Computer-aided diagnosis of keratoconus through VAE-augmented images using deep learning.

Detecting clinical keratoconus (KCN) poses a challenging and time-consuming task. During the diagnostic process, ophthalmologists are required to review demographic and clinical ophthalmic examinations in order to make an accurate diagnosis. This study aims to develop and evaluate the accuracy of deep convolutional neural network (CNN) models for the detection of keratoconus (KCN) using corneal topographic maps. We retrospectively collected 1758 corneal images (978 normal and 780 keratoconus) from 1010 subjects of the KCN group with clinically evident keratoconus and the normal group with regular astigmatism. To expand the dataset, we developed a model using Variational Auto Encoder (VAE) to generate and augment images, resulting in a dataset of 4000 samples. Four deep learning models were used to extract and identify deep corneal features of original and synthesized images. We demonstrated that the utilization of synthesized images during training process increased classification performance. The overall average accuracy of the deep learning models ranged from 99% for VGG16 to 95% for EfficientNet-B0. All CNN models exhibited sensitivity and specificity above 0.94, with the VGG16 model achieving an AUC of 0.99. The customized CNN model achieved satisfactory results with an accuracy and AUC of 0.97 at a much faster processing speed compared to other models. In conclusion, the DL models showed high accuracy in screening for keratoconus based on corneal topography images. This is a development toward the potential clinical implementation of a more enhanced computer-aided diagnosis (CAD) system for KCN detection, which would aid ophthalmologists in validating the clinical decision and carrying out prompt and precise KCN treatment.

Compliance with design principles: a case study of a widely used laboratory information system.

BACKGROUND: Laboratory information systems are widely used health information systems that have the potential to improve health care quality. Despite their benefits, many studies have indicated problems with user interaction with these systems due to poor interface design. AIMS: To evaluate the usability of a laboratory information system. METHODS: In this descriptive, cross-sectional study, we used heuristic evaluation to examine the user interface design of a laboratory information system in an academic hospital affiliated with Kerman University of Medical Sciences in 2017. This system is also used in 59 other Iranian hospitals .We investigated the usability of different parts of the usability of a laboratory information system (outpatient admission, inpatient admission, sample collection, and test result reporting). Data were collected using a standard form based on the heuristic evaluation method, and categorized based on their severity and violated heuristics. The content validity was confirmed by 3 medical informatics specialists. RESULTS: We identified 162 usability problems. In terms of the heuristics, the highest number of problems concerned flexibility and efficiency of use (n = 32, 19.75%) and the lowest concerned help users recognize, diagnose, and recover from errors (n = 2, 1.23%). In terms of different modules of the system, the highest number of problems (n = 51, 31.48%) concerned outpatient admission and the lowest (n = 29, 17.9%) concerned sample collection. In terms of severity, 45.06% of the problems were rated as major. CONCLUSIONS: Despite widespread use of laboratory information systems, their user interface design has usability problems that diminish the quality of user interaction with these systems and may affect the quality of health care. Consideration of standards and principles for user interface design, such as the heuristics used in this study, could improve system usability.

The Prediction of the Risk Level of Pulmonary Embolism and Deep Vein Thrombosis through Artificial Neural Network.

BACKGROUND: Venous thromboembolism is a common cause of mortality among hospitalized patients and yet it is preventable through detecting the precipitating factors and a prompt diagnosis by specialists. The present study has been carried out in order to assist specialists in the diagnosis and prediction of the risk level of pulmonary embolism in patients, by means of artificial neural network. METHOD: A number of 31 risk factors have been used in this study in order to evaluate the conditions of 294 patients hospitalized in 3 educational hospitals affiliated with Kerman University of Medical Sciences. Two types of artificial neural networks, namely Feed-Forward Back Propagation and Elman Back Propagation, were compared in this study. RESULTS: Through an optimized artificial neural network model, an accuracy and risk level index of 93.23 percent was achieved and, subsequently, the results have been compared with those obtained from the perfusion scan of the patients. 86.61 percent of high risk patients diagnosed through perfusion scan diagnostic method were also diagnosed correctly through the method proposed in the present study. CONCLUSIONS: The results of this study can be a good resource for physicians, medical assistants, and healthcare staff to diagnose high risk patients more precisely and prevent the mortalities. Additionally, expenses and other unnecessary diagnostic methods such as perfusion scans can be efficiently reduced.

Attitude of Iranian physicians and nurses toward a clinical decision support system for pulmonary embolism and deep vein thrombosis.

This research project sought to design and implement a computerized clinical decision support system (CDSS) that was able to identify patients who were at risk of pulmonary embolism (PE) and deep vein thrombosis (DVT), as well as produce reminders for prophylactic action for these diseases. The main purpose of the CDSS was to attempt to reduce the morbidity and mortality caused by embolism and thrombosis in patients admitted to hospitals. After implementation of this system in one of the large educational hospitals of Iran, a standard questionnaire was used, and interviews were conducted with physicians and nurses to evaluate the performance of the designed system for reducing the incidence of pulmonary embolism and thrombosis. From physicians and nurses' point of view, a system which assists the medical staff in making better decisions regarding patient care, and also reminds pulmonary embolism and thrombosis preventive procedures with timely warnings, can influence patient care quality improvement and lead to the improved performance of the medical staff in preventing the incidence of pulmonary embolism and thrombosis.