On medical application of neural networks trained with various types of data

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.

An artificial intelligence model for the radiographic diagnosis of osteoarthritis of the temporomandibular joint

The interpretation of the signs of Temporomandibular joint (TMJ) osteoarthritis on cone-beam computed tomography (CBCT) is highly subjective that hinders the diagnostic process. The objectives of this study were to develop and test the performance of an artificial intelligence (AI) model for the diagnosis of TMJ osteoarthritis from CBCT. A total of 2737 CBCT images from 943 patients were used for the training and validation of the AI model. The model was based on a single convolutional network while object detection was achieved using a single regression model. Two experienced evaluators performed a Diagnostic Criteria for Temporomandibular Disorders (DC/TMD)-based assessment to generate a separate model-testing set of 350 images in which the concluded diagnosis was considered the golden reference. The diagnostic performance of the model was then compared to an experienced oral radiologist. The AI diagnosis showed statistically higher agreement with the golden reference compared to the radiologist. Cohen's kappa showed statistically significant differences in the agreement between the AI and the radiologist with the golden reference for the diagnosis of all signs collectively (P = 0.0079) and for subcortical cysts (P = 0.0214). AI is expected to eliminate the subjectivity associated with the human interpretation and expedite the diagnostic process of TMJ osteoarthritis.

Comprehensive Review on the Use of Artificial Intelligence in Ophthalmology and Future Research Directions

BACKGROUND

Having several applications in medicine, and in ophthalmology in particular, artificial intelligence (AI) tools have been used to detect visual function deficits, thus playing a key role in diagnosing eye diseases and in predicting the evolution of these common and disabling diseases. AI tools, i.e., artificial neural networks (ANNs), are progressively involved in detecting and customized control of ophthalmic diseases. The studies that refer to the efficiency of AI in medicine and especially in ophthalmology were analyzed in this review.

MATERIALS AND METHODS

We conducted a comprehensive review in order to collect all accounts published between 2015 and 2022 that refer to these applications of AI in medicine and especially in ophthalmology. Neural networks have a major role in establishing the demand to initiate preliminary anti-glaucoma therapy to stop the advance of the disease.

RESULTS

Different surveys in the literature review show the remarkable benefit of these AI tools in ophthalmology in evaluating the visual field, optic nerve, and retinal nerve fiber layer, thus ensuring a higher precision in detecting advances in glaucoma and retinal shifts in diabetes. We thus identified 1762 applications of artificial intelligence in ophthalmology: review articles and research articles (301 pub med, 144 scopus, 445 web of science, 872 science direct). Of these, we analyzed 70 articles and review papers (diabetic retinopathy (N = 24), glaucoma (N = 24), DMLV (N = 15), other pathologies (N = 7)) after applying the inclusion and exclusion criteria.

CONCLUSION

In medicine, AI tools are used in surgery, radiology, gynecology, oncology, etc., in making a diagnosis, predicting the evolution of a disease, and assessing the prognosis in patients with oncological pathologies. In ophthalmology, AI potentially increases the patient's access to screening/clinical diagnosis and decreases healthcare costs, mainly when there is a high risk of disease or communities face financial shortages. AI/DL (deep learning) algorithms using both OCT and FO images will change image analysis techniques and methodologies. Optimizing these (combined) technologies will accelerate progress in this area.

The Prediction of Peritoneal Carcinomatosis in Patients with Colorectal Cancer Using Machine Learning

The incidence of colon, rectal, and colorectal cancer is very high, and diagnosis is often made in the advanced stages of the disease. In cases where peritoneal carcinomatosis is limited, patients can benefit from newer treatment options if the disease is promptly identified, and they are referred to specialized centers. Therefore, an essential diagnostic benefit would be identifying those factors that could lead to early diagnosis. A retrospective study was performed using patient data gathered from 2010 to 2020. The collected data were represented by routine blood tests subjected to stringent inclusion and exclusion criteria. In order to determine the presence or absence of peritoneal carcinomatosis in colorectal cancer patients, three types of machine learning approaches were applied: a neuro-evolutive methodology based on artificial neural network (ANN), support vector machines (SVM), and random forests (RF), all combined with differential evolution (DE). The optimizer (DE in our case) determined the internal and structural parameters that defined the ANN, SVM, and RF in their optimal form. The RF strategy obtained the best accuracy in the testing phase (0.75). Using this RF model, a sensitivity analysis was applied to determine the influence of each parameter on the presence or absence of peritoneal carcinomatosis.

Identifying individuals with recent COVID-19 through voice classification using deep learning

Recently deep learning has attained a breakthrough in model accuracy for the classification of images due mainly to convolutional neural networks. In the present study, we attempted to investigate the presence of subclinical voice feature alteration in COVID-19 patients after the recent resolution of disease using deep learning. The study was a prospective study of 76 post COVID-19 patients and 40 healthy individuals. The diagnoses of post COVID-19 patients were based on more than the eighth week after onset of symptoms. Voice samples of an ‘ah’ sound, coughing sound and a polysyllabic sentence were collected and preprocessed to log-mel spectrogram. Transfer learning using the VGG19 pre-trained convolutional neural network was performed with all voice samples. The performance of the model using the polysyllabic sentence yielded the highest classification performance of all models. The coughing sound produced the lowest classification performance while the ability of the monosyllabic ‘ah’ sound to predict the recent COVID-19 fell between the other two vocalizations. The model using the polysyllabic sentence achieved 85% accuracy, 89% sensitivity, and 77% specificity. In conclusion, deep learning is able to detect the subtle change in voice features of COVID-19 patients after recent resolution of the disease.

Prediction of Recurrence in Pyogenic Vertebral Osteomyelitis by Artificial Neural Network Using Time-series Data of C-Reactive Protein: A Retrospective Cohort Study of 704 Patients

STUDY DESIGN

A retrospective cohort study.

OBJECTIVE

The aim of this study was to develop recurrence-prediction models of pyogenic vertebral osteomyelitis (PVO).

SUMMARY OF BACKGROUND DATA

Prediction of recurrence in PVO is crucial to avoid additional prolonged antibiotic therapy and aggressive spinal surgery and to reduce mortality. However, prediction of PVO recurrence by previously identified, initial risk factors is limited in PVO patients who exceptionally require prolonged antibiotic therapy and experience various clinical events during the treatment. We hypothesized that time-series analysis of sequential C-reactive protein (CRP) routinely measured to estimate the response to the antibiotics in PVO patients could reflect such long treatment process and increase the power of the recurrence-prediction model.

METHODS

A retrospective study was performed to develop a PVO recurrence-prediction model, including initial risk factors and time-series data of CRP. Of 704 PVO patients, 493 and 211 were divided into training and test cohorts, respectively. Conventional stepwise logistic regression and artificial neural network (ANN) models were created from the training cohort, and the predictions of recurrence in the test cohort were compared.

RESULTS

Prediction models using initial risk factors showed poor sensitivity (4.7%) in both conventional logistic model and ANN models. However, baseline ANN models using time-series CRP data showed remarkably increased sensitivity (55.8%-60.5%). Ensemble ANN model using both initial risk factors and time-series CRP data showed additional benefit in prediction power.

CONCLUSION

The recurrence-prediction models for PVO created only using the initial risk factors showed low sensitivity, regardless of statistical method. However, ANN models using time-series data of CRP values and their ensemble model showed considerably increased prediction power. Therefore, clinicians treating PVO patients should pay attention to the treatment response including changes of CRP levels to identify high-risk patients for recurrence, and further studies to develop recurrence-prediction model for PVO should focus on the treatment response rather than initial risk factors.Level of Evidence: 4.

Real-Time Clinical Decision Support Based on Recurrent Neural Networks for In-Hospital Acute Kidney Injury: External Validation and Model Interpretation

Background

Acute kidney injury (AKI) is commonly encountered in clinical practice and is associated with poor patient outcomes and increased health care costs. Despite it posing significant challenges for clinicians, effective measures for AKI prediction and prevention are lacking. Previously published AKI prediction models mostly have a simple design without external validation. Furthermore, little is known about the process of linking model output and clinical decisions due to the black-box nature of neural network models.

Objective

We aimed to present an externally validated recurrent neural network (RNN)–based continuous prediction model for in-hospital AKI and show applicable model interpretations in relation to clinical decision support.

Methods

Study populations were all patients aged 18 years or older who were hospitalized for more than 48 hours between 2013 and 2017 in 2 tertiary hospitals in Korea (Seoul National University Bundang Hospital and Seoul National University Hospital). All demographic data, laboratory values, vital signs, and clinical conditions of patients were obtained from electronic health records of each hospital. We developed 2-stage hierarchical prediction models (model 1 and model 2) using RNN algorithms. The outcome variable for model 1 was the occurrence of AKI within 7 days from the present. Model 2 predicted the future trajectory of creatinine values up to 72 hours. The performance of each developed model was evaluated using the internal and external validation data sets. For the explainability of our models, different model-agnostic interpretation methods were used, including Shapley Additive Explanations, partial dependence plots, individual conditional expectation, and accumulated local effects plots.

Results

We included 69,081 patients in the training, 7675 in the internal validation, and 72,352 in the external validation cohorts for model development after excluding cases with missing data and those with an estimated glomerular filtration rate less than 15 mL/min/1.73 m2 or end-stage kidney disease. Model 1 predicted any AKI development with an area under the receiver operating characteristic curve (AUC) of 0.88 (internal validation) and 0.84 (external validation), and stage 2 or higher AKI development with an AUC of 0.93 (internal validation) and 0.90 (external validation). Model 2 predicted the future creatinine values within 3 days with mean-squared errors of 0.04-0.09 for patients with higher risks of AKI and 0.03-0.08 for those with lower risks. Based on the developed models, we showed AKI probability according to feature values in total patients and each individual with partial dependence, accumulated local effects, and individual conditional expectation plots. We also estimated the effects of feature modifications such as nephrotoxic drug discontinuation on future creatinine levels.

Conclusions

We developed and externally validated a continuous AKI prediction model using RNN algorithms. Our model could provide real-time assessment of future AKI occurrences and individualized risk factors for AKI in general inpatient cohorts; thus, we suggest approaches to support clinical decisions based on prediction models for in-hospital AKI.

An artificial neural network-based model to predict chronic kidney disease in aged cats

BACKGROUND

Chronic kidney disease (CKD) frequently causes death in older cats; its early detection is challenging.

OBJECTIVES

To build a sensitive and specific model for early prediction of CKD in cats using artificial neural network (ANN) techniques applied to routine health screening data.

ANIMALS

Data from 218 healthy cats ≥7 years of age screened at the Royal Veterinary College (RVC) were used for model building. Performance was tested using data from 3546 cats in the Banfield Pet Hospital records and an additional 60 RCV cats-all initially without a CKD diagnosis.

METHODS

Artificial neural network (ANN) modeling used a multilayer feed-forward neural network incorporating a back-propagation algorithm. Clinical variables from single cat visits were selected using factorial discriminant analysis. Independent submodels were built for different prediction time frames. Two decision threshold strategies were investigated.

RESULTS

Input variables retained were plasma creatinine and blood urea concentrations, and urine specific gravity. For prediction of CKD within 12 months, the model had accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 88%, 87%, 70%, 53%, and 92%, respectively. An alternative decision threshold increased specificity and PPV to 98% and 87%, but decreased sensitivity and NPV to 42% and 79%, respectively.

CONCLUSIONS AND CLINICAL IMPORTANCE

A model was generated that identified cats in the general population ≥7 years of age that are at risk of developing CKD within 12 months. These individuals can be recommended for further investigation and monitoring more frequently than annually. Predictions were based on single visits using common clinical variables.