Development of machine learning models for diagnosis of glaucoma

Analysis of anterior segment in primary angle closure suspect with deep learning models

OBJECTIVE

To analyze primary angle closure suspect (PACS) patients' anatomical characteristics of anterior chamber configuration, and to establish artificial intelligence (AI)-aided diagnostic system for PACS screening.

METHODS

A total of 1668 scans of 839 patients were included in this cross-sectional study. The subjects were divided into two groups: PACS group and normal group. With anterior segment optical coherence tomography scans, the anatomical diversity between two groups was compared, and anterior segment structure features of PACS were extracted. Then, AI-aided diagnostic system was constructed, which based different algorithms such as classification and regression tree (CART), random forest (RF), logistic regression (LR), VGG-16 and Alexnet. Then the diagnostic efficiencies of different algorithms were evaluated, and compared with junior physicians and experienced ophthalmologists.

RESULTS

RF [sensitivity (Se) = 0.84; specificity (Sp) = 0.92; positive predict value (PPV) = 0.82; negative predict value (NPV) = 0.95; area under the curve (AUC) = 0.90] and CART (Se = 0.76, Sp = 0.93, PPV = 0.85, NPV = 0.92, AUC = 0.90) showed better performance than LR (Se = 0.68, Sp = 0.91, PPV = 0.79, NPV = 0.90, AUC = 0.86). In convolutional neural networks (CNN), Alexnet (Se = 0.83, Sp = 0.95, PPV = 0.92, NPV = 0.87, AUC = 0.85) was better than VGG-16 (Se = 0.84, Sp = 0.90, PPV = 0.85, NPV = 0.90, AUC = 0.79). The performance of 2 CNN algorithms was better than 5 junior physicians, and the mean value of diagnostic indicators of 2 CNN algorithm was similar to experienced ophthalmologists.

CONCLUSION

PACS patients have distinct anatomical characteristics compared with health controls. AI models for PACS screening are reliable and powerful, equivalent to experienced ophthalmologists.

Machine learning-based ensemble approach in prediction of lung cancer predisposition using XRCC1 gene polymorphism

The employment of machine learning approaches has shown promising results in predicting cancer. In the current study, polymorphisms data of five single nucleotide polymorphisms (SNPs) of DNA repair gene XRCC1 (XRCC1 399, XRCC1 194, XRCC1 206, XRCC1 632, XRCC1 280) of the north Indian population along with four smoking status data is considered as an input to the proposed ensemble model to predict the risk of individual susceptibility to the lung cancer. The prediction accuracy of the proposed ensemble model for cancer predisposition was found to be 85%. The model performance is also evaluated using sensitivity, specificity, precision and the Gini index, which is found in the range of 0.83-0.87. The proposed model also outperformed in all evaluation parameters when compared with the individual Model (LM, SVM, RF, KNN and baseline neural net). Collectively, current results suggest the potential of the proposed ensemble model in predicting the risk of cancer based on XRCC1 SNPs data.Communicated by Ramaswamy H. Sarma.

Role of Artificial Intelligence in Retinal Diseases

Artificial intelligence (AI) has already found its way into ophthalmology, with the first approved algorithms that can be used in clinical routine. Retinal diseases in particular are proving to be an important area of application for AI, as they are the main cause of blindness and the number of patients suffering from retinal diseases is constantly increasing. At the same time, regular imaging using high-resolution modalities in a standardised and reproducible manner generates immense amounts of data that can hardly be processed by human experts. In addition, ophthalmology is constantly experiencing new developments and breakthroughs that require a re-evaluation of patient management in routine clinical practice. AI is able to analyse these volumes of data efficiently and objectively and also provide new insights into disease progression and therapeutic mechanisms by identifying relevant biomarkers. AI can make a significant contribution to screening, classification and prognosis of various retinal diseases and can ultimately be a clinical decision support system, that significantly reduces the burden on both everyday clinical practice and the healthcare system, by making more efficient use of costly and time-consuming resources.

Role of artificial intelligence, machine learning and deep learning models in corneal disorders - A narrative review

In the last decade, artificial intelligence (AI) has significantly impacted ophthalmology, particularly in managing corneal diseases, a major reversible cause of blindness. This review explores AI's transformative role in the corneal subspecialty, which has adopted advanced technology for superior clinical judgment, early diagnosis, and personalized therapy. While AI's role in anterior segment diseases is less documented compared to glaucoma and retinal pathologies, this review highlights its integration into corneal diagnostics through imaging techniques like slit-lamp biomicroscopy, anterior segment optical coherence tomography (AS-OCT), and in vivo confocal biomicroscopy. AI has been pivotal in refining decision-making and prognosis for conditions such as keratoconus, infectious keratitis, and dystrophies. Multi-disease deep learning neural networks (MDDNs) have shown diagnostic ability in classifying corneal diseases using AS-OCT images, achieving notable metrics like an AUC of 0.910. AI's progress over two decades has significantly improved the accuracy of diagnosing conditions like keratoconus and microbial keratitis. For instance, AI has achieved a 90.7% accuracy rate in classifying bacterial and fungal keratitis and an AUC of 0.910 in differentiating various corneal diseases. Convolutional neural networks (CNNs) have enhanced the analysis of color-coded corneal maps, yielding up to 99.3% diagnostic accuracy for keratoconus. Deep learning algorithms have also shown robust performance in detecting fungal hyphae on in vivo confocal microscopy, with precise quantification of hyphal density. AI models combining tomography scans and visual acuity have demonstrated up to 97% accuracy in keratoconus staging according to the Amsler-Krumeich classification. However, the review acknowledges the limitations of current AI models, including their reliance on binary classification, which may not capture the complexity of real-world clinical presentations with multiple coexisting disorders. Challenges also include dependency on data quality, diverse imaging protocols, and integrating multimodal images for a generalized AI diagnosis. The need for interpretability in AI models is emphasized to foster trust and applicability in clinical settings. Looking ahead, AI has the potential to unravel the intricate mechanisms behind corneal pathologies, reduce healthcare's carbon footprint, and revolutionize diagnostic and management paradigms. Ethical and regulatory considerations will accompany AI's clinical adoption, marking an era where AI not only assists but augments ophthalmic care.

Comparison of Glaucoma Diagnosis by Telemedicine, In-Person Ophthalmologist, and Optometrist

PRCIS

Diagnosis of glaucoma through telemedicine demonstrates moderate agreement with in-person ophthalmologist (MD) and in-person optometrist (OD) diagnosis, providing evidence that telemedicine is a timely, accurate screening method in settings where an in-person visit may not be feasible.

OBJECTIVE

To compare diagnostic agreement of glaucoma between in-person MD, in-person OD, and a simulated telemedicine program.

PATIENTS AND METHODS

A cross-sectional study of patients with normal optic nerve structural and functional imaging and new patients referred for glaucoma evaluation examined in-person by an MD for glaucoma with a dilated examination and structural and functional optic nerve testing (optical coherence tomography, photos, and visual field); examined in person by an OD with a dilated examination and optic nerve testing; and structural and functional optic nerve testing reviewed separately by 2 ophthalmologists [telemedicine ophthalmologist reviewer 1 (TMD1), telemedicine ophthalmologist reviewer 2 (TMD2)] with masking of prior MD and OD diagnoses. Interrater agreement between each diagnostic method (MD, OD, TMD1, and TMD2) of normal versus disease (open angle glaucoma, normal tension glaucoma, other types of glaucoma, other optic nerve disorders, ocular hypertension, and glaucoma suspect) for each eye was calculated (Cohen unweighted kappa).

RESULTS

A total of 100 patients with a median age of 66 years (interquartile range: 59-72), male (40%) and white (62%) were analyzed. There was moderate agreement between MD and telemedicine [TMD1 kappa 0.49 (95% CI: 0.37-0.61), TMD2 kappa 0.44 (95% CI: 0.32-0.56)] and between MD and OD diagnosis [0.41 (95% CI: 0.28-0.54)] and fair-moderate agreement between OD and telemedicine [TMD1: 0.46 (95% CI: 0.34-0.58), TMD2: 0.61 (95% CI: 0.50-0.72)].

CONCLUSIONS

The simulated telemedicine approach had comparable levels of agreement in glaucoma diagnosis with in-person fellowship-trained ophthalmologists, presenting a crucial complementary role in screening and increasing access to care, particularly in rural or underserved settings.

Screening Strategies and Methodologies

PRCIS

While glaucoma is a leading cause of irreversible vision loss, it presents technical challenges in the design and implementation of screening. New technologies such as PRS and AI offer potential improvements in our ability to identify people at high risk of sight loss from glaucoma and may improve the viability of screening for this important disease.

PURPOSE

To review the current evidence and concepts around screening for glaucoma.

METHODS/RESULTS

A group of glaucoma-focused clinician scientists drew on knowledge and experience around glaucoma, its etiology, and the options for screening. Glaucoma is a chronic progressive optic neuropathy affecting around 76 million individuals worldwide and is the leading cause of irreversible blindness globally. Early stages of the disease are asymptomatic meaning a substantial proportion of cases remain undiagnosed. Early detection and timely intervention reduce the risk of glaucoma-related visual morbidity. However, imperfect tests and a relatively low prevalence currently limit the viability of population-based screening approaches. The diagnostic yield of opportunistic screening strategies, relying on the identification of disease during unrelated health care encounters, such as cataract clinics and diabetic retinopathy screening programs, focusing on older people and/or those with a family history, are hindered by a large number of false-positive and false-negative results. Polygenic risk scores (PRS) offer personalized risk assessment for adult-onset glaucoma. In addition, artificial intelligence (AI) algorithms have shown impressive performance, comparable to expert humans, in discriminating between potentially glaucomatous and non-glaucomatous eyes. These emerging technologies may offer a meaningful improvement in diagnostic yield in glaucoma screening.

CONCLUSIONS

While glaucoma is a leading cause of irreversible vision loss, it presents technical challenges in the design and implementation of screening. New technologies such as PRS and AI offer potential improvements in our ability to identify people at high risk of sight loss from glaucoma and may improve the viability of screening for this important disease.

A Dual-Modal Fusion Network Using Optical Coherence Tomography and Fundus Images in Detection of Glaucomatous Optic Neuropathy

PURPOSE

We designed a dual-modal fusion network to detect glaucomatous optic neuropathy, which utilized both retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images.

METHODS

A total of 327 healthy subjects (410 eyes) and 87 glaucomatous optic neuropathy patients (113 eyes) were included. The retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images were used as predictors in the dual-modal fusion network to diagnose glaucoma. The area under the receiver operation characteristic curve, accuracy, sensitivity, and specificity were measured to compare our method and other approaches.

RESULTS

The accuracy of our dual-modal fusion network using both retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images was 0.935 and we achieved a significant larger area under the receiver operation characteristic curve of our method with 0.968 (95% confidence interval, 0.937-0.999). For only using retinal nerve fiber layer thickness, we compared the area under the receiver operation characteristic curves between our network and other three approaches: 0.916 (95% confidence interval, 0.855, 0.977) with our optical coherence tomography Net; 0.841 (95% confidence interval, 0.749, 0.933) with Clock sectors division; 0.862 (95% confidence interval, 0.757, 0.968) with inferior, superior, nasal temporal sectors division and 0.886 (95% confidence interval, 0.815, 0.957) with optic disc sectors division. For only using fundus images, we compared the area under the receiver operation characteristic curves between our network and other two approaches: 0.867 (95% confidence interval: 0.781-0.952) with our Image Net; 0.774 (95% confidence interval: 0.670, 0.878) with ResNet50; 0.747 (95% confidence interval: 0.628, 0.866) with VGG16.

CONCLUSION

Our dual-modal fusion network utilizing both retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images can diagnose glaucoma with a much better performance than the current approaches based on optical coherence tomography only or fundus images only.

Integrating Deep Learning with Electronic Health Records for Early Glaucoma Detection: A Multi-Dimensional Machine Learning Approach

BACKGROUND

Recent advancements in deep learning have significantly impacted ophthalmology, especially in glaucoma, a leading cause of irreversible blindness worldwide. In this study, we developed a reliable predictive model for glaucoma detection using deep learning models based on clinical data, social and behavior risk factor, and demographic data from 1652 participants, split evenly between 826 control subjects and 826 glaucoma patients.

METHODS

We extracted structural data from control and glaucoma patients' electronic health records (EHR). Three distinct machine learning classifiers, the Random Forest and Gradient Boosting algorithms, as well as the Sequential model from the Keras library of TensorFlow, were employed to conduct predictive analyses across our dataset. Key performance metrics such as accuracy, F1 score, precision, recall, and the area under the receiver operating characteristics curve (AUC) were computed to both train and optimize these models.

RESULTS

The Random Forest model achieved an accuracy of 67.5%, with a ROC AUC of 0.67, outperforming the Gradient Boosting and Sequential models, which registered accuracies of 66.3% and 64.5%, respectively. Our results highlighted key predictive factors such as intraocular pressure, family history, and body mass index, substantiating their roles in glaucoma risk assessment.

CONCLUSIONS

This study demonstrates the potential of utilizing readily available clinical, lifestyle, and demographic data from EHRs for glaucoma detection through deep learning models. While our model, using EHR data alone, has a lower accuracy compared to those incorporating imaging data, it still offers a promising avenue for early glaucoma risk assessment in primary care settings. The observed disparities in model performance and feature significance show the importance of tailoring detection strategies to individual patient characteristics, potentially leading to more effective and personalized glaucoma screening and intervention.

Telemedicine for Screening and Follow-Up of Glaucoma: A Descriptive Study

Introduction: Glaucoma is a leading cause of irreversible blindness. It is a prevalent disease worldwide, affecting ∼70 million people and expected to reach up to 112 million by 2040. Purpose: The aim of this study is to describe the implementation and initial experience of a telemedicine program to monitor glaucoma and glaucoma suspect patients in a large, integrated health care system during the COVID-19 pandemic. Methods: A retrospective chart review of established glaucoma or glaucoma suspect patients who participated in a telemedicine evaluation at the ophthalmic center of a large, Colombian health care system between June 2020 and April 2023 was conducted. Clinical and sociodemographic variables were analyzed. Generated clinical orders for additional testing, surgical procedures, follow-ups, and referrals, as well as changes in medical treatment, were evaluated. Results: A total of 11,034 telemedicine consults were included. The mean ± standard deviation age of this group was 63 ± 17.2 years and 67% were female. Of the patients who attended teleconsults, 49% were glaucoma suspects and 38.5% were followed with a diagnosis of open-angle glaucoma. After the consult, 25% of patients were referred to a glaucoma specialist, 40% had additional testing ordered, and 8% had a surgical procedure ordered, mainly laser iridotomy (409 cases). Almost a third of patients returned for subsequent telemedicine visits after the initial encounter. Despite some technical difficulties, 99.8% of patients attended and completed their scheduled telemedicine appointments. Conclusions: A telemedicine program aimed to monitor established glaucoma patients can be successfully implemented. Established patients within an integrated health care system have high adherence to the virtual model. Further research by health care institutions and government agencies will be key to expand coverage to additional populations. Clinical Trial Registration Number: CEIFUS 1026-24.

Real-world artificial intelligence-based interpretation of fundus imaging as part of an eyewear prescription renewal protocol

OBJECTIVE

A real-world evaluation of the diagnostic accuracy of the Opthai® software for artificial intelligence-based detection of fundus image abnormalities in the context of the French eyewear prescription renewal protocol (RNO).

METHODS

A single-center, retrospective review of the sensitivity and specificity of the software in detecting fundus abnormalities among consecutive patients seen in our ophthalmology center in the context of the RNO protocol from July 28 through October 22, 2021. We compared abnormalities detected by the software operated by ophthalmic technicians (index test) to diagnoses confirmed by the ophthalmologist following additional examinations and/or consultation (reference test).

RESULTS

The study included 2056 eyes/fundus images of 1028 patients aged 6-50years. The software detected fundus abnormalities in 149 (7.2%) eyes or 107 (10.4%) patients. After examining the same fundus images, the ophthalmologist detected abnormalities in 35 (1.7%) eyes or 20 (1.9%) patients. The ophthalmologist did not detect abnormalities in fundus images deemed normal by the software. The most frequent diagnoses made by the ophthalmologist were glaucoma suspect (0.5% of eyes), peripapillary atrophy (0.44% of eyes), and drusen (0.39% of eyes). The software showed an overall sensitivity of 100% (95% CI 0.879-1.00) and an overall specificity of 94.4% (95% CI 0.933-0.953). The majority of false-positive software detections (5.6%) were glaucoma suspect, with the differential diagnosis of large physiological optic cups. Immediate OCT imaging by the technician allowed diagnosis by the ophthalmologist without separate consultation for 43/53 (81%) patients.

CONCLUSION

Ophthalmic technicians can use this software for highly-sensitive screening for fundus abnormalities that require evaluation by an ophthalmologist.

Assessing the efficacy of 2D and 3D CNN algorithms in OCT-based glaucoma detection

Glaucoma is a progressive neurodegenerative disease characterized by the gradual degeneration of retinal ganglion cells, leading to irreversible blindness worldwide. Therefore, timely and accurate diagnosis of glaucoma is crucial, enabling early intervention and facilitating effective disease management to mitigate further vision deterioration. The advent of optical coherence tomography (OCT) has marked a transformative era in ophthalmology, offering detailed visualization of the macula and optic nerve head (ONH) regions. In recent years, both 2D and 3D convolutional neural network (CNN) algorithms have been applied to OCT image analysis. While 2D CNNs rely on post-prediction aggregation of all B-scans within OCT volumes, 3D CNNs allow for direct glaucoma prediction from the OCT data. However, in the absence of extensively pre-trained 3D models, the comparative efficacy of 2D and 3D-CNN algorithms in detecting glaucoma from volumetric OCT images remains unclear. Therefore, this study explores the efficacy of glaucoma detection through volumetric OCT images using select state-of-the-art (SOTA) 2D-CNN models, 3D adaptations of these 2D-CNN models with specific weight transfer techniques, and a custom 5-layer 3D-CNN-Encoder algorithm. The performance across two distinct datasets is evaluated, each focusing on the macula and the ONH, to provide a comprehensive understanding of the models' capabilities in identifying glaucoma. Our findings demonstrate that the 2D-CNN algorithm consistently provided robust results compared to their 3D counterparts tested in this study for glaucoma detection, achieving AUC values of 0.960 and 0.943 for the macular and ONH OCT test images, respectively. Given the scarcity of pre-trained 3D models trained on extensive datasets, this comparative analysis underscores the overall utility of 2D and 3D-CNN algorithms in advancing glaucoma diagnostic systems in ophthalmology and highlights the potential of 2D algorithms for volumetric OCT image-based glaucoma detection.

Identifying necrotizing soft tissue infection using infectious fluid analysis and clinical parameters based on machine learning algorithms

Background

Determining the presence of necrotizing soft tissue infection (NSTI) poses a significant hurdle. As of late, there has been a notable increase in the application of artificial intelligence (AI) machine learning techniques in identifying diseases, a shift that can be attributed to their exceptional efficiency, unbiased nature, and high precision.

Methods

Information was gathered from a cohort of 13 patients suffering from NSTI, alongside 12 patients with cellulitis. The construction of NSTI diagnostic machine learning models utilized four different algorithms, specifically random forest, k-nearest neighbors (KNN), support vector machine (SVM), and logistic regression. These models were constructed based on 28 distinctive attributes identified through statistical examination. Following this, the diagnostic efficiency of each algorithms was evaluated. A novel random forest model, streamlined for clinical use, was later developed by focusing on 6 attributes that had the most pronounced influence on the accuracy of our initial random forest model.

Results

The following data was noted regarding the sensitivity and specificity of the four NSTI diagnostic models:logistic regression displayed 78.2 % and 83.7 %, KNN presented 79.1 % and 87.1 %, SVM showed 83.5 % and 86.3 %, and random forest exhibited 89.6 % and 92.9 %, respectively. In comparison, lactate levels in fluid demonstrated 100 % sensitivity and 76.9 % specificity at an optimal cut-off point of 69.6 mg/dL. Among all four machine learning models, random forest outperformed the others and also showed better results than fluid lactate. A newly constructed random forest model, created using 6 of the 13 identified features, displayed promising results in diagnosing NSTI, having a sensitivity and specificity of 90.2 % and 92.2 %, respectively.

Conclusions

Developing a diagnostic model for NSTI employing the random forest algorithm has resulted in a diagnostic technique that is more efficient, cost-effective, and expedient. This approach could provide healthcare practitioners with the tools to identify and manage NSTI with greater efficacy.

A hybrid framework for glaucoma detection through federated machine learning and deep learning models

BACKGROUND

Glaucoma, the second leading cause of global blindness, demands timely detection due to its asymptomatic progression. This paper introduces an advanced computerized system, integrates Machine Learning (ML), convolutional neural networks (CNNs), and image processing for accurate glaucoma detection using medical imaging data, surpassing prior research efforts.

METHOD

Developing a hybrid glaucoma detection framework using CNNs (ResNet50, VGG-16) and Random Forest. Models analyze pre-processed retinal images independently, and post-processing rules combine predictions for an overall glaucoma impact assessment.

RESULT

The hybrid framework achieves a significant 95.41% accuracy, with precision and recall at 99.37% and 88.37%, respectively. The F1 score, balancing precision and recall, reaches a commendable 93.52%. These results highlight the robustness and effectiveness of the hybrid framework in accurate glaucoma diagnosis.

CONCLUSION

In summary, our research presents an innovative hybrid framework combining CNNs and traditional ML models for glaucoma detection. Using ResNet50, VGG-16, and Random Forest in an ensemble approach yields remarkable accuracy, precision, recall, and F1 score. These results showcase the methodology's potential to enhance glaucoma diagnosis, emphasizing its promising role in early detection and preventing irreversible vision loss. The integration of ML and DNNs in medical imaging analysis suggests a valuable path for future advancements in ophthalmic healthcare.

Role of Machine Learning and Artificial Intelligence in the Diagnosis and Treatment of Refractive Errors for Enhanced Eye Care: A Systematic Review

A significant contributor to blindness and visual impairment globally is uncorrected refractive error. To plan effective interventions, eye care professionals must promptly identify people at a high risk of acquiring myopia, and monitor disease progress. Artificial intelligence (AI) and machine learning (ML) have enormous potential to improve diagnosis and treatment. This systematic review explores the current state of ML and AI applications in the diagnoses and treatment of refractory errors in optometry. A systematic review and meta-analysis of studies evaluating the diagnostic performance of AI-based tools in PubMed was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. To find relevant studies on the use of ML or AI in the diagnosis or treatment of refractive errors in optometry, a thorough search was conducted in various electronic databases such as PubMed, Google Scholar, and Web of Science. The search was limited to studies published between January 2015 and December 2022. The search terms used were "refractive errors," "myopia," "optometry," "machine learning," "ophthalmology," and "artificial intelligence." A total of nine studies met the inclusion criteria and were included in the final analysis. ML is increasingly being utilized for automating clinical data processing as AI technology progresses, making the formerly labor-intensive work possible. AI models that primarily use a neural network demonstrated exceptional efficiency and performance in the analysis of vast medical data, rivaling board-certified, healthcare professionals. Several studies showed that ML models could support diagnosis and clinical decision-making. Moreover, an ML algorithm predicted future refraction values in patients with myopia. AI and ML models have great potential to improve the diagnosis and treatment of refractive errors in optometry.

Uncovering the burden of hidradenitis suppurativa misdiagnosis and underdiagnosis: a machine learning approach

Hidradenitis suppurativa (HS) is a chronic inflammatory follicular skin condition that is associated with significant psychosocial and economic burden and a diminished quality of life and work productivity. Accurate diagnosis of HS is challenging due to its unknown etiology, which can lead to underdiagnosis or misdiagnosis that results in increased patient and healthcare system burden. We applied machine learning (ML) to a medical and pharmacy claims database using data from 2000 through 2018 to develop a novel model to better understand HS underdiagnosis on a healthcare system level. The primary results demonstrated that high-performing models for predicting HS diagnosis can be constructed using claims data, with an area under the curve (AUC) of 81%-82% observed among the top-performing models. The results of the models developed in this study could be input into the development of an impact of inaction model that determines the cost implications of HS diagnosis and treatment delay to the healthcare system.

Statistical performance review on diagnosis of leukemia, glaucoma and diabetes mellitus using AI

The growth of artificial intelligence (AI) in the healthcare industry tremendously increases the patient outcomes by reshaping the way we diagnose, treat and monitor patients. AI-based innovation in healthcare include exploration of drugs, personalized medicine, clinical diagnosis investigations, robotic-assisted surgery, verified prescriptions, pregnancy care for women, radiology, and reviewed patient information analytics. However, prediction of AI-based solutions are depends mainly on the implementation of statistical algorithms and input data set. In this article, statistical performance review on various algorithms, Accuracy, Precision, Recall and F1-Score used to predict the diagnosis of leukemia, glaucoma, and diabetes mellitus is presented. Review on statistical algorithms' performance, used for individual disease diagnosis gives a complete picture of various research efforts during the last two decades. At the end of statistical review on each disease diagnosis, we have discussed our inferences that will give future directions for the new researchers on selection of AI statistical algorithm as well as the input data set.

Artificial intelligence in glaucoma detection using color fundus photographs

PURPOSE

To explore the potential of artificial intelligence (AI) for glaucoma detection using deep learning algorithm and evaluate its accuracy for image classification of glaucomatous optic neuropathy (GON) from color fundus photographs.

METHODS

A total of 1375 color fundus photographs, 735 normal optic nerve head and 640 GON, were uploaded on the AI software for training, validation, and testing using deep learning model, which is based on Residual Network (Res Net) 50V2. For initial training and validation, 400 fundus images (200 normal and 200 GON) were uploaded and for the final training and testing 975 (535 normal and 440 GON) were uploaded later. Accuracy, sensitivity, and specificity were used to evaluate the image classification performance of the algorithm. Also, positive predictive value, negative predictive value, positive likelihood ratio, and negative likelihood ratio were calculated.

RESULTS

The model used in the study showed an image classification accuracy of 81.3%, sensitivity of 83%, and specificity of 80% for the detection of GON. The false-negative grading was 17% and false-positive grading was 20% for the image classification of GON. Coexistence of glaucoma in patients with high myopia, early glaucoma in a small disc, and software misclassification of GON were the reasons for false-negative results. Physiological large cupping in a large disc, myopic or titled disc, and software misclassification of normal optic disc were the reasons for false-positive results.

CONCLUSION

The model employed in this study achieved a good accuracy, and hence has a good potential in detection of GON using color fundus photographs.

Artificial intelligence in the diagnosis of glaucoma and neurodegenerative diseases

Artificial Intelligence is a rapidly expanding field within computer science that encompasses the emulation of human intelligence by machines. Machine learning and deep learning - two primary data-driven pattern analysis approaches under the umbrella of artificial intelligence - has created considerable interest in the last few decades. The evolution of technology has resulted in a substantial amount of artificial intelligence research on ophthalmic and neurodegenerative disease diagnosis using retinal images. Various artificial intelligence-based techniques have been used for diagnostic purposes, including traditional machine learning, deep learning, and their combinations. Presented here is a review of the literature covering the last 10 years on this topic, discussing the use of artificial intelligence in analysing data from different modalities and their combinations for the diagnosis of glaucoma and neurodegenerative diseases. The performance of published artificial intelligence methods varies due to several factors, yet the results suggest that such methods can potentially facilitate clinical diagnosis. Generally, the accuracy of artificial intelligence-assisted diagnosis ranges from 67-98%, and the area under the sensitivity-specificity curve (AUC) ranges from 0.71-0.98, which outperforms typical human performance of 71.5% accuracy and 0.86 area under the curve. This indicates that artificial intelligence-based tools can provide clinicians with useful information that would assist in providing improved diagnosis. The review suggests that there is room for improvement of existing artificial intelligence-based models using retinal imaging modalities before they are incorporated into clinical practice.

Deep Learning Detection of Early Retinal Peripheral Degeneration From Ultra-Widefield Fundus Photographs of Asymptomatic Young Adult (17-19 Years) Candidates to Airforce Cadets

Purpose

Artificial intelligence (AI)-assisted ultra-widefield (UWF) fundus photographic interpretation is beneficial to improve the screening of fundus abnormalities. Therefore we constructed an AI machine-learning approach and performed preliminary training and validation.

Methods

We proposed a two-stage deep learning-based framework to detect early retinal peripheral degeneration using UWF images from the Chinese Air Force cadets' medical selection between February 2016 and June 2022. We developed a detection model for the localization of optic disc and macula, which are used to find the peripheral areas. Then we developed six classification models for the screening of various retinal cases. We also compared our proposed framework with two baseline models reported in the literature. The performance of the screening models was evaluated by area under the receiver operating curve (AUC) with 95% confidence interval.

Results

A total of 3911 UWF fundus images were used to develop the deep learning model. The external validation included 760 UWF fundus images. The results of comparison study revealed that our proposed framework achieved competitive performance compared to existing baselines while also demonstrating significantly faster inference time. The developed classification models achieved an average AUC of 0.879 on six different retinal cases in the external validation dataset.

Conclusions

Our two-stage deep learning-based framework improved the machine learning efficiency of the AI model for fundus images with high resolution and many interference factors by maximizing the retention of valid information and compressing the image file size.

Translational Relevance

This machine learning model may become a new paradigm for developing UWF fundus photography AI-assisted diagnosis.

AI-based clinical assessment of optic nerve head robustness superseding biomechanical testing

BACKGROUND/AIMS

To use artificial intelligence (AI) to: (1) exploit biomechanical knowledge of the optic nerve head (ONH) from a relatively large population; (2) assess ONH robustness (ie, sensitivity of the ONH to changes in intraocular pressure (IOP)) from a single optical coherence tomography (OCT) volume scan of the ONH without the need for biomechanical testing and (3) identify what critical three-dimensional (3D) structural features dictate ONH robustness.

METHODS

316 subjects had their ONHs imaged with OCT before and after acute IOP elevation through ophthalmo-dynamometry. IOP-induced lamina cribrosa (LC) deformations were then mapped in 3D and used to classify ONHs. Those with an average effective LC strain superior to 4% were considered fragile, while those with a strain inferior to 4% robust. Learning from these data, we compared three AI algorithms to predict ONH robustness strictly from a baseline (undeformed) OCT volume: (1) a random forest classifier; (2) an autoencoder and (3) a dynamic graph convolutional neural network (DGCNN). The latter algorithm also allowed us to identify what critical 3D structural features make a given ONH robust.

RESULTS

All three methods were able to predict ONH robustness from a single OCT volume scan alone and without the need to perform biomechanical testing. The DGCNN (area under the curve (AUC): 0.76±0.08) outperformed the autoencoder (AUC: 0.72±0.09) and the random forest classifier (AUC: 0.69±0.05). Interestingly, to assess ONH robustness, the DGCNN mainly used information from the scleral canal and the LC insertion sites.

CONCLUSIONS

We propose an AI-driven approach that can assess the robustness of a given ONH solely from a single OCT volume scan of the ONH, and without the need to perform biomechanical testing. Longitudinal studies should establish whether ONH robustness could help us identify fast visual field loss progressors.

PRECIS

Using geometric deep learning, we can assess optic nerve head robustness (ie, sensitivity to a change in IOP) from a standard OCT scan that might help to identify fast visual field loss progressors.

Artificial intelligence in glaucoma: opportunities, challenges, and future directions

Artificial intelligence (AI) has shown excellent diagnostic performance in detecting various complex problems related to many areas of healthcare including ophthalmology. AI diagnostic systems developed from fundus images have become state-of-the-art tools in diagnosing retinal conditions and glaucoma as well as other ocular diseases. However, designing and implementing AI models using large imaging data is challenging. In this study, we review different machine learning (ML) and deep learning (DL) techniques applied to multiple modalities of retinal data, such as fundus images and visual fields for glaucoma detection, progression assessment, staging and so on. We summarize findings and provide several taxonomies to help the reader understand the evolution of conventional and emerging AI models in glaucoma. We discuss opportunities and challenges facing AI application in glaucoma and highlight some key themes from the existing literature that may help to explore future studies. Our goal in this systematic review is to help readers and researchers to understand critical aspects of AI related to glaucoma as well as determine the necessary steps and requirements for the successful development of AI models in glaucoma.

Normative Percentiles of Retinal Nerve Fiber Layer Thickness and Glaucomatous Visual Field Loss

Purpose

Circumpapillary retinal nerve fiber layer thickness (RNFLT) measurement aids in the clinical diagnosis of glaucoma. Spectral domain optical coherence tomography (SD-OCT) machines measure RNFLT and provide normative color-coded plots. In this retrospective study, we investigate whether normative percentiles of RNFLT (pRNFLT) from Spectralis SD-OCT improve prediction of glaucomatous visual field loss over raw RNFLT.

Methods

A longitudinal database containing OCT scans and visual fields from Massachusetts Eye & Ear glaucoma clinic patients was generated. Reliable OCT-visual field pairs were selected. Spectralis OCT normative distributions were extracted from machine printouts. Supervised machine learning models compared predictive performance between pRNFLT and raw RNFLT inputs. Regional structure-function associations were assessed with univariate regression to predict mean deviation (MD). Multivariable classification predicted MD, pattern standard deviation, MD change per year, and glaucoma hemifield test.

Results

There were 3016 OCT-visual field pairs that met the reliability criteria. Spectralis norms were found to be independent of age, sex, and ocular magnification. Regional analysis showed significant decrease in R2 from pRNFLT models compared to raw RNFLT models in inferotemporal sectors, across multiple regressors. In multivariable classification, there were no significant improvements in area under the curve of receiver operating characteristic curve (ROC-AUC) score with pRNFLT models compared to raw RNFLT models.

Conclusions

Our results challenge the assumption that normative percentiles from OCT machines improve prediction of glaucomatous visual field loss. Raw RNFLT alone shows strong prediction, with no models presenting improvement by the manufacturer norms. This may result from insufficient patient stratification in tested norms.

Translational Relevance

Understanding correlation of normative databases to visual function may improve clinical interpretation of OCT data.

Identifying, Understanding, and Addressing Disparities in Glaucoma Care in the United States

Glaucoma is the leading cause of irreversible blindness worldwide, currently affecting around 80 million people. Glaucoma prevalence is rapidly rising in the United States due to an aging population. Despite recent advances in the diagnosis and treatment of glaucoma, significant disparities persist in disease detection, management, and outcomes among the diverse patient populations of the United States. Research on disparities is critical to identifying, understanding, and addressing societal and healthcare inequalities. Disparities research is especially important and impactful in the context of irreversible diseases such as glaucoma, where earlier detection and intervention are the primary approach to improving patient outcomes. In this article, we first review recent studies identifying disparities in glaucoma care that affect patient populations based on race, age, and gender. We then review studies elucidating and furthering our understanding of modifiable factors that contribute to these inequities, including socioeconomic status (particularly age and education), insurance product, and geographic region. Finally, we present work proposing potential strategies addressing disparities in glaucoma care, including teleophthalmology and artificial intelligence. We also discuss the presence of non-modifiable factors that contribute to differences in glaucoma burden and can confound the detection of glaucoma disparities.

Translational Relevance

By recognizing underlying causes and proposing potential solutions, healthcare providers, policymakers, and other stakeholders can work collaboratively to reduce the burden of glaucoma and improve visual health and clinical outcomes in vulnerable patient populations.

Exploring alternative approaches to precision medicine through genomics and artificial intelligence - a systematic review

The core idea behind precision medicine is to pinpoint the subpopulations that differ from one another in terms of disease risk, drug responsiveness, and treatment outcomes due to differences in biology and other traits. Biomarkers are found through genomic sequencing. Multi-dimensional clinical and biological data are created using these biomarkers. Better analytic methods are needed for these multidimensional data, which can be accomplished by using artificial intelligence (AI). An updated review of 80 latest original publications is presented on four main fronts-preventive medicine, medication development, treatment outcomes, and diagnostic medicine-All these studies effectively illustrated the significance of AI in precision medicine. Artificial intelligence (AI) has revolutionized precision medicine by swiftly analyzing vast amounts of data to provide tailored treatments and predictive diagnostics. Through machine learning algorithms and high-resolution imaging, AI assists in precise diagnoses and early disease detection. AI's ability to decode complex biological factors aids in identifying novel therapeutic targets, allowing personalized interventions and optimizing treatment outcomes. Furthermore, AI accelerates drug discovery by navigating chemical structures and predicting drug-target interactions, expediting the development of life-saving medications. With its unrivaled capacity to comprehend and interpret data, AI stands as an invaluable tool in the pursuit of enhanced patient care and improved health outcomes. It's evident that AI can open a new horizon for precision medicine by translating complex data into actionable information. To get better results in this regard and to fully exploit the great potential of AI, further research is required on this pressing subject.

Discriminative-Region Multi-Label Classification of Ultra-Widefield Fundus Images

Ultra-widefield fundus image (UFI) has become a crucial tool for ophthalmologists in diagnosing ocular diseases because of its ability to capture a wide field of the retina. Nevertheless, detecting and classifying multiple diseases within this imaging modality continues to pose a significant challenge for ophthalmologists. An automated disease classification system for UFI can support ophthalmologists in making faster and more precise diagnoses. However, existing works for UFI classification often focus on a single disease or assume each image only contains one disease when tackling multi-disease issues. Furthermore, the distinctive characteristics of each disease are typically not utilized to improve the performance of the classification systems. To address these limitations, we propose a novel approach that leverages disease-specific regions of interest for the multi-label classification of UFI. Our method uses three regions, including the optic disc area, the macula area, and the entire UFI, which serve as the most informative regions for diagnosing one or multiple ocular diseases. Experimental results on a dataset comprising 5930 UFIs with six common ocular diseases showcase that our proposed approach attains exceptional performance, with the area under the receiver operating characteristic curve scores for each class spanning from 95.07% to 99.14%. These results not only surpass existing state-of-the-art methods but also exhibit significant enhancements, with improvements of up to 5.29%. These results demonstrate the potential of our method to provide ophthalmologists with valuable information for early and accurate diagnosis of ocular diseases, ultimately leading to improved patient outcomes.

Machine learning-couched treatment algorithms tailored to individualized profile of patients with primary anterior chamber angle closure predisposed to the glaucomatous optic neuropathy

Background

Primary angle closure glaucoma (PACG) is still one of the leading causes of irreversible blindness, with a trend towards an increase in the number of patients to 32.04 million by 2040, an increase of 58.4% compared with 2013. Health risk assessment based on multi-level diagnostics and machine learning-couched treatment algorithms tailored to individualized profile of patients with primary anterior chamber angle closure are considered essential tools to reverse the trend and protect vulnerable subpopulations against health-to-disease progression.

Aim

To develop a methodology for personalized choice of an effective method of primary angle closure (PAC) treatment based on comparing the prognosis of intraocular pressure (IOP) changes due to laser peripheral iridotomy (LPI) or lens extraction (LE).

Methods

The multi-parametric data analysis was used to develop models predicting individual outcomes of the primary angle closure (PAC) treatment with LPI and LE. For doing this, we suggested a positive dynamics in the intraocular pressure (IOP) after treatment, as the objective measure of a successful treatment. Thirty-seven anatomical parameters have been considered by applying artificial intelligence to the prospective study on 30 (LE) + 30 (LPI) patients with PAC.

Results and data interpretation in the framework of 3P medicine

Based on the anatomical and topographic features of the patients with PAC, mathematical models have been developed that provide a personalized choice of LE or LPI in the treatment. Multi-level diagnostics is the key tool in the overall advanced approach. To this end, for the future application of AI in the area, it is strongly recommended to consider the following:Clinically relevant phenotyping applicable to advanced population screeningSystemic effects causing suboptimal health conditions considered in order to cost-effectively protect affected individuals against health-to-disease transitionClinically relevant health risk assessment utilizing health/disease-specific molecular patterns detectable in body fluids with high predictive power such as a comprehensive tear fluid analysis.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-023-00337-1.

Diagnosis of Acanthamoeba Keratitis: Past, Present and Future

Acanthamoeba keratitis (AK) is a painful and sight-threatening parasitic corneal infection. In recent years, the incidence of AK has increased. Timely and accurate diagnosis is crucial during the management of AK, as delayed diagnosis often results in poor clinical outcomes. Currently, AK diagnosis is primarily achieved through a combination of clinical suspicion, microbiological investigations and corneal imaging. Historically, corneal scraping for microbiological culture has been considered to be the gold standard. Despite its technical ease, accessibility and cost-effectiveness, the long diagnostic turnaround time and variably low sensitivity of microbiological culture limit its use as a sole diagnostic test for AK in clinical practice. In this review, we aim to provide a comprehensive overview of the diagnostic modalities that are currently used to diagnose AK, including microscopy with staining, culture, corneal biopsy, in vivo confocal microscopy, polymerase chain reaction and anterior segment optical coherence tomography. We also highlight emerging techniques, such as next-generation sequencing and artificial intelligence-assisted models, which have the potential to transform the diagnostic landscape of AK.

Interpretable deep learning for diagnosis of fungal and acanthamoeba keratitis using in vivo confocal microscopy images

Infectious keratitis refers to a group of corneal disorders in which corneal tissues suffer inflammation and damage caused by pathogenic infections. Among these disorders, fungal keratitis (FK) and acanthamoeba keratitis (AK) are particularly severe and can cause permanent blindness if not diagnosed early and accurately. In Vivo Confocal Microscopy (IVCM) allows for imaging of different corneal layers and provides an important tool for an early and accurate diagnosis. In this paper, we introduce the IVCM-Keratitis dataset, which comprises of a total of 4001 sample images of AK and FK, as well as non-specific keratitis (NSK) and healthy corneas classes. We use this dataset to develop multiple deep-learning models based on Convolutional Neural Networks (CNNs) to provide automated assistance in enhancing the diagnostic accuracy of confocal microscopy in infectious keratitis. Densenet161 had the best performance among these models, with an accuracy, precision, recall, and F1 score of 93.55%, 92.52%, 94.77%, and 96.93%, respectively. Our study highlights the potential of deep learning models to provide automated diagnostic assistance for infectious keratitis via confocal microscopy images, particularly in the early detection of AK and FK. The proposed model can provide valuable support to both experienced and inexperienced eye-care practitioners in confocal microscopy image analysis, by suggesting the most likely diagnosis. We further demonstrate that these models can highlight the areas of infection in the IVCM images and explain the reasons behind their diagnosis by utilizing saliency maps, a technique used in eXplainable Artificial Intelligence (XAI) to interpret these models.

A knowledge-enhanced transform-based multimodal classifier for microbial keratitis identification

Microbial keratitis, a nonviral corneal infection caused by bacteria, fungi, and protozoa, is an urgent condition in ophthalmology requiring prompt treatment in order to prevent severe complications of corneal perforation and vision loss. It is difficult to distinguish between bacterial and fungal keratitis from image unimodal alone, as the characteristics of the sample images themselves are very close. Therefore, this study aims to develop a new deep learning model called knowledge-enhanced transform-based multimodal classifier that exploited the potential of slit-lamp images along with treatment texts to identify bacterial keratitis (BK) and fungal keratitis (FK). The model performance was evaluated in terms of the accuracy, specificity, sensitivity and the area under the curve (AUC). 704 images from 352 patients were divided into training, validation and testing set. In the testing set, our model reached the best accuracy was 93%, sensitivity was 0.97(95% CI [0.84,1]), specificity was 0.92(95% CI [0.76,0.98]) and AUC was 0.94(95% CI [0.92,0.96]), exceeding the benchmark accuracy of 0.86. The diagnostic average accuracies of BK ranged from 81 to 92%, respectively and those for FK were 89-97%. It is the first study to focus on the influence of disease changes and medication interventions on infectious keratitis and our model outperformed the benchmark models and reaching the state-of-the-art performance.

Does multidimensional daily information predict the onset of myopia? A 1-year prospective cohort study

PURPOSE

This study aimed to develop an interpretable machine learning model to predict the onset of myopia based on individual daily information.

METHOD

This study was a prospective cohort study. At baseline, non-myopia children aged 6-13 years old were recruited, and individual data were collected through interviewing students and parents. One year after baseline, the incidence of myopia was evaluated based on visual acuity test and cycloplegic refraction measurement. Five algorithms, Random Forest, Support Vector Machines, Gradient Boosting Decision Tree, CatBoost and Logistic Regression were utilized to develop different models and their performance was validated by area under curve (AUC). Shapley Additive exPlanations was applied to interpret the model output on the individual and global level.

RESULT

Of 2221 children, 260 (11.7%) developed myopia in 1 year. In univariable analysis, 26 features were associated with the myopia incidence. Catboost algorithm had the highest AUC of 0.951 in the model validation. The top 3 features for predicting myopia were parental myopia, grade and frequency of eye fatigue. A compact model using only 10 features was validated with an AUC of 0.891.

CONCLUSION

The daily information contributed reliable predictors for childhood's myopia onset. The interpretable Catboost model presented the best prediction performance. Oversampling technology greatly improved model performance. This model could be a tool in myopia preventing and intervention that can help identify children who are at risk of myopia, and provide personalized prevention strategies based on contributions of risk factors to the individual prediction result.

Characteristics of a large, labeled dataset for the training of artificial intelligence for glaucoma screening with fundus photographs

Purpose

Significant visual impairment due to glaucoma is largely caused by the disease being detected too late.

Objective

To build a labeled data set for training artificial intelligence (AI) algorithms for glaucoma screening by fundus photography, to assess the accuracy of the graders, and to characterize the features of all eyes with referable glaucoma (RG).

Design

Cross-sectional study.

Subjects

Color fundus photographs (CFPs) of 113 893 eyes of 60 357 individuals were obtained from EyePACS, California, United States, from a population screening program for diabetic retinopathy.

Methods

Carefully selected graders (ophthalmologists and optometrists) graded the images. To qualify, they had to pass the European Optic Disc Assessment Trial optic disc assessment with ≥ 85% accuracy and 92% specificity. Of 90 candidates, 30 passed. Each image of the EyePACS set was then scored by varying random pairs of graders as "RG," "no referable glaucoma (NRG)," or "ungradable (UG)." In case of disagreement, a glaucoma specialist made the final grading. Referable glaucoma was scored if visual field damage was expected. In case of RG, graders were instructed to mark up to 10 relevant glaucomatous features.

Main Outcome Measures

Qualitative features in eyes with RG.

Results

The performance of each grader was monitored; if the sensitivity and specificity dropped below 80% and 95%, respectively (the final grade served as reference), they exited the study and their gradings were redone by other graders. In all, 20 graders qualified; their mean sensitivity and specificity (standard deviation [SD]) were 85.6% (5.7) and 96.1% (2.8), respectively. The 2 graders agreed in 92.45% of the images (Gwet's AC2, expressing the inter-rater reliability, was 0.917). Of all gradings, the sensitivity and specificity (95% confidence interval) were 86.0 (85.2-86.7)% and 96.4 (96.3-96.5)%, respectively. Of all gradable eyes (n = 111 183; 97.62%) the prevalence of RG was 4.38%. The most common features of RG were the appearance of the neuroretinal rim (NRR) inferiorly and superiorly.

Conclusions

A large data set of CFPs was put together of sufficient quality to develop AI screening solutions for glaucoma. The most common features of RG were the appearance of the NRR inferiorly and superiorly. Disc hemorrhages were a rare feature of RG.

Financial Disclosures

Proprietary or commercial disclosure may be found after the references.

The use of machine learning and deep learning techniques to assess proprioceptive impairments of the upper limb after stroke

BACKGROUND

Robots can generate rich kinematic datasets that have the potential to provide far more insight into impairments than standard clinical ordinal scales. Determining how to define the presence or absence of impairment in individuals using kinematic data, however, can be challenging. Machine learning techniques offer a potential solution to this problem. In the present manuscript we examine proprioception in stroke survivors using a robotic arm position matching task. Proprioception is impaired in 50-60% of stroke survivors and has been associated with poorer motor recovery and longer lengths of hospital stay. We present a simple cut-off score technique for individual kinematic parameters and an overall task score to determine impairment. We then compare the ability of different machine learning (ML) techniques and the above-mentioned task score to correctly classify individuals with or without stroke based on kinematic data.

METHODS

Participants performed an Arm Position Matching (APM) task in an exoskeleton robot. The task produced 12 kinematic parameters that quantify multiple attributes of position sense. We first quantified impairment in individual parameters and an overall task score by determining if participants with stroke fell outside of the 95% cut-off score of control (normative) values. Then, we applied five machine learning algorithms (i.e., Logistic Regression, Decision Tree, Random Forest, Random Forest with Hyperparameters Tuning, and Support Vector Machine), and a deep learning algorithm (i.e., Deep Neural Network) to classify individual participants as to whether or not they had a stroke based only on kinematic parameters using a tenfold cross-validation approach.

RESULTS

We recruited 429 participants with neuroimaging-confirmed stroke (< 35 days post-stroke) and 465 healthy controls. Depending on the APM parameter, we observed that 10.9-48.4% of stroke participants were impaired, while 44% were impaired based on their overall task score. The mean performance metrics of machine learning and deep learning models were: accuracy 82.4%, precision 85.6%, recall 76.5%, and F1 score 80.6%. All machine learning and deep learning models displayed similar classification accuracy; however, the Random Forest model had the highest numerical accuracy (83%). Our models showed higher sensitivity and specificity (AUC = 0.89) in classifying individual participants than the overall task score (AUC = 0.85) based on their performance in the APM task. We also found that variability was the most important feature in classifying performance in the APM task.

CONCLUSION

Our ML models displayed similar classification performance. ML models were able to integrate more kinematic information and relationships between variables into decision making and displayed better classification performance than the overall task score. ML may help to provide insight into individual kinematic features that have previously been overlooked with respect to clinical importance.

Assessing the external validity of machine learning-based detection of glaucoma

Studies using machine learning (ML) approaches have reported high diagnostic accuracies for glaucoma detection. However, none assessed model performance across ethnicities. The aim of the study is to externally validate ML models for glaucoma detection from optical coherence tomography (OCT) data. We performed a prospective, cross-sectional study, where 514 Asians (257 glaucoma/257 controls) were enrolled to construct ML models for glaucoma detection, which was then tested on 356 Asians (183 glaucoma/173 controls) and 138 Caucasians (57 glaucoma/81 controls). We used the retinal nerve fibre layer (RNFL) thickness values produced by the compensation model, which is a multiple regression model fitted on healthy subjects that corrects the RNFL profile for anatomical factors and the original OCT data (measured) to build two classifiers, respectively. Both the ML models (area under the receiver operating [AUC] = 0.96 and accuracy = 92%) outperformed the measured data (AUC = 0.93; P < 0.001) for glaucoma detection in the Asian dataset. However, in the Caucasian dataset, the ML model trained with compensated data (AUC = 0.93 and accuracy = 84%) outperformed the ML model trained with original data (AUC = 0.83 and accuracy = 79%; P < 0.001) and measured data (AUC = 0.82; P < 0.001) for glaucoma detection. The performance with the ML model trained on measured data showed poor reproducibility across different datasets, whereas the performance of the compensated data was maintained. Care must be taken when ML models are applied to patient cohorts of different ethnicities.

Recognizing the Differentiation Degree of Human Induced Pluripotent Stem Cell-Derived Retinal Pigment Epithelium Cells Using Machine Learning and Deep Learning-Based Approaches

Induced pluripotent stem cells (iPSCs) can be differentiated into mesenchymal stem cells (iPSC-MSCs), retinal ganglion cells (iPSC-RGCs), and retinal pigmental epithelium cells (iPSC-RPEs) to meet the demand of regeneration medicine. Since the production of iPSCs and iPSC-derived cell lineages generally requires massive and time-consuming laboratory work, artificial intelligence (AI)-assisted approach that can facilitate the cell classification and recognize the cell differentiation degree is of critical demand. In this study, we propose the multi-slice tensor model, a modified convolutional neural network (CNN) designed to classify iPSC-derived cells and evaluate the differentiation efficiency of iPSC-RPEs. We removed the fully connected layers and projected the features using principle component analysis (PCA), and subsequently classified iPSC-RPEs according to various differentiation degree. With the assistance of the support vector machine (SVM), this model further showed capabilities to classify iPSCs, iPSC-MSCs, iPSC-RPEs, and iPSC-RGCs with an accuracy of 97.8%. In addition, the proposed model accurately recognized the differentiation of iPSC-RPEs and showed the potential to identify the candidate cells with ideal features and simultaneously exclude cells with immature/abnormal phenotypes. This rapid screening/classification system may facilitate the translation of iPSC-based technologies into clinical uses, such as cell transplantation therapy.

AI-Aided Disease Prediction in Visualized Medicine

Artificial intelligence (AI) is playing a vitally important role in promoting the revolution of future technology. Healthcare is one of the promising applications in AI, which covers medical imaging, diagnosis, robotics, disease prediction, pharmacy, health management, and hospital management. Numbers of achievements that made in these fields overturn every aspect in traditional healthcare system. Therefore, to understand the state-of-art AI in healthcare, as well as the chances and obstacles in its development, the applications of AI in disease detection and outlook and the future trends of AI-aided disease prediction were discussed in this chapter.

Vision-Based Eye Image Classification for Ophthalmic Measurement Systems

The accuracy and the overall performances of ophthalmic instrumentation, where specific analysis of eye images is involved, can be negatively influenced by invalid or incorrect frames acquired during everyday measurements of unaware or non-collaborative human patients and non-technical operators. Therefore, in this paper, we investigate and compare the adoption of several vision-based classification algorithms belonging to different fields, i.e., Machine Learning, Deep Learning, and Expert Systems, in order to improve the performance of an ophthalmic instrument designed for the Pupillary Light Reflex measurement. To test the implemented solutions, we collected and publicly released PopEYE as one of the first datasets consisting of 15 k eye images belonging to 22 different subjects acquired through the aforementioned specialized ophthalmic device. Finally, we discuss the experimental results in terms of classification accuracy of the eye status, as well as computational load analysis, since the proposed solution is designed to be implemented in embedded boards, which have limited hardware resources in computational power and memory size.

Predicting prediction: A systematic workflow to analyze factors affecting the classification performance in genomic biomarker discovery

High throughput technologies in genomics enable the analysis of small alterations in gene expression levels. Patterns of such deviations are an important starting point for the discovery and verification of new biomarker candidates. Identifying such patterns is a challenging task that requires sophisticated machine learning approaches. Currently, there are a variety of classification models, and a common approach is to compare the performance and select the best one for a given classification problem. Since the association between the features of a data set and the performance of a particular classification method is still not fully understood, the main contribution of this work is to provide a new methodology for predicting the prediction results of different classifiers in the field of biomarker discovery. We propose here a three-steps computational workflow that includes an analysis of the data set characteristics, the calculation of the classification accuracy and, finally, the prediction of the resulting classification error. The experiments were carried out on synthetic and microarray datasets. Using this method, we showed that the predictability strongly depends on the discriminatory ability of the features, e.g., sets of genes, in two or multi-class datasets. If a dataset has a certain discriminatory ability, this method enables prediction of the classification performance before applying a learning model. Thus, our results contribute to a better understanding of the relationship between dataset characteristics and the corresponding performance of a machine learning method, and suggest the optimal classification method for a given dataset based on its discriminatory ability.

Explainable machine learning methods and respiratory oscillometry for the diagnosis of respiratory abnormalities in sarcoidosis

BACKGROUND

In this work, we developed many machine learning classifiers to assist in diagnosing respiratory changes associated with sarcoidosis, based on results from the Forced Oscillation Technique (FOT), a non-invasive method used to assess pulmonary mechanics. In addition to accurate results, there is a particular interest in their interpretability and explainability, so we used Genetic Programming since the classification is made with intelligible expressions and we also evaluate the feature importance in different experiments to find the more discriminative features.

METHODOLOGY/PRINCIPAL FINDINGS

We used genetic programming in its traditional tree form and a grammar-based form. To check if interpretable results are competitive, we compared their performance to K-Nearest Neighbors, Support Vector Machine, AdaBoost, Random Forest, LightGBM, XGBoost, Decision Trees and Logistic Regressor. We also performed experiments with fuzzy features and tested a feature selection technique to bring even more interpretability. The data used to feed the classifiers come from the FOT exams in 72 individuals, of which 25 were healthy, and 47 were diagnosed with sarcoidosis. Among the latter, 24 showed normal conditions by spirometry, and 23 showed respiratory changes. The results achieved high accuracy (AUC > 0.90) in two analyses performed (controls vs. individuals with sarcoidosis and normal spirometry and controls vs. individuals with sarcoidosis and altered spirometry). Genetic Programming and Grammatical Evolution were particularly beneficial because they provide intelligible expressions to make the classification. The observation of which features were selected most frequently also brought explainability to the study of sarcoidosis.

CONCLUSIONS

The proposed system may provide decision support for clinicians when they are struggling to give a confirmed clinical diagnosis. Clinicians may reference the prediction results and make better decisions, improving the productivity of pulmonary function services by AI-assisted workflow.

The Role of Optical Coherence Tomography Criteria and Machine Learning in Multiple Sclerosis and Optic Neuritis Diagnosis

BACKGROUND AND OBJECTIVES

Recent studies have suggested that intereye differences (IEDs) in peripapillary retinal nerve fiber layer (pRNFL) or ganglion cell + inner plexiform (GCIPL) thickness by spectral domain optical coherence tomography (SD-OCT) may identify people with a history of unilateral optic neuritis (ON). However, this requires further validation. Machine learning classification may be useful for validating thresholds for OCT IEDs and for examining added utility for visual function tests, such as low-contrast letter acuity (LCLA), in the diagnosis of people with multiple sclerosis (PwMS) and for unilateral ON history.

METHODS

Participants were from 11 sites within the International Multiple Sclerosis Visual System consortium. pRNFL and GCIPL thicknesses were measured using SD-OCT. A composite score combining OCT and visual measures was compared individual measurements to determine the best model to distinguish PwMS from controls. These methods were also used to distinguish those with a history of ON among PwMS. Receiver operating characteristic (ROC) curve analysis was performed on a training data set (2/3 of cohort) and then applied to a testing data set (1/3 of cohort). Support vector machine (SVM) analysis was used to assess whether machine learning models improved diagnostic capability of OCT.

RESULTS

Among 1,568 PwMS and 552 controls, variable selection models identified GCIPL IED, average GCIPL thickness (both eyes), and binocular 2.5% LCLA as most important for classifying PwMS vs controls. This composite score performed best, with area under the curve (AUC) = 0.89 (95% CI 0.85-0.93), sensitivity = 81%, and specificity = 80%. The composite score ROC curve performed better than any of the individual measures from the model (p < 0.0001). GCIPL IED remained the best single discriminator of unilateral ON history among PwMS (AUC = 0.77, 95% CI 0.71-0.83, sensitivity = 68%, specificity = 77%). SVM analysis performed comparably with standard logistic regression models.

DISCUSSION

A composite score combining visual structure and function improved the capacity of SD-OCT to distinguish PwMS from controls. GCIPL IED best distinguished those with a history of unilateral ON. SVM performed as well as standard statistical models for these classifications.

CLASSIFICATION OF EVIDENCE

This study provides Class III evidence that SD-OCT accurately distinguishes multiple sclerosis from normal controls as compared with clinical criteria.

Investigation of the Role of Convolutional Neural Network Architectures in the Diagnosis of Glaucoma using Color Fundus Photography

Objectives:

To evaluate the performance of convolutional neural network (CNN) architectures to distinguish eyes with glaucoma from normal eyes.

Materials and Methods:

A total of 9,950 fundus photographs of 5,388 patients from the database of Eskişehir Osmangazi University Faculty of Medicine Ophthalmology Clinic were labelled as glaucoma, glaucoma suspect, or normal by three different experienced ophthalmologists. The categorized fundus photographs were evaluated using a state-of-the-art two-dimensional CNN and compared with deep residual networks (ResNet) and very deep neural networks (VGG). The accuracy, sensitivity, and specificity of glaucoma detection with the different algorithms were evaluated using a dataset of 238 normal and 320 glaucomatous fundus photographs. For the detection of suspected glaucoma, ResNet-101 architectures were tested with a data set of 170 normal, 170 glaucoma, and 167 glaucoma-suspect fundus photographs.

Results:

Accuracy, sensitivity, and specificity in detecting glaucoma were 96.2%, 99.5%, and 93.7% with ResNet-50; 97.4%, 97.8%, and 97.1% with ResNet-101; 98.9%, 100%, and 98.1% with VGG-19, and 99.4%, 100%, and 99% with the 2D CNN, respectively. Accuracy, sensitivity, and specificity values in distinguishing glaucoma suspects from normal eyes were 62%, 68%, and 56% and those for differentiating glaucoma from suspected glaucoma were 92%, 81%, and 97%, respectively. While 55 photographs could be evaluated in 2 seconds with CNN, a clinician spent an average of 24.2 seconds to evaluate a single photograph.

Conclusion:

An appropriately designed and trained CNN was able to distinguish glaucoma with high accuracy even with a small number of fundus photographs.

Glaucoma diagnosis using multi-feature analysis and a deep learning technique

In this study, we aimed to facilitate the current diagnostic assessment of glaucoma by analyzing multiple features and introducing a new cross-sectional optic nerve head (ONH) feature from optical coherence tomography (OCT) images. The data (n = 100 for both glaucoma and control) were collected based on structural, functional, demographic and risk factors. The features were statistically analyzed, and the most significant four features were used to train machine learning (ML) algorithms. Two ML algorithms: deep learning (DL) and logistic regression (LR) were compared in terms of the classification accuracy for automated glaucoma detection. The performance of the ML models was evaluated on unseen test data, n = 55. An image segmentation pilot study was then performed on cross-sectional OCT scans. The ONH cup area was extracted, analyzed, and a new DL model was trained for glaucoma prediction. The DL model was estimated using five-fold cross-validation and compared with two pre-trained models. The DL model trained from the optimal features achieved significantly higher diagnostic performance (area under the receiver operating characteristic curve (AUC) 0.98 and accuracy of 97% on validation data and 96% on test data) compared to previous studies for automated glaucoma detection. The second DL model used in the pilot study also showed promising outcomes (AUC 0.99 and accuracy of 98.6%) to detect glaucoma compared to two pre-trained models. In combination, the result of the two studies strongly suggests the four features and the cross-sectional ONH cup area trained using deep learning have a great potential for use as an initial screening tool for glaucoma which will assist clinicians in making a precise decision.

Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology

PURPOSE OF REVIEW

The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each.

RECENT FINDINGS

Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks.

SUMMARY

AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.

Machine Learning-Based Analysis and Prediction of Unplanned 30-Day Readmissions After Pituitary Adenoma Resection: A Multi-Institutional Retrospective Study With External Validation

BACKGROUND

Unplanned readmission after transsphenoidal resection of pituitary adenoma can occur in up to 10% of patients but is unpredictable.

OBJECTIVE

To develop a reliable system for predicting unplanned readmission and create a validated method for stratifying patients by risk.

METHODS

Data sets were retrospectively collected from the National Surgical Quality Improvement Program and 2 tertiary academic medical centers. Eight machine learning classifiers were fit to the National Surgical Quality Improvement Program data, optimized using Bayesian parameter optimization and evaluated on the external data. Permutation analysis identified the relative importance of predictive variables, and a risk stratification system was built using the trained machine learning models.

RESULTS

Readmissions were accurately predicted by several classification models with an area under the receiving operator characteristic curve of 0.76 (95% CI 0.68-0.83) on the external data set. Permutation analysis identified the most important variables for predicting readmission as preoperative sodium level, returning to the operating room, and total operation time. High-risk and medium-risk patients, as identified by the proposed risk stratification system, were more likely to be readmitted than low-risk patients, with relative risks of 12.2 (95% CI 5.9-26.5) and 4.2 (95% CI 2.3-8.7), respectively. Overall risk stratification showed high discriminative capability with a C-statistic of 0.73.

CONCLUSION

In this multi-institutional study with outside validation, unplanned readmissions after pituitary adenoma resection were accurately predicted using machine learning techniques. The features identified in this study and the risk stratification system developed could guide clinical and surgical decision making, reduce healthcare costs, and improve the quality of patient care by better identifying high-risk patients for closer perioperative management.