Diagnostic Artificial Intelligence Research Articles

Use in clinical practice of an automated screening method of diabetic retinopathy that can be derived using a diagnostic artificial intelligence system

Abstract Background and Objective To compare the diagnostic performance of an autonomous diagnostic artificial intelligence (AI) system for the diagnosis of derivable diabetic retinopathy (RDR) with manual classification. Materials and Methods Patients with type 1 and type 2 diabetes participated in a diabetic retinopathy (RD) screening program between 2011–2012. 2 images of each eye were collected. Unidentifiable retinal images were obtained, one centered on the disc and one on the fovea. The exams were classified with th e autonomous AI system and manually by anonymous ophthalmologists. The results of the AI system and manual classification were compared in terms of sensitivity and specificity for the diagnosis of both (RDR) and diabetic retinopathy with decreased vision (VTDR). Results 10.257 retinografias of 5.360 eyes of 2680 subjects were included. According to the manual classification, the prevalence of RDR was 4.14% and that of VTDR 2.57%. The AI system recorded 100% (95% CI: 97% -100%) sensitivity and 81.82% (95% CI: 80% -83%) specificity for RDR, and 100% (95% CI: 95% -100%) of sensitivity and 94.64% (95% CI: 94% -95%) of specificity for VTDR. Conclusions Compared to the manual classification, the autonomous diagnostic AI system registered a high sensitivity (100%) and specificity (82%) in the diagnosis of RDR and macular edema in people with diabetes. Due to its immediate diagnosis, the autonomous diagnostic AI system can increase the accessibility of RDR screening in primary care settings.

Artificial Intelligence and its future potential in lung cancer screening.

Artificial intelligence (AI) simulates intelligent behavior as well as critical thinking comparable to a human being and can be used to analyze and interpret complex medical data. The application of AI in imaging diagnostics reduces the burden of radiologists and increases the sensitivity of lung cancer screening so that the morbidity and mortality associated with lung cancer can be decreased. In this article, we have tried to evaluate the role of artificial intelligence in lung cancer screening, as well as the future potential and efficiency of AI in the classification of nodules. The relevant studies between 2010-2020 were selected from the PubMed database after excluding animal studies and were analyzed for the contribution of AI. Techniques such as deep learning and machine learning allow automatic characterization and classification of nodules with high precision and promise an advanced lung cancer screening method in the future. Even though several combination models with high performance have been proposed, an effectively validated model for routine use still needs to be improvised. Combining the performance of artificial intelligence with a radiologist's expertise offers a successful outcome with higher accuracy. Thus, we can conclude that higher sensitivity, specificity, and accuracy of lung cancer screening and classification of nodules is possible through the integration of artificial intelligence and radiology. The validation of models and further research is to be carried out to determine the feasibility of this integration.

Cystoscopic Imaging for Bladder Cancer Detection Based on Stepwise Organic Transfer Learning with a Pretrained Convolutional Neural Network.

Background: Nonmuscle-invasive bladder cancer is diagnosed, treated, and monitored using cystoscopy. Artificial intelligence (AI) is increasingly used to augment tumor detection, but its performance is hindered by the limited availability of cystoscopic images required to form a large training data set. This study aimed to determine whether stepwise transfer learning with general images followed by gastroscopic images can improve the accuracy of bladder tumor detection on cystoscopic imaging. Materials and Methods: We trained a convolutional neural network with 1.2 million general images, followed by 8728 gastroscopic images. In the final step of the transfer learning process, the model was additionally trained with 2102 cystoscopic images of normal bladder tissue and bladder tumors collected at the University of Tsukuba Hospital. The diagnostic accuracy was evaluated using a receiver operating characteristic curve. The diagnostic performance of the models trained with cystoscopic images with or without stepwise organic transfer learning was compared with that of medical students and urologists with varying levels of experience. Results: The model developed by stepwise organic transfer learning had 95.4% sensitivity and 97.6% specificity. This performance was better than that of the other models and comparable with that of expert urologists. Notably, it showed superior diagnostic accuracy when tumors occupied >10% of the image. Conclusions: Our findings demonstrate the value of stepwise organic transfer learning in applications with limited data sets for training and further confirm the value of AI in medical diagnostics. Here, we applied deep learning to develop a tool to detect bladder tumors with an accuracy comparable with that of a urologist. To address the limitation that few bladder tumor images are available to train the model, we demonstrate that pretraining with general and gastroscopic images yields superior results.

Reporting of screening and diagnostic AI rarely acknowledges ethical, legal, and social implications: a mass media frame analysis

BackgroundHealthcare is a rapidly expanding area of application for Artificial Intelligence (AI). Although there is considerable excitement about its potential, there are also substantial concerns about the negative impacts of these technologies. Since screening and diagnostic AI tools now have the potential to fundamentally change the healthcare landscape, it is important to understand how these tools are being represented to the public via the media.MethodsUsing a framing theory approach, we analysed how screening and diagnostic AI was represented in the media and the frequency with which media articles addressed the benefits and the ethical, legal, and social implications (ELSIs) of screening and diagnostic AI.ResultsAll the media articles coded (n = 136) fit into at least one of three frames: social progress (n = 131), economic development (n = 59), and alternative perspectives (n = 9). Most of the articles were positively framed, with 135 of the articles discussing benefits of screening and diagnostic AI, and only 9 articles discussing the ethical, legal, and social implications.ConclusionsWe found that media reporting of screening and diagnostic AI predominantly framed the technology as a source of social progress and economic development. Screening and diagnostic AI may be represented more positively in the mass media than AI in general. This represents an opportunity for health journalists to provide publics with deeper analysis of the ethical, legal, and social implications of screening and diagnostic AI, and to do so now before these technologies become firmly embedded in everyday healthcare delivery.

Cost-effectiveness of Artificial Intelligence for Proximal Caries Detection

Artificial intelligence (AI) can assist dentists in image assessment, for example, caries detection. The wider health and cost impact of employing AI for dental diagnostics has not yet been evaluated. We compared the cost-effectiveness of proximal caries detection on bitewing radiographs with versus without AI. U-Net, a fully convolutional neural network, had been trained, validated, and tested on 3,293, 252, and 141 bitewing radiographs, respectively, on which 4 experienced dentists had marked carious lesions (reference test). Lesions were stratified for initial lesions (E1/E2/D1, presumed noncavitated, receiving caries infiltration if detected) and advanced lesions (D2/D3, presumed cavitated, receiving restorative care if detected). A Markov model was used to simulate the consequences of true- and false-positive and true- and false-negative detections, as well as the subsequent decisions over the lifetime of patients. A German mixed-payers perspective was adopted. Our health outcome was tooth retention years. Costs were measured in 2020 euro. Monte-Carlo microsimulations and univariate and probabilistic sensitivity analyses were conducted. The incremental cost-effectiveness ratio (ICER) and the cost-effectiveness acceptability at different willingness-to-pay thresholds were quantified. AI showed an accuracy of 0.80; dentists’ mean accuracy was significantly lower at 0.71 (minimum–maximum: 0.61–0.78, P < 0.05). AI was significantly more sensitive than dentists (0.75 vs. 0.36 [0.19–0.65]; P = 0.006), while its specificity was not significantly lower (0.83 vs. 0.91 [0.69–0.98]; P > 0.05). In the base-case scenario, AI was more effective (tooth retention for a mean 64 [2.5%–97.5%: 61–65] y) and less costly (298 [244–367] euro) than assessment without AI (62 [59–64] y; 322 [257–394] euro). The ICER was −13.9 euro/y (i.e., AI saved money at higher effectiveness). In the majority (>77%) of all cases, AI was less costly and more effective. Applying AI for caries detection is likely to be cost-effective, mainly as fewer lesions remain undetected. Notably, this cost-effectiveness requires dentists to manage detected early lesions nonrestoratively.

Uso en la práctica clínica, de un método de cribado automatizado de retinopatía diabética derivable mediante un sistema de inteligencia artificial de diagnóstico

Background and objectiveTo compare the diagnostic performance of an autonomous diagnostic artificial intelligence (AI) system for the diagnosis of derivable diabetic retinopathy (RDR) with manual classification. Materials and methodsPatients with type 1 and type 2 diabetes participated in a diabetic retinopathy (DR) screening program between 2011-2012. 2 images of each eye were collected. Unidentifiable retinal images were obtained, one centered on the disc and one on the fovea. The exams were classified with the autonomous AI system and manually by anonymous ophthalmologists. The results of the AI system and manual classification were compared in terms of sensitivity and specificity for the diagnosis of both (RDR) and diabetic retinopathy with decreased vision (VTDR). Results10,257 retinal inages of 5,630 eyes of 2,680 subjects were included. According to the manual classification, the prevalence of RDR was 4.14% and that of VTDR 2.57%. The AI system recorded 100% (95% CI: 97-100%) sensitivity and 81.82% (95% CI: 80 -83%) specificity for RDR, and 100% (95% CI: 95-100%) of sensitivity and 94.64% (95% CI: 94-95%) of specificity for VTDR. ConclusionsCompared to the manual classification, the autonomous diagnostic AI system registered a high sensitivity (100%) and specificity (82%) in the diagnosis of RDR and macular edema in people with diabetes. Due to its immediate diagnosis, the autonomous diagnostic AI system can increase the accessibility of RDR screening in primary care settings.

A narrative review of digital pathology and artificial intelligence: focusing on lung cancer.

The emergence of whole slide imaging technology allows for pathology diagnosis on a computer screen. The applications of digital pathology are expanding, from supporting remote institutes suffering from a shortage of pathologists to routine use in daily diagnosis including that of lung cancer. Through practice and research large archival databases of digital pathology images have been developed that will facilitate the development of artificial intelligence (AI) methods for image analysis. Currently, several AI applications have been reported in the field of lung cancer; these include the segmentation of carcinoma foci, detection of lymph node metastasis, counting of tumor cells, and prediction of gene mutations. Although the integration of AI algorithms into clinical practice remains a significant challenge, we have implemented tumor cell count for genetic analysis, a helpful application for routine use. Our experience suggests that pathologists often overestimate the contents of tumor cells, and the use of AI-based analysis increases the accuracy and makes the tasks less tedious. However, there are several difficulties encountered in the practical use of AI in clinical diagnosis. These include the lack of sufficient annotated data for the development and validation of AI systems, the explainability of black box AI models, such as those based on deep learning that offer the most promising performance, and the difficulty in defining the ground truth data for training and validation owing to inherent ambiguity in most applications. All of these together present significant challenges in the development and clinical translation of AI methods in the practice of pathology. Additional research on these problems will help in resolving the barriers to the clinical use of AI. Helping pathologists in developing knowledge of the working and limitations of AI will benefit the use of AI in both diagnostics and research.

Human-computer collaboration for skin cancer recognition.

The rapid increase in telemedicine coupled with recent advances in diagnostic artificial intelligence (AI) create the imperative to consider the opportunities and risks of inserting AI-based support into new paradigms of care. Here we build on recent achievements in the accuracy of image-based AI for skin cancer diagnosis to address the effects of varied representations of AI-based support across different levels of clinical expertise and multiple clinical workflows. We find that good quality AI-based support of clinical decision-making improves diagnostic accuracy over that of either AI or physicians alone, and that the least experienced clinicians gain the most from AI-based support. We further find that AI-based multiclass probabilities outperformed content-based image retrieval (CBIR) representations of AI in the mobile technology environment, and AI-based support had utility in simulations of second opinions and of telemedicine triage. In addition to demonstrating the potential benefits associated with good quality AI in the hands of non-expert clinicians, we find that faulty AI can mislead the entire spectrum of clinicians, including experts. Lastly, we show that insights derived from AI class-activation maps can inform improvements in human diagnosis. Together, our approach and findings offer a framework for future studies across the spectrum of image-based diagnostics to improve human-computer collaboration in clinical practice.

Artificial intelligence system for detecting superficial laryngopharyngeal cancer with high efficiency of deep learning.

There are no published reports evaluating the ability of artificial intelligence (AI) in the endoscopic diagnosis of superficial laryngopharyngeal cancer (SLPC). We presented our newly developed diagnostic AI model for SLPC detection. We used RetinaNet for object detection. SLPC and normal laryngopharyngeal mucosal images obtained from narrow-band imaging were used for the learning and validation data sets. Each independent data set comprised 400 SLPC and 800 normal mucosal images. The diagnostic AI model was constructed stage-wise and evaluated at each learning stage using validation data sets. In the validation data sets (100 SLPC cases), the median tumor size was 13.2 mm; flat/elevated/depressed types were found in 77/21/2 cases. Sensitivity, specificity, and accuracy improved each time a learning image was added and were 95.5%, 98.4%, and 97.3%, respectively, after learning all SLPC and normal mucosal images. The novel AI model is helpful for detection of laryngopharyngeal cancer at an early stage.

Validation of Automated Screening for Referable Diabetic Retinopathy With an Autonomous Diagnostic Artificial Intelligence System in a Spanish Population.

The purpose of this study is to compare the diagnostic performance of an autonomous artificial intelligence (AI) system for the diagnosis of referable diabetic retinopathy (RDR) to manual grading by Spanish ophthalmologists. Subjects with type 1 and 2 diabetes participated in a diabetic retinopathy (DR) screening program in 2011 to 2012 in Valencia (Spain), and two images per eye were collected according to their standard protocol. Mydriatic drops were used in all patients. Retinal images-one disc and one fovea centered-were obtained under the Medical Research Ethics Committee approval and de-identified. Exams were graded by the autonomous AI system (IDx-DR, Coralville, Iowa, United States), and manually by masked ophthalmologists using adjudication. The outputs of the AI system and manual adjudicated grading were compared using sensitivity and specificity for diagnosis of both RDR and vision-threatening diabetic retinopathy (VTDR). A total of 2680 subjects were included in the study. According to manual grading, prevalence of RDR was 111/2680 (4.14%) and of VTDR was 69/2680 (2.57%). Against manual grading, the AI system had a 100% (95% confidence interval [CI]: 97%-100%) sensitivity and 81.82% (95% CI: 80%-83%) specificity for RDR, and a 100% (95% CI: 95%-100%) sensitivity and 94.64% (95% CI: 94%-95%) specificity for VTDR. Compared to manual grading by ophthalmologists, the autonomous diagnostic AI system had high sensitivity (100%) and specificity (82%) for diagnosing RDR and macular edema in people with diabetes in a screening program. Because of its immediate, point of care diagnosis, autonomous diagnostic AI has the potential to increase the accessibility of RDR screening in primary care settings.

Lessons Learned About Autonomous AI: Finding a Safe, Efficacious, and Ethical Path Through the Development Process

Artificial intelligence (AI) describes systems capable of making decisions of high cognitive complexity; autonomous AI systems in healthcare are AI systems that make clinical decisions without human oversight. Such rigorously validated medical diagnostic AI systems hold great promise for improving access to care, increasing accuracy, and lowering cost, while enabling specialist physicians to provide the greatest value by managing and treating patients whose outcomes can be improved. Ensuring that autonomous AI provides these benefits requires evaluation of the autonomous AI's effect on patient outcome, design, validation, data usage, and accountability, from a bioethics and accountability perspective. We performed a literature review of bioethical principles for AI, and derived evaluation rules for autonomous AI, grounded in bioethical principles. The rules include patient outcome, validation, reference standard, design, data usage, and accountability for medical liability. Application of the rules explains successful US Food and Drug Administration (FDA) de novo authorization of an example, the first autonomous point-of-care diabetic retinopathy examination de novo authorized by the FDA, after a preregistered clinical trial. Physicians need to become competent in understanding the potential risks and benefits of autonomous AI, and understand its design, safety, efficacy and equity, validation, and liability, as well as how its data were obtained. The autonomous AI evaluation rules introduced here can help physicians understand limitations and risks as well as the potential benefits of autonomous AI for their patients.

Surgery in the 2020s: Implications of advancing technology for patients and the workforce

As the surgical workforce, surgical techniques and patient expectations change, the Royal College of Surgeons of England is actively engaged in taking forward the recommendations of its Future of Surgery Commission. Here the commission's chair articulates the implications for smaller hospitals and the need for achieving interoperability and safe sharing of patient data across different systems, so enabling immediate access to patients' records across healthcare organisations; extension of regulation to surgical care practitioners, reflecting the recent decision to regulate physician associates and physician assistants; introducing a UK-wide registry of surgical devices, with tracking for implantable devices; implementing a robotics strategy to help the NHS plan and purchase new surgical robotics, as well as monitor their use and the effect on outcomes; and investing in genomic medicine and artificial intelligence for diagnostics, and in stem-cell research for treatment.

Exploring the impact and applications of artificial intelligence in advancing modern medical diagnostic practices-role of healthcare providers

Introduction: Since its inception in 1956, artificial intelligence (AI) has advanced significantly, especially in the past decade. AI's integration into healthcare has revolutionized medical diagnostic practices, enabling faster and more accurate analysis of medical records. By mimicking human intelligence, AI facilitates the processing of vast amounts of data, thus improving diagnosis, treatment, and patient care. Aim: This review article aims to explore the impact and applications of AI in modern medical diagnostics and evaluate its role across various healthcare providers, including physicians, pharmacists, nurses, radiologists, and pathologists. Methods: The article reviews recent advancements in AI technologies and their implementation in healthcare. It examines the benefits of AI across different medical domains and its impact on improving diagnostic accuracy, patient management, and treatment outcomes. Results: AI has demonstrated significant benefits in healthcare by enhancing diagnostic accuracy, personalizing treatment plans, and improving patient outcomes. Key technologies such as machine learning, artificial neural networks, and natural language processing have been pivotal in advancing medical diagnostics and patient care. Conclusion: AI is increasingly vital in modern medicine, offering solutions to complex diagnostic and treatment challenges. Its applications improve healthcare efficiency, accuracy, and patient satisfaction.

Psychosocial Factors Affecting Artificial Intelligence Adoption in Health Care in China: Cross-Sectional Study.

BackgroundPoor quality primary health care is a major issue in China, particularly in blindness prevention. Artificial intelligence (AI) could provide early screening and accurate auxiliary diagnosis to improve primary care services and reduce unnecessary referrals, but the application of AI in medical settings is still an emerging field.ObjectiveThis study aimed to investigate the general public’s acceptance of ophthalmic AI devices, with reference to those already used in China, and the interrelated influencing factors that shape people’s intention to use these devices.MethodsWe proposed a model of ophthalmic AI acceptance based on technology acceptance theories and variables from other health care–related studies. The model was verified via a 32-item questionnaire with 7-point Likert scales completed by 474 respondents (nationally random sampled). Structural equation modeling was used to evaluate item and construct reliability and validity via a confirmatory factor analysis, and the model’s path effects, significance, goodness of fit, and mediation and moderation effects were analyzed.ResultsStandardized factor loadings of items were between 0.583 and 0.876. Composite reliability of 9 constructs ranged from 0.673 to 0.841. The discriminant validity of all constructs met the Fornell and Larcker criteria. Model fit indicators such as standardized root mean square residual (0.057), comparative fit index (0.915), and root mean squared error of approximation (0.049) demonstrated good fit. Intention to use (R2=0.515) is significantly affected by subjective norms (beta=.408; P<.001), perceived usefulness (beta=.336; P=.03), and resistance bias (beta=–.237; P=.02). Subjective norms and perceived behavior control had an indirect impact on intention to use through perceived usefulness and perceived ease of use. Eye health consciousness had an indirect positive effect on intention to use through perceived usefulness. Trust had a significant moderation effect (beta=–.095; P=.049) on the effect path of perceived usefulness to intention to use.ConclusionsThe item, construct, and model indicators indicate reliable interpretation power and help explain the levels of public acceptance of ophthalmic AI devices in China. The influence of subjective norms can be linked to Confucian culture, collectivism, authoritarianism, and conformity mentality in China. Overall, the use of AI in diagnostics and clinical laboratory analysis is underdeveloped, and the Chinese public are generally mistrustful of medical staff and the Chinese medical system. Stakeholders such as doctors and AI suppliers should therefore avoid making misleading or over-exaggerated claims in the promotion of AI health care products.

P839Lifetime cost-effectiveness of diagnostic artificial intelligence tool for evaluating individuals with stable chest pain. The co-operative ARTICA registry database

Abstract Background Non-invasive cardiac imaging testing has been often favored as an initial test for symptomatic patients with at least intermediate pre-test likelihood (pt-lk) of obstructive CAD. Despite this condition, uncertainty remains regarding the optimal testing strategies. It is known that intelligence applied with automatic decision support system (AI DSS) is able to correctly identify absence of significant CAD versus standard care (SD) in patients with stable chest pain (SCP). No evidence of long-term cost-effectiveness about AI DSS has been published in this setting. Purpose The aim is to determine the cost-effectiveness of AI DSS when applied to individuals without known CAD presenting with stable chest pain syndrome. Methods 1725 subjects, 982 males, age 61±12 years, with SCP were referred for clinical evaluation by human standard care (SD) and AI DSS administration during same day visit on a 2 years period. Exercise treadmill test (ETT), coronary tomographic angiography (CTA), invasive coronary angiography (ICA), stress echocardiography (SE)/gated myocardial perfusion scintigraphy (gMPS) and follow up/no tests (FNT) alone and combined strategies were analyzed. For the post-diagnosis follow up period of 16±3 months, we employed a Markov model based on 1-year cycle to account for outcomes for those correctly diagnosed with CAD. All subjects performed CTA to verify presence of CAD. CAD was defined as ≥70% stenosis in at least one major epicardial coronary artery vessels. Monte Carlo simulation was performed to derive mean values for costs and QALYs at different CAD prevalence of 15%, 50% and 80%. Results Data from ARTICA registry about lifelong costs based upon different diagnostic strategies in subjects with 15%, 50% and 80% CAD pt-lk are shown in Table. Lifelong costs related to strategies FNT (€) ETT-SE/gMPS-ICA (€) SE/gMPS-ICA (€) CTA-ICA (€) CTA-SE/gMPS-ICA pt-lk CAD 15% AI DSS 350 8,250 8,850 10,450 11,020 SD 1,015 11,100 12,715 12.215 12,215 pt-lk CAD 50% AI DSS 1,610 17,375 19,540 20,410 20,110 SD 1,855 19,650 21,340 22,950 22,115 pt-lk CAD 80% AI DSS 2,910 28,210 30,875 31,215 31,765 CD 4,110 32,715 34,815 35,755 35,660 Conclusion Data from ARTICA registry demonstrate that automatic use of AI DSS result in improved costs and enhanced effectiveness when compared with human SD in subjects with stable chest pain.

Update on thyroid ultrasound: a narrative review from diagnostic criteria to artificial intelligence techniques.

ObjectiveUltrasound imaging is well known to play an important role in the detection of thyroid disease, but the management of thyroid ultrasound remains inconsistent. Both standardized diagnostic criteria and new ultrasound technologies are essential for improving the accuracy of thyroid ultrasound. This study reviewed the global guidelines of thyroid ultrasound and analyzed their common characteristics for basic clinical screening. Advances in the application of a combination of thyroid ultrasound and artificial intelligence (AI) were also presented.Data sourcesAn extensive search of the PubMed database was undertaken, focusing on research published after 2001 with keywords including thyroid ultrasound, guideline, AI, segmentation, image classification, and deep learning.Study selectionSeveral types of articles, including original studies and literature reviews, were identified and reviewed to summarize the importance of standardization and new technology in thyroid ultrasound diagnosis.ResultsUltrasound has become an important diagnostic technique in thyroid nodules. Both standardized diagnostic criteria and new ultrasound technologies are essential for improving the accuracy of thyroid ultrasound. In the standardization, since there are no global consensus exists, common characteristics such as a multi-feature diagnosis, the performance of lymph nodes, explicit indications of fine needle aspiration, and the diagnosis of special populations should be focused on. Besides, evidence suggests that AI technique has a good effect on the unavoidable limitations of traditional ultrasound, and the combination of diagnostic criteria and AI may lead to a great promotion in thyroid diagnosis.ConclusionStandardization and development of novel techniques are key factors to improving thyroid ultrasound, and both should be considered in normal clinical use.

Techniques in Evaluating Nursing Expert Systems: A Case Study

This study addresses the problems in evaluating nursing diagnostic artificial intelligence (AI) expert systems. Two separate experiments (N = 49) were conducted using a computer expert system. The first experiment, the "white box" experiment (n = 9), compared the diagnostic techniques applied by experience RNs against the programmed techniques used by the expert system. The second experiment, the "black box" experiment (n = 40), compared diagnostic results of beginning nurses against the computer expert systems results. In some cases the computer outperformed the nurses and vice versa. The evaluation techniques, as applied in both experiments, enhance the ability of nurses to evaluate and select AI expert systems to be used in computer-assisted diagnosis of nursing problems.