RESUMO
INTRODUCTION: Deep Learning (DL) and Artificial Intelligence (AI) have become widespread due to the advanced technologies and availability of digital data. Supervised learning algorithms have shown human-level performance or even better and are better feature extractor-quantifier than unsupervised learning algorithms. To get huge dataset with good quality control, there is a need of an annotation tool with a customizable feature set. This paper evaluates the viability of having an in house annotation tool which works on a smartphone and can be used in a healthcare setting. METHODS: We developed a smartphone-based grading system to help researchers in grading multiple retinal fundi. The process consisted of designing the flow of user interface (UI) keeping in view feedback from experts. Quantitative and qualitative analysis of change in speed of a grader over time and feature usage statistics was done. The dataset size was approximately 16,000 images with adjudicated labels by a minimum of 2 doctors. Results for an AI model trained on the images graded using this tool and its validation over some public datasets were prepared. RESULTS: We created a DL model and analysed its performance for a binary referrable DR Classification task, whether a retinal image has Referrable DR or not. A total of 32 doctors used the tool for minimum of 20 images each. Data analytics suggested significant portability and flexibility of the tool. Grader variability for images was in favour of agreement on images annotated. Number of images used to assess agreement is 550. Mean of 75.9% was seen in agreement. CONCLUSION: Our aim was to make Annotation of Medical imaging easier and to minimize time taken for annotations without quality degradation. The user feedback and feature usage statistics confirm our hypotheses of incorporation of brightness and contrast variations, green channels and zooming add-ons in correlation to certain disease types. Simulation of multiple review cycles and establishing quality control can boost the accuracy of AI models even further. Although our study aims at developing an annotation tool for diagnosing and classifying diabetic retinopathy fundus images but same concept can be used for fundus images of other ocular diseases as well as other streams of medical science such as radiology where image-based diagnostic applications are utilised.
RESUMO
BACKGROUND: Studies have shown that the prevalence of psychiatric disorders, particularly depression, is high among tuberculosis (TB) patients, and may adversely affect treatment compliance. A person suffering from TB can develop depression in due course of time owing to a number of factors, namely the long duration of treatment for TB, stigmatization faced by the patient due to the disease and lack of family support to name a few. OBJECTIVES: The present study aimed to determine the prevalence of depression and its correlates among TB patients enrolled at a Directly Observed Treatment Short-course (DOTS) center in a rural area of Delhi. METHODS: The study was a DOTS center-based, cross-sectional study, among 106 patients of pulmonary and extrapulmonary TB, above 18 years of age. An interviewer-administered questionnaire in Hindi was used to collect basic sociodemographic data and the Patient Health Questionnaire (PHQ)-9 was used for detecting depression. Those with a score of 10 or more were considered to be suffering from depression. Data analysis was done using SPSS licensed version 20. Chi-square was used to test for association between qualitative variables, and a P < 0.05 was considered statistically significant. RESULTS: A total of 106 patients participated in the study, of which 61 (57.5%) were males. The median age was 30 years (inter-quartile range 24-40 years). Depression was found to be present in 25 (23.6%) participants. A higher proportion of patients with depression were unemployed currently, and also belonged to middle or lower class (P < 0.05). Depression was not found to be associated with religion, gender, marital status, HIV status, presence of diabetes, DOTS category nor with the phase of treatment. CONCLUSION: Depression among TB patients is common, affecting almost one in four TB patients. Physicians and DOTS providers should have a high index of suspicion for depression when assessing TB patients.
