Search

Chemogenomics, also known as proteochemometrics, covers various computational methods for predicting interactions between related drugs and targets on large-scale data. Chemogenomics is used in the early stages of drug discovery to predict the off-target effects of proteins against therapeutic candidates. This study aims to predict unknown ligand–target interactions using one-dimensional SMILES as inputs for ligands and binding site residues for proteins in a computationally efficient manner. We first formulate a Deep learning CNN model using one-dimensional SMILES for drugs and motif-rich binding pocket subsequences of proteins as inputs. We evaluate and compare the proposed deep learning model trained on expert-based features against shallow feature-based machine learning methods. The proposed method achieved better or similar performance on the MSE and AUPR metrics than the shallow methods. Additionally, We show that our deep learning model, DeepPS is computationally more efficient than the deep learning model trained on full-length raw sequences of proteins. We conclude that a beneficial research approach would be to integrate structural information of proteins for modeling drug-target interaction prediction of large datasets for more interpretability, high throughput, and broad applicability. Graphical abstract

Purpose Conventional robotic ultrasound systems were utilized with patients in supine positions. Meanwhile, the limitation of the systems is that it is difficult to evacuate the patients in case of emergency (e.g., patient discomfort and system failure) because the patients are restricted between the robot system and bed. Therefore, we validated a feasibility study of seated-style echocardiography using a robot. Method Preliminary experiments were conducted to verify the following two points: (1) diagnostic image quality due to the sitting posture angle and (2) physical load due to the sitting posture angle. For reducing the physical burden, two unique mechanisms were incorporated into the system: (1) a leg pendulum base mechanism to reduce the load on the legs when the lateral bending angle increases, and (2) a roll angle division by a lumbar lateral bending and thoracic rotation mechanisms. Results Preliminary results demonstrated that adjusting the diagnostic posture angle allowed to obtain the views, including cardiac disease features, as in the conventional examination. The results also demonstrated that the body load reduction mechanism incorporated in the results could reduce the physical load in the seated echocardiography. Furthermore, this system was shown to provide greater safety and shorter evacuation times than conventional systems. Conclusion These results indicate that diagnostic echocardiographic images can be obtained by seated-style echocardiography. It was also suggested that the proposed system can reduce the physical load and guarantee a sense of safety and emergency evacuation. These results demonstrated the possibility of the usage of the seated-style echocardiography robot.

The aim of this study was to investigate why adults participate in summative eHealth evaluations, and whether their reasons for participating affect their (non-)use of eHealth. A questionnaire was distributed among adults (aged ≥ 18 years) who participated in a summative eHealth evaluation. This questionnaire focused on participants’ reason to enroll, their expectations, and on whether the study met their expectations. Answers to open-ended questions were coded by two researchers independently. With the generalized estimating equations method we tested whether there is a difference between the type of reasons in use of the eHealth service. One hundred and thirty-one adults participated (64.9% female; mean age 62.5 years (SD = 10.5)). Their reasons for participating were mainly health-related (e.g., being more active). Between two types of motivations there was a difference in the use of the eHealth service: Participants with an intellectual motivation were more likely to drop out, compared to participants with an altruistic motivation. The most prevalent expectations when joining a summative eHealth evaluation were health-related (like expecting to improve one’s health). 38.6% of the participants said their expectation was fulfilled by the study. In conclusion, We encourage eHealth evaluators to learn about adults’ motivation to participate in their summative evaluation, as this motivation is very likely to affect their results. Including altruistically motivated participants biases the results by their tendency to continue participating in a study.

Despite the advances in modern medicine, the use of data-driven technologies (DDTs) to prevent surgical site infections (SSIs) remains a major challenge. Scholars recognise that data management is the next frontier in infection prevention, but many aspects related to the benefits and advantages of using DDTs to mitigate SSI risk factors remain unclear and underexplored in the literature. This study explores how DDTs enable value creation in the prevention of SSIs. This study follows a systematic literature review approach and the PRISMA statement to analyse peer-reviewed articles from seven databases. Fifty-nine articles were included in the review and were analysed through a descriptive and a thematic analysis. The findings suggest a growing interest in DDTs in SSI prevention in the last 5 years, and that machine learning and smartphone applications are widely used in SSI prevention. DDTs are mainly applied to prevent SSIs in clean and clean-contaminated surgeries and often used to manage patient-related data in the postoperative stage. DDTs enable the creation of nine categories of value that are classified in four dimensions: cost/sacrifice, functional/instrumental, experiential/hedonic, and symbolic/expressive. This study offers a unique and systematic overview of the value creation aspects enabled by DDT applications in SSI prevention and suggests that additional research is needed in four areas: value co-creation and product-service systems, DDTs in contaminated and dirty surgeries, data legitimation and explainability, and data-driven interventions.

The tumor resection ratio must be improved due the increased possibility of recurrence or malignancy. The purpose of this study was to develop a system that includes forceps with a continuous suction function and flow cytometry to diagnose the malignancy of the tumor for safe, accurate, and effective surgery. A newly developed continuous tumor resection forceps consists of a triple pipe structure, which enables continuous suction of the tumor by integrating the reflux water and suction system. The forceps includes tip opening/closure detection switch to control the adsorption and suction strength when tip is opened and closed. To perform accurate tumor diagnosis using flow cytometry, a filtering mechanism was developed for dehydrating reflux water from continuous suction forceps. In addition, a cell isolation mechanism comprising a roller pump and shear force loading mechanism was also newly developed. By using a triple pipe structure, a significantly larger tumor collection ratio was observed compared to the previous double-pipe structure. By performing suction pressure control with the opening/closure detection switch, inaccurate suction can be prevented. By widening the filter area of dehydration mechanism, it was possible to improve the reflux water dehydration ratio. The most appropriate filter area was 85 mm2. By using a newly developed cell isolation mechanism, the processing time can be reduced to less than 1/10 of the original time, keeping the same cell isolation ratio, when compared to the existing pipetting method. Neurosurgery assistance system with continuous tumor resection forceps and a cell separation, dehydration and isolation mechanism was developed. An effective and safe tumor resection, accurate and fast diagnosis of malignancy can be achieved by using the current system.

Purpose: This study intended to determine, and non-invasively evaluate, sternal intraosseous oxygen saturation (SsO2) and study its variation during provoked hypoxia or hypovolaemia. Furthermore, the relation between SsO2 and arterial (SaO2) or mixed venous oxygen saturation (SvO2) was investigated. Methods: Sixteen anaesthetised male pigs underwent exsanguination to a mean arterial pressure of 50 mmHg. After resuscitation and stabilisation, hypoxia was induced with hypoxic gas mixtures (air/N2). Repeated blood samples from sternal intraosseous cannulation were compared to arterial and pulmonary artery blood samples. Reflection spectrophotometry measurements by a non-invasive sternal probe were performed continuously. Results: At baseline SaO2 was 97.0% (IQR 0.2), SsO2 73.2% (IQR 19.6) and SvO2 52.3% (IQR 12.4). During hypovolaemia, SsO2 and SvO2 decreased to 58.9% (IQR 16.9) and 38.1% (IQR 12.5), respectively, p 2 remained unaltered (p = 0.44). During hypoxia all saturations decreased; SaO2 71.5% (IQR 5.2), SsO2 39.0% (IQR 6.9) and SvO2 22.6% (IQR 11.4) (p 2 relate well with changes in SvO2 during hypovolaemia or hypoxia. Further studies on the feasibility of using non-invasive measurement of changes in SsO2 to estimate changes in SvO2 are warranted.

Purpose Artificial intelligence in computer vision has been increasingly adapted in clinical application since the implementation of neural networks, potentially providing incremental information beyond the mere detection of pathology. As its algorithmic approach propagates input variation, neural networks could be used to identify and evaluate relevant image features. In this study, we introduce a basic dataset structure and demonstrate a pertaining use case. Methods A multidimensional classification of ankle x-rays (n = 1493) rating a variety of features including fracture certainty was used to confirm its usability for separating input variations. We trained a customized neural network on the task of fracture detection using a state-of-the-art preprocessing and training protocol. By grouping the radiographs into subsets according to their image features, the influence of selected features on model performance was evaluated via selective training. Results The models trained on our dataset outperformed most comparable models of current literature with an ROC AUC of 0.943. Excluding ankle x-rays with signs of surgery improved fracture classification performance (AUC 0.955), while limiting the training set to only healthy ankles with and without fracture had no consistent effect. Conclusion Using multiclass datasets and comparing model performance, we were able to demonstrate signs of surgery as a confounding factor, which, following elimination, improved our model. Also eliminating pathologies other than fracture in contrast had no effect on model performance, suggesting a beneficial influence of feature variability for robust model training. Thus, multiclass datasets allow for evaluation of distinct image features, deepening our understanding of pathology imaging.

Purpose There is a growing interest in minimally invasive surgery as interventional radiology (IVR), which decreases the burden on a patient. However, occupational exposure is a problem because the treatment is performed using X-ray fluoroscopic images. This problem can be solved by the development of a teleoperation system, but rapid force presentation is important to perform safe surgery. The purpose of this study is to develop a new teleoperation system that can be controlled at a high speed and can provide feedback force sensation within 20 ms delay. Methods A master–slave-type remote-control system for catheterization was developed. A compact and high-speed force feedback system is realized using a novel electro-attractive material (EAM) device by which the resistance force is generated by the magnitude of the voltage applied. The linear and rotational movement of master is transferred to the slave device by UDP communication with the LAN cable, and the same movement is performed by two motors. The collision force of catheter or guidewire, detected by the sensor inside the slave device, is also transmitted to the master device. Two voltage-based methods for EAM: the ON/OFF and linear control methods, were implemented. Results After the collision force is detected by the slave sensor, the voltage is applied to the EAM in the master device for an average of 10.33 ms and 15.64 ms by the ON/OFF and linear control methods, respectively. These delays are less than required 20 ms. The movement of the master was stopped by the resistance force of EAM, and that of the slave was also stopped accordingly. Conclusion A master–slave-type remote-control system for catheterization that is capable of high-speed force feedback was developed. With a low delay, the developed system achieved the requirements of 20 ms that was aimed for this study. Therefore, this system may facilitate the realization of IVR surgery that is safe for both doctors and patients.

Purpose 7T time-of-flight (TOF) MRI provides high resolution for the evaluation of cerebrovascular vessels and pathologies. In combination with 4D flow fields acquired with phase-contrast (PC) MRI, hemodynamic information can be extracted to enhance the analysis by providing direct measurements in the larger arteries or patient-specific boundary conditions. Hence, a registration between both modalities is required. Methods To combine TOF and PC-MRI data, we developed a hybrid registration approach. Vessels and their centerlines are segmented from the TOF data. The centerline is fit to the intensity ridges of the lower resolved PC-MRI data, which provides temporal information. We used a metric that utilizes a scaled sum of weighted intensities and gradients on the normal plane. The registration is then guided by decoupled local affine transformations. It is applied hierarchically following the branching order of the vessel tree. Results A landmark validation over Monte Carlo simulations yielded an average mean squared error of 184.73 mm and an average Hausdorff distance of 15.20 mm. The hierarchical traversal that transforms child vessels with their parents registers even small vessels not detectable in the PC-MRI. Conclusion The presented work combines high-resolution tomographic information from 7T TOF-MRI and measured flow data from 4D 7T PC-MRI scan for the arteries of the brain. This enables usage of patient-specific flow parameters for realistic simulations, thus supporting research in areas such as cerebral small vessel disease. Automatization and free deformations can help address the limiting error measures in the future.

Purpose: Surgery scene understanding with tool-tissue interaction recognition and automatic report generation can play an important role in intra-operative guidance, decision-making and postoperative analysis in robotic surgery. However, domain shifts between different surgeries with inter and intra-patient variation and novel instruments' appearance degrade the performance of model prediction. Moreover, it requires output from multiple models, which can be computationally expensive and affect real-time performance. Methodology: A multi-task learning (MTL) model is proposed for surgical report generation and tool-tissue interaction prediction that deals with domain shift problems. The model forms of shared feature extractor, mesh-transformer branch for captioning and graph attention branch for tool-tissue interaction prediction. The shared feature extractor employs class incremental contrastive learning (CICL) to tackle intensity shift and novel class appearance in the target domain. We design Laplacian of Gaussian (LoG) based curriculum learning into both shared and task-specific branches to enhance model learning. We incorporate a task-aware asynchronous MTL optimization technique to fine-tune the shared weights and converge both tasks optimally. Results: The proposed MTL model trained using task-aware optimization and fine-tuning techniques reported a balanced performance (BLEU score of 0.4049 for scene captioning and accuracy of 0.3508 for interaction detection) for both tasks on the target domain and performed on-par with single-task models in domain adaptation. Conclusion: The proposed multi-task model was able to adapt to domain shifts, incorporate novel instruments in the target domain, and perform tool-tissue interaction detection and report generation on par with single-task models., Comment: Manuscript accepted in the International Journal of Computer Assisted Radiology and Surgery. codes available: https://github.com/lalithjets/Domain-adaptation-in-MTL

Retzius-sparing robot-assisted radical prostatectomy (RS-RARP) has emerged as a surgical option for patients with prostatic cancer in high-volume centers. The objective is to assess oncological and functional outcomes when implementing RS-RARP in a medium-volume center without previous experience of robotic surgery. This is a prospective observational single-center study. Patients operated between July 2017 and April 2020 were divided into two consecutive groups, A and B, each with 104 patients. The surgeons had prior experience in laparoscopic surgery and underwent robotic training. Positive surgical margin (PSM) status, urinary continence, and erectile function projected by Kaplan–Meier curves, together with patient reported quality of life outcomes at 12 months post-surgery were documented. Median patient age was 63 years (IQR = 59–67), overall PSM rate were 33%, 28% for pT2 disease. Pre-operative values showed no significant difference between both groups. The rate of urinary continence dropped from 81 to 78% (SE = 5.7) (Group A) and from 90 to 72% (SE = 6.3) (Group B) using the International Consultation on Incontinence Questionnaire-Short Form. Baseline sexual function was regained in 41% (Group A) and 47% (Group B) of patients. The median Expanded Prostate Index Composite-26 total score decreased from 86 to 82. These outcomes relate favorably to prior reports. There was a clinically significant decrease in median operative time in the successive groups with post-operative complications occurring in less than 2% of surgical procedures overall. A 12-month follow-up suggests that RS-RARP may be safely introduced in a medium-volume center without previous experience of robotic surgery.

Background The application of Enhanced Recovery After Surgery (ERAS) protocol in gastrointestinal surgery has been widely accepted. The aim of this study was to compare the effect of ERAS in total robotic distal gastrectomy (TRDG) versus 3D total laparoscopic distal gastrectomy (3D-TLDG) for gastric cancer. Methods We retrospectively evaluated 73 patients underwent TRDG and 163 patients who received 3D-TLDG. The propensity score was used for matching analysis according to a 1:1 ratio, so that there was no significant difference in the baseline data between the two groups. The short-term effect and safety of the two groups were compared. Results The TRDG group had a less intraoperative bleeding (30.21 ± 13.78 vs. 41.44 ± 17.41 ml, P P P P = 0.007), shorter postoperative anal exhaust time (1.78 ± 0.79 vs. 2.18 ± 0.79 days, P = 0.003), shorter postoperative hospital stay (7.74 ± 3.15 vs. 9.97 ± 3.23 days, P P = 0.006) and higher hospitalization cost (89,907.15 ± 17,147.19 vs. 125,615.82 ± 11,900.80 RMB, P Conclusion TRDG and 3D-TLDG under ERAS protocol are safe and feasible. Compared with 3D-TLDG, the TRDG has better intraoperative bleeding control effect and greater advantages in digestive tract reconstruction. After the combination of ERAS protocol, TRDG also has certain advantages in the recovery process of patients after surgery.

Background As volatile anaesthetic gases contribute to global warming, improving the efficiency of their delivery can reduce their environmental impact. This can be achieved by rebreathing from a circle system, but also by anaesthetic reflection with an open intensive care ventilator. We investigated whether the efficiency of such a reflection system could be increased by warming the reflector during inspiration and cooling it during expiration (thermocycling). Methods The Sedaconda-ACD-S (Sedana Medical, Danderyd, Sweden) was connected between an intensive care ventilator and a test lung. Liquid isoflurane was infused into the device at 0.5, 1.0, 2.0 and 5.0 mL/h; ventilator settings were 500 mL tidal volume, 12 bpm, 21% oxygen. Isoflurane concentrations were measured inside the test lung after equilibration. Thermocycling was achieved by heating the breathing gas in the inspiratory hose to 37 °C via a heated humidifier without water. Breathing gas expired from the test lung was cooled to 14 °C before reaching the ACD-S. In the test lung, body temperature pressure saturated conditions prevailed. Isoflurane concentrations and reflective efficiency were compared between thermocycling and control conditions. Results With thermocycling higher isoflurane concentrations in the test lung were measured for all infusion rates studied. Interpolation of data showed that for achieving 0.4 (0.6) Vol% isoflurane, the infusion rate can be reduced from 1.2 to 0.7 (2.0 to 1.2) mL/h or else to 56% (58%) of control. Conclusion Thermocycling of the anaesthetic gas considerably increases the efficiency of the anaesthetic reflector and reduces anaesthetic consumption by almost half in a test lung model. Given that cooling can be miniaturized, this method carries a potential for further saving anaesthetics in clinical practice in the operating theatre as well as for inhaled sedation in the ICU.

The Japan Society of Gynecologic and Obstetric Endoscopy and Minimally Invasive Therapy (JSGOE) introduced a system for the certification of laparoscopic surgeons in 2002 and a system for the certification of facilities in 2014. We examined the opinions of the members of the Japan Society of Gynecologic and Obstetric Endoscopy and Minimally Invasive Therapy (JSGOE) regarding the necessity of a certification training system and a technical certification system for robotic surgery skills in Japan. Members of the JSGOE were surveyed with two questionnaires. Overall, 870 and 519 participants responded to the first and second questionnaires, respectively. Half of the respondents indicated that both systems were necessary. The breakdown by age and qualifications showed that this was especially true for the younger generation and respondents with more experience with robotic surgery. Overall, 40% of the respondents judged that a certification system for robotic surgery alone (with or without certification in laparoscopic surgery but with a requirement of experience in laparoscopic surgery) would be necessary. The opinions of the JSGOE members on making a certification system for robotic surgery were split into two clear-cut camps. Thus, we must further seek the extent of public demand for using a public survey so that a final decision can be made on whether to establish this system.

Accurate segregation of retinal blood vessels network plays a crucial role in clinical assessments, treatments, and rehabilitation process. Owing to the presence of acquisition and instrumentation anomalies, precise tracking of vessels network is challenging. For this, a new fundus image segmentation framework is proposed by combining deep neural networks, and hidden Markov model. It has three main modules: the Atrous spatial pyramid pooling-based encoder, the decoder, and hidden Markov model vessel tracker. The encoder utilized modified ResNet18 deep neural networks model for low-and-high-levels features extraction. These features are concatenated in module-II by the decoder to perform convolution operations to obtain the initial segmentation. Previous modules detected the main vessel structure and overlooked some small capillaries. For improved segmentation, hidden Markov model vessel tracker is integrated with module-I and-II to detect overlooked small capillaries of the vessels network. In last module, final segmentation is obtained by combining multi-oriented sub-images using logical OR operation. This novel framework is validated experimentally using two standard DRIVE and STARE datasets. The developed model offers high average values of accuracy, area under the curve, and sensitivity of 99.8, 99.0, and 98.2%, respectively. Analysis of the results revealed that the developed approach offered enhanced performance in terms of sensitivity 18%, accuracy 3%, and specificity 1% over the state-of-the-art approaches. Owing to better learning and generalization capability, the developed approach tracked blood vessels network efficiently and automatically compared to other approaches. The proposed approach can be helpful for human eye assessment, disease diagnosis, and rehabilitation process.

The optimization of positive end-expiratory pressure (PEEP) according to respiratory mechanics [driving pressure or respiratory system compliance (Crs)] is a simple and straightforward strategy. However, its validity to prevent postoperative pulmonary complications (PPCs) remains unclear. Here, we performed a meta-analysis to assess such efficacy. We searched PubMed, Embase, and the Cochrane Library to identify randomized controlled trials (RCTs) that compared personalized PEEP based on respiratory mechanics and constant PEEP to prevent PPCs in adults. The primary outcome was PPCs. Fourteen studies with 1105 patients were included. Compared with those who received constant PEEP, patients who received optimized PEEP exhibited a significant reduction in the incidence of PPCs (RR = 0.54, 95% CI 0.42 to 0.69). The results of commonly happened PPCs (pulmonary infections, hypoxemia, and atelectasis but not pleural effusion) also supported individualized PEEP group. Moreover, the application of PEEP based on respiratory mechanics improved intraoperative respiratory mechanics (driving pressure and Crs) and oxygenation. The PEEP titration method based on respiratory mechanics seems to work positively for lung protection in surgical patients undergoing general anesthesia.

Multiple medical imaging modalities are used for clinical follow-up ischemic stroke analysis. Mixed-modality datasets are challenging, both for clinical rating purposes and for training machine learning models. While image-to-image translation methods have been applied to harmonize stroke patient images to a single modality, they have only been used for paired data so far. In the more common unpaired scenario, the standard cycle-consistent generative adversarial network (CycleGAN) method is not able to translate the stroke lesions properly. Thus, the aim of this work was to develop and evaluate a novel image-to-image translation regularization approach for unpaired 3D follow-up stroke patient datasets.A modified CycleGAN was used to translate images between 238 non-contrast computed tomography (NCCT) and 244 fluid-attenuated inversion recovery (FLAIR) MRI datasets, two of the most relevant follow-up modalities in clinical practice. We introduced an additional attention-guided mechanism to encourage an improved translation of the lesion and a gradient-consistency loss to preserve structural brain morphology.The proposed modifications were able to preserve the overall quality provided by the CycleGAN translation. This was confirmed by the FID score and gradient correlation results. Furthermore, the lesion preservation was significantly improved compared to a standard CycleGAN. This was evaluated for location and volume with segmentation models, which were trained on real datasets and applied to the translated test images. Here, the Dice score coefficient resulted in 0.81 and 0.62 for datasets translated to FLAIR and NCCT, respectively, compared to 0.57 and 0.50 for the corresponding datasets translated using a standard CycleGAN. Finally, an analysis of the distribution of mean lesion intensities showed substantial improvements.The results of this work show that the proposed image-to-image translation method is effective at preserving stroke lesions in unpaired modality translation, supporting its potential as a tool for stroke image analysis in real-life scenarios.

This prospective method comparison study compared cerebral oxygen saturation (ScO

Different organs have different autoregulatory capacities for blood pressure changes and/or circulatory volume changes. This study assessed the autoregulation of the stomach, liver, kidney and skeletal muscle, under baseline, hypovolemic, and post-fluid-resuscitation conditions using near-infrared spectroscopy (NIRS).Ten pigs (bodyweight 24.5 ± 0.5 kg) were anesthetized with 2.5% isoflurane and administered 0.5, 1, 2 and 5 µg kgBased on the evaluation using each TOI as a substitute of blood flow, the kidney autoregulation was robust, similar to muscle, but had a prominent lower limit. The stomach had weaker autoregulation than the kidney and muscle. The liver had no autoregulation. The kidney TOI showed 2-fold greater changes in response to volume condition changes than the stomach and liver TOIs.In our NIRS-based assessment of autoregulatory capacity, the liver oxygenation is highly blood pressure dependent, and the kidney is highly susceptible and the skeletal muscle is highly tolerable to low blood pressure and volume loss.

Acute respiratory distress syndrome (ARDS) caused by multilobar pneumonia (MLP) is markedly different from typical ARDS in pathology, imaging characteristics, and lung mechanics. Regional lung assessment is required. We aimed to analyze the relationship between two regional assessment tools, lung ultrasound (LUS) and electrical impedance tomography (EIT) during positive end-expiratory pressure (PEEP) titration, and determine an appropriate PEEP level. We conducted a prospective study of patients with ARDS caused by MLP with PaO

Volatile anaesthetics are potent greenhouse gasses but contemporary workstations enable considerable savings while improving patient safety. Institutions may provide this technology to reduce the ecological footprint but proper training and motivation is required to maximize their ecologic and financial benefit. This study aims to compare the sevoflurane consumption of 22 anaesthesiologists in a medium sized hospital 4 years after flow-i workstations (Getinge, Sweden) entered into service, in three airway approaches: intubated patients, laryngeal mask ventilation, and mask anaesthesia. Typical sevoflurane consumption for each anaesthesiologist was defined as the mean cumulative consumption in the chronologically first 50 cases meeting the inclusion criteria for each airway group in 2019. The potential savings, if everyone were to adopt the approach of the more economical anaesthesiologists (15th percentile), was calculated. The CO

The robotic platform can overcome technical difficulties associated with laparoscopic colon surgery. Transitioning from laparoscopic right colectomy with extracorporeal anastomosis (ECA) to robotic right colectomy with intracorporeal anastomosis (ICA) is associated with a learning phase. This study aimed at determining the length of this learning phase and its associated morbidity. We retrospectively analyzed all laparoscopic right colectomies with ECA (n = 38) and robotic right colectomies with ICA (n = 67) for (pre)malignant lesions performed by a single surgeon between January 2014 and December 2020. CUSUM-plot analysis of total procedure time was used for learning curve determination of robotic colectomies. Non-parametric tests were used for statistical analysis. Compared to laparoscopy, the learning phase robotic right colectomies (n = 35) had longer procedure times (p

Automatic surgical workflow recognition enabled by computer vision algorithms plays a key role in enhancing the learning experience of surgeons. It also supports building context-aware systems that allow better surgical planning and decision making which may in turn improve outcomes. Utilizing temporal information is crucial for recognizing context; hence, various recent approaches use recurrent neural networks or transformers to recognize actions.We design and implement a two-stage method for surgical workflow recognition. We utilize R(2+1)D for video clip modeling in the first stage. We propose Action Segmentation Temporal Convolutional Transformer (ASTCFormer) network for full video modeling in the second stage. ASTCFormer utilizes action segmentation transformers (ASFormers) and temporal convolutional networks (TCNs) to build a temporally aware surgical workflow recognition system.We compare the proposed ASTCFormer with recurrent neural networks, multi-stage TCN, and ASFormer approaches. The comparison is done on a dataset comprised of 207 robotic and laparoscopic cholecystectomy surgical videos annotated for 7 surgical phases. The proposed method outperforms the compared methods achieving a [Formula: see text] relative improvement in the average segmental F1-score over the state-of-the-art ASFormer method. Moreover, our proposed method achieves state-of-the-art results on the publicly available Cholec80 dataset.The improvement in the results when using the proposed method suggests that temporal context could be better captured when adding information from TCN to the ASFormer paradigm. This addition leads to better surgical workflow recognition.

To determine the experiences of perioperative nurses with robotic-assisted surgery is needed to improve the robotic-assisted surgery practices. This study systematically reviewed and analysed the qualitative studies concerning perioperative nurses' experiences of robotic-assisted surgery. This systematic literature review included studies up to December 2020. The study data were analysed using inductive content analysis. This systematic review included six articles. There were a total of 71 nurses who participated in the included articles (min = 6, max = 17). Their mean age was 35.7, and their experience in robotic-assisted surgery ranged from 8 months to 10 years. Content analysis generated six categories: adaptation to robotic-assisted surgery technology, the importance of teamwork in robotic-assisted surgery, changing tasks and responsibilities in robotic-assisted surgery, training requirements for robotic-assisted surgery, the effects of robotic-assisted surgery on patients and patient safety, and difficulties with robotic-assisted surgery. A variety of themes and sub-themes emerged in these categories. The review highlights the importance of developing new ways of thinking about the assessment and management of disruptions, developing different teamwork patterns and communication skills, and overcoming the challenges involved in technologically advanced surgeries. Nurses' roles in robotic technology should be redefined in healthcare. Nurses should learn how to adapt to advancing technology and how to supplement and enhance their skills.

With global expansion of robotic surgery, there is increasing interest in its application in colonic surgery. This study aimed to report the feasibility of robotic assisted colonic resection as a post hoc analysis of a randomised controlled trial (RCT) by comparing outcomes following laparoscopic and robotic colectomy. The PAROS trial was a phase III RCT that compared outcomes in low pressure (LP, 7 mmHg) and standard pressure (SP, 12 mmHg) pneumoperitoneum in elective colectomy. A post hoc analysis was performed to compare clinical and operative outcomes in laparoscopic and robotic colonic resection in a high volume colorectal surgery practice. A health economic comparison was also performed. Data were analysed using IBM SPSS Statistics

Video-based instructional tools are an important emerging component of robotic surgical education. However, there is a paucity of literature on the structure of video as an instructional tool in robotic surgery. This paper reviews the literature on video-based instructional tools and provides a series of recommendations for the structure of a video- based training tool in robotic surgery. Key educational aspects to consider in designing a video training tool are student engagement, content validity, cognitive load, and active learning. Key recommendations for structure of instructional videos are that videos should be short, presented in modular blocks with appropriate narration and engagement strategies.

BackgroundThere has been widespread adoption of robotic total mesorectal excision (TME) for rectal cancer in recent years. There is now increasing interest in training robotic novice surgeons in robotic TME surgery using the principles of component-based learning. The aims of our study were to assess the feasibility of delivering a structured, parallel, component-based, training curriculum to surgical trainees and fellows. MethodsA prospective pilot study was undertaken between January 2021 and May 2021. A dedicated robotic training pathway was designed with two trainees trained in parallel per each robotic case based on prior experience, training grade and skill set. Component parts of each operation were allocated by the robotic trainer prior to the start of each case. Robotic proficiency was assessed using the Global Evaluative Assessment of Robotic Skills (GEARS) and the EARCS Global Assessment Score (GAS). Results Three trainees participated in this pilot study; performing a combined number of 52 TME resections. Key components of all 52 TME operations were performed by the trainees. GEARS scores improved throughout the study, with a mean overall baseline score of 17.3 (95% CI 15.1 – 1.4) compared to an overall final assessment mean score of 23.8 (95% CI 21.6 – 25.9), p=0.003. The GAS component improved incrementally for all trainees at each candidate assessment (pConclusion Employing a parallel, component-based approach to training in robotic TME surgery is safe and feasible and can be used to train multiple trainees of differing grades simultaneously, whilst maintaining high quality clinical outcomes.

Objective To determine the impact of enhanced recovery after surgery (ERAS) pathway implementation on outcomes and cost of robotic- and video-assisted thoracoscopic (RATS and VATS) lobectomy. Methods Retrospective review of 116 consecutive VATS and RATS lobectomies in the pre-ERAS (Oct 2018-Sep 2019) and ERAS (Oct 2019-Sep 2020) period. Multivariate analysis was used to determine the impact of ERAS and operative approach alone, and in combination, on length of hospital stay (LOS) and overall cost. Results Operative approach was 49.1% VATS, 50.9% RATS, with 44.8% pre-ERAS, and 55.2% ERAS (median age 68, 65.5% female). ERAS patients had shorter LOS (2.22 vs 3.45 days) and decreased total-cost ($15,022 vs $20,155) compared with non-ERAS patients, while RATS was associated with decreased LOS (2.16 vs 4.19 days) and decreased total-cost ($14,729 vs $20,484) compared with VATS. The combination of ERAS + RATS showed the shortest LOS and the lowest total-cost (1.35 days and $13,588, p

Purpose: The adjustment of medical devices in the operating room is currently done by the circulating nurses. As digital interfaces for the devices are not foreseeable in the near future and to incorporate legacy devices, the robotic operation of medical devices is an open topic. Methods: We propose a teleoperated learning from demonstration process to acquire the high-level device functionality with given motion primitives. The proposed system is validated using an insufflator as an exemplary medical device. Results: At the beginning of the proposed learning period, the teacher annotates the user interface to obtain the outline of the medical device. During the demonstrated interactions, the system observes the state change of the device to generalize logical rules describing the internal functionality. The combination of the internal logics with the interface annotations enable the robotic system to adjust the medical device autonomously. To interact with the device, a robotic manipulator with a finger-like end-effector is used while relying on haptic feedback from torque sensors. Conclusion: The proposed approach is a first step towards teaching a robotic system to operate medical devices. We aim at validating the system in an extensive user study with clinical personnel. The logical rule generalization and the logical rule inference based on computer vision methods will be focused in the future.

Laparoscopic surgery has demonstrated various advantages for the patients' care, but also presents some difficulties for the surgeons, such as kinematic restrictions. Robotic comanipulation, in which control of instruments is shared between the robot and the surgeon, can provide adaptative damping assistance which allows stabilisation of movements. The objective of the present study was to determine the contribution of this assistance on a bimanual laparoscopic task.Adaptative damping was studied on Peg Transfer task, performed by eighteen surgery-naive subjects. This exercise was repeated seven times without (Classic repetitions) and seven times with comanipulated robots (Robot repetitions), in a randomised order. We measured task performance, using Peg Transfer score; gesture performance, using hand oscillations and travelled distance; eye-tracking movements as an indicator of emergence of expertise. Participants' perceived workload was assessed by NASA TLX questionnaire, and difference in impression between the two conditions by UEQ questionnaire.Adaptative damping improved gesture performance (oscillations F(1,17) = 23.473, p 0.001, ηAssistance by adaptative damping applied by comanipulated robots improved gesture performance during a laparoscopic bimanual task, without impacting task's performance without allowing the emergence of comportments associated with an expertise, and at the cost of a high perceived workload. Further research should investigate this assistance on more precise and clinical tasks performed by professionals.

Bone identification and segmentation in X-ray images are crucial in orthopedics for the automation of clinical procedures, but it often involves some manual operations. In this work, using a modified SegNet neural network, we automatically identify and segment lower limb bone structures on radiographs presenting various fields of view and different patient orientations.A wide contextual neural network architecture is proposed to perform a high-quality pixel-wise semantic segmentation on X-ray images presenting structures with a similar appearance and strong superposition. The proposed architecture is based on the premise that every output pixel on the label map has a wide receptive field. This allows the network to capture both global and local contextual information. The overlapping between structures is handled with additional labels.The proposed approach was evaluated on a test dataset composed of 70 radiographs with entire and partial bones. We obtained an average detection rate of 98.00% and an average Dice coefficient of 95.25 ± 9.02% across all classes. For the challenging subset of images with high superposition, we obtained an average detection rate of 96.36% and an average Dice coefficient of 93.81 ± 10.03% across all classes.The results show the effectiveness of the proposed approach in segmenting and identifying lower limb bone structures and overlapping structures in radiographs with strong bone superposition and highly variable configurations, as well as in radiographs containing only small pieces of bone structures.

A foundational component of digital health involves collecting and leveraging electronic health data to improve health and wellbeing. One of the central technologies for collecting these data are electronic health records (EHRs). In this commentary, the authors explore intersection between digital health and data-driven reflective practice that is described, including an overview of the role of EHRs underpinning technology innovation in healthcare. Subsequently, they argue that EHRs are a rich but under-utilised source of information on the performance of health professionals and healthcare teams that could be harnessed to support reflective practice and behaviour change. EHRs currently act as systems of data collection, not systems of data engagement and reflection by end users such as health professionals and healthcare organisations. Further consideration should be given to supporting reflective practice by health professionals in the design of EHRs and other clinical information systems.