Improving fetal congenital heart disease screening using a checklist-based approach

Use of 'Printed Investigation Sheet' as Checklist in Admitted Antenatal Patients: A Quality Improvement Initiative

Background

The study was conducted to establish use of printed investigation sheets as checklists for timely workup and clinical evaluation of antenatal women with medical diseases; admitted in maternity ward, by third day of their hospital admission. This was aimed to standardize care, avoid repeated blood sampling of patients, avoid delay in starting the treatment and help teams perform optimally by systematic use of quality improvement (QI) tools.

Methods

The present study was conducted in the Department of Obstetrics and Gynaecology at a tertiary care teaching hospital using point-of-care quality improvement methodology systematically. A QI team was made who formulated an aim statement, conducted a root-cause analysis, performed plan-do-study-act (PDSA) cycles. The outcome was measured as complete clinical evaluation of antenatal women with anaemia, hypertension, and/or diabetes by third day of admission in the maternity ward.

Results

The baseline data showed that median percentage of patients with complete clinical evaluation was only 29.2%. After a root-cause analysis with fishbone tool, three PDSA cycles were conducted to achieve the target of 80%. After the third PDSA cycle, complete clinical evaluation in anaemia, hypertension, diabetes showed an improving trend with a median of 75%.

Conclusion

Adopting simple principles of quality improvement, initiating use of printed investigation sheets as checklist can streamline and expedite clinical evaluation of antenatal patients with medical problems so as to avoid unnecessary delay in initiating the management in busy maternity wards.

A Framework for AI-Assisted Detection of Patent Ductus Arteriosus from Neonatal Phonocardiogram

The current diagnosis of Congenital Heart Disease (CHD) in neonates relies on echocardiography. Its limited availability requires alternative screening procedures to prioritise newborns awaiting ultrasound. The routine screening for CHD is performed using a multidimensional clinical examination including (but not limited to) auscultation and pulse oximetry. While auscultation might be subjective with some heart abnormalities not always audible it increases the ability to detect heart defects. This work aims at developing an objective clinical decision support tool based on machine learning (ML) to facilitate differentiation of sounds with signatures of Patent Ductus Arteriosus (PDA)/CHDs, in clinical settings. The heart sounds are pre-processed and segmented, followed by feature extraction. The features are fed into a boosted decision tree classifier to estimate the probability of PDA or CHDs. Several mechanisms to combine information from different auscultation points, as well as consecutive sound cycles, are presented. The system is evaluated on a large clinical dataset of heart sounds from 265 term and late-preterm newborns recorded within the first six days of life. The developed system reaches an area under the curve (AUC) of 78% at detecting CHD and 77% at detecting PDA. The obtained results for PDA detection compare favourably with the level of accuracy achieved by an experienced neonatologist when assessed on the same cohort.