Portable robot for autonomous venipuncture using 3D near infrared image guidance

Advances in the Application of AI Robots in Critical Care: Scoping Review

BACKGROUND

In recent epochs, the field of critical medicine has experienced significant advancements due to the integration of artificial intelligence (AI). Specifically, AI robots have evolved from theoretical concepts to being actively implemented in clinical trials and applications. The intensive care unit (ICU), known for its reliance on a vast amount of medical information, presents a promising avenue for the deployment of robotic AI, anticipated to bring substantial improvements to patient care.

OBJECTIVE

This review aims to comprehensively summarize the current state of AI robots in the field of critical care by searching for previous studies, developments, and applications of AI robots related to ICU wards. In addition, it seeks to address the ethical challenges arising from their use, including concerns related to safety, patient privacy, responsibility delineation, and cost-benefit analysis.

METHODS

Following the scoping review framework proposed by Arksey and O'Malley and the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we conducted a scoping review to delineate the breadth of research in this field of AI robots in ICU and reported the findings. The literature search was carried out on May 1, 2023, across 3 databases: PubMed, Embase, and the IEEE Xplore Digital Library. Eligible publications were initially screened based on their titles and abstracts. Publications that passed the preliminary screening underwent a comprehensive review. Various research characteristics were extracted, summarized, and analyzed from the final publications.

RESULTS

Of the 5908 publications screened, 77 (1.3%) underwent a full review. These studies collectively spanned 21 ICU robotics projects, encompassing their system development and testing, clinical trials, and approval processes. Upon an expert-reviewed classification framework, these were categorized into 5 main types: therapeutic assistance robots, nursing assistance robots, rehabilitation assistance robots, telepresence robots, and logistics and disinfection robots. Most of these are already widely deployed and commercialized in ICUs, although a select few remain under testing. All robotic systems and tools are engineered to deliver more personalized, convenient, and intelligent medical services to patients in the ICU, concurrently aiming to reduce the substantial workload on ICU medical staff and promote therapeutic and care procedures. This review further explored the prevailing challenges, particularly focusing on ethical and safety concerns, proposing viable solutions or methodologies, and illustrating the prospective capabilities and potential of AI-driven robotic technologies in the ICU environment. Ultimately, we foresee a pivotal role for robots in a future scenario of a fully automated continuum from admission to discharge within the ICU.

CONCLUSIONS

This review highlights the potential of AI robots to transform ICU care by improving patient treatment, support, and rehabilitation processes. However, it also recognizes the ethical complexities and operational challenges that come with their implementation, offering possible solutions for future development and optimization.

Design of composite puncture blood collection system and research on puncture force

Venous blood collection testing is one of the most commonly used medical diagnostic methods. Compared with conventional venous blood collection, robotic collection can reduce needle-stick injuries, medical staff workload, and infection risk; allow doctor-patient isolation; and improve collection reliability. Existing venous blood collection robots use rigid puncture needles, which can easily puncture the lower wall of blood vessels, causing vessel damage and collection failure. This paper proposes a bionic blood collection strategy based on a composite puncture needle that mimics the structure and function of mosquito mouthparts. A bionic composite puncture needle insertion system with puncture-force sensing was designed, and venipuncture forces were simulated and mathematically modelled. A prototype insertion system was built and used in an experiment, which demonstrated effective composite puncture blood collection and explored the factors influencing puncture force. Puncture force decreases with increased puncture speed and angle and with a decreased needle diameter. This provides a basis for optimising the parameters of blood collection robots.

Visualization of Subcutaneous Blood Vessels Based on Hyperspectral Imaging and Three-Wavelength Index Images

Blood vessel visualization technology allows nursing staff to transition from traditional palpation or touch to locate the subcutaneous blood vessels to visualized localization by providing a clear visual aid for performing various medical procedures accurately and efficiently involving blood vessels; this can further improve the first-attempt puncture success rate for nursing staff and reduce the pain of patients. We propose a novel technique for hyperspectral visualization of blood vessels in human skin. An experiment with six participants with different skin types, race, and nationality backgrounds is described. A mere separation of spectral layers for different skin types is shown to be insufficient. The use of three-wavelength indices in imaging has shown a significant improvement in the quality of results compared to using only two-wavelength indices. This improvement can be attributed to an increase in the contrast ratio, which can be as high as 25%. We propose and implement a technique for finding new index formulae based on an exhaustive search and a binary blood-vessel image obtained through an expert assessment. As a result of the search, a novel index formula was deduced, allowing high-contrast blood vessel images to be generated for any skin type.

Puncture site decision method for venipuncture robot based on near-infrared vision and multiobjective optimization

Venipuncture robots have superior perception and stability to humans and are expected to replace manual venipuncture. However, their use is greatly restricted because they cannot make decisions regarding the puncture sites. Thus, this study presents a multi-information fusion method for determining puncture sites for venipuncture robots to improve their autonomy in the case of limited resources. Here, numerous images have been gathered and processed to establish an image dataset of human forearms for training the U-Net with the soft attention mechanism (SAU-Net) for vein segmentation. Then, the veins are segmented from the images, feature information is extracted based on near-infrared vision, and a multiobjective optimization model for puncture site decision is provided by considering the depth, diameter, curvature, and length of the vein to determine the optimal puncture site. Experiments demonstrate that the method achieves a segmentation accuracy of 91.2% and a vein extraction rate of 86.7% while achieving the Pareto solution set (average time: 1.458 s) and optimal results for each vessel. Finally, a near-infrared camera is applied to the venipuncture robot to segment veins and determine puncture sites in real time, with the results transmitted back to the robot for an attitude adjustment. Consequently, this method can enhance the autonomy of venipuncture robots if implemented dramatically.

Competitive Real-Time Near Infrared (NIR) Vein Finder Imaging Device to Improve Peripheral Subcutaneous Vein Selection in Venipuncture for Clinical Laboratory Testing

In this study, near-infrared (NIR) technology was utilized to develop a low-cost real-time near infrared (NIR) guiding device for cannulation. A portable device that can be used by medical practitioners and also by students for their skills development training in performing cannulation. Methods. First, is the development of a reflectance type optical vein finder using three (3) light emitting diode (LED) lights with 960 nm wavelength, complementary metal-oxide-semiconductor-infrared (CMOS-IR) sensor camera with 1920 × 1080 UXGA (1080P), IR filter set for the given wavelength, and an open-source image processing software. Second, is the actual in-vitro human testing in two sites: the arm and dorsal hand of 242 subjects. The following parameters were included, such as gender, age, mass index (BMI), and skin tone. In order to maximize the assessment process towards the device, the researchers included the arm circumference. This augmented subcutaneous vein imaging study using the develop vein finder device compared the difference in the captured vein images through visual and digital imaging approaches. The human testing was performed in accordance with the ethical standards of the Trinity University of Asia—Institutional Ethics Review Committee (TUA—IERC). Results. The NIR imaging system of the developed vein finder in this study showed its capability as an efficient guiding device through real-time vein pattern recognition, for both sites. Improved captured vein images were observed, having 100% visibility of vein patterns on the dorsal hand site. Fourteen (5.79%) out of 242 subjects reported non-visible peripheral subcutaneous veins in the arm sites. Conclusions. The developed vein finder device with the NIR technology and reflected light principle with low-energy consumption was efficient for real-time peripheral subcutaneous vein imaging without the application of a tourniquet. This might be utilized as a guiding device in locating the vein for the purpose of cannulation, at a very low cost as compared to the commercially available vein finders. Moreover, it may be used as an instructional device for student training in performing cannulation.

A novel design proposal for low-cost vein-viewer for medical and non-contact biometric applications using NIR imaging

The vein-viewer is a new revolution in the health industry. In fact, it is one of the must-have gadgets for any medical professional. The vein-viewer is device that helps to access easily veins when trying to collect a blood sample or for administering Intravenous (IV) cannulation. It is also an aid for dermatologist/aesthetic physician to access client's veins for sclerotherapy procedures or avoiding veins in cosmetic procedures. The vein-viewer is highly applicable where vascular positioning is really difficult; examples while canulating infants, obese, hairy/dark skins, dialysis/cancer patients etc. In addition, frequent attempts affect patients, causing trauma and subcutaneous haemorrhage. As palm/finger vein patterns are unique and complex, difficult to duplicate or steal as it is beneath the skin. So, in this Covid19 pandemic time, the vein-viewer finds applications in the secure non-contact bio-metric authentications for secure banking and attendance registering system to identify an individual. In this article I am trying to explain the design overview of vein-viewer system, its design challenges, cost aspects, its availability and also sharing a few inputs for the new compact, low-cost design and implementation.

Role of Artificial Intelligence in Kidney Disease

Artificial intelligence (AI), as an advanced science technology, has been widely used in medical fields to promote medical development, mainly applied to early detections, disease diagnoses, and management. Owing to the huge number of patients, kidney disease remains a global health problem. Challenges remain in its diagnosis and treatment. AI could take individual conditions into account, produce suitable decisions and promise to make great strides in kidney disease management. Here, we review the current studies of AI applications in kidney disease in alerting systems, diagnostic assistance, guiding treatment and evaluating prognosis. Although the number of studies related to AI applications in kidney disease is small, the potential of AI in the management of kidney disease is well recognized by clinicians; AI will greatly enhance clinicians' capacity in their clinical practice in the future.

First-in-human evaluation of a hand-held automated venipuncture device for rapid venous blood draws

Obtaining venous access for blood sampling or intravenous (IV) fluid delivery is an essential first step in patient care. However, success rates rely heavily on clinician experience and patient physiology. Difficulties in obtaining venous access result in missed sticks and injury to patients, and typically require alternative access pathways and additional personnel that lengthen procedure times, thereby creating unnecessary costs to healthcare facilities. Here, we present the first-in-human assessment of an automated robotic venipuncture device designed to safely perform blood draws on peripheral forearm veins. The device combines ultrasound imaging and miniaturized robotics to identify suitable vessels for cannulation and robotically guide an attached needle toward the lumen center. The device demonstrated results comparable to or exceeding that of clinical standards, with a success rate of 87% on all participants (n = 31), a 97% success rate on nondifficult venous access participants (n = 25), and an average procedure time of 93 ± 30 s (n = 31). In the future, this device can be extended to other areas of vascular access such as IV catheterization, central venous access, dialysis, and arterial line placement.

Vein Pattern Locating Technology for Cannulation: A Review of the Low-Cost Vein Finder Prototypes Utilizing near Infrared (NIR) Light to Improve Peripheral Subcutaneous Vein Selection for Phlebotomy

One of the most common means for diagnosis is through medical laboratory testing, which primarily uses venous blood as a sample. This requires an invasive method by cannulation that needs proper vein selection. The use of a vein finder would help the phlebotomist to easily locate the vein, preventing possible pre-analytical error in the specimen collection and even more discomfort and pain to the patient. This paper is a review of the scientific publications on the different developed low-cost vein finder prototypes utilizing camera assisted near infrared (NIR) light technology. Methods: Electronic databases were searched online, these included PubMed (PMC), MEDLINE, Science Direct, ResearchGate, and Institute of Electrical and Electronics Engineers (IEEE) Xplore digital library. Specifically, publications with the terms vein finder prototype, NIR technology, vein detection, and infrared imaging were screened. In addition, reference lists were used to further review related publications. Results: Cannulation challenges medical practitioners because of the different factors that can be reduced by the utilization of a vein finder. A limited number of publications regarding the assessment of personnel performing cannulation were observed. Moreover, variations in methodology, number of patients, type of patients according to their demographics and materials used in the assessment of the developed prototypes were noted. Some studies were limited with regard to the actual human testing of the prototype. Conclusions: The development of a low-cost effective near infrared (NIR) vein finder remains in the phase of improvement. Since, it is being challenged by different human factors, increasing the number of parameters and participants/human for actual testing of the prototypes must also be taken into consideration for possible commercialization. Finally, it was noted that publications regarding the assessment of the performance of phlebotomists using vein finders were limited.

A New Venous Entry Detection Method Based on Electrical Bio-impedance Sensing

Peripheral intravenous catheterization (PIVC) is frequently required for various medical treatments. Over 1 billion PIVC operations are performed per year in the United States alone. However, this operation is characterized by a very low success rate, especially amongst pediatric patients. Statistics show that only 53% of first PIVC attempts are successful in pediatric patients. Since their veins are small and readily rupture, multiple attempts are commonly required before successfully inserting the catheter into the vein. This article presents and evaluates a novel venous entry detection method based on measuring the electrical bio-impedance of the contacting tissue at the tip of a concentric electrode needle (CEN). This detection method is then implemented in the design of a clinical device called smart venous entry indicator (SVEI), which lights up a LED to indicate the venous entry when the measured value is within the range of blood. To verify this detection method, two experiments are conducted. In the first experiment, we measured the bio-impedance during the insertion of a CEN into a rat's tail vein with different excitation frequencies. Then three classifiers are tested to discriminate blood from surrounding tissues. The experimental results indicate that with 100 kHz excitation frequency the blood bio-impedance can be identified with accuracy nearly 100%, demonstrating the feasibility and reliability of the proposed method for venous entry detection. The second experiment aims to assess the impact of SVEI on PIVC performance. Ten naive subjects were invited to catheterize a realistic baby arm phantom. The subjects are equally divided into two groups, where one group does PIVC with SVEI and the other group uses an ordinary IV catheter. The results show that subjects using SVEI can achieve much higher success rates (86%) than those performing PIVC in a conventional way (12%). Also, all subjects assisted by SVEI succeeded in their first trials while no one succeed in their first attempt using the conventional unassisted system. These results demonstrate the proposed detection method has great potential to improve pediatric PIVC performance, especially for non-expert clinicians. This supports further investment towards clinical validation of the technology.

A hand-held robotic device for peripheral intravenous catheterization

Intravenous catheterization is frequently required for numerous medical treatments. However, this process is characterized by a high failure rate, especially when performed on difficult patients such as newborns and infants. Very young patients have small veins, and that increases the chances of accidentally puncturing the catheterization needle directly through them. In this article, we present the design, development and experimental evaluation of a novel hand-held robotic device for improving the process of peripheral intravenous catheterization by facilitating the needle insertion procedure. To our knowledge, this design is the first hand-held robotic device for assisting in the catheterization insertion task. Compared to the other available technologies, it has several unique advantages such as being compact, low-cost and able to reliably detect venipuncture. The system is equipped with an electrical impedance sensor at the tip of the catheterization needle, which provides real-time measurements used to supervise and control the catheter insertion process. This allows the robotic system to precisely position the needle within the lumen of the target vein, leading to enhanced catheterization success rate. Experiments conducted to evaluate the device demonstrated that it is also effective to deskill the task. Naïve subjects achieved an average catheterization success rate of 88% on a 1.5 mm phantom vessel with the robotic device versus 12% with the traditional unassisted system. The results of this work prove the feasibility of a hand-held assistive robotic device for intravenous catheterization and show that such device has the potential to greatly improve the success rate of these difficult operations.

Novel Opportunities for Improving the Quality of Preanalytical Phase. A Glimpse to the Future?

The preanalytical phase is crucial for assuring the quality of in vitro diagnostics. The leading aspects which contribute to enhance the vulnerability of this part of the total testing process include the lack of standardization of different practices for collecting, managing, transporting and processing biological specimens, the insufficient compliance with available guidelines and the still considerable number of preventable human errors. As in heavy industry, road traffic and aeronautics, technological advancement holds great promise for decreasing the risk of medical and diagnostic errors, thus including those occurring in the extra-analytical phases of the total testing process. The aim of this article is to discuss some potentially useful technological advances, which are not yet routine practice, but may be especially suited for improving the quality of the preanalytical phase in the future. These are mainly represented by introduction of needlewielding robotic phlebotomy devices, active blood tubes, drones for biological samples transportation, innovative approaches for detecting spurious hemolysis and preanalytical errors recording software products.

On the use of an optoacoustic and laser ultrasonic imaging system for assessing peripheral intravenous access

We describe a universal system for research in combined real-time optoacoustic (OA) and laser-ultrasonic (LU) imaging. The results of its testing on the task of needle insertion into the blood vessel model diagnostics are presented. In OA mode, where laser light is absorbed directly in the sample, the contents of blood vessel model is clearly visible. In LU mode, where the short ultrasonic probe pulse scattered on the sample is detected, the needle is clearly visible. The developed solution combining OA and LU imaging modalities due to the common detection system allowed real-time diagnostics of the position of medical needles (0.63 mm and 0.7 mm in diameter) inside blood vessel models (1.6 mm and 2.4 mm in diameter). Frame rate was 10 Hz. High longitudinal spatial resolution of the system - 0.1 mm - allows distinguishing the two walls of the vessel model and the position of the needle inside.

Adaptive Kinematic Control of a Robotic Venipuncture Device Based on Stereo Vision, Ultrasound, and Force Guidance

Robotic systems have slowly entered the realm of modern medicine; however, outside the operating room, medical robotics has yet to be translated to more routine interventions such as blood sampling or intravenous fluid delivery. In this paper, we present a medical robot that safely and rapidly cannulates peripheral blood vessels-a procedure commonly known as venipuncture. The device uses near-infrared and ultrasound imaging to scan and select suitable injection sites, and a 9-DOF robot to insert the needle into the center of the vessel based on image and force guidance. We first present the system design and visual servoing scheme of the latest generation robot, and then evaluate the performance of the device through workspace simulations and free-space positioning tests. Finally, we perform a series of motion tracking experiments using stereo vision, ultrasound, and force sensing to guide the position and orientation of the needle tip. Positioning experiments indicate sub-millimeter accuracy and repeatability over the operating workspace of the system, while tracking studies demonstrate real-time needle servoing in response to moving targets. Lastly, robotic phantom cannulations demonstrate the use of multiple system states to confirm that the needle has reached the center of the vessel.

Augmented reality based real-time subcutaneous vein imaging system

A novel 3D reconstruction and fast imaging system for subcutaneous veins by augmented reality is presented. The study was performed to reduce the failure rate and time required in intravenous injection by providing augmented vein structures that back-project superimposed veins on the skin surface of the hand. Images of the subcutaneous vein are captured by two industrial cameras with extra reflective near-infrared lights. The veins are then segmented by a multiple-feature clustering method. Vein structures captured by the two cameras are matched and reconstructed based on the epipolar constraint and homographic property. The skin surface is reconstructed by active structured light with spatial encoding values and fusion displayed with the reconstructed vein. The vein and skin surface are both reconstructed in the 3D space. Results show that the structures can be precisely back-projected to the back of the hand for further augmented display and visualization. The overall system performance is evaluated in terms of vein segmentation, accuracy of vein matching, feature points distance error, duration times, accuracy of skin reconstruction, and augmented display. All experiments are validated with sets of real vein data. The imaging and augmented system produces good imaging and augmented reality results with high speed.

Real-time Needle Steering in Response to Rolling Vein Deformation by a 9-DOF Image-Guided Autonomous Venipuncture Robot

Venipuncture is the most common invasive medical procedure performed in the United States and the number one cause of hospital injury. Failure rates are particularly high in pediatric and elderly patients, whose veins tend to deform, move, or roll as the needle is introduced. To improve venipuncture accuracy in challenging patient populations, we have developed a portable device that autonomously servos a needle into a suitable vein under image guidance. The device operates in real time, combining near-infrared and ultrasound imaging, computer vision software, and a 9 degrees-of-freedom robot that servos the needle. In this paper, we present the kinematic and mechanical design of the latest generation robot. We then investigate in silico and in vitro the mechanics of vessel rolling and deformation in response to needle insertions performed by the robot. Finally, we demonstrate how the robot can make real-time adjustments under ultrasound image guidance to compensate for subtle vessel motions during venipuncture.

The System Design and Evaluation of a 7-DOF Image-Guided Venipuncture Robot

Accessing the venous bloodstream to deliver fluids or obtain a blood sample is the most common clinical routine practiced in the U.S. Practitioners continue to rely on manual venipuncture techniques, but success rates are heavily dependent on clinician skill and patient physiology. In the U.S., failure rates can be as high as 50% in difficult patients, making venipuncture the leading cause of medical injury. To improve the rate of first-stick success, we have developed a portable autonomous venipuncture device that robotically servos a needle into a suitable vein under image guidance. The device operates in real time, combining near-infrared and ultra-sound imaging, image analysis, and a 7-degree-of-freedom (DOF) robotic system to perform the venipuncture. The robot consists of a 3-DOF gantry to image the patient's peripheral forearm veins and a miniaturized 4-DOF serial arm to guide the cannula into the selected vein under closed-loop control. In this paper, we present the system architecture of the robot and evaluate the accuracy and precision through tracking, free-space positioning, and in vitro phantom cannulation experiments. The results demonstrate sub-millimeter accuracy throughout the operating workspace of the manipulator and a high rate of success when cannulating phantom veins in a skin-mimicking tissue model.