Accuracy of a computer vision system for estimating biomechanical measures of body function in axial spondyloarthropathy patients and healthy subjects

OBJECTIVE

Advances in computer vision make it possible to combine low-cost cameras with algorithms, enabling biomechanical measures of body function and rehabilitation programs to be performed anywhere. We evaluated a computer vision system's accuracy and concurrent validity for estimating clinically relevant biomechanical measures.

DESIGN

Cross-sectional study.

SETTING

Laboratory.

PARTICIPANTS

Thirty-one healthy participants and 31 patients with axial spondyloarthropathy.

INTERVENTION

A series of clinical functional tests (including the gold standard Bath Ankylosing Spondylitis Metrology Index tests). Each test was performed twice: the first performance was recorded with a camera, and a computer vision algorithm was used to estimate variables. During the second performance, a clinician measured the same variables manually.

MAIN MEASURES

Joint angles and inter-limb distances. Clinician measures were compared with computer vision estimates.

RESULTS

For all tests, clinician and computer vision estimates were correlated (r² values: 0.360-0.768). There were no significant mean differences between methods for shoulder flexion (left: 2 ± 14° (mean ± standard deviation), t = 0.99, p < 0.33; right: 3 ± 15°, t = 1.57, p < 0.12), side flexion (left: - 0.5 ± 3.1 cm, t = -1.34, p = 0.19; right: 0.5 ± 3.4 cm, t = 1.05, p = 0.30) and lumbar flexion ( - 1.1 ± 8.2 cm, t = -1.05, p = 0.30). For all other movements, significant differences were observed, but could be corrected using a systematic offset.

CONCLUSION

We present a computer vision approach that estimates distances and angles from clinical movements recorded with a phone or webcam. In the future, this approach could be used to monitor functional capacity and support physical therapy management remotely.

Radiomics: A radiological evidence-based artificial intelligence technique to facilitate personalized precision medicine in hepatocellular carcinoma

The high postoperative recurrence rates in hepatocellular carcinoma (HCC) remain a major hurdle in its management. Appropriate staging and treatment selection may alleviate the extent of fatal recurrence. However, effective methods to preoperatively evaluate pathophysiologic and molecular characteristics of HCC are lacking. Imaging plays a central role in HCC diagnosis and stratification due to the non-invasive diagnostic criteria. Vast and crucial information is hidden within image data. Other than providing a morphological sketch for lesion diagnosis, imaging could provide new insights to describe the pathophysiological and genetic landscape of HCC. Radiomics aims to facilitate diagnosis and prognosis of HCC using artificial intelligence techniques to harness the immense information contained in medical images. Radiomics produces a set of archetypal and robust imaging features that are correlated to key pathological or molecular biomarkers to preoperatively risk-stratify HCC patients. Inferred with outcome data, comprehensive combination of radiomic, clinical and/or multi-omics data could also improve direct prediction of response to treatment and prognosis. The evolution of radiomics is changing our understanding of personalized precision medicine in HCC management. Herein, we review the key techniques and clinical applications in HCC radiomics and discuss current limitations and future opportunities to improve clinical decision making.

Designing an optimal multi-objective model for a sustainable closed-loop supply chain: a case study of pomegranate in Iran

The competitive environment in the global market makes most countries look for better ways to solve their problems. Food waste is the largest concern facing the food security of the world. Not paying attention to process of pomegranate wastes, such as separating the peel from the other parts and ignoring the cost of using artificial intelligence for pest control in gardens and the cost of maintaining the processed products are the gaps of previous researches. To cope with this challenge, recent studies have presented sustainable closed-loop supply chains (SCLSCs) as a strategic approach and a competitive advantage. The present study distinguishes itself from other studies by using the artificial intelligence technology in a supply chain along with the reverse logistics section, i.e., waste recycling. This paper proposes a design for a CLSC pomegranates. The corresponding logistics network is designed for several periods and covers manufacturers, distribution centers, customers, factories, recycling centers (compost centers), and compost end user (compost markets). Using reverse logistics, the wasted pomegranates are also converted into recycled products including ethanol, as an automotive fuel and a renewable energy, and a type of compost processed as an organic fertilizer. The goal of proposed model is to minimize the costs of supply chains, reduce the supply risks involved, and increase the profits for gardeners and investors in the public and non-profit agriculture sectors in Iran. The first pareto solution is 1,869,908.962, 2172.638 and 65.926, and the CPU time is 412 Ms. The results show a rise in the maximum supply risk occurs in the total cost and risk but a reduction in the accountability of the network and also an increase in the disruption period findings in increased total cost and risk of the network, while it first increases and then decreases the accountability.

microRNAs combined to radiomic features as a predictor of complete clinical response after neoadjuvant radio-chemotherapy for locally advanced rectal cancer: a preliminary study

OBJECTIVE

To define a predictive Artificial Intelligence (AI) algorithm based on the integration of a set of biopsy-based microRNAs expression data and radiomic features to understand their potential impact in predicting clinical response (CR) to neoadjuvant radio-chemotherapy (nRCT). The identification of patients who would truly benefit from nRCT for Locally Advanced Rectal Cancer (LARC) could be crucial for an improvement in a tailored therapy.

METHODS

Forty patients with LARC were retrospectively analyzed. An MRI of the pelvis before and after nRCT was performed. In the diagnostic biopsy, the expression levels of 7 miRNAs were measured and correlated with the tumor response rate (TRG), assessed on the surgical sample. The accuracy of complete CR (cCR) prediction was compared for i) clinical predictors; ii) radiomic features; iii) miRNAs levels; and iv) combination of radiomics and miRNAs.

RESULTS

Clinical predictors showed the lowest accuracy. The best performing model was based on the integration of radiomic features with miR-145 expression level (AUC-ROC = 0.90). AI algorithm, based on radiomics features and the overexpression of miR-145, showed an association with the TRG class and demonstrated a significant impact on the outcome.

CONCLUSION

The pre-treatment identification of responders/NON-responders to nRCT could address patients to a personalized strategy, such as total neoadjuvant therapy (TNT) for responders and upfront surgery for non-responders. The combination of radiomic features and miRNAs expression data from images and biopsy obtained through standard of care has the potential to accelerate the discovery of a noninvasive multimodal approach to predict the cCR after nRCT for LARC.

Deep learning-based automatic left atrial appendage filling defects assessment on cardiac computed tomography for clinical and subclinical atrial fibrillation patients

Rationale and objectives

Selecting region of interest (ROI) for left atrial appendage (LAA) filling defects assessment can be time consuming and prone to subjectivity. This study aimed to develop and validate a novel artificial intelligence (AI), deep learning (DL) based framework for automatic filling defects assessment on CT images for clinical and subclinical atrial fibrillation (AF) patients.

Materials and methods

A total of 443,053 CT images were used for DL model development and testing. Images were analyzed by the AI framework and expert cardiologists/radiologists. The LAA segmentation performance was evaluated using Dice coefficient. The agreement between manual and automatic LAA ROI selections was evaluated using intraclass correlation coefficient (ICC) analysis. Receiver operating characteristic (ROC) curve analysis was used to assess filling defects based on the computed LAA to ascending aorta Hounsfield unit (HU) ratios.

Results

A total of 210 patients (Group 1: subclinical AF, n = 105; Group 2: clinical AF with stroke, n = 35; Group 3: AF for catheter ablation, n = 70) were enrolled. The LAA volume segmentation achieved 0.931-0.945 Dice scores. The LAA ROI selection demonstrated excellent agreement (ICC ≥0.895, p < 0.001) with manual selection on the test sets. The automatic framework achieved an excellent AUC score of 0.979 in filling defects assessment. The ROC-derived optimal HU ratio threshold for filling defects detection was 0.561.

Conclusion

The novel AI-based framework could accurately segment the LAA region and select ROIs while effectively avoiding trabeculae for filling defects assessment, achieving close-to-expert performance. This technique may help preemptively detect the potential thromboembolic risk for AF patients.

Robotics and cybersurgery in ophthalmology: a current perspective

Ophthalmology is one of the most enriched fields, allowing the domain of artificial intelligence to be part of its point of interest in scientific research. The requirement of specialized microscopes and visualization systems presents a challenge to adapting robotics in ocular surgery. Cyber-surgery has been used in other surgical specialties aided by Da Vinci robotic system. This study focuses on the current perspective of using robotics and cyber-surgery in ophthalmology and highlights factors limiting their progression. A review of literature was performed with the aid of Google Scholar, Pubmed, CINAHL, MEDLINE (N.H.S. Evidence), Cochrane, AMed, EMBASE, PsychINFO, SCOPUS, and Web of Science. Keywords: Cybersurgery, Telesurgery, ophthalmology robotics, Da Vinci robotic system, artificial intelligence in ophthalmology, training on robotic surgery, ethics of the use of robots in medicine, legal aspects, and economics of cybersurgery and robotics. 150 abstracts were reviewed for inclusion, and 68 articles focusing on ophthalmology were included for full-text review. Da Vinci Surgical System has been used to perform a pterygium repair in humans and was successful in ex vivo corneal, strabismus, amniotic membrane, and cataract surgery. Gamma Knife enabled effective treatment of uveal melanoma. Robotics used in ophthalmology were: Da Vinci Surgical System, Intraocular Robotic Interventional Surgical System (IRISS), Johns Hopkins Steady-Hand Eye Robot and smart instruments, and Preceyes' B.V. Cybersurgery is an alternative to overcome distance and the shortage of surgeons. However, cost, availability, legislation, and ethics are factors limiting the progression of these fields. Robotic and cybersurgery in ophthalmology are still in their niche. Cost-effective studies are needed to overcome the delay. Technologies, such as 5G and Tactile Internet, are required to help reduce resource scheduling problems in cybersurgery. In addition, prototype development and the integration of artificial intelligence applications could further enhance the safety and precision of ocular surgery.

Gender and sex bias in COVID-19 epidemiological data through the lens of causality

The COVID-19 pandemic has spurred a large amount of experimental and observational studies reporting clear correlation between the risk of developing severe COVID-19 (or dying from it) and whether the individual is male or female. This paper is an attempt to explain the supposed male vulnerability to COVID-19 using a causal approach. We proceed by identifying a set of confounding and mediating factors, based on the review of epidemiological literature and analysis of sex-dis-aggregated data. Those factors are then taken into consideration to produce explainable and fair prediction and decision models from observational data. The paper outlines how non-causal models can motivate discriminatory policies such as biased allocation of the limited resources in intensive care units (ICUs). The objective is to anticipate and avoid disparate impact and discrimination, by considering causal knowledge and causal-based techniques to compliment the collection and analysis of observational big-data. The hope is to contribute to more careful use of health related information access systems for developing fair and robust predictive models.

Machine Learning Approach to Drug Treatment Strategy for Diabetes Care

Globally, the number of people with diabetes mellitus has quadrupled in the past three decades, and approximately one in 11 adults worldwide have diabetes mellitus. Since both microvascular and macrovascular diseases in patients with diabetes predispose them to a lower quality of life as well as higher rates of mortality, managing blood glucose levels is of clinical relevance in diabetes care. Many classes of antihyperglycemic drugs are currently approved to treat hyperglycemia in patients with type 2 diabetes mellitus, with several new drugs having been developed during the last decade. Diabetes-related complications have been reduced substantially worldwide. Prioritization of therapeutic agents varies according to national guidelines. However, since the characteristics of participants in clinical trials differ from patients in actual clinical practice, it is difficult to apply the results of such trials to clinical practice. Machine learning approaches became highly topical issues in medicine along with rapid technological innovations in the fields of information and communication in the 1990s. However, adopting these technologies to support decision-making regarding drug treatment strategies for diabetes care has been slow. This review summarizes data from recent studies on the choice of drugs for type 2 diabetes mellitus focusing on machine learning approaches.

An AI-based patient-specific clinical decision support system for OA patients choosing surgery or not: study protocol for a single-centre, parallel-group, non-inferiority randomised controlled trial

BACKGROUND

Osteoarthritis (OA) affects 20% of the adult Danish population, and the financial burden to society amounts to DKK 4.6 billion annually. Research suggests that up to 75% of surgical patients could have postponed an operation and managed with physical training. ERVIN.2 is an artificial intelligence (AI)-based clinical support system that addresses this problem by enhancing patient involvement in decisions concerning surgical knee and hip replacement. However, the clinical outcomes and cost-effectiveness of using such a system are scantily documented.

OBJECTIVE

The primary objective is to investigate whether the usual care is non-inferior to ERVIN.2 supported care. The second objective is to determine if ERVIN.2 enhances clinical decision support and whether ERVIN.2 supported care is cost-effective.

METHODS

This study used a single-centre, non-inferiority, randomised controlled in a two-arm parallel-group design. The study will be reported in compliance with CONSORT guidelines. The control group receives the usual care. As an add-on, the intervention group have access to baseline scores and predicted Oxford hip/knee scores and HRQoL for both the surgical and the non-surgical trajectory. A cost-utility analysis will be conducted alongside the trial using a hospital perspective, a 1-year time horizon and effects estimated using EQ-5D-3L. Results will be presented as cost per QALY gain.

DISCUSSION

This study will bring knowledge about whether ERVIN.2 enhances clinical decision support, clinical effects, and cost-effectiveness of the AI system. The study design will not allow for the blinding of surgeons.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04332055 . Registered on 2 April 2020.

Radiomics-based machine learning models in STEMI: a promising tool for the prediction of major adverse cardiac events

OBJECTIVE

To evaluate the potential value of the machine learning (ML) models using radiomic features of late gadolinium enhancement (LGE) and cine images on magnetic resonance imaging (MRI) along with relevant clinical information and conventional MRI parameters for the prediction of major adverse cardiac events (MACE) in ST-segment elevation myocardial infarction (STEMI) patients.

METHODS

This retrospective study included 60 patients with the first STEMI. MACE consisted of new-onset congestive heart failure, ventricular arrhythmia, and cardiac death. Radiomic features were extracted from cine and LGE images. Inter-class correlation coefficients (ICCs) were calculated to assess inter-observer reproducibility. LASSO (least absolute shrinkage and selection operator) method was used for radiomic feature selection. Seven separate models using a different combination of the available information were investigated. Classifications with repeat random sampling were done using adaptive boosting, k-nearest neighbor, naive Bayes, neural network, random forest, stochastic gradient descent, and support vector machine algorithms.

RESULTS

Of the 1748 extracted radiomic features, 1393 showed good inter-observer agreement. With LASSO, 25 features were selected. Among the ML algorithms, the neural network showed the highest predictive performance on average (area under the curve (AUC) 0.822 ± 0.181). Of the best-calculated model, the one using clinical parameters, CMRI parameters, and selected radiomic features (model 7), the diagnostic performance was as follows: 0.965 AUC, 0.894 classification accuracy, 0.906 sensitivity, 0.883 specificity, 0.875 positive predictive value (PPV), and 0.912 negative predictive value (NPV).

CONCLUSION

The radiomics-based ML models incorporating clinical and conventional MRI parameters are promising for predicting MACE occurrence in STEMI patients in the follow-up period.

KEY POINTS

• Acute coronary occlusion results in variable changes at the cellular level ranging from myocyte swelling to myonecrosis depending on the duration of the ischemia and the metabolic state of the heart, which causes subtle heterogeneous signal changes that are imperceptible to the human eye with cardiac MRI. • Radiomics-based machine learning analysis of cardiac MR images is promising for risk prediction. • Combining MRI-derived parameters and clinical variables increases the accuracy of predictive models.

A Cocktail of Polyherbal Bioactive Compounds and Regular Mobility Training as Senolytic Approaches in Age-dependent Alzheimer's: the In Silico Analysis, Lifestyle Intervention in Old Age

Alzheimer's is a principal concern globally. Machine learning is a valuable tool to determine protective and diagnostic approaches for the elderly. We analyzed microarray datasets of Alzheimer's cases based on artificial intelligence by R statistical software. This study provided a screened pool of ncRNAs and coding RNAs related to Alzheimer's development. We designed hub genes as cut points in networks and predicted potential microRNAs and LncRNA to regulate protein networks in aging and Alzheimer's through in silico algorithms. Notably, we collected effective traditional herbal medicines. A list of bioactive compounds prepared including capsaicin, piperine, crocetin, safranal, saffron oil, coumarin, thujone, rosmarinic acid, sabinene, thymoquinone, ascorbic acid, vitamin E, cyanidin, rhaponticin, isovitexin, coumarin, nobiletin, evodiamine, gingerol, curcumin, quercetin, fisetin, and allicin as an effective fusion that potentially modulates hub proteins and molecular signaling pathways based on pharmacophore model screening and chemoinformatics survey. We identified profiles of 21 mRNAs, 272 microRNAs, and eight LncRNA in Alzheimer's based on prediction algorithms. We suggested a fusion of senolytic herbal ligands as an alternative therapy and preventive formulation in dementia. Also, we provided ncRNAs expression status as novel monitoring strategies in Alzheimer's and new cut-point proteins as novel therapeutic approaches. Synchronizing fusion drugs and lifestyle could reverse Alzheimer's hallmarks to amelioration via an offset of the signaling pathways, leading to increased life quality in the elderly.

Learning deep architectures for the interpretation of first-trimester fetal echocardiography (LIFE) - a study protocol for developing an automated intelligent decision support system for early fetal echocardiography

BACKGROUND

Congenital Heart Disease represents the most frequent fetal malformation. The lack of prenatal identification of congenital heart defects can have adverse consequences for the neonate, while a correct prenatal diagnosis of specific cardiac anomalies improves neonatal care neurologic and surgery outcomes. Sonographers perform prenatal diagnosis manually during the first or second-trimester scan, but the reported detection rates are low. This project's primary objective is to develop an Intelligent Decision Support System that uses two-dimensional video files of cardiac sweeps obtained during the standard first-trimester fetal echocardiography (FE) to signal the presence/absence of previously learned key features.

METHODS

The cross-sectional study will be divided into a training part of the machine learning approaches and the testing phase on previously unseen frames and eventually on actual video scans. Pregnant women in their 12-13 + 6 weeks of gestation admitted for routine first-trimester anomaly scan will be consecutively included in a two-year study, depending on the availability of the experienced sonographers in early fetal cardiac imaging involved in this research. The Data Science / IT department (DSIT) will process the key planes identified by the sonographers in the two- dimensional heart cine loop sweeps: four-chamber view, left and right ventricular outflow tracts, three vessels, and trachea view. The frames will be grouped into the classes representing the plane views, and then different state-of-the- art deep-learning (DL) pre-trained algorithms will be tested on the data set. The sonographers will validate all the intermediary findings at the frame level and the meaningfulness of the video labeling.

DISCUSSION

FE is feasible and efficient during the first trimester. Still, the continuous training process is impaired by the lack of specialists or their limited availability. Therefore, in our study design, the sonographer benefits from a second opinion provided by the developed software, which may be very helpful, especially if a more experienced colleague is unavailable. In addition, the software may be implemented on the ultrasound device so that the process could take place during the live examination.

TRIAL REGISTRATION

The study is registered under the name "Learning deep architectures for the Interpretation of Fetal Echocardiography (LIFE)", project number 408PED/2020, project code PN-III-P2-2.1-PED-2019.

TRIAL REGISTRATION

ClinicalTrials.gov , unique identifying number NCT05090306, date of registration 30.10.2020.

Exploring celebrity influence on public attitude towards the COVID-19 pandemic: social media shared sentiment analysis

OBJECTIVES

The COVID-19 pandemic has introduced new opportunities for health communication, including an increase in the public's use of online outlets for health-related emotions. People have turned to social media networks to share sentiments related to the impacts of the COVID-19 pandemic. In this paper, we examine the role of social messaging shared by Persons in the Public Eye (ie, athletes, politicians, news personnel, etc) in determining overall public discourse direction.

METHODS

We harvested approximately 13 million tweets ranging from 1 January 2020 to 1 March 2022. The sentiment was calculated for each tweet using a fine-tuned DistilRoBERTa model, which was used to compare COVID-19 vaccine-related Twitter posts (tweets) that co-occurred with mentions of People in the Public Eye.

RESULTS

Our findings suggest the presence of consistent patterns of emotional content co-occurring with messaging shared by Persons in the Public Eye for the first 2 years of the COVID-19 pandemic influenced public opinion and largely stimulated online public discourse.

DISCUSSION

We demonstrate that as the pandemic progressed, public sentiment shared on social networks was shaped by risk perceptions, political ideologies and health-protective behaviours shared by Persons in the Public Eye, often in a negative light.

CONCLUSION

We argue that further analysis of public response to various emotions shared by Persons in the Public Eye could provide insight into the role of social media shared sentiment in disease prevention, control and containment for COVID-19 and in response to future disease outbreaks.

Are ChatGPT’s knowledge and interpretation ability comparable to those of medical students in Korea for taking a parasitology examination?: a descriptive study

This study aimed to compare the knowledge and interpretation ability of ChatGPT, a language model of artificial general intelligence, with those of medical students in Korea by administering a parasitology examination to both ChatGPT and medical students. The examination consisted of 79 items and was administered to ChatGPT on January 1, 2023. The examination results were analyzed in terms of ChatGPT’s overall performance score, its correct answer rate by the items’ knowledge level, and the acceptability of its explanations of the items. ChatGPT’s performance was lower than that of the medical students, and ChatGPT’s correct answer rate was not related to the items’ knowledge level. However, there was a relationship between acceptable explanations and correct answers. In conclusion, ChatGPT’s knowledge and interpretation ability for this parasitology examination were not yet comparable to those of medical students in Korea.

Robotics-assisted, organic agricultural-biotechnology based environment-friendly healthy food option: Beyond the binary of GM versus Organic crops

Human society cannot afford the luxury of the business-as-usual approach when dealing with the emerging challenges of the 21st century. The challenges of food production to meet the pace of population growth in an environmentally-sustainable manner have increased considerably, emphasizing the need to explore newer approaches to agriculture. Agrochemical-based agricultural practices are known to have serious environmental and health implications. Even conventional organic farming is not sustainable in the long run. Although some "age-old" practices are useful, these will not help feed more people on the same or less land more sustainably. Sustainable intensification is the way forward. There is a need to incorporate a customer-centric outlook and make the organic system sustainable. Here, we bring forth the necessity to enhance the efficiency of organic agriculture by the inclusion of robotics and agrochemical-free GM seeds. Such an organic-GM hybrid agriculture system integrated with the use of artificial intelligence (AI) based technologies will have better energy efficiency. The produce from such a system will offer consumers a 'third' choice and create a new food label, 'organically-grown GM produce'.

Automated lung cancer assessment on 18F-PET/CT using Retina U-Net and anatomical region segmentation

OBJECTIVES

To develop and test a Retina U-Net algorithm for the detection of primary lung tumors and associated metastases of all stages on FDG-PET/CT.

METHODS

A data set consisting of 364 FDG-PET/CTs of patients with histologically confirmed lung cancer was used for algorithm development and internal testing. The data set comprised tumors of all stages. All lung tumors (T), lymphatic metastases (N), and distant metastases (M) were manually segmented as 3D volumes using whole-body PET/CT series. The data set was split into a training (n = 216), validation (n = 74), and internal test data set (n = 74). Detection performance for all lesion types at multiple classifier thresholds was evaluated and false-positive-findings-per-case (FP/c) calculated. Next, detected lesions were assigned to categories T, N, or M using an automated anatomical region segmentation. Furthermore, reasons for FPs were visually assessed and analyzed. Finally, performance was tested on 20 PET/CTs from another institution.

RESULTS

Sensitivity for T lesions was 86.2% (95% CI: 77.2-92.7) at a FP/c of 2.0 on the internal test set. The anatomical correlate to most FPs was the physiological activity of bone marrow (16.8%). TNM categorization based on the anatomical region approach was correct in 94.3% of lesions. Performance on the external test set confirmed the good performance of the algorithm (overall detection rate = 88.8% (95% CI: 82.5-93.5%) and FP/c = 2.7).

CONCLUSIONS

Retina U-Nets are a valuable tool for tumor detection tasks on PET/CT and can form the backbone of reading assistance tools in this field. FPs have anatomical correlates that can lead the way to further algorithm improvements. The code is publicly available.

KEY POINTS

• Detection of malignant lesions in PET/CT with Retina U-Net is feasible. • All false-positive findings had anatomical correlates, physiological bone marrow activity being the most prevalent. • Retina U-Nets can build the backbone for tools assisting imaging professionals in lung tumor staging.

Clinician and computer: a study on doctors' perceptions of artificial intelligence in skeletal radiography

BACKGROUND

Traumatic musculoskeletal injuries are a common presentation to emergency care, the first-line investigation often being plain radiography. The interpretation of this imaging frequently falls to less experienced clinicians despite well-established challenges in reporting. This study presents novel data of clinicians' confidence in interpreting trauma radiographs, their perception of AI in healthcare, and their support for the development of systems applied to skeletal radiography.

METHODS

A novel questionnaire was distributed through a network of collaborators to clinicians across the Southeast of England. Over a three-month period, responses were compiled into a database before undergoing statistical review.

RESULTS

The responses of 297 participants were included. The mean self-assessed knowledge of AI in healthcare was 3.68 out of ten, with significantly higher knowledge reported by the most senior doctors (Specialty Trainee/Specialty Registrar or above = 4.88). 13.8% of participants reported an awareness of AI in their clinical practice. Overall, participants indicated substantial favourability towards AI in healthcare (7.87) and in AI applied to skeletal radiography (7.75). There was a preference for a hypothetical system indicating positive findings rather than ruling as negative (7.26 vs 6.20).

CONCLUSIONS

This study identifies clear support, amongst a cross section of student and qualified doctors, for both the general use of AI technology in healthcare and in its application to skeletal radiography for trauma. The development of systems to address this demand appear well founded and popular. The engagement of a small but reticent minority should be sought, along with improving the wider education of doctors on AI.

Data on human decision, feedback, and confidence during an artificial intelligence-assisted decision-making task

The data are collected from a human subjects study in which 100 participants solve chess puzzle problems with artificial intelligence (AI) assistance. The participants are assigned to one of the two experimental conditions determined by the direction of the change in AI performance at problem 20: 1) high- to low-performing and 2) low- to high-performing. The dataset contains information about the participants' move before an AI suggestion, the goodness evaluation score of these moves, AI suggestion, feedback, and the participants' confidence in AI and self-confidence during three initial practice problems and 30 experimental problems. The dataset contains 100 CSV files, one per participant. There is opportunity for this dataset to be utilized in various domains that research human-AI collaboration scenarios such as human-computer interaction, psychology, computer science, and team management in engineering/business. Not only can the dataset enable further cognitive and behavioral analysis in human-AI collaboration contexts but also provide an experimental platform to develop and test future confidence calibration methods.

Acceleration of knee magnetic resonance imaging using a combination of compressed sensing and commercially available deep learning reconstruction: a preliminary study

PURPOSE

To evaluate whether deep learning reconstruction (DLR) accelerates the acquisition of 1.5-T magnetic resonance imaging (MRI) knee data without image deterioration.

MATERIALS AND METHODS

Twenty-one healthy volunteers underwent MRI of the right knee on a 1.5-T MRI scanner. Proton-density-weighted images with one or four numbers of signal averages (NSAs) were obtained via compressed sensing, and DLR was applied to the images with 1 NSA to obtain 1NSA-DLR images. The 1NSA-DLR and 4NSA images were compared objectively (by deriving the signal-to-noise ratios of the lateral and the medial menisci and the contrast-to-noise ratios of the lateral and the medial menisci and articular cartilages) and subjectively (in terms of the visibility of the anterior cruciate ligament, the medial collateral ligament, the medial and lateral menisci, and bone) and in terms of image noise, artifacts, and overall diagnostic acceptability. The paired t-test and Wilcoxon signed-rank test were used for statistical analyses.

RESULTS

The 1NSA-DLR images were obtained within 100 s. The signal-to-noise ratios (lateral: 3.27 ± 0.30 vs. 1.90 ± 0.13, medial: 2.71 ± 0.24 vs. 1.80 ± 0.15, both p < 0.001) and contrast-to-noise ratios (lateral: 2.61 ± 0.51 vs. 2.18 ± 0.58, medial 2.19 ± 0.32 vs. 1.97 ± 0.36, both p < 0.001) were significantly higher for 1NSA-DLR than 4NSA images. Subjectively, all anatomical structures (except bone) were significantly clearer on the 1NSA-DLR than on the 4NSA images. Also, in the former images, the noise was lower, and the overall diagnostic acceptability was higher.

CONCLUSION

Compared with the 4NSA images, the 1NSA-DLR images exhibited less noise, higher overall image quality, and allowed more precise visualization of the menisci and ligaments.

Clinical value of artificial intelligence in thyroid ultrasound: a prospective study from the real world

OBJECTIVE

To evaluate the diagnostic performance of a commercial artificial intelligence (AI)-assisted ultrasonography (US) for thyroid nodules and to validate its value in real-world medical practice.

MATERIALS AND METHODS

From March 2021 to July 2021, 236 consecutive patients with 312 suspicious thyroid nodules were prospectively enrolled in this study. One experienced radiologist performed US examinations with a real-time AI system (S-Detect). US images and AI reports of the nodules were recorded. Nine residents and three senior radiologists were invited to make a "benign" or "malignant" diagnosis based on recorded US images without knowing the AI reports. After referring to AI reports, the diagnosis was made again. The diagnostic performance of AI, residents, and senior radiologists with and without AI reports were analyzed.

RESULTS

The sensitivity, accuracy, and AUC of the AI system were 0.95, 0.84, and 0.753, respectively, and were not statistically different from those of the experienced radiologists, but were superior to those of the residents (all p < 0.01). The AI-assisted resident strategy significantly improved the accuracy and sensitivity for nodules ≤ 1.5 cm (all p < 0.01), while reducing the unnecessary biopsy rate by up to 27.7% for nodules > 1.5 cm (p = 0.034).

CONCLUSIONS

The AI system achieved performance, for cancer diagnosis, comparable to that of an average senior thyroid radiologist. The AI-assisted strategy can significantly improve the overall diagnostic performance for less-experienced radiologists, while increasing the discovery of thyroid cancer ≤ 1.5 cm and reducing unnecessary biopsies for nodules > 1.5 cm in real-world medical practice.

KEY POINTS

• The AI system reached a senior radiologist-like level in the evaluation of thyroid cancer and could significantly improve the overall diagnostic performance of residents. • The AI-assisted strategy significantly improved ≤ 1.5 cm thyroid cancer screening AUC, accuracy, and sensitivity of the residents, leading to an increased detection of thyroid cancer while maintaining a comparable specificity to that of radiologists alone. • The AI-assisted strategy significantly reduced the unnecessary biopsy rate for thyroid nodules > 1.5 cm by the residents, while maintaining a comparable sensitivity to that of radiologists alone.

A study on endovascular treatment alone and bridging treatment for acute ischemic stroke

OBJECTIVES

To investigate whether intravenous thrombolysis (IVT) with alteplase (a recombinant tissue plasminogen activator, rt-PA) before endovascular treatment (EVT) is beneficial for acute ischemic stroke (AIS) patients in different periods.

METHODS

This study enrolled a total of 140 patients hospitalized between 2019 and 2022 with AIS from large vessel occlusion (LVO) in the anterior circulation. Those patients were divided into the EVT alone group and IVT + EVT group, in which EVT was preceded by intravenous rt-PA. According to the time from onset to femoral artery puncture, the above two groups were divided into the following subgroups: < 4.5 h, between 4.5 and 6 h, between 6 and 8 h, and between 8 and 10 h. There were 78 patients in the EVT alone group and 62 patients in the IVT + EVT group.

RESULTS

There was no statistically significant difference in functional independence, recanalization rate, favorable outcome rate, or mortality between the EVT and IVT + EVT groups (P > 0.05). After adjusting for confounding factors, a lower incidence of intracerebral hemorrhage was observed in the EVT group (P < 0.05). A comparison of time-dependent efficacy between the two groups showed that within 6-8 h, there were statistically significant differences between admission and postoperation in the National Institutes of Health Stroke Scale scores at 24 h (P = 0.01) or 7 days (P = 0.02).

CONCLUSIONS

Although there was no difference in clinical efficacy and safety between the abovementioned two groups, treatment with IVT + EVT could increase the risk of bleeding compared to EVT. Moreover, in the 6-8 h subgroup, the efficacy of EVT alone was better than that of IVT + EVT.

Cardiovascular events and artificial intelligence-predicted age using 12-lead electrocardiograms

Background

There is increasing evidence that 12-lead electrocardiograms (ECG) can be used to predict biological age, which is associated with cardiovascular events. However, the utility of artificial intelligence (AI)-predicted age using ECGs remains unclear.

Methods

Using a single-center database, we developed an AI-enabled ECG using 17 042 sinus rhythm ECGs (SR-ECG) to predict chronological age (CA) with a convolutional neural network that yields AI-predicted age. Using the 5-fold cross validation method, AI-predicted age deriving from the test dataset was yielded for all ECGs. The incidence by AgeDiff and the areas under the curve by receiver operating characteristic curve with AI-predicted age for cardiovascular events were analyzed.

Results

During the mean follow-up period of 460.1 days, there were 543 cardiovascular events. The annualized incidence of cardiovascular events was 2.24 %, 2.44 %, and 3.01 %/year for patients with AgeDiff < -6, -6 to ≤6, and >6 years, respectively. The areas under the curve for cardiovascular events with CA and AI-predicted age, respectively, were 0.673 and 0.679 (Delong's test, P = 0.388) for all patients; 0.642 and 0.700 (P = 0.003) for younger patients (CA < 60 years); and 0.584 and 0.570 (P = 0.268) for older patients (CA ≥ 60 years).

Conclusions

AI-predicted age using 12-lead ECGs showed superiority in predicting cardiovascular events compared with CA in younger patients, but not in older patients.

Kyoto classification of gastritis, virtual chromoendoscopy and artificial intelligence: Where are we going? What do we need?

Chronic gastritis (CG) is a widespread and frequent disease, mainly caused by Helicobacter pylori infection, which is associated with an increased risk of gastric cancer. Virtual chromoendoscopy improves the endoscopic diagnostic efficacy, which is essential to establish the most appropriate therapy and to enable cancer prevention. Artificial intelligence provides algorithms for the diagnosis of gastritis and, in particular, early gastric cancer, but it is not yet used in practice. Thus, technological innovation, through image resolution and processing, optimizes the diagnosis and management of CG and gastric cancer. The endoscopic Kyoto classification of gastritis improves the diagnosis and management of this disease, but through the analysis of the most recent literature, new algorithms can be proposed.

Diabetic wounds and artificial intelligence: A mini-review

Diabetic wound takes longer time to heal due to micro and macro-vascular ailment. This longer healing time can lead to infections and other health complications. Foot ulcers are one of the most common diabetic wounds. These are one of the leading cause of amputations. Medical science is continuously striving for improving quality of human life. A recent trend of amalgamation of knowledge, efforts and technological advancement of medical science experts and artificial intelligence researchers, has made tremendous success in diagnosis, prognosis and treatment of a variety of diseases. Diabetic wounds are no exception, as artificial intelligence experts are putting their research efforts to apply latest technological advancements in the field to help medical care personnel to deal with diabetic wounds in more effective manner. The presented study reviews the diagnostic and treatment research under the umbrella of Artificial Intelligence and computational science, for diabetic wound healing. Framework for diabetic wound assessment using artificial intelligence is presented. Moreover, this review is focused on existing and potential contribution of artificial intelligence to improve medical services for diabetic wound patients. The article also discusses the future directions for the betterment of the field that can lead to facilitate both, clinician and patients.

XSMILES: interactive visualization for molecules, SMILES and XAI attribution scores

BACKGROUND

Explainable artificial intelligence (XAI) methods have shown increasing applicability in chemistry. In this context, visualization techniques can highlight regions of a molecule to reveal their influence over a predicted property. For this purpose, some XAI techniques calculate attribution scores associated with tokens of SMILES strings or with atoms of a molecule. While an association of a score with an atom can be directly visually represented on a molecule diagram, scores computed for SMILES non-atom tokens cannot. For instance, a substring [N+] contains 3 non-atom tokens, i.e., [, [Formula: see text], and ], and their attributions, depending on the model, are not necessarily revealing an influence of the nitrogen atom over the predicted property; for that reason, it is not possible to represent the scores on a molecule diagram. Moreover, SMILES's notation is complex, foregrounding the need for techniques to facilitate the analysis of explanations associated with their tokens.

RESULTS

We propose XSMILES, an interactive visualization technique, to explore explainable artificial intelligence attributions scores and support the interpretation of SMILES. Users can input any type of score attributed to atom and non-atom tokens and visualize them on top of a 2D molecule diagram coordinated with a bar chart that represents a SMILES string. We demonstrate how attributions calculated for SMILES strings can be evaluated and better interpreted through interactivity with two use cases.

CONCLUSIONS

Data scientists can use XSMILES to understand their models' behavior and compare multiple modeling approaches. The tool provides a set of parameters to adapt the visualization to users' needs and it can be integrated into different platforms. We believe XSMILES can support data scientists to develop, improve, and communicate their models by making it easier to identify patterns and compare attributions through interactive exploratory visualization.