Quality improvement initiative in paediatric echocardiography laboratory in a low- to middle-income country.

AIMS: To determine the impact of a quality improvement (QI) initiative in the area of paediatric echocardiography (echo) in a low- to middle-income country (LMIC).Care for patients with congenital heart disease is challenging, especially in LMICs. Collaborative learning through QI projects is imperative to ensure improvement in delivery processes leading to better patient outcomes. METHODS AND RESULTS: This QI initiative was taken by a team consisting of physicians and sonographers. Problems were identified, a key driver diagram (KDD) was created, and simple process re-engineering was done using interventions based on the KDD. Metrics (five process and one outcome) were assessed to determine the effectiveness of the QI project. The process metrics assessed were comprehensiveness of exam, timeliness of reporting, diagnostic accuracy and error, and sedation adverse event rates of transthoracic echocardiograms, while a novel comprehensive echo laboratory (lab) quality score was developed as an outcome metric. Data were collected quarterly and analysed in the post-implementation phase. Significant improvement was seen in comprehensive mean score (20.4-29.7), timeliness (40-95%), and diagnostic accuracy rate (91-100%), while a decrease was seen in the diagnostic error rate (7.5-3.5%) and the sedation adverse event rate (6.8-0%), pre- vs. post-implementation. The overall quality outcome score improved from 7 to 19 and the echo lab was able to achieve adequate quality. CONCLUSION: This QI initiative produced improvement in all the processes, and the overall quality of the echo lab without any substantial increase in resources or cost.

Diabetic retinopathy detection through novel tetragonal local octa patterns and extreme learning machines.

Diabetic retinopathy (DR) is an eye disease that victimize the people suffering from diabetes from many years. The severe form of DR results in form of the blindness that can initially be controlled by the DR-screening oriented treatment. The effective screening programs require the trained human resource that manually grade the fundus images to understand the severity of the disease. But due to the complexity of this process, and the insufficient number of the trained workers, the precise manual grading is an expensive process. The CAD-based solutions try to address these limitations but most of the existing DR detection systems are as evaluated over small sets and become ineffective when applied in real scenarios. Therefore, in this paper we proposed a novel technique to precisely detect the various stages of the DR by extending the research of the content-based image retrieval domain. To achieve the human-level performance over the large-scale DR-datasets (i.e. Kaggle-DR), the fundus images are represented by the novel tetragonal local octa pattern (T-LOP) features, that are then classified through the extreme learning machine (ELM). To justify the significance of the method, the proposed scheme is compared against several state-of-the-art methods including the deep learning-based methods over four DR-datasets of variational lengths (i.e. Kaggle-DR, DRIVE, Review-DB, STARE). The experimental results confirm the significance of the DR-detection scheme to serve as a stand-alone solution for providing the precise information of the severity of the DR in an efficient manner.