Artificial Intelligence Classification Research Articles

Human Skin-Mimicking Ionogel-Based Electronic Skin for Intelligent Robotic Sorting.

Creating bionic intelligent robotic systems that emulate human-like skin perception presents a considerable scientific challenge. This study introduces a multifunctional bionic electronic skin (e-skin) made from polyacrylic acid ionogel (PAIG), designed to detect human motion signals and transmit them to robotic systems for recognition and classification. The PAIG is synthesized using a suspension of liquid metal and graphene oxide nanosheets as initiators and cross-linkers. The resulting PAIGs demonstrate excellent mechanical properties, resistance to freezing and drying, and self-healing capabilities. Functionally, the PAIG effectively captures human motion signals through electromechanical sensing. Furthermore, a bionic intelligent sorting robot system is developed by integrating the PAIG-based e-skin with a robotic manipulator. This system leverages its ability to detect frictional electrical signals, enabling precise identification and sorting of materials. The innovations presented in this study hold significant potential for applications in artificial intelligence, rehabilitation training, and intelligent classification systems.

Artificial intelligence literacy: a proposed faceted taxonomy

Purpose The purpose of this paper is to propose a taxonomy of artificial intelligence (AI) literacy to support AI literacy education and research. Design/methodology/approach This study makes use of the facet analysis technique and draws upon various sources of data and information to develop a taxonomy of AI literacy. The research consists of the following key steps: a comprehensive review of the literature published on AI literacy research, an examination of well-known AI classification schemes and taxonomies, a review of prior research on data/information/digital literacy research and a qualitative and quantitative analysis of 1,031 metadata records on AI literacy publications. The KH Coder 3 software application was used to analyse metadata records from the Scopus multidisciplinary database. Findings A new taxonomy of AI literacy is proposed with 13 high-level facets and a list of specific subjects for each facet. Research limitations/implications The proposed taxonomy may serve as a conceptual AI literacy framework to support the critical understanding, use, application and examination of AI-enhanced tools and technologies in various educational and organizational contexts. Practical implications The proposed taxonomy provides a knowledge organization and knowledge mapping structure to support curriculum development and the organization of digital information. Social implications The proposed taxonomy provides a cross-disciplinary perspective of AI literacy. It can be used, adapted, modified or enhanced to accommodate education and learning opportunities and curricula in different domains, disciplines and subject areas. Originality/value The proposed AI literacy taxonomy offers a new and original conceptual framework that builds on a variety of different sources of data and integrates literature from various disciplines, including computing, information science, education and literacy research.

Polygonati Rhizoma varieties and origins traceability based on multivariate data fusion combined with an artificial intelligence classification algorithm

This study collected multidimensional feature data such as spectra, texture, and component contents of Polygonati Rhizoma from different origins and varieties (Polygonatum kingianum Coll. et Hemsl from Yunnan and Guizhou; Polygonatum cyrtonema Hua from Anhui and Jiangxi; Polygonatum sibiricum Red from Hunan). Multivariate statistical analysis was used to select 39 characteristic factors for distinguishing PR origins and 14 characteristic factors for discriminating PR varieties (VIP > 1 and P < 0.05). In addition, by combining multivariate statistical analysis with a deep belief network (DBN) classification algorithm, a novel artificial intelligence algorithm was developed and optimized. Compared to traditional discriminant analysis methods, the accuracy of this new approach was significantly improved, achieving a 100% discrimination rate for PR varieties and a 100% accuracy rate for tracing the origin of PR. This research provides a reference and data support for constructing intelligent algorithms based on multidimensional data fusion, to achieve food variety discrimination and origin tracing.

Human Skin-Mimicking Ionogel-Based Electronic Skin for Intelligent Robotic Sorting.

Creating bionic intelligent robotic systems that emulate human-like skin perception presents a considerable scientific challenge. This study introduces a multifunctional bionic electronic skin (e-skin) made from polyacrylic acid ionogel (PAIG), designed to detect human motion signals and transmit them to robotic systems for recognition and classification. The PAIG is synthesized using a suspension of liquid metal and graphene oxide nanosheets as initiators and cross-linkers. The resulting PAIGs demonstrate excellent mechanical properties, resistance to freezing and drying, and self-healing capabilities. Functionally, the PAIG effectively captures human motion signals through electromechanical sensing. Furthermore, a bionic intelligent sorting robot system is developed by integrating the PAIG-based e-skin with a robotic manipulator. This system leverages its ability to detect frictional electrical signals, enabling precise identification and sorting of materials. The innovations presented in this study hold significant potential for applications in artificial intelligence, rehabilitation training, and intelligent classification systems.

Role of artificial intelligence in colorectal cancer

The sphere of artificial intelligence (AI) is ever expanding. Applications for clinical practice have been emerging over recent years. Although its uptake has been most prominent in endoscopy, this represents only one aspect of holistic patient care. There are a multitude of other potential avenues in which gastrointestinal care may be involved. We aim to review the role of AI in colorectal cancer as a whole. We performed broad scoping and focused searches of the applications of AI in the field of colorectal cancer. All trials including qualitative research were included from the year 2000 onwards. Studies were grouped into pre-operative, intra-operative and post-operative aspects. Pre-operatively, the major use is with endoscopic recognition. Colonoscopy has embraced the use for human derived classifications such as Narrow-band Imaging International Colorectal Endoscopic, Japan Narrow-band Imaging Expert Team, Paris and Kudo. However, novel detection and diagnostic methods have arisen from advances in AI classification. Intra-operatively, adjuncts such as image enhanced identification of structures and assessment of perfusion have led to improvements in clinical outcomes. Post-operatively, monitoring and surveillance have taken strides with potential socioeconomic and environmental savings. The uses of AI within the umbrella of colorectal surgery are multiple. We have identified existing technologies which are already augmenting cancer care. The future applications are exciting and could at least match, if not surpass human standards.

Interaction between clinicians and artificial intelligence to detect fetal atrioventricular septal defects on ultrasound: how can we optimize collaborative performance?

Artificial intelligence (AI) has shown promise in improving the performance of fetal ultrasound screening in detecting congenital heart disease (CHD). The effect of giving AI advice to human operators has not been studied in this context. Giving additional information about AI model workings, such as confidence scores for AI predictions, may be a way of further improving performance. Our aims were to investigate whether AI advice improved overall diagnostic accuracy (using a single CHD lesion as an exemplar), and to determine what, if any, additional information given to clinicians optimized the overall performance of the clinician-AI team. An AI model was trained to classify a single fetal CHD lesion (atrioventricular septal defect (AVSD)), using a retrospective cohort of 121 130 cardiac four-chamber images extracted from 173 ultrasound scan videos (98 with normal hearts, 75 with AVSD); a ResNet50 model architecture was used. Temperature scaling of model prediction probability was performed on a validation set, and gradient-weighted class activation maps (grad-CAMs) produced. Ten clinicians (two consultant fetal cardiologists, three trainees in pediatric cardiology and five fetal cardiac sonographers) were recruited from a center of fetal cardiology to participate. Each participant was shown 2000 fetal four-chamber images in a random order (1000 normal and 1000 AVSD). The dataset comprised 500 images, each shown in four conditions: (1) image alone without AI output; (2) image with binary AI classification; (3) image with AI model confidence; and (4) image with grad-CAM image overlays. The clinicians were asked to classify each image as normal or AVSD. A total of 20 000 image classifications were recorded from 10 clinicians. The AI model alone achieved an accuracy of 0.798 (95% CI, 0.760-0.832), a sensitivity of 0.868 (95% CI, 0.834-0.902) and a specificity of 0.728 (95% CI, 0.702-0.754), and the clinicians without AI achieved an accuracy of 0.844 (95% CI, 0.834-0.854), a sensitivity of 0.827 (95% CI, 0.795-0.858) and a specificity of 0.861 (95% CI, 0.828-0.895). Showing a binary (normal or AVSD) AI model output resulted in significant improvement in accuracy to 0.865 (P < 0.001). This effect was seen in both experienced and less-experienced participants. Giving incorrect AI advice resulted in a significant deterioration in overall accuracy, from 0.761 to 0.693 (P < 0.001), which was driven by an increase in both Type-I and Type-II errors by the clinicians. This effect was worsened by showing model confidence (accuracy, 0.649; P < 0.001) or grad-CAM (accuracy, 0.644; P < 0.001). AI has the potential to improve performance when used in collaboration with clinicians, even if the model performance does not reach expert level. Giving additional information about model workings such as model confidence and class activation map image overlays did not improve overall performance, and actually worsened performance for images for which the AI model was incorrect. © 2024 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Clinical Application of Artificial Intelligence in the Ultrasound Classification of Hepatic Cystic Echinococcosis.

Hepatic cystic echinococcosis (HCE) is a zoonotic disease that occurs when the larvae of Echinococcus granulosus parasitize the livers of humans and mammals. HCE has five subtypes, and accurate subtype classification is critical for choosing a treatment strategy. To evaluate the clinical utility of artificial intelligence (AI) based on convolutional neural networks (CNNs) in the classification of HCE subtypes via ultrasound imaging, we collected ultrasound images from 4,012 HCE patients at the First Affiliated Hospital of Xinjiang Medical University between 2008 and 2020. Specifically, 1,820 HCE images from 967 patients were used as the training and validation sets for the construction of the AI model, and the remaining 6,808 images from 3,045 patients were used as the test set to evaluate the performance of the AI models. The 6,808 images were randomly divided into six groups, and each group contained equal proportions of the five subtypes. The data of each group were analyzed by a resident physician. The accuracy of HCE subtype classification by the AI model and by manual inspection was compared. The AI HCE classification model showed good performance in the diagnosis of subtypes CE1, CE2, CE4, and CE5. The overall accuracy of the AI classification (90.4%) was significantly greater than that of manual classification by physicians (86.1%; P <0.05). The CNN can better identify the five subtypes of HCE on ultrasound images and should help doctors with little experience in more accurately diagnosing HCE.

Discovery of Jupiter Family Comet 2011 UG104 Through AI Enhanced Citizen Science

We report the discovery of cometary activity from minor planet 2011 UG104, which we classify as a Jupiter Family Comet (JFC). This discovery was aided by our Artificial Intelligence (AI) classification system: TailNet. JFC's, short-period comets with eccentric Jupiter-crossing orbits, originate from the Kuiper Belt and thus give us unique insight into the composition and distribution of volatiles in the outer solar system, past and present. Our AI assistant TailNet first classified 2011 UG104 as active, which was affirmed by Citizen Scientists on our NASA Partner Program Active Asteroids. Through further archival image searches our science team found evidence of activity on 2011 UG104 on three separate observations from 2021 February to 2021 April (81.°8 < f < 95.°0).

Application of Artificial Intelligence Methods on Osteoporosis Classification with Radiographs-A Systematic Review.

Osteoporosis is a complex endocrine disease characterized by a decline in bone mass and microstructural integrity. It constitutes a major global health problem. Recent progress in the field of artificial intelligence (AI) has opened new avenues for the effective diagnosis of osteoporosis via radiographs. This review investigates the application of AI classification of osteoporosis in radiographs. A comprehensive exploration of electronic repositories (ClinicalTrials.gov, Web of Science, PubMed, MEDLINE) was carried out in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 statement (PRISMA). A collection of 31 articles was extracted from these repositories and their significant outcomes were consolidated and outlined. This encompassed insights into anatomical regions, the specific machine learning methods employed, the effectiveness in predicting BMD, and categorizing osteoporosis. Through analyzing the respective studies, we evaluated the effectiveness and limitations of AI osteoporosis classification in radiographs. The pooled reported accuracy, sensitivity, and specificity of osteoporosis classification ranges from 66.1% to 97.9%, 67.4% to 100.0%, and 60.0% to 97.5% respectively. This review underscores the potential of AI osteoporosis classification and offers valuable insights for future research endeavors, which should focus on addressing the challenges in technical and clinical integration to facilitate practical implementation of this technology.

Prospective study of AI-assisted prediction of breast malignancies in physical health examinations: role of off-the-shelf AI software and comparison to radiologist performance.

In physical health examinations, breast sonography is a commonly used imaging method, but it can lead to repeated exams and unnecessary biopsy due to discrepancies among radiologists and health centers. This study explores the role of off-the-shelf artificial intelligence (AI) software in assisting radiologists to classify incidentally found breast masses in two health centers. Female patients undergoing breast ultrasound examinations with incidentally discovered breast masses were categorized according to the 5th edition of the Breast Imaging Reporting and Data System (BI-RADS), with categories 3 to 5 included in this study. The examinations were conducted at two municipal health centers from May 2021 to May 2023.The final pathological results from surgical resection or biopsy served as the gold standard for comparison. Ultrasonographic images were obtained in longitudinal and transverse sections, and two junior radiologists and one senior radiologist independently assessed the images without knowing the pathological findings. The BI-RADS classification was adjusted following AI assistance, and diagnostic performance was compared using receiver operating characteristic curves. A total of 196 patients with 202 breast masses were included in the study, with pathological results confirming 107 benign and 95 malignant masses. The receiver operating characteristic curve showed that experienced breast radiologists had higher diagnostic performance in BI-RADS classification than junior radiologists, similar to AI classification (AUC = 0.936, 0.806, 0.896, and 0.950, p < 0.05). The AI software improved the accuracy, sensitivity, and negative predictive value of the adjusted BI-RADS classification for the junior radiologists' group (p< 0.05), while no difference was observed in the senior radiologist group. Furthermore, AI increased the negative predictive value for BI-RADS 4a masses and the positive predictive value for 4b masses among radiologists (p < 0.05). AI enhances the sensitivity of invasive breast cancer detection more effectively than ductal carcinoma in situ and rare subtypes of breast cancer. The AI software enhances diagnostic efficiency for breast masses, reducing the performance gap between junior and senior radiologists, particularly for BI-RADS 4a and 4b masses. This improvement reduces unnecessary repeat examinations and biopsies, optimizing medical resource utilization and enhancing overall diagnostic effectiveness.

AI-driven Characterization of Solid Pulmonary Nodules on CT Imaging for Enhanced Malignancy Prediction in Small-sized Lung Adenocarcinoma

ObjectivesDistinguishing solid nodules from nodules with ground-glass lesions in lung cancer is a critical diagnostic challenge, especially for tumors ≤2 cm. Human assessment of these nodules is associated with high inter-observer variability, which is why an objective and reliable diagnostic tool is necessary. This study focuses on artificial intelligence (AI) to automatically analyze such tumors and to develop prospective AI systems that can independently differentiate highly malignant nodules. Materials and methodsOur retrospective study analyzed 246 patients who were diagnosed with negative clinical lymph node metastases (cN0) using positron emission tomography-computed tomography (PET/CT) imaging and underwent surgical resection for lung adenocarcinoma. AI detected tumor sizes ≤2 cm in these patients. By utilizing AI to classify these nodules as solid (AI_solid) or non-solid (non-AI_solid) based on confidence scores, we aim to correlate AI determinations with pathological findings, thereby advancing the precision of preoperative assessments. ResultsSolid nodules identified by AI with a confidence score ≥0.87 showed significantly higher solid component volumes and proportions in patients with AI_solid than in those with non-AI_solid, with no differences in overall diameter or total volume of the tumors. Among patients with AI_solid, 16% demonstrated lymph node metastasis, and a significant 94% harbored invasive adenocarcinoma. Additionally, 44% were upstaging postoperatively. These AI_solid nodules represented high-grade malignancies. ConclusionIn small-sized lung cancer diagnosed as cN0, AI automatically identifies tumors as solid nodules ≤2 cm and evaluates their malignancy preoperatively. The AI classification can inform lymph node assessment necessity in sublobar resections, reflecting metastatic potential.

Reinvestigating the performance of artificial intelligence classification algorithms on COVID-19 X-Ray and CT images

There are concerns that artificial intelligence (AI) algorithms may create underdiagnosis bias by mislabeling patient individuals with certain attributes (e.g., female and young) as healthy. Addressing this bias is crucial given the urgent need for AI diagnostics facing rapidly spreading infectious diseases like COVID-19. We find the prevalent AI diagnostic models show an underdiagnosis rate among specific patient populations, and the underdiagnosis rate is higher in some intersectional specific patient populations (for example, females aged 20-40 years). Additionally, we find training AI models on heterogeneous datasets (positive and negative samples from different datasets) may lead to poor model generalization. The model's classification performance varies significantly across test sets, with the accuracy of the better performance being over 40% higher than that of the poor performance. In conclusion, we developed an AI bias analysis pipeline to help researchers recognize and address biases that impact medical equality and ethics.

Deep learning model for classifying shoulder pain rehabilitation exercises using IMU sensor

BackgroundArtificial intelligence is being used for rehabilitation, including monitoring exercise compliance through sensor technology. AI classification of shoulder exercise wearing an IMU sensor has only been reported in normal (i.e. painless) subjects. To prove the feasibility of monitoring exercise compliance, we aimed to classify 11 types of shoulder rehabilitation exercises using an AI (artificial intelligence) algorithm in patients with shoulder pain. We had the patients wear an IMU-based sensor, collected data during exercise, and determined the accuracy of exercise classification.MethodsData were collected from 58 patients (27 males, 31 females, age range 37–82 years) diagnosed with shoulder diseases such as adhesive capsulitis and rotator cuff disease. 11 types of shoulder pain rehabilitation exercise programs were developed and repeated each exercise ten times per session while wearing an IMU sensor. The study applied the Rectified Linear Unit (ReLU) and the SoftMax as the activation function for hidden layers, the output layer.ResultsThe acquired data was used to train a DNN model using the multilayer perceptron algorithm. The trained model was used to classify 11 types of shoulder pain rehabilitation exercises. The training accuracy was 0.975 and the test accuracy was 0.925.ConclusionThe study demonstrates that IMU sensor data can effectively classify shoulder pain rehabilitation exercises, providing more appropriate feedback for patients. The model can be utilized to establish a system for remotely monitoring patients’ exercise performance. The use of deep learning in patient monitoring and rehabilitation has significant potential to bring innovative changes to healthcare service delivery.

A Comparative Study and Improved Bearing Fault Classifier Using Raw Vibration Data Under Limited Training Samples

Artificial intelligence is gaining traction in bearing fault detection and diagnosis. Generally, signal processing and feature selection are carried out to facilitate the fault classification process; however, classification accuracy tends to degrade under limited training data. In this paper, various artificial intelligence (AI) classification models are studied and compared using raw vibration data without signal processing and feature engineering. A Cosine k-Nearest Neighbours (CosKNN)-based classification model is optimized by integrating a Segmentive Mechanism, resulting in an overall classification F1-score improvement to 90.8% compared to the original classifier's 76.9%. The comparative findings show that the proposed model is suitable for circumstances with limited availability of training data, signal processing tools, and feature engineering tuning.

A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart

In this study, we implemented a combination of data augmentation and artificial intelligence (AI) model—Convolutional Neural Network (CNN)—to help physicians classify colonic polyps into traditional adenoma (TA), sessile serrated adenoma (SSA), and hyperplastic polyp (HP). We collected ordinary endoscopy images under both white and NBI lights. Under white light, we collected 257 images of HP, 423 images of SSA, and 60 images of TA. Under NBI light, were collected 238 images of HP, 284 images of SSA, and 71 images of TA. We implemented the CNN-based artificial intelligence model, Inception V4, to build a classification model for the types of colon polyps. Our final AI classification model with data augmentation process is constructed only with white light images. Our classification prediction accuracy of colon polyp type is 94%, and the discriminability of the model (area under the curve) was 98%. Thus, we can conclude that our model can help physicians distinguish between TA, SSA, and HPs and correctly identify precancerous lesions such as TA and SSA.

Classification of posttransfusion adverse events using a publicly available artificial intelligence system.

Correct classification of transfusion reactions is important not only for effective patient care and donor management but also for accurate tracking of events in hemovigilance systems. We compared the ability of a generative artificial intelligence (AI) system to correctly diagnose hypothetical clinical situations as transfusion reactions in comparison to previous studies reporting the accuracy of transfusion medicine (TM) specialists in assessing these cases. An AI system was requested to assess 36 case scenarios to provide a diagnosis, severity, and imputability of the transfusion reactions using the CDC National Healthcare Safety Network (NHSN) criteria. Responses were compared to an expert panel's classifications and to the published responses of a panel of TM specialists. Additionally, the AI's responses were compared to the TM specialists' prior attempts to use the TrDDx web-based algorithm for the five most challenging cases. The AI's classification accuracy varied widely depending on the NHSN category. The AI accurately classified all transfusion-associated circulatory overload and transfusion-related acute lung injury cases, exceeding TM specialists' assessments. Conversely, it did not correctly identify any cases in select NHSN categories such as DSTR. Overall accuracy among all diagnostic categories was 48.7% for AI responses versus 72.1% for prior TM specialist responses (p = 0.005). AI-generated responses included non-standard terminology, limited severity assessments, and no imputability determinations. A generative AI system may have a role in helping healthcare providers to consider transfusion reaction categories that might be missed, but caution is advised in applying the AI's output to transfusion reaction classification at present.

Basic principles of artificial intelligence in dermatology explained using melanoma.

The use of artificial intelligence (AI) continues to establish itself in the most diverse areas of medicine at an increasingly fast pace. Nevertheless, many healthcare professionals lack the basic technical understanding of how this technology works, which severely limits its application in clinical settings and research. Thus, we would like to discuss the functioning and classification of AI using melanoma as an example in this review to build an understanding of the technology behind AI. For this purpose, elaborate illustrations are used that quickly reveal the technology involved. Previous reviews tend to focus on the potential applications of AI, thereby missing the opportunity to develop a deeper understanding of the subject matter that is so important for clinical application. Malignant melanoma has become a significant burden for healthcare systems. If discovered early, a better prognosis can be expected, which is why skin cancer screening has become increasingly popular and is supported by health insurance. The number of experts remains finite, reducing their availability and leading to longer waiting times. Therefore, innovative ideas need to be implemented to provide the necessary care. Thus, machine learning offers the ability to recognize melanomas from images at a level comparable to experienced dermatologists under optimized conditions.

A Fault Detection System for Wiring Harness Manufacturing Using Artificial Intelligence

Due to its simplicity, accuracy, and adaptability, Crimp Force Monitoring (CFM) has long been the standard for fault detection in wiring harness manufacturing. However, it necessitates frequent reconfigurations based on the variability in materials, dependency on operator skill, and high costs of implementation, and thus reconfiguration presents significant challenges. To solve these problems, this paper introduces a fault detection system that employs an Artificial Intelligence (AI) classification model to enhance the performance and cost-efficiency of the quality control process of wiring harness manufacturing. Since there are no labeled data to train the classification model at the onset of manufacturing, a small number of normal data from each production run are manually extracted to train the model. To address the constraint of the limited available data, the system generates synthetic data from normal data, simulating potential defects by using Regional Selective Data Scaling (RSDS). This innovative method performs upscaling or downscaling on specific regions of the original data to produce synthetic abnormal data, which enables the fault detection system to efficiently train its classification model with a dataset consisting solely of normal operation data.

Correlation between peri-implant bone mineral density and primary implant stability based on artificial intelligence classification

Currently, the classification of bone mineral density (BMD) in many research studies remains rather broad, often neglecting localized changes in BMD. This study aims to explore the correlation between peri-implant BMD and primary implant stability using a new artificial intelligence (AI)-based BMD grading system. 49 patients who received dental implant treatment at the Affiliated Hospital of Stomatology of Fujian Medical University were included. Recorded the implant stability quotient (ISQ) after implantation and the insertion torque value (ITV). A new AI-based BMD grading system was used to obtain the distribution of BMD in implant site, and the bone mineral density coefficients (BMDC) of the coronal, middle, apical, and total of the 1 mm site outside the implant were calculated by model overlap and image overlap technology. Our objective was to investigate the relationship between primary implant stability and BMDC values obtained from the new AI-based BMD grading system. There was a significant positive correlation between BMDC and ISQ value in the coronal, middle, and total of the implant (P < 0.05). However, there was no significant correlation between BMDC and ISQ values in the apical (P > 0.05). Furthermore, BMDC was notably higher at implant sites with greater ITV (P < 0.05). BMDC calculated from the new AI-based BMD grading system could more accurately present the BMD distribution in the intended implant site, thereby providing a dependable benchmark for predicting primary implant stability.

Application of near-infrared spectral imaging and artificial intelligence classification in basketball motion image recognition

Application of near-infrared spectral imaging and artificial intelligence classification in basketball motion image recognition