Artificial Intelligence Assistance Research Articles

Deep Neural Network Augments Performance of Junior Residents in Diagnosing COVID-19 Pneumonia on Chest Radiographs

Chest X-rays (CXRs) are essential in the preliminary radiographic assessment of patients affected by COVID-19. Junior residents, as the first point-of-contact in the diagnostic process, are expected to interpret these CXRs accurately. We aimed to assess the effectiveness of a deep neural network in distinguishing COVID-19 from other types of pneumonia, and to determine its potential contribution to improving the diagnostic precision of less experienced residents. A total of 5051 CXRs were utilized to develop and assess an artificial intelligence (AI) model capable of performing three-class classification, namely non-pneumonia, non-COVID-19 pneumonia, and COVID-19 pneumonia. Additionally, an external dataset comprising 500 distinct CXRs was examined by three junior residents with differing levels of training. The CXRs were evaluated both with and without AI assistance. The AI model demonstrated impressive performance, with an Area under the ROC Curve (AUC) of 0.9518 on the internal test set and 0.8594 on the external test set, which improves the AUC score of the current state-of-the-art algorithms by 1.25% and 4.26%, respectively. When assisted by the AI model, the performance of the junior residents improved in a manner that was inversely proportional to their level of training. Among the three junior residents, two showed significant improvement with the assistance of AI. This research highlights the novel development of an AI model for three-class CXR classification and its potential to augment junior residents' diagnostic accuracy, with validation on external data to demonstrate real-world applicability. In practical use, the AI model effectively supported junior residents in interpreting CXRs, boosting their confidence in diagnosis. While the AI model improved junior residents' performance, a decline in performance was observed on the external test compared to the internal test set. This suggests a domain shift between the patient dataset and the external dataset, highlighting the need for future research on test-time training domain adaptation to address this issue.

Deep learning based automatic detection algorithm for acute intracranial haemorrhage: a pivotal randomized clinical trial

Acute intracranial haemorrhage (AIH) is a potentially life-threatening emergency that requires prompt and accurate assessment and management. This study aims to develop and validate an artificial intelligence (AI) algorithm for diagnosing AIH using brain-computed tomography (CT) images. A retrospective, multi-reader, pivotal, crossover, randomised study was performed to validate the performance of an AI algorithm was trained using 104,666 slices from 3010 patients. Brain CT images (12,663 slices from 296 patients) were evaluated by nine reviewers belonging to one of the three subgroups (non-radiologist physicians, n = 3; board-certified radiologists, n = 3; and neuroradiologists, n = 3) with and without the aid of our AI algorithm. Sensitivity, specificity, and accuracy were compared between AI-unassisted and AI-assisted interpretations using the chi-square test. Brain CT interpretation with AI assistance results in significantly higher diagnostic accuracy than that without AI assistance (0.9703 vs. 0.9471, p < 0.0001, patient-wise). Among the three subgroups of reviewers, non-radiologist physicians demonstrate the greatest improvement in diagnostic accuracy for brain CT interpretation with AI assistance compared to that without AI assistance. For board-certified radiologists, the diagnostic accuracy for brain CT interpretation is significantly higher with AI assistance than without AI assistance. For neuroradiologists, although brain CT interpretation with AI assistance results in a trend for higher diagnostic accuracy compared to that without AI assistance, the difference does not reach statistical significance. For the detection of AIH, brain CT interpretation with AI assistance results in better diagnostic performance than that without AI assistance, with the most significant improvement observed for non-radiologist physicians.

Passive Type Reconfigurable Intelligent Surface: Measurement of Radiation Patterns

The demand for unprecedented data and ubiquitous wireless connections have led to the adoption of new types of transmitters and receivers. Additionally, different new types of devices and technologies need to be proposed for such demand. Reconfigurable intelligent surface (RIS) is going to play a very significant role in the upcoming beyond-5G/6G communications. It is envisioned that not only the RIS will be deployed to assist and create a smart wireless environment for the upcoming communications, but also the receiver and transmitter can be fabricated using RIS to make a smart and intelligent transmitter and receiver. Thus, the latency of upcoming communications can be reduced very significantly using RIS, which is a very important factor. Artificial intelligence assists communications and shall be adopted widely for the next generation networks. In this paper, radiation pattern measurement results of our previously published RIS have been provided. This work is the extension work of our previously proposed RIS. The polarization-independent passive type of RIS working in the sub-6 GHz frequency band using low-cost FR4-substrate was designed. Each unit cell with dimensions of 42 mm × 42 mm had a single-layer substrate backed by a copper plate. A 10 × 10-unit cell array was fabricated to check the performance of the RIS. Such types of unit cells and RIS were designed to set up initial measurement facilities in our laboratory for any kinds of RIS measurements.

Artificial intelligence-based model for lymph node metastases detection on whole slide images in bladder cancer: a retrospective, multicentre, diagnostic study.

Accurate lymph node staging is important for the diagnosis and treatment of patients with bladder cancer. We aimed to develop a lymph node metastases diagnostic model (LNMDM) on whole slide images and to assess the clinical effect of an artificial intelligence-assisted (AI) workflow. In this retrospective, multicentre, diagnostic study in China, we included consecutive patients with bladder cancer who had radical cystectomy and pelvic lymph node dissection, and from whom whole slide images of lymph node sections were available, for model development. We excluded patients with non-bladder cancer and concurrent surgery, or low-quality images. Patients from two hospitals (Sun Yat-sen Memorial Hospital of Sun Yat-sen University and Zhujiang Hospital of Southern Medical University, Guangzhou, Guangdong, China) were assigned before a cutoff date to a training set and after the date to internal validation sets for each hospital. Patients from three other hospitals (the Third Affiliated Hospital of Sun Yat-sen University, Nanfang Hospital of Southern Medical University, and the Third Affiliated Hospital of Southern Medical University, Guangzhou, Guangdong, China) were included as external validation sets. A validation subset of challenging cases from the five validation sets was used to compare performance between the LNMDM and pathologists, and two other datasets (breast cancer from the CAMELYON16 dataset and prostate cancer from the Sun Yat-sen Memorial Hospital of Sun Yat-sen University) were collected for a multi-cancer test. The primary endpoint was diagnostic sensitivity in the four prespecified groups (ie, the five validation sets, a single-lymph-node test set, the multi-cancer test set, and the subset for a performance comparison between the LNMDM and pathologists). Between Jan 1, 2013 and Dec 31, 2021, 1012 patients with bladder cancer had radical cystectomy and pelvic lymph node dissection and were included (8177 images and 20 954 lymph nodes). We excluded 14 patients (165 images) with concurrent non-bladder cancer and also excluded 21 low-quality images. We included 998 patients and 7991 images (881 [88%] men; 117 [12%] women; median age 64 years [IQR 56-72]; ethnicity data not available; 268 [27%] with lymph node metastases) to develop the LNMDM. The area under the curve (AUC) for accurate diagnosis of the LNMDM ranged from 0·978 (95% CI 0·960-0·996) to 0·998 (0·996-1·000) in the five validation sets. Performance comparisons between the LNMDM and pathologists showed that the diagnostic sensitivity of the model (0·983 [95% CI 0·941-0·998]) substantially exceeded that of both junior pathologists (0·906 [0·871-0·934]) and senior pathologists (0·947 [0·919-0·968]), and that AI assistance improved sensitivity for both junior (from 0·906 without AI to 0·953 with AI) and senior (from 0·947 to 0·986) pathologists. In the multi-cancer test, the LNMDM maintained an AUC of 0·943 (95% CI 0·918-0·969) in breast cancer images and 0·922 (0·884-0·960) in prostate cancer images. In 13 patients, the LNMDM detected tumour micrometastases that had been missed by pathologists who had previously classified these patients' results as negative. Receiver operating characteristic curves showed that the LNMDM would enable pathologists to exclude 80-92% of negative slides while maintaining 100% sensitivity in clinical application. We developed an AI-based diagnostic model that did well in detecting lymph node metastases, particularly micrometastases. The LNMDM showed substantial potential for clinical applications in improving the accuracy and efficiency of pathologists' work. National Natural Science Foundation of China, the Science and Technology Planning Project of Guangdong Province, the National Key Research and Development Programme of China, and the Guangdong Provincial Clinical Research Centre for Urological Diseases.

Connecting with Generation Z: Consumer Acceptance of the Use of Artificial Intelligence in Online Shopping

In the civilized era, artificial intelligence (AI) is the imitation of human intellectual functions by machines or computer systems. It is challenging for e-retailers to offer customised discounts despite the unlimited product selection in an online store at the same time, satisfy customers’ expectations while providing a distinctive customer experience. To provide clients with real experiences, recommendations and products must be tailored to their preferences and needs. Therefore, the purpose of this study was to ascertain whether generation Z consumers embrace the use of artificial intelligence (AI) in online buying. This study also aimed to provide recommendations and insights for SMEs to learn more about adopting AI that will enhance their online businesses. For this study, an online survey with quantitative approach is used and gathered 135 respondents. The data were examined by using SPSS version 25. The results of the correlation study showed that each component significantly increases the adoption of AI in online purchasing. The regression research showed that technology literacy has a negative impact on artificial intelligence (AI), while all independent factors (perceived utility, perceived ease of use, and trust) have significant positive impacts on AI (AI). The R² value of the study which is 0.364 indicated good model fit. Due to the AI assistant's constant availability, customers may ask simple questions and report minor difficulties at any time without having to wait for a response. The analysis of client data also helps the online retailer better understand its customers and emerging trends. Thus, advantages like enhanced usability and customisation that satisfy consumer needs and expectations strengthen customer loyalty and boost corporate revenues over the long run.

Artificial intelligence of digital morphology analyzers improves the efficiency of manual leukocyte differentiation of peripheral blood

Background and objectiveMorphological identification of peripheral leukocytes is a complex and time-consuming task, having especially high requirements for personnel expertise. This study is to investigate the role of artificial intelligence (AI) in assisting the manual leukocyte differentiation of peripheral blood.MethodsA total of 102 blood samples that triggered the review rules of hematology analyzers were enrolled. The peripheral blood smears were prepared and analyzed by Mindray MC-100i digital morphology analyzers. Two hundreds leukocytes were located and their cell images were collected. Two senior technologists labeled all cells to form standard answers. Afterward, the digital morphology analyzer unitized AI to pre-classify all cells. Ten junior and intermediate technologists were selected to review the cells with the AI pre-classification, yielding the AI-assisted classifications. Then the cell images were shuffled and re-classified without AI. The accuracy, sensitivity and specificity of the leukocyte differentiation with or without AI assistance were analyzed and compared. The time required for classification by each person was recorded.ResultsFor junior technologists, the accuracy of normal and abnormal leukocyte differentiation increased by 4.79% and 15.16% with the assistance of AI. And for intermediate technologists, the accuracy increased by 7.40% and 14.54% for normal and abnormal leukocyte differentiation, respectively. The sensitivity and specificity also significantly increased with the help of AI. In addition, the average time for each individual to classify each blood smear was shortened by 215 s with AI.ConclusionAI can assist laboratory technologists in the morphological differentiation of leukocytes. In particular, it can improve the sensitivity of abnormal leukocyte differentiation and lower the risk of missing detection of abnormal WBCs.

Optical Biopsy of Dysplasia in Barrett’s Oesophagus Assisted by Artificial Intelligence

Optical biopsy in Barrett's oesophagus (BE) using endocytoscopy (EC) could optimize endoscopic screening. However, the identification of dysplasia is challenging due to the complex interpretation of the highly detailed images. Therefore, we assessed whether using artificial intelligence (AI) as second assessor could help gastroenterologists in interpreting endocytoscopic BE images. First, we prospectively videotaped 52 BE patients with EC. Then we trained and tested the AI pm distinct datasets drawn from 83,277 frames, developed an endocytoscopic BE classification system, and designed online training and testing modules. We invited two successive cohorts for these online modules: 10 endoscopists to validate the classification system and 12 gastroenterologists to evaluate AI as second assessor by providing six of them with the option to request AI assistance. Training the endoscopists in the classification system established an improved sensitivity of 90.0% (+32.67%, p < 0.001) and an accuracy of 77.67% (+13.0%, p = 0.020) compared with the baseline. However, these values deteriorated at follow-up (-16.67%, p < 0.001 and -8.0%, p = 0.009). Contrastingly, AI-assisted gastroenterologists maintained high sensitivity and accuracy at follow-up, subsequently outperforming the unassisted gastroenterologists (+20.0%, p = 0.025 and +12.22%, p = 0.05). Thus, best diagnostic scores for the identification of dysplasia emerged through human-machine collaboration between trained gastroenterologists with AI as the second assessor. Therefore, AI could support clinical implementation of optical biopsies through EC.

Advances in flexible sensors for intelligent perception system enhanced by artificial intelligence

AbstractIntelligent perception means that with the assistance of artificial intelligence (AI)‐motivated brain, flexible sensors achieve the ability of memory, learning, judgment, and reasoning about external information like the human brain. Due to the superiority of machine learning (ML) algorithms in data processing and intelligent recognition, intelligent perception systems possess the ability to match or even surpass human perception systems. However, the built‐in flexible sensors in these systems need to work on dynamic and irregular surfaces, inevitably affecting the precision and fidelity of the acquired data. In recent years, the strategy of introducing the developed functional materials and innovative structures into flexible sensors has made some progress toward the above challenges, and with the blessing of ML algorithms, accurate perception and reasoning in various scenarios have been achieved. Here, the most representative functional materials and innovative structures for constructing flexible sensors are comprehensively reviewed, the research progress of intelligent perception systems based on flexible sensors and ML algorithms is further summarized, and the intersection of the two is expected to unlock new opportunities for next‐stage AI development.image

Artificial intelligence for assistance of radiology residents in chest CT evaluation for COVID-19 pneumonia: a comparative diagnostic accuracy study.

In hospitals, it is crucial to rule out coronavirus disease 2019 (COVID-19) timely and reliably. Artificial intelligence (AI) provides sufficient accuracy to identify chest computed tomography (CT) scans with signs of COVID-19. To compare the diagnostic accuracy of radiologists with different levels of experience with and without assistance of AI in CT evaluation for COVID-19 pneumonia and to develop an optimized diagnostic pathway. The retrospective, single-center, comparative case-control study included 160 consecutive participants who had undergone chest CT scan between March 2020 and May 2021 without or with confirmed diagnosis of COVID-19 pneumonia in a ratio of 1:3. Index tests were chest CT evaluation by five radiological senior residents, five junior residents, and an AI software. Based on the diagnostic accuracy in every group and on comparison of groups, a sequential CT assessment pathway was developed. Areas under receiver operating curves were 0.95 (95% confidence interval [CI]=0.88-0.99), 0.96 (95% CI=0.92-1.0), 0.77 (95% CI=0.68-0.86), and 0.95 (95% CI=0.9-1.0) for junior residents, senior residents, AI, and sequential CT assessment, respectively. Proportions of false negatives were 9%, 3%, 17%, and 2%, respectively. With the developed diagnostic pathway, junior residents evaluated all CT scans with the support of AI. Senior residents were only required as second readers in 26% (41/160) of the CT scans. AI can support junior residents with chest CT evaluation for COVID-19 and reduce the workload of senior residents. A review of selected CT scans by senior residents is mandatory.

A125 TANDEM STUDY DESIGN IS LESS LIKELY TO DEMONSTRATE IMPROVED ADENOMA DETECTION RATE THAN PARALLEL STUDY DESIGN IN THE ASSESSMENT OF ARTIFICIAL INTELLIGENCE-ASSISTED COLONOSCOPY

Abstract Background Randomized controlled trials have reported that artificial intelligence (AI) improves adenoma detection rate (ADR). Different methodologies, namely parallel and tandem study designs, have been employed to evaluate the efficacy of AI-assisted colonoscopy in randomized controlled trials. In systematic reviews and meta-analyses, a pooled effect that includes both study designs have been reported. However, it is unclear whether there are inconsistencies in the reported results of these two designs. Purpose To determine if there are differences in ADR using AI-aided technologies during colonoscopy between parallel and tandem study designs Method A systematic search of Ovid MEDLINE (1946 to October 2022) and EMBASE (1947 to October 2022) for randomized controlled trials comparing AI-assisted colonoscopy with routine high-definition colonoscopy in polyp detection was conducted. Reference lists of systematic reviews were searched for additional studies. The publications were divided based on trial design: parallel vs. tandem. Analysis was conducted using Review Manager 5.4.1 using a random effects model. Result(s) The search identified 540 articles. After screening the title and abstract for relevance, 19 randomized controlled trials involving a total of 14 657 patients were included for full-text review. Fourteen were parallel studies (14 136 patients) and 5 were tandem studies (521 patients). ADR was reported in 17 studies, and there was overall improvement in ADR with AI-assisted colonoscopy (risk ratio [RR] 1.33, 95% CI 1.22-1.44; p&amp;lt;.0001). Based on a separate pooled analyses of 13 parallel studies and 4 tandem studies, ADR significantly improved with AI assistance compared to routine colonoscopy, regardless of study design (RR 1.35, 95% CI 1.24-1.47 and p&amp;lt;.0001; RR 1.15, 95% CI 1.03-1.28; p=0.02, respectively). A significant increase in ADR with AI assistance were found in 84.6% (11/13) of parallel design studies, but in only 25% (1/4) of tandem studies. Image Conclusion(s) AI assistance during colonoscopy significantly increased ADR in both parallel and tandem studies; however, improvement in ADR was less likely to be seen in tandem compared to parallel studies. It remains unclear why this difference exists, but some hypotheses include smaller sample sizes in the tandem studies, significant heterogeneity in the tandem design, and differences in operator bias depending on study design. Better understanding the differences in these study designs will inform future studies of new endoscopic technologies. Disclosure of Interest None Declared

Toward AI assistants that let designers design

AbstractWe need to rethink how we assist designers with artificial intelligence (AI). AI should aim to cooperate, not automate, by supporting and leveraging the creativity and problem‐solving capabilities of designers. The challenge for such AI is how to infer designers' goals and then help them without being needlessly disruptive. We introduce AI‐assisted design, a new framework for creating such AI, built around generative user models, which allow it to infer and adapt to designers' goals, reasoning, and capabilities.

Noninferiority of Artificial Intelligence–Assisted Analysis of Ki-67 and Estrogen/Progesterone Receptor in Breast Cancer Routine Diagnostics

Image analysis assistance with artificial intelligence (AI) has become one of the great promises over recent years in pathology, with many scientific studies being published each year. Nonetheless, and perhaps surprisingly, only few image AI systems are already in routine clinical use. A major reason for this is the missing validation of the robustness of many AI systems: beyond a narrow context, the large variability in digital images due to differences in preanalytical laboratory procedures, staining procedures, and scanners can be challenging for the subsequent image analysis. Resulting faulty AI analysis may bias the pathologist and contribute to incorrect diagnoses and, therefore, may lead to inappropriate therapy or prognosis. In this study, a pretrained AI assistance tool for the quantification of Ki-67, estrogen receptor (ER), and progesterone receptor (PR) in breast cancer was evaluated within a realistic study set representative of clinical routine on a total of 204 slides (72 Ki-67, 66 ER, and 66 PR slides). This represents the cohort with the largest image variance for AI tool evaluation to date, including 3 staining systems, 5 whole-slide scanners, and 1 microscope camera. These routine cases were collected without manual preselection and analyzed by 10 participant pathologists from 8 sites. Agreement rates for individual pathologists were found to be 87.6% for Ki-67 and 89.4% for ER/PR, respectively, between scoring with and without the assistance of the AI tool regarding clinical categories. Individual AI analysis results were confirmed by the majority of pathologists in 95.8% of Ki-67 cases and 93.2% of ER/PR cases. The statistical analysis provides evidence for high interobserver variance between pathologists (Krippendorff's α, 0.69) in conventional immunohistochemical quantification. Pathologist agreement increased slightly when using AI support (Krippendorff α, 0.72). Agreement rates of pathologist scores with and without AI assistance provide evidence for the reliability of immunohistochemical scoring with the support of the investigated AI tool under a large number of environmental variables that influence the quality of the diagnosed tissue images.

Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift.

On November 30, 2022, OpenAI enabled public access to ChatGPT, a next-generation artificial intelligence with a highly sophisticated ability to write, solve coding issues, and answer questions. This communication draws attention to the prospect that ChatGPT and its successors will become important virtual assistants to patients and health-care providers. In our assessments, ranging from answering basic fact-based questions to responding to complex clinical questions, ChatGPT demonstrated a remarkable ability to formulate interpretable responses, which appeared to minimize the likelihood of alarm compared with Google's feature snippet. Arguably, the ChatGPT use case presents an urgent need for regulators and health-care professionals to be involved in developing standards for minimum quality and to raise patient awareness of current limitations of emerging artificial intelligence assistants. This commentary aims to raise awareness at the tipping point of a paradigm shift.

The CONFIDENT-P trial: Clinical implementation of artificial intelligence assistance in prostate cancer pathology.

TPS405 Background: Prostate cancer grading has been subject to variation, putting patients at risk for over- and under-treatment (Flach et al., 2022). As a response, development of artificial intelligence (AI) prostate cancer algorithms has been on the rise in the field of pathology. Despite promising results in retrospective studies, and several FDA-approved and CE-IVD certified algorithms on the market, prospective clinical implementation studies of AI are lacking. Moreover, uptake of digital pathology is currently insufficient due to high implementation costs (Ho et al., 2014). In this trial, we will explore the benefits of an AI-assisted pathology workflow in prostate cancer detection, while maintaining diagnostic safety standards. We will focus on reducing costly immunohistochemistry stains (IHC), which are currently used to aid in the diagnosis of prostate cancer. Methods: CONFIDENT-P is a SPIRIT-AI compliant single-centre, clinical trial, in a fully digital academic pathology laboratory. We will prospectively enroll 80 prostate cancer patients who undergo prostate needle biopsies. The pathology specimens will be pseudo-randomized to be assessed by a pathologist with- or without AI-assistance in a pragmatic (bi-)weekly sequential design, in a 1:1 allocation ratio. Patients are excluded when they are redirected for a second opinion to the UMC Utrecht. In the intervention group, pathologists will assess whole slide images (WSI) of the standard haematoxylin-eosin (HE)-stained sections assisted by the output of a CE-IVD approved prostate cancer detection and grading algorithm. In the control group, pathologists will assess HE WSI according to the current clinical workflow. If no tumour cells are identified or when the pathologist is in doubt, staining by immunohistochemistry (IHC) will be performed. Primary endpoint is the number of saved resources on IHC for detecting tumour cells, since this will clarify tangible cost savings that will help to build the business case for AI. We will compare the proportion of IHC-use in both arms, and calculate adjusted relative risks, using a log-binomial model. The sample size gives at least 80% power to detect a 30% difference in IHC usage, using a one-sided significance level of 5%. Enrolment is set to begin in November 2022. The ethics committee (MREC NedMec) waived the need of official ethical approval, as participants are not subjected to procedures and as they are not required to follow rules. Furthermore, they are not at risk of an inferior diagnosis. Trial registration is therefore applicable nor suitable.

Supporting Speaking Practice by Social Network-Based Interaction in Artificial Intelligence (AI)-Assisted Language Learning

In recent decades, the rapid development of artificial intelligence (AI) technology has led to the increasing use of AI speaking apps in foreign language learning. This research investigates the impact of social network-based interaction on students’ English speaking practice with the assistance of AI speaking apps in China. During the summer vacation, 70 students from different Chinese universities and majors were recruited for the experiment. They were required to practice speaking skills with AI apps for five weeks and were divided into two groups. Participants in the experimental group were encouraged to engage in various interactive activities when practicing speaking with AI apps, while those in the control group were asked to use AI speaking apps without interaction. Data were collected through questionnaires and semi-structured interviews as well as pre-and post-tests. The results indicated that students generally held positive attitudes towards interactive activities when using AI apps to practice their spoken English. The finding also showed that social network-based interaction can effectively improve learners’ speaking skills in the AI context. This study contributes to the research on the implementation and promotion of AI speaking apps with social networking and extends the previous studies on network-based interaction to the AI-assisted learning environment. An investigation of interactions based on Chinese social network-based platforms such as WeChat can be further applied to other social networking platforms such as Facebook or WhatsApp in different cultural contexts for AI-assisted speaking practice.

Artificial intelligence assists surgeons' decision-making of temporary ileostomy in patients with rectal cancer who have received anterior resection.

Due to the difficult evaluation of the risk of anastomotic leakage (AL) after rectal cancer resection, the decision to perform a temporary ileostomy is not easily distinguishable. The aim of the present study was to develop an artificial intelligence (AI) model for identifying the risk of AL to assist surgeons in the selective implementation of a temporary ileostomy. The data from 2240 patients with rectal cancer who received anterior resection were collected, and these patients were divided into one training and two test cohorts. Five AI algorithms, such as support vector machine (SVM), logistic regression (LR), Naive Bayes (NB), stochastic gradient descent (SGD) and random forest (RF) were employed to develop predictive models using clinical variables and were assessed using the two test cohorts. The SVM model indicated good discernment of AL, and might have increased the implementation of temporary ileostomy in patients with AL in the training cohort (p<0.001). Following the assessment of the two test cohorts, the SVM model could identify AL in a favorable manner, which performed with positive predictive values of 0.150 (0.091-0.234) and 0.151 (0.091-0.237), and negative predictive values of 0.977 (0.958-0.988) and 0.986 (0.969-0.994), respectively. It is important to note that the implementation of temporary ileostomy in patients without AL would have been significantly reduced (p<0.001) and which would have been significantly increased in patients with AL (p<0.05). The model (https://alrisk.21cloudbox.com/) indicated good discernment of AL, which may be used to assist the surgeon's decision-making of performing temporary ileostomy.

Advanced User Interfaces for Teleoperated Surgical Robotic Systems

AbstractIn recent years, advances in modern technology have altered the practice of surgery from open to minimally invasive surgery (MIS) aided by robots. Teleoperated surgical robotic systems (TSRSs) provide numerous significant benefits for MIS over traditional approaches, including improved safety, more efficient and precise surgery, better cosmesis, shorter recovery time, and reduced postoperative pain. Existing TSRSs’ master consoles, with improvements in vision systems, designs, and control methods, have significantly enhanced human–robot interactions, resulting in safer and more accurate medical intervention operations. Despite advances, haptic technologies, including sensors, machine assistance, and intuitive devices for user interfaces, are still limited, resulting in less effective usage of TSRSs for surgical operations. This review presents a summary of the emerging TSRSs with a focus on their user interfaces. In addition, advanced sensing, haptic, smart garments, and medical image artificial intelligence (AI) assistance technologies are shown with their potential for use in master consoles of the TSRSs are shown. Finally, a discussion on the need for a smart human‐robot interface for TSRSs is given.

Strategic Communication and Artificial Intelligence: Reviewing Emerging Innovations and Future Directions

This review examines the adoption of artificial intelligence (AI) as a novel technology for strategic communication. This study includes a survey of pertinent literature that highlights innovative communication linked to AI applications in public relations, marketing and branding, political communication, and customer relations with the goal of enlightening both research and practice. Emerald Insight and Google Scholar, two essential online databases, were used to retrieve and analyse information from peer-reviewed journal articles and chapters (n = 17) published between 2017 and 2022. Based on the main inquiries raised by the research, significant themes were discovered and critically explored. Political communication with AI, AI-focused public relations and marketing approach, and conversational AI assistants were the major themes in the research on strategic communication and AI integration. These studies were primarily the outcome of quantitative and mixed-method techniques used in a western environment. This review satisfies the need for research on AI and strategic communication that makes inferences applicable to the context in Ghana. The study's conclusion outlines a research agenda for the future, emphasising the need for research on particular topics like integration of AI voice assistants in relationship marketing domains, adoption of wearable technology and its relevance to customers' health consciousness as well as privacy concerns of emerging innovation. Future studies should also focus on developing more evidence-based AI suggestions for strategic communication practitioners, as well as a thorough methodological and theoretical discussion of how to further close the gap between research and practice in the African setting.

Detecting pediatric wrist fractures using deep-learning-based object detection.

Missed fractures are the leading cause of diagnostic error in the emergency department, and fractures of pediatric bones, particularly subtle wrist fractures, can be misidentified because of their varying characteristics and responses to injury. This study evaluated the utility of an object detection deep learning framework for classifying pediatric wrist fractures as positive or negative for fracture, including subtle buckle fractures of the distal radius, and evaluated the performance of this algorithm as augmentation to trainee radiograph interpretation. We obtained 395 posteroanterior wrist radiographs from unique pediatric patients (65% positive for fracture, 30% positive for distal radial buckle fracture) and divided them into train (n = 229), tune (n = 41) and test (n = 125) sets. We trained a Faster R-CNN (region-based convolutional neural network) deep learning object-detection model. Two pediatric and two radiology residents evaluated radiographs initially without the artificial intelligence (AI) assistance, and then subsequently with access to the bounding box generated by the Faster R-CNN model. The Faster R-CNN model demonstrated an area under the curve (AUC) of 0.92 (95% confidence interval [CI] 0.87-0.97), accuracy of 88% (n = 110/125; 95% CI 81-93%), sensitivity of 88% (n = 70/80; 95% CI 78-94%) and specificity of 89% (n = 40/45, 95% CI 76-96%) in identifying any fracture and identified 90% of buckle fractures (n = 35/39, 95% CI 76-97%). Access to Faster R-CNN model predictions significantly improved average resident accuracy from 80 to 93% in detecting any fracture (P < 0.001) and from 69 to 92% in detecting buckle fracture (P < 0.001). After accessing AI predictions, residents significantly outperformed AI in cases of disagreement (73% resident correct vs. 27% AI, P = 0.002). An object-detection-based deep learning approach trained with only a few hundred examples identified radiographs containing pediatric wrist fractures with high accuracy. Access to model predictions significantly improved resident accuracy in diagnosing these fractures.

Transfer learning-based ensemble convolutional neural network for accelerated diagnosis of foot fractures.

The complex shape of the foot, consisting of 26 bones, variable ligaments, tendons, and muscles leads to misdiagnosis of foot fractures. Despite the introduction of artificial intelligence (AI) to diagnose fractures, the accuracy of foot fracture diagnosis is lower than that of conventional methods. We developed an AI assistant system that assists with consistent diagnosis and helps interns or non-experts improve their diagnosis of foot fractures, and compared the effectiveness of the AI assistance on various groups with different proficiency. Contrast-limited adaptive histogram equalization was used to improve the visibility of original radiographs and data augmentation was applied to prevent overfitting. Preprocessed radiographs were fed to an ensemble model of a transfer learning-based convolutional neural network (CNN) that was developed for foot fracture detection with three models: InceptionResNetV2, MobilenetV1, and ResNet152V2. After training the model, score class activation mapping was applied to visualize the fracture based on the model prediction. The prediction result was evaluated by the receiver operating characteristic (ROC) curve and its area under the curve (AUC), and the F1-Score. Regarding the test set, the ensemble model exhibited better classification ability (F1-Score: 0.837, AUC: 0.95, Accuracy: 86.1%) than other single models that showed an accuracy of 82.4%. With AI assistance for the orthopedic fellow, resident, intern, and student group, the accuracy of each group improved by 3.75%, 7.25%, 6.25%, and 7% respectively and diagnosis time was reduced by 21.9%, 14.7%, 24.4%, and 34.6% respectively.