statistical modeling of cardiovascular signals and parameter estimation based on the extended Kalman filter.

Cardiovascular signals such as arterial blood pressure (ABP), pulse oximetry (POX), and intracranial pressure (ICP) contain useful information such as heart rate, respiratory rate, and pulse pressure variation (PPV). We present a novel state-space model of cardiovascular signals and describe how it can be used with the extended Kalman filter (EKF) to simultaneously estimate and track many cardiovascular parameters of interest using a unified statistical approach. We analyze data from four databases containing cardiovascular signals and present representative examples intended to illustrate the versatility, accuracy, and robustness of the algorithm. Our results demonstrate the ability of the algorithm to estimate and track several clinically relevant features of cardiovascular signals. We illustrate how the algorithm can be used to elegantly solve several actively researched and clinically significant problems including heart and respiratory rate estimation, artifact removal, pulse morphology characterization, and PPV estimation.

A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis.

We present an automatic image processing algorithm to detect hard exudates. Automatic detection of hard exudates from retinal images is an important problem since hard exudates are associated with diabetic retinopathy and have been found to be one of the most prevalent earliest signs of retinopathy. The algorithm is based on Fisher's linear discriminant analysis and makes use of colour information to perform the classification of retinal exudates. We prospectively assessed the algorithm performance using a database containing 58 retinal images with variable colour, brightness, and quality. Our proposed algorithm obtained a sensitivity of 88% with a mean number of 4.83+/-4.64 false positives per image using the lesion-based performance evaluation criterion, and achieved an image-based classification accuracy of 100% (sensitivity of 100% and specificity of 100%).

Pulse morphology visualization and analysis with applications in cardiovascular pressure signals.

We present a new analysis and visualization method for studying the functional relationship between the pulse morphology of pressure signals and time or signal metrics such as heart rate, pulse pressure, and means of pressure signals, such as arterial blood pressure and central venous pressure. The pulse morphology is known to contain potentially useful clinical information, but it is difficult to study in the time domain without the aid of a tool such as the method we present here. The primary components of the method are established signal processing techniques, nonparametric regression, and an automatic beat detection algorithm. Some of the insights that can be gained from this are demonstrated through the analysis of intracranial pressure signals acquired from patients with traumatic brain injuries. The analysis indicates the point of transition from low-pressure morphology consisting of three distinct peaks to a high-pressure morphology consisting of a single peak. In addition, we demonstrate how the analysis can reveal distinctions in the relationship between morphology and several signal metrics for different patients.

Design and implementation of a portable physiologic data acquisition system.

OBJECTIVE: To describe and report the reliability of a portable, laptop-based, real-time, continuous physiologic data acquisition system (PDAS) that allows for synchronous recording of physiologic data, clinical events, and event markers at the bedside for physiologic research studies in the intensive care unit. DESIGN: Descriptive report of new research technology. SETTING: Adult and pediatric intensive care units in three tertiary care academic hospitals. PATIENTS: Sixty-four critically ill and injured patients were studied, including 34 adult (22 males and 12 females) and 30 pediatric (19 males and 11 females). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Data transmission errors during bench and field testing were measured. The PDAS was used in three separate research studies, by multiple users, and for repeated recordings of the same set of signals at various intervals for different lengths of time. Both parametric (1 Hz) and waveform (125-500 Hz) signals were recorded and analyzed. Details of the PDAS components are explained and examples are given from the three experimental physiology-based protocols. Waveform data include electrocardiogram, respiration, systemic arterial pressure (invasive and noninvasive), oxygen saturation, central venous pressure, pulmonary arterial pressure, left and right atrial pressures, intracranial pressure, and regional cerebral blood flow. Bench and field testing of the PDAS demonstrated excellent reliability with 100% accuracy and no data transmission errors. The key feature of simultaneously capturing physiologic signal data and clinical events (e.g., changes in mechanical ventilation, drug administration, clinical condition) is emphasized. CONCLUSIONS: The PDAS provides a reliable tool to record physiologic signals and associated clinical events on a second-to-second basis and may serve as an important adjunctive research tool in designing and performing clinical physiologic studies in critical illness and injury.

Analysis of intracranial pressure during acute intracranial hypertension using Lempel-Ziv complexity: further evidence.

We analyzed intracranial pressure (ICP) signals during periods of acute intracranial hypertension (ICH) using the Lempel-Ziv (LZ) complexity measure. Our results indicate the LZ complexity of ICP decreases during periods of ICH. The mean LZ complexity before ICH was 0.20+/-0.04, while the mean LZ complexity during ICH was 0.16+/-0.03 (p<0.05). The mean decrease of the LZ complexity values during the ICH episodes was 19.5%. Additionally, we present preliminary evidence suggesting that periods of ICH may be detectable from non-invasive signals coupled with ICP, such as pulse oximetry (SpO2).

Unsupervised classification of ventricular extrasystoles using bounded clustering algorithms and morphology matching.

Ventricular extrasystoles (VE) are ectopic heartbeats involving irregularities in the heart rhythm. VEs arise in response to impulses generated in some part of the heart different from the sinoatrial node. These are caused by the premature discharge of a ventricular ectopic focus. VEs after myocardial infarction are associated with increased mortality. Screening of VEs is typically a manual and time consuming task that involves analysis of the heartbeat morphology, QRS duration, and variations of the RR intervals using long-term electrocardiograms. We describe a novel algorithm to perform automatic classification of VEs and report the results of our validation study. The proposed algorithm makes use of bounded clustering algorithms, morphology matching, and RR interval length to perform automatic VE classification without prior knowledge of the number of classes and heartbeat features. Additionally, the proposed algorithm does not need a training set.