Deep learning algorithm in detecting intracranial hemorrhages on emergency computed tomographies

There is an urgent need for streamlining radiology Quality Assurance (QA) programs to make them better and faster. Here, we present a novel approach, Artificial Intelligence (AI)-Based Quality Assurance by Restricted Investigation of Unequal Scores (AQUARIUS), for re-defining radiology QA, which reduces human effort by up to several orders of magnitude over existing approaches. AQUARIUS typically includes automatic comparison of AI-based image analysis with natural language processing (NLP) on radiology reports. Only the usually small subset of cases with discordant reads is subsequently reviewed by human experts. To demonstrate the clinical applicability of AQUARIUS, we performed a clinical QA study on Intracranial Hemorrhage (ICH) detection in 1936 head CT scans from a large academic hospital. Immediately following image acquisition, scans were automatically analyzed for ICH using a commercially available software (Aidoc, Tel Aviv, Israel). Cases rated positive for ICH by AI (ICH-AI+) were automatically flagged in radiologists' reading worklists, where flagging was randomly switched off with probability 50%. Using AQUARIUS with NLP on final radiology reports and targeted expert neuroradiology review of only 29 discordantly classified cases reduced the human QA effort by 98.5%, where we found a total of six non-reported true ICH+ cases, with radiologists' missed ICH detection rates of 0.52% and 2.5% for flagged and non-flagged cases, respectively. We conclude that AQUARIUS, by combining AI-based image analysis with NLP-based pre-selection of cases for targeted human expert review, can efficiently identify missed findings in radiology studies and significantly expedite radiology QA programs in a hybrid human-machine interoperability approach.

Background The use of artificial intelligence (AI) algorithms for the diagnosis of skin diseases has shown promise in experimental settings but has not yet been tested in real-life conditions. The COVID-19 pandemic led to a worldwide disruption of health systems, increasing the use of telemedicine. There is an opportunity to include AI algorithms in the teledermatology workflow. Objective The aim of this study is to test the performance of and physicians’ preferences regarding an AI algorithm during the evaluation of patients via teledermatology. Methods We performed a prospective study in 340 cases from 281 patients using patient-taken photos during teledermatology encounters. The photos were evaluated by an AI algorithm and the diagnosis was compared with the clinician’s diagnosis. Physicians also reported whether the AI algorithm was useful or not. Results The balanced (in-distribution) top-1 accuracy of the algorithm (47.6%) was comparable to the dermatologists (49.7%) and residents (47.7%) but superior to the general practitioners (39.7%; P=.049). Exposure to the AI algorithm results was considered useful in 11.8% of visits (n=40) and the teledermatologist correctly modified the real-time diagnosis in 0.6% (n=2) of cases. Algorithm performance was associated with patient skin type and image quality. Conclusions AI algorithms appear to be a promising tool in the triage and evaluation of lesions in patient-taken photographs via telemedicine. Conflicts of Interest None declared.

Myopic maculopathy (MM) is a major cause of vision impairment globally. Artificial intelligence (AI) and deep learning (DL) algorithms for detecting MM from fundus images could potentially improve diagnosis and assist screening in a variety of health care settings. To evaluate DL algorithms for MM classification and segmentation and compare their performance with that of ophthalmologists. The Myopic Maculopathy Analysis Challenge (MMAC) was an international competition to develop automated solutions for 3 tasks: (1) MM classification, (2) segmentation of MM plus lesions, and (3) spherical equivalent (SE) prediction. Participants were provided 3 subdatasets containing 2306, 294, and 2003 fundus images, respectively, with which to build algorithms. A group of 5 ophthalmologists evaluated the same test sets for tasks 1 and 2 to ascertain performance. Results from model ensembles, which combined outcomes from multiple algorithms submitted by MMAC participants, were compared with each individual submitted algorithm. This study was conducted from March 1, 2023, to March 30, 2024, and data were analyzed from January 15, 2024, to March 30, 2024. DL algorithms submitted as part of the MMAC competition or ophthalmologist interpretation. MM classification was evaluated by quadratic-weighted κ (QWK), F1 score, sensitivity, and specificity. MM plus lesions segmentation was evaluated by dice similarity coefficient (DSC), and SE prediction was evaluated by R2 and mean absolute error (MAE). The 3 tasks were completed by 7, 4, and 4 teams, respectively. MM classification algorithms achieved a QWK range of 0.866 to 0.901, an F1 score range of 0.675 to 0.781, a sensitivity range of 0.667 to 0.778, and a specificity range of 0.931 to 0.945. MM plus lesions segmentation algorithms achieved a DSC range of 0.664 to 0.687 for lacquer cracks (LC), 0.579 to 0.673 for choroidal neovascularization, and 0.768 to 0.841 for Fuchs spot (FS). SE prediction algorithms achieved an R2 range of 0.791 to 0.874 and an MAE range of 0.708 to 0.943. Model ensemble results achieved the best performance compared to each submitted algorithms, and the model ensemble outperformed ophthalmologists at MM classification in sensitivity (0.801; 95% CI, 0.764-0.840 vs 0.727; 95% CI, 0.684-0.768; P = .006) and specificity (0.946; 95% CI, 0.939-0.954 vs 0.933; 95% CI, 0.925-0.941; P = .009), LC segmentation (DSC, 0.698; 95% CI, 0.649-0.745 vs DSC, 0.570; 95% CI, 0.515-0.625; P < .001), and FS segmentation (DSC, 0.863; 95% CI, 0.831-0.888 vs DSC, 0.790; 95% CI, 0.742-0.830; P < .001). In this diagnostic study, 15 AI models for MM classification and segmentation on a public dataset made available for the MMAC competition were validated and evaluated, with some models achieving better diagnostic performance than ophthalmologists.

Trusted evidence. Informed decisions. Better health.

Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive, and heterogeneous interstitial lung disease with a median survival of 2–5 years. Though the diagnosis has been improved due to newly published guidelines, the recognition of the prognosis of IPF remains a challenge. Recently, several studies attempted to build prognostic models by extracting predictive variates from pulmonary function data, basic information, or chest computed tomography (CT) and CT-derived parameters with clinical characteristics. Artificial intelligence (AI) algorithms, including principal component analysis, support vector machine, random survival forest, and convolutional neural network, could be applied to the procedure of IPF prognostic model, that is, region of interest extraction, image feature selection, clinical feature selection, and model construction. Compared to human visualization, AI algorithms show a higher efficiency in calculating and extracting deep features and a lower inter-observer variation. Thus, this review provides a comprehensive CT evaluation of IPF prognostic models and discusses the role of AI in constructing IPF prognostic models. The potential improvements of AI in CT assessments, including time-series CT analysis, optimization of AI algorithms, utilization of multi-modal data, and discovery of new biomarkers through unsupervised algorithms, could be introduced to make a more accurate and convenient assessment for the prognosis of IPF patients. This review describes the status quo and future direction of AI applications in CT analysis for prognostic models of IPF.Take home messageThe review summarizes the applications of CT and AI algorithms for prognostic models in IPF and procedures of model construction. It reveals the current limitations and prospects of AI-aid models, and helps clinicians to recognize the AI algorithms and apply them to more clinical work.

This article is devoted to the creation of a model of observational diagnostics for patients in dentistry using artificial intelligence as an information and measurement system. Artificial intelligence technology and algorithms in the field of clinical and radiographic image analysis in general dentistry and orthopedics have become the most common systems, contributing to accurate and timely diagnosis of a particular patient. Along with clinical practice images, radiographs are key tools for graphic visualization of the patient's dentition. A model of observational diagnostics for patients using artificial intelligence technology as the latest tool in the healthcare industry can become a structured method of information standardization and measurements in general dentistry. The model of observational diagnostics can serve as a fundamental component of functional diagnostics based on artificial intelligence algorithms, since they have a special potential for increasing the reliability and consistency of diagnostic measurements and information used by a dentist during treatment planning and restoration of the dentition. The model of observational diagnostics of dental patients presented by the authors implies a significant step forward in the development of highprecision methods of functional diagnostics, monitoring and analysis of patient condition measurements. The algorithm of the observational diagnostics model was integrated into the program, the operation of which is based on artificial intelligence technology in order to increase the efficiency, consistency, optimality and accuracy of the processes carried out in clinical practice. The purpose of the study is to determine the characteristics of the model of observational diagnostics of dental patients using artificial intelligence as an information and measuring system. Main results of the study: 1) the characteristics of the practical application of artificial intelligence technology for radiographs, clinical images of patients' teeth are provided; 2) the essential aspects of the model of observational diagnostics of dental patients, as well as the features of its practical application for planning dental treatment of patients are highlighted; 3) the results of practical testing of the model of observational diagnostics of dental patients are reflected (using the example of detection and treatment of caries). Research materials: the results of academic studies on the assessment of functional diagnostics of oral cavity and dentition pathologies using artificial intelligence technology; practical testing of the model of observational diagnostics for dental patients (using the example of detection and treatment of caries in a 49yearold woman). Research methods: systematization, comparative analysis, contrastive analysis, generalization, abstractlogical method, induction, deduction, systems approach, data conceptualization, graphical and tabular visualization of data, construction of informationmeasuring systems, artificial intelligence methods, study of clinical images and radiographs of patients' dental arches. The main conclusions of the study: 1) information and measuring instruments, the operation of which is based on artificial intelligence technology, have become the basis for the rapid processing of significant amounts of information, increasing the accuracy and efficiency of clinical decisions in dentistry. These information and measuring systems allow us to determine complex patterns on radiographs and clinical images of dental arches, to increase the degree of accuracy of functional diagnostics, in particular, in the presence of subtle pathologies and disorders; 2) artificial intelligence technology cannot replace a qualified dentist, such information and measuring systems only complement the accumulated human professional experience, allowing us to jointly carry out functional diagnostics of patients with a dental profile; 3) the potential of artificial intelligence technologies to create comprehensive plans and reports for dental treatment and dental restoration forms the basis for the joint activities of the latest tools and a dentist. In the context of the study, it is noted that artificial intelligence algorithms have become a powerful informationmeasuring tool for improving the decisionmaking process in dental practice, since digital technology promptly and quickly provides feedback to the dentist about missed anomalies or suboptimal methods of dental treatment and restorative medicine. Integration of the model of observational diagnostics for dental patients will make it possible to form an algorithm for the operation of artificial intelligence that fully complies with the recommendations for functional diagnostics and dental treatment of patients, developed on the basis of factual information. The use of artificial intelligence algorithms in dental practice will increase the efficiency of the general industry standard for providing dental services to patients.

A Comprehensive Review of AI Algorithms for Performance Prediction, Optimization, and Process Control in Desalination Systems.

Background As per the Global Burden of Disease Study (GBD) 2019, chronic obstructive pulmonary disease (COPD) and asthma had a significant global burden. COPD is the fourth leading cause of death in the world and the second leading cause of death and disability-adjusted life years (DALYs) in India. Pulmonary function tests (PFTs) are commonly used diagnostic tools. They include spirometry, body plethysmography, and diffusion capacity. In regions with limited resources, pulmonologists often only have access to spirometry. Additionally, PFT pattern interpretation is usually unreliable and subjective. Recent rapid advances in artificial intelligence (AI) algorithms can bridge the gaps. Objectives This study aims to compare the accuracy of the predictions made by AI algorithms with pulmonologists using limited clinical data and spirometry. It also examines the consistency and accuracy of pulmonologists' predictions based on the same information. Methodology Different AI algorithms were trained, and their accuracy was evaluated. Spirometry and limited clinical data from 440 patients were interpreted by an AI algorithm and eight senior pulmonologists. Accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for the different patterns. Results Approximately 60% of the cases involved male patients, and about 70% were between the ages of 21 and 60. The Fleiss's kappa was 0.46. While the accuracy of pulmonologists against the gold standard was 65.82%, the accuracy of the AI was 86.59%. Conclusions PFTs, when interpreted by pulmonologists with limited clinical and spirometry data, have lower accuracy and higher variability. AI algorithms can consistently produce high accuracy. Adopting such technology among clinicians, especially in resource-constrained regions, could be pivotal for offering quality healthcare. In addition, it will also help in getting rid of inter-observer variability.

Background and Objectives Hand and wrist fractures are among the most frequently encountered injuries in emergency departments and are often misdiagnosed, particularly when interpreted by non-specialist clinicians. These diagnostic errors can lead to treatment delays and long-term complications. Artificial intelligence (AI), particularly deep learning algorithms, is emerging as a promising adjunct to improve diagnostic accuracy in radiographic fracture detection. This study aims to evaluate the effectiveness of Artificial Intelligence (AI) in detecting hand and wrist fractures compared to manual radiographic interpretation by clinicians. Materials and Methods A systematic review and meta-analysis were conducted to assess the diagnostic performance of AI models in detecting hand and wrist fractures compared to conventional radiographic interpretation by clinicians. A comprehensive search of PubMed, Google Scholar, Science Direct, and Wiley Online Library was performed. Eligible studies included those utilizing AI for fracture detection with sensitivity and specificity data. Pooled estimates were calculated using fixed- and random-effects models. Heterogeneity was assessed via I 2 statistics, and publication bias was examined using funnel plots and Egger’s test. Results Eighteen studies met inclusion criteria. The pooled sensitivity and specificity under the random-effects model were 0.910 and 0.912, respectively, indicating high diagnostic accuracy of AI models. However, substantial heterogeneity (I 2 = 99.09% for sensitivity; 96.43% for specificity) and publication bias were observed, likely due to variations in AI algorithms, sample sizes, and study designs. Conclusions Most AI models demonstrated good diagnostic accuracy, with high sensitivity and specificity scores (≥90%). However, some models fell short in sensitivity and specificity (≤90%), indicating performance variations across different AI models or algorithms. From a clinical perspective, AI models with lower sensitivity scores may fail to detect hand and wrist fractures, potentially delaying treatment, while those with lower specificity scores could lead to unnecessary interventions—treating hands and wrists that are not fractured.

Evaluation of Atrial Fibrillation Risk and Outcome after Allogeneic Transplantation Using an Artificial Intelligence ECG Algorithm and Echocardiographic Parameters in an MDS Cohort

Artificial intelligence research started with computers trying to take the place of what humans have to do intelligently. Research started in the 1950s went through several ups and downs and reached the same period of the third boom as it is now. With the shocking situation where Alpha Go defeated Lee Se-dol, the strongest player in Go, in 2016, interest in artificial intelligence increased rapidly, and stories about the future situations that artificial intelligence will bring about, such as the possibility and singularity of artificial intelligence, are talked about even among the general public. Certainly, artificial intelligence has the potential to fundamentally change the way humans live, not just technological advances. The real value of artificial intelligence algorithms is prediction. At the center of all the algorithmic revolutions that have taken place in the various fields of modern society, there is one unchanging purpose: prediction. The algorithm for predicting the risk of recidivism used in US law enforcement fits precisely with the principle that individual humans behave in a predictable and consistent manner. While using the algorithm of predicting the risk of a second offender, an artificial intelligence algorithm, not a judge, actually takes the place of the defendant s decision on whether or not to be arrested or sentenced. Automated decision making continues to grow at an unprecedented rate and benefits because machine learning offers the possibility to extend the automated decision-making process, allowing wider, deeper decisions without human intervention. It is also very large and is expected to continue to expand its use. However, the risks are as great as the benefits of artificial intelligence algorithms. The risks of artificial intelligence algorithms outweigh the individual risks of any algorithmic technology specifically applied. Despite the widespread use of artificial intelligence in the social sphere, the reality is that the problems of artificial intelligence cannot be properly grasped. However, people who were treated differently due to automatic decision-making by artificial intelligence began to question the fairness or fairness of artificial intelligence, and in particular, while causing sensitive problems such as discriminatory results, controversy surrounding artificial intelligence algorithms gradually became more and more controversial. It is expanding. Even if a decision made by artificial intelligence is wrong or causes negative effects such as discrimination, there is a big problem that there are few means to object to this. In a situation where automated decision-making is more likely to threaten human autonomy and dignity, in order to secure an individual s autonomous personality, make sure that the entire process of the individual s automatic decision-making that affects him or her is fair and error-free. It is of utmost importance to know and allow humans to directly intervene if necessary. Although available data is increasing and algorithms are gradually improving, artificial intelligence algorithms do not completely eliminate the uncertainty posed by decision making. Eventually, there are cases in which humans, as finalists, have to make important decisions in situations where uncertainty has not been resolved. It is necessary to build a system in which artificial intelligence algorithms and human experts cooperate well to make the best decisions, and in addition to the direction of such a collaboration system establishment, the problem of legal responsibility due to errors in decision-making in artificial intelligence algorithms or collaboration systems is necessary. I want to deal with it in this paper.

BackgroundThe purpose of this scoping review was to explore the current applications of objective gait analysis using inertial measurement units, custom algorithms and artificial intelligence algorithms in detecting neurological and musculoskeletal gait altering pathologies from healthy gait patterns.MethodsLiterature searches were conducted of four electronic databases (Medline, PubMed, Embase and Web of Science) to identify studies that assessed the accuracy of these custom gait analysis models with inputs derived from wearable devices. Data was collected according to the preferred reporting items for systematic reviews and meta-analysis statement guidelines.ResultsA total of 23 eligible studies were identified for inclusion in the present review, including 10 custom algorithms articles and 13 artificial intelligence algorithms articles. Nine studies evaluated patients with Parkinson’s disease of varying severity and subtypes. Support vector machine was the commonest adopted artificial intelligence algorithm model, followed by random forest and neural networks. Overall classification accuracy was promising for articles that use artificial intelligence algorithms, with nine articles achieving more than 90% accuracy.ConclusionsCurrent applications of artificial intelligence algorithms are reasonably effective discrimination between pathological and non-pathological gait. Of these, machine learning algorithms demonstrate the additional capacity to handle complicated data input, when compared to other custom algorithms. Notably, there has been increasing application of machine learning algorithms for conducting gait analysis. More studies are needed with unsupervised methods and in non-clinical settings to better reflect the community and home-based usage.

Simple SummaryThe primary purpose of this review is to provide an in-depth analysis of existing Artificial Intelligence (AI) algorithms used in the field of prostate cancer (PC) for diagnosis and treatment. This review aims to show the research community that AI-enabled technologies have the potential for widespread growth and penetration of PC diagnostics and therapeutics to simplify and accelerate existing healthcare processes.As medical science and technology progress towards the era of “big data”, a multi-dimensional dataset pertaining to medical diagnosis and treatment is becoming accessible for mathematical modelling. However, these datasets are frequently inconsistent, noisy, and often characterized by a significant degree of redundancy. Thus, extensive data processing is widely advised to clean the dataset before feeding it into the mathematical model. In this context, Artificial intelligence (AI) techniques, including machine learning (ML) and deep learning (DL) algorithms based on artificial neural networks (ANNs) and their types, are being used to produce a precise and cross-sectional illustration of clinical data. For prostate cancer patients, datasets derived from the prostate-specific antigen (PSA), MRI-guided biopsies, genetic biomarkers, and the Gleason grading are primarily used for diagnosis, risk stratification, and patient monitoring. However, recording diagnoses and further stratifying risks based on such diagnostic data frequently involves much subjectivity. Thus, implementing an AI algorithm on a PC’s diagnostic data can reduce the subjectivity of the process and assist in decision making. In addition, AI is used to cut down the processing time and help with early detection, which provides a superior outcome in critical cases of prostate cancer. Furthermore, this also facilitates offering the service at a lower cost by reducing the amount of human labor. Herein, the prime objective of this review is to provide a deep analysis encompassing the existing AI algorithms that are being deployed in the field of prostate cancer (PC) for diagnosis and treatment. Based on the available literature, AI-powered technology has the potential for extensive growth and penetration in PC diagnosis and treatment to ease and expedite the existing medical process.

Rationale and Objectives: Accurate diagnosis and staging of cervical precancers is essential for practical medicine in determining the extent of the lesion extension and determines the most correct and effective therapeutic approach. For accurate diagnosis and staging of cervical precancers, we aim to create a diagnostic method optimized by artificial intelligence (AI) algorithms and validated by achieving accurate and favorable results by conducting a clinical trial, during which we will use the diagnostic method optimized by artificial intelligence (AI) algorithms, to avoid errors, to increase the understanding on interpretation of colposcopy images and improve therapeutic planning. Materials and Methods: The optimization of the method will consist in the development and formation of artificial intelligence models, using complicated convolutional neural networks (CNN) to identify precancers and cancers on colposcopic images. We will use topologies that have performed well in similar image recognition projects, such as Visual Geometry Group Network (VGG16), Inception deep neural network with an architectural design that consists of repeating components referred to as Inception modules (Inception), deeply separable convolutions that significantly reduce the number of parameters (MobileNet) that is a class of Convolutional Neural Network (CNN), Return of investment for machine Learning (ROI), Fully Convolutional Network (U-Net) and Overcomplete Convolutional Network Kite-Net (KiU-Net). Validation of the diagnostic method, optimized by algorithm of artificial intelligence will consist of achieving accurate results on diagnosis and staging of cervical precancers by conducting a randomized, controlled clinical trial, for a period of 17 months. Results: We will validate the computer assisted diagnostic (CAD) method through a clinical study and, secondly, we use various network topologies specified above, which have produced promising results in the tasks of image model recognition and by using this mixture. By using this method in medical practice, we aim to avoid errors, provide precision in diagnosing, staging and establishing the therapeutic plan in cervical precancers using AI. Conclusion: This diagnostic method, optimized by artificial intelligence algorithms and validated by the clinical trial, which we consider “second opinion”, improves the quality standard in diagnosing, staging and establishing therapeutic conduct in cervical precancer.

Artificial Intelligence: The Future of Maxillofacial Prognosis and Diagnosis?